Wireless Thermal Detection Capsule

Abstract

An apparatus for detecting gastrointestinal pathology includes a capsule including at least one temperature sensor, the capsule configured to be swallowed by a subject, and the at least one temperature sensor configured to detect ambient heat radiated by tissue of the subject.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. patent application Ser. No. 63 / 384,564, filed Nov. 21, 2022, the entire disclosure of which is incorporated herein by reference.

[0002] (Statement Regarding Federally Sponsored Research or Development) Not applicable. [Background technology]

[0003] Video capsule endoscopy (VCE) has shown promise as a noninvasive tool for diagnosing and monitoring Crohn's disease, but it has several drawbacks, including its inability to obtain data from below the tissue surface, its inability to detect disease at early stages, and the fact that good preoperative bowel preparation is usually required for adequate visualization of the colon. Summary of the Invention

[0004] Therefore, new systems, methods, and devices for detecting gastrointestinal pathologies are desirable.

[0005] Thus, various embodiments provide a swallowable wireless thermal sensing (e.g., using temperature sensors and / or infrared (IR) imaging) capsule that enables non-invasive diagnosis and monitoring of inflammatory gastrointestinal diseases and other gastrointestinal pathologies. VCE has become a common method used in medical practice to identify gastrointestinal diseases and has proven successful as a non-invasive tool for diagnosing Crohn's disease and monitoring disease progression.

[0006] One of the obstacles to optimal management of inflammatory diseases such as Crohn's disease is the lack of sensitive, noninvasive, and easily performed methods to diagnose inflammation in the intestine. Swallowable wireless capsule technology that can identify inflammatory activity could change this landscape by providing one or more of the following: early diagnosis, regular monitoring, treatment optimization, and / or a method to deliver treatment locally in conditions such as Crohn's disease.

[0007] Active inflammation in other organ systems causes tissue temperature increases that can be detected through infrared (IR) blackbody radiation. Therefore, VCE is limited to observing the luminal surface and cannot detect early disease. However, heat easily diffuses through moist tissue, allowing thermal imaging to overcome this limitation. The diagnostic capabilities of one potential thermal imaging sensing technology, IR sensor arrays, can be limited by their low pixel resolution. Therefore, we instead developed a sensing (e.g., via temperature sensors and / or thermal IR imaging) capsule that utilizes a super-resolution neural network to improve resolution and identify intestinal lesions (e.g., by detecting inflammation and other tissue conditions) occurring deep within the submucosa / muscularis layer.

[0008] The disclosed embodiments of the thermal imaging capsule provide a mechanism for more sensitive detection of signs of inflammation and other pathologies at any depth in the bowel wall, requiring little or no preoperative bowel preparation, which is expected to make the device particularly suitable for monitoring Crohn's disease. In certain embodiments with a local treatment delivery mechanism, the thermal imaging capsule may also be able to directly treat inflamed tissue, reducing systemic side effects and thereby providing better outcomes for Crohn's disease patients.

[0009] Thus, in various embodiments, the disclosure provides one or more of the following: 1) a wireless thermal sensing capsule system, 2) a super-resolution neural network for capsule endoscopy, and 3) a mechanism for detecting inflammatory bowel pathology in conditions such as Crohn's disease. Various embodiments provide a platform for both diagnostics and routine monitoring, enabling optimized and targeted treatment of Crohn's disease and / or other pathologies.

[0010] Accordingly, one embodiment provides an apparatus for detecting gastrointestinal pathology, comprising a capsule including at least one temperature sensor, the capsule configured to be swallowed by a subject, the at least one temperature sensor configured to ambiently detect heat emitted from tissue of the subject.

[0011] Another embodiment provides a system for detecting gastrointestinal pathology, including a capsule including at least one temperature sensor, the capsule configured to be swallowed by a subject, the at least one temperature sensor configured to ambiently detect heat emitted from tissue of the subject, and a receiving belt configured to be coupled to the subject.

[0012] Yet another embodiment provides a method for detecting a gastrointestinal lesion, comprising providing a capsule including at least one temperature sensor, the capsule configured to be swallowed by a subject, the at least one temperature sensor configured to ambiently detect heat emitted from tissue of the subject, and using the at least one temperature sensor to ambiently detect heat emitted from tissue of the subject.

[0013] Another embodiment provides an apparatus for detecting gastrointestinal lesions, comprising a capsule including a thermal imaging sensor, the capsule configured to be swallowed by a subject, and the thermal imaging sensor configured to detect infrared radiation emitted from tissue of the subject.

[0014] Another embodiment provides a system for detecting gastrointestinal pathologies, comprising a capsule including a thermal imaging sensor and a wireless transmitter in communication with a controller, and a plurality of antennas in communication with the capsule, the capsule configured to be swallowed by a subject, the thermal imaging sensor configured to detect infrared radiation emitted from tissue of the subject, the controller configured to generate at least one image of the detected infrared radiation emitted from tissue of the subject, the controller configured to transmit the at least one image to the wireless transmitter, the wireless transmitter configured to transmit the at least one image to the plurality of antennas, and the plurality of antennas configured to receive the at least one image from the wireless transmitter.

[0015] Yet another embodiment provides a method for detecting lesions in the gastrointestinal tract, comprising providing a capsule including a thermal imaging sensor, the capsule configured to be swallowed by a subject, and using the thermal imaging sensor to detect infrared radiation emitted from tissue of the subject.

[0016] Yet another embodiment provides a method for detecting lesions in the gastrointestinal tract, comprising: providing a capsule including a thermal imaging sensor, a wireless transmitter, and a plurality of antennas in communication with a controller, the capsule configured to be swallowed by a subject; detecting infrared radiation emitted from tissue of the subject by the thermal imaging sensor; generating at least one image of the detected infrared radiation emitted from tissue of the subject by the controller; transmitting the at least one image to a wireless transmitter by the controller; the wireless transmitter transmitting the at least one image to a plurality of antennas; and receiving the at least one image from the wireless transmitter.

[0017] Various objects, features, and advantages of the disclosed subject matter may be more fully understood by reference to the following detailed description of the disclosed subject matter when considered in conjunction with the following drawings. [Brief explanation of the drawings]

[0018] [Figure 1] 1 shows a diagram of a system for detecting inflammation or other pathology in the gastrointestinal tract depicting a thermal IR imaging capsule moving through the gastrointestinal tract and acquiring thermal IR image information that can be presented as an image using, for example, a pseudocolor scale representing different temperatures. [Figure 2] 1 illustrates the structure of a wireless thermal IR imaging capsule consistent with the present disclosure, showing a catadioptric reflector, an IR sensor, a power supply / battery, a viewing window (LDPE), a printed circuit board (PCB), and an antenna. [Figure 3] The structure of the catadioptric reflector as shown with the capsule in Figure 2 is shown, with the left panel showing a perspective view of the pyramidal reflector and indicating which parts of the reflector reflect which parts of the IR sensor (the top of the pyramid reflects the inner 16x16 pixels of the IR detector, and the bottom of the pyramid reflects the remaining outer pixels of the IR detector), and the two right panels showing ZEMAX diagrams of the light path from the reflector. [Figure 4] Several reflector embodiments for reflecting light from the sample to an IR sensor are shown. In the left panel, the bottom photograph shows an IR sensor with a conical reflector, and the top diagram of the photograph shows the field of view of the IR sensor with the conical reflector, indicating where the "blind spots" on the IR sensor that do not receive reflected light are located. In the middle panel, the bottom photograph shows an IR sensor with a wedge-shaped reflector, and the top diagram of the photograph shows the field of view of the IR sensor with the wedge-shaped reflector, indicating where the "blind spots" on the IR sensor that do not receive reflected light are located. In the right panel, the bottom photograph shows the catadioptric reflector of Figures 2 and 3, and the top diagram of the photograph shows the field of view of the IR sensor with the catadioptric reflector, indicating where the "blind spots" on the IR sensor that do not receive reflected light are located. As shown in the right panel, the catadioptric reflector minimizes blind spots and maximizes utilization of the IR sensor. [Figure 5]The top panel shows a photograph of a PCB for use in the construction of a wireless thermal IR imaging capsule, the PCB having a snap-off programmer element that provides a connection for programming the device and can be removed before placing the PCB in the capsule, and an IR sensor attached to it. The bottom panel of Figure 5 shows the construction of a wireless thermal IR imaging capsule with a rounded reflector as in Figure 2. [Figure 6A] 1 shows a diagram of a receiver module attached to a subject (an animal subject used during testing) with multiple antennas connected to the receiver module via coaxial connectors. [Figure 6B] 1 shows a diagram of a subject with a capsule device in the digestive tract with an antenna array attached to the subject's body using an adhesive. [Figure 7] A photograph of the circuit board for the receiver module is shown, which contains an RF multiplexer connected to eight input channels, each containing a coaxial connector for establishing connection to an antenna. [Figure 8A] An experimental setup for generating a hot spot for conducting ex vivo testing of the wireless thermal IR imaging capsule is shown. [Figure 8B] 1 shows thermal IR imaging results obtained with a capsule device observing hot spots through a section of excised ileal tissue. [Figure 9] A layered dielectric model of human tissue for RF transmission from the lumen to the skin surface is shown. Dimensions are based on anatomical CT and ultrasound studies of the US population, accounting for variations in gender, weight, and tissue pathology, providing a maximum upper limit for total attenuation (dielectric parameters are taken from the IT'IS Foundation tissue database). [Figure 10] Using the model in Figure 9, reflection and transmission losses calculated at 433 MHz using the maximum tissue thickness recorded in both healthy and diseased patients are shown. Results were validated on a 43 kg porcine tissue model. [Figure 11]Shown is the prototype IR capsule PCB (panel a), the length of the capsule (panel b), and the front of the capsule (panel c). [Figure 12] 1 shows a block diagram of the electronic communication and power supply of the IR capsule device. [Figure 13] 1 shows a photograph of the experimental setup for performing ex vivo testing of the wireless thermal IR imaging capsule structure. [Figure 14] FIG. 1 shows a diagram of the experimental setup for performing ex vivo testing of the wireless thermal IR imaging capsule. [Figure 15] Shown are an ideal image (left panel) and an 8-frame average image for the insertion 1 cm inside the heated section (center panel) and at the end edge of the heated section of tissue (3 cm, right panel). Images were taken with the capsule inside the intestine. The overlapping area of ​​the resistive heating pad causes a warm corner of the image and is marked "TC" in the image. [Figures 16A-16B] FIG. 16A shows a general schematic diagram of one structure of a thermal IR imaging capsule with a single IR sensor. The outer shell is made of PMMA, where "IR" stands for infrared, "PCB" stands for "printed circuit board," and "PMMA" stands for polymethyl methacrylate. FIG. 16B shows a general schematic diagram of one structure of a thermal IR imaging capsule with one IR sensor on each end of the capsule, where "PCB" stands for printed circuit board, and "PMMA" stands for polymethyl methacrylate. [Figure 16C] 1 shows a diagram of another configuration of a thermal IR imaging capsule with one IR sensor. [Figure 17] Here is an overview of the entire IR capsule system from the perspective of the data stream: Here, "PCB" means printed circuit board, "EEPROM" means electrically erasable programmable read-only memory, and "IR" means infrared. [Figure 18] 1 shows a schematic diagram of the experimental temperature measurement setup. [Figure 19]1 illustrates an example of a system for detecting gastrointestinal inflammation or other pathology in accordance with some embodiments of the disclosed subject matter. [Figure 20] 1 illustrates example hardware that can be used to implement computing devices and servers consistent with some embodiments of the disclosed subject matter. [Figure 21] 1 illustrates an example process for detecting gastrointestinal inflammation or other pathology, consistent with some embodiments of the disclosed subject matter. [Figure 22] 10 illustrates another example of a process for detecting gastrointestinal inflammation or other pathology, consistent with some embodiments of the disclosed subject matter. [Figure 23] 1 illustrates the structure of a wireless thermal sensing capsule according to the disclosure, showing the front cap, thermistor block, processing unit and wireless transmission, main power supply, and rear cap. [Figure 24] 1 shows an exploded cross-sectional view of a wireless thermal sensing capsule, showing the front cap, capsule wall, thermistor ring, drug reservoir, battery, printed circuit board 1 (PCB1), printed circuit board 2 (PCB2), printed circuit board 3 (PCB3), printed circuit board 4 (PCB4), battery, and back cap. [Figure 25] 1 shows a perspective view of a wireless thermal sensing capsule. [Figures 26A-26B] Figure 26A shows a side view of the thermistor block of Figure 24, showing the capsule wall and thermistor ring, and Figure 26B shows a front view of printed circuit board 1 (PCB1) of Figure 24, including the thermistor ring. [Figures 27A-27C] Figure 27A shows a front view of printed circuit board 2 (PCB2) of Figure 24. Figure 27B shows the processing unit and wireless transmitter of Figure 23, including printed circuit board 2 (PCB2), printed circuit board 3 (PCB3), and antenna. Figure 27C shows a back view of printed circuit board 3 (PCB3) of Figure 24. [Figures 28A-28C]Figure 28A shows a front view of printed circuit board 2 (PCB2) of Figure 24. Figure 28B shows a side view of the processing unit and wireless transmitter of Figure 23, including the locations of printed circuit board 2 (PCB2) and printed circuit board 3 (PCB3). Figure 28C shows a rear perspective view of printed circuit board 3 (PCB3) of Figure 24. [Figures 29A-29B] Figure 29A shows the processing unit and wireless transmitter of Figure 23, including the drug reservoir, printed circuit board 2 (PCB2), and printed circuit board 3 (PCB3). Figure 29B shows the processing unit and wireless transmitter of Figure 23, including the drug reservoir, antenna, printed circuit board 2 (PCB2), and printed circuit board 3 (PCB3). [Figures 30A-30C] Figure 30A shows a side view of the main power supply of Figure 23. Figure 30B shows a side view of the battery of the main power supply of Figure 23. Figure 30C shows a front view of the main power supply of Figure 23. [Figures 31A-31C] Figure 31A shows a front view of the printed circuit board 4 (PCB4) of Figure 24. Figure 31B shows a side view of the printed circuit board 4 (PCB4) of Figure 24. Figure 31C shows a rear side view of the printed circuit board 4 (PCB4) for contacting the mains power supply of Figure 23. [Figure 32A-32B] Figure 32A shows examples of internal circuit board housings for printed circuit board 1 (PCB1), printed circuit board 2 (PCB2), printed circuit board 3 (PCB3), and printed circuit board 4 (PCB4) of Figure 24. Figure 32B shows examples of internal circuit board housings for printed circuit board 1 (PCB1), printed circuit board 2 (PCB2), printed circuit board 3 (PCB3), and printed circuit board 4 (PCB4) of Figure 24. [Figure 33A-33B]Figure 33A shows an example of a folded and assembled internal circuit board housing for printed circuit board 1 (PCB1), printed circuit board 2 (PCB2), printed circuit board 3 (PCB3), printed circuit board 4 (PCB4), and the thermistor ring of Figure 24. Figure 33B shows an example of a folded and assembled internal circuit board housing for printed circuit board 1 (PCB1), printed circuit board 2 (PCB2), printed circuit board 3 (PCB3), printed circuit board 4 (PCB4), and thermistor ring of Figure 24. [Figure 34] A system block diagram of the capsule is shown in Figure 23, showing the steps from measurement to transmission, and then from reception to processing and storage. [Figure 35A-35B] Figure 35A shows the receiving belt, showing the antenna location, shoulder strap, belt, and holster. Figure 35B shows the antenna location of Figure 12A, including the shoulder strap, holster, and belt. [Figure 36] A functional block diagram of network 1 is shown. [Figure 37] A functional block diagram of Network 2 is shown. DETAILED DESCRIPTION OF THE INVENTION

[0019] In accordance with some embodiments of the disclosed subject matter, mechanisms (which may include systems, methods, and devices) for detecting gastrointestinal lesions are provided.

[0020] Current capsule endoscopes operate in the visible or near-infrared spectrum. As a result, only the luminal surface can be examined, requiring preoperative bowel preparation, which does not detect inflammatory diseases in their early stages. Given that inflammation in other body systems has been shown to cause significant temperature increases, the disclosed embodiments aim to provide more sensitive and earlier detection of inflammatory diseases of the gastrointestinal tract, including but not limited to Crohn's disease, using a swallowable capsule configured to detect heat emitted from a subject's tissues.

[0021] Accordingly, certain embodiments provide devices, systems, and methods for detecting gastrointestinal pathologies that can include a capsule including at least one temperature sensor, which can be configured to be swallowed by a subject, and the at least one temperature sensor can be configured to ambiently sense heat emitted from tissue of the subject.

[0022] In some embodiments, the at least one temperature sensor can include a thermistor including a thermistor ring, wherein the thermistor ring can include multiple thermistors arranged around the cylindrical wall of the capsule (see FIGS. 23-37). In certain embodiments, the multiple thermistors in the thermistor ring can be configured to detect a spatial pattern of heat radiating from the subject's tissue. In various embodiments, the multiple thermistors can be arranged partway around the cylindrical wall of the capsule (e.g., halfway, one-third, one-quarter, etc. around the capsule), or can be arranged completely around the cylindrical wall of the capsule.

[0023] In certain embodiments, the capsule can include two or more groups of thermistors arranged around the cylindrical wall of the capsule. In some embodiments, the various arrays, groups, or rings of thermistors can be aligned with one another, while in other embodiments, the groups or rings of thermistors can be offset from one another. When the arrays, groups, or rings of thermistors are arranged in an offset manner around the cylindrical wall of the capsule, they can obtain information from tissue with higher resolution than a single array or multiple aligned arrays.

[0024] In various embodiments, data obtained from a plurality of thermistor arrays disposed around the cylindrical wall of the capsule can be used to improve the spatial resolution of an image formed using the data, to determine the speed of capsule movement within the subject's tissue, and / or to reduce the amount of noise associated with the transmission of data.

[0025] In some embodiments, the cylindrical wall of the capsule may comprise or consist of a thermally conductive material, and the array of thermistors may be in thermal contact with the thermally conductive material of the cylindrical wall of the capsule. In various embodiments, the cylindrical wall may be made of a material comprising any linear combination of the following materials as a core conductive element, in the form of a solid, thermal paste, or thermally conductive adhesive: The material may be protected with a thin layer of a biocompatible material, such as polycarbonate, PMMA, or polystyrene. The core conductive element may be or comprise one or more of metals or other alloys, such as platinum, gold, silver, copper, bronze, and / or aluminum, or may be or comprise diamond, carbon nanotube sheets, and / or carbon composites and crystals, such as carbon matrix composites (CAMCs). In other embodiments, the cylindrical wall may be made without a thermally conductive material or from a material with low thermal conductivity, and in the absence of a thermal conductor, contact between the tissue and the temperature sensor may be promoted by applying pressure between the tissue and the capsule wall, and the thickness of the capsule wall at the sensor contact point may be minimized to reduce thermal insulation from the sensor through the wall to the tissue.

[0026] In some embodiments, the capsule can include a flexible printed circuit board, and the array or thermistor can be coupled to the flexible printed circuit board (see Figures 33-34). In certain embodiments, the capsule can include a power source, such as a battery, in electrical contact with the printed circuit board (see Figures 23-26, Figure 31).

[0027] In various embodiments, the capsule can further include a controller (e.g., including a processor and / or memory) in communication with the thermistor array. The controller can be configured to obtain data from the thermistor array related to heat emitted and detected from the subject's tissue. In some embodiments, the controller can be further configured to encrypt data obtained from the at least one temperature sensor, e.g., to maintain data integrity and / or patient confidentiality.

[0028] In certain embodiments, the capsule can further include a wireless transmitter and antenna in communication with a controller. The controller can be configured to transmit data obtained from the thermistor via the wireless transmitter and antenna to an external device for at least one of storing and analyzing the transmitted data. The external device can be a control unit attached to the subject using a receiving belt (see below). In some embodiments, the controller can be further configured to generate at least one image based on data obtained from the at least one temperature sensor. In other embodiments, the external device receiving the transmitted data can be configured to generate an image. In still other embodiments, the external device can transmit the data to another component (e.g., a remote computer or server) for further processing, including generating an image based on the data.

[0029] In various embodiments, the controller, external device, or other system may be further configured to generate a plurality of images based on data obtained from the thermistor. The plurality of images may be based on data obtained at a particular rate of data acquisition from the at least one temperature sensor. In some embodiments, the controller may be further configured to receive a signal from an external device and instruct the controller to adjust at least one of the rate of data acquisition from the thermistor (e.g., 0.1-1 MHz) or an operational setting of the thermistor. In various embodiments, multiple frames may be averaged to create a final image frame for further analysis and / or display. In some embodiments, frames are sampled at a rate of 100 kHz, and these sampled frames may be averaged (e.g., averaged by 1 / (sqrt(#frames)) to further improve accuracy by reducing thermal noise; in general, the number of frames averaged to produce a single final frame may vary based on a trade-off between speed and noise level. Thus, in certain embodiments, thermistor operating settings may include the voltage / current at which the thermistor is driven, the number of frames averaged from the thermistor before transmission, and / or the waveform thermistor is driven with (duty cycle, sine wave vs. square wave vs. triangle wave vs. sawtooth wave vs. custom shape).

[0030] In some embodiments, the capsule can further include a drug reservoir, and the controller can be configured to receive a signal from the external device and release a drug payload from the drug reservoir. In some embodiments, the controller can be further configured to detect a target site by detecting heat emitted from the tissue of the subject and release the drug payload from the drug reservoir based on detecting the target site. In various embodiments, the drug payload can include one or more components of a corticosteroid, an immunosuppressant (e.g., a chemotherapeutic agent), a biologic (e.g., an anti-TNF-alpha, a Jak inhibitor, etc.), a gene therapy agent (e.g., adenovirally delivered siRNA, gene transfer, CART, TIL, mRNA, RNAi, oncolytic virotherapy, gene editing CRISPR-Cas9, TALEN, prodrug activation, immunotherapy, and / or small molecule therapy), and / or other agents (see Table 1 for a list of possible agents).

[0031] [Table 1] Table 1 shows the drug payloads that can be encapsulated.

[0032] In various embodiments, the controller is further configured to receive signals from an external device containing information regarding the current location of the capsule within the subject. In certain embodiments, the wireless transmitter can be configured to transmit to and from the external device at frequencies in the range of 300 MHz to 500 MHz, suitable for transmission through body tissue, and in certain embodiments, in the range of 430 MHz to 440 MHz.

[0033] In some embodiments, the capsule can further include a thermal imaging sensor configured to detect infrared radiation emitted from the tissue of the subject. In certain embodiments, the capsule can include a cylindrical housing, and the thermal imaging sensor can be disposed at an end of the cylindrical housing. In certain embodiments, the thermal imaging sensor can be configured to detect infrared radiation including wavelengths in the range of 7 μm to 14 μm. In certain embodiments, the thermal imaging sensor can include a thermopile sensor.

[0034] In some embodiments, the capsule can further include an ultrasound transducer coupled to the controller. The ultrasound transducer can be configured to acquire data indicative of the depth of feces between the capsule and the subject's tissue. In various embodiments, the controller can be further configured to acquire data indicative of the depth of feces between the capsule and the tissue from the ultrasound transducer. The controller can be further configured to transmit the data indicative of the depth of feces between the capsule and the tissue to an external device using a wireless transmitter and antenna.

[0035] In some embodiments, the capsule can include a window that is transparent to infrared radiation (e.g., transparent or translucent), and the window can be positioned adjacent to a thermal imaging sensor. In certain embodiments, the capsule can further include a reflector positioned adjacent to the thermal imaging sensor, and the reflector can be configured to redirect infrared radiation from the tissue toward the thermal imaging sensor. In some embodiments, the reflector can be configured to direct infrared radiation from an annular region around the capsule, e.g., a ring of tissue surrounding the capsule. In various embodiments, the reflector is conical or pyramidal, and in certain embodiments, the pyramidal reflector can include an apex that includes a triangular wedge.

[0036] In various embodiments, the capsule is part of a receiver belt that includes an external device and multiple receiver belt antennas that communicate with the external device, the receiver belt being worn by the subject, and the external device being capable of communicating with the capsule during the procedure. In some embodiments, the receiver belt includes a waist belt and shoulder straps that may be configured to hold the multiple receiver belt antennas in a fixed position relative to the subject's body.

[0037] In certain embodiments, the controller is further configured to receive a signal received from the external device, the signal received from the external device may include information regarding a current location of the capsule within the subject. In certain embodiments, the information regarding the current location of the capsule within the subject may be determined based on information from the multiple receiving belt antennas. The information from the receiving belt antennas can be used to determine the current location of the capsule within the subject based on a comparison with a predetermined data set relating the attenuation of the antenna signal to tissue depth.

[0038] In some embodiments, the information regarding the position of the capsule may be obtained using a neural network. In certain embodiments, the information from the multiple receiving belt antennas may be processed by a first neural network to identify at least one of a tissue type or a tissue thickness between the capsule and the surface of the subject adjacent the multiple receiving belt antennas, and the current position of the capsule may be determined based on the tissue type and / or the tissue thickness. In various embodiments, information including one or more current positions of the capsule, at least one of a tissue type or a tissue thickness, and / or data obtained from at least one temperature sensor may be processed by a second neural network to determine at least one of a lesion depth, a lesion type, or a lesion severity in the tissue of the subject. In certain embodiments, the information from the multiple receiving belt antennas may be processed (e.g., using a neural network or other procedure) to identify at least one of a tissue type or a tissue thickness between the capsule and the surface of the subject adjacent the multiple receiving belt antennas.

[0039] In various embodiments, the above-described devices and / or systems may be used to perform a method for detecting gastrointestinal pathology. In one embodiment, a controller of the capsule is configured to acquire data from a thermistor related to heat emitted from tissue of a subject at a first time, and the data may be used to determine a first position of the capsule at the first time based on information obtained from multiple receiving belt antennas (e.g., by the controller, an external device, and / or yet another system).

[0040] In some embodiments, a first image of the subject's tissue at a first location may be generated (e.g., by a controller, an external device, and / or yet another system) based on data from the first and second plurality of thermistors regarding heat emitted and detected from the subject's tissue at a first time. In another embodiment, a second data set from the thermistors regarding heat emitted and detected from the subject's tissue at a second time may be obtained, and this second data set may be used to determine a second location of the capsule at the second time based on information from the multiple receiving belt antennas. In certain embodiments, a second image of the subject's tissue at a second location may be generated (e.g., by a controller, an external device, and / or yet another system) based on data regarding heat emitted and detected from the subject's tissue at the second time. In some embodiments, a map of heat emitted from the subject's tissue may be generated (e.g., by a controller, an external device, and / or yet another system) based on the first image at the first location and the second image at the second location. In other embodiments, information from the first and second images may be combined to create a single, improved third image, which may also be used to generate a map of the heat released. Thus, as the capsule moves through the subject's body, the thermistor provides a detailed map of the subject's tissue, including information about tissue pathology.

[0041] In the above discussion, the temperature sensors are primarily referred to as thermistors, but in various embodiments, the temperature sensors may include one or more of thermistors, thermocouples, semiconductor-based sensors, and / or resistance-based temperature sensors. Additionally, various calculations or operations may be performed by one or more of a controller within the capsule, an external device, and / or other units in communication with the capsule controller and / or the external device.

[0042] Considering that active inflammation can cause elevated tissue temperatures, manifested as radiated infrared (IR) light (wavelength: 7-14 μm), various embodiments of the disclosed procedures provide a capsule with IR imaging capabilities. Accordingly, certain embodiments may provide a swallowable, wireless IR imaging capsule with IR imaging capabilities for imaging mucosal temperature and, therefore, inflammatory activity, along with systems and methods for collecting and processing data from the capsule. Of particular note, because heat diffuses through water-rich tissues and fecal content, various embodiments of the capsule can also identify intestinal inflammation occurring deep within the submucosa / muscularis layer. As a result, procedures based on the disclosed thermal IR imaging capsule may require little or no colonic bowel preparation. One or more embodiments provide procedures for at least one of the following: 1) characterizing the relationship between intestinal wall inflammation and temperature, 2) measuring intestinal wall temperature through feces, 3) operating the wireless thermal imaging capsule, and / or 4) detecting inflammatory bowel pathology in subjects with inflammatory bowel disease, such as Crohn's disease. Embodiments of the disclosed procedures provide a new platform technology that can be used for the diagnosis, routine monitoring of disease activity, treatment optimization, and targeted therapy of conditions such as Crohn's disease.

[0043] Crohn's disease (CD) is a chronic condition characterized by inflammation and irritation of any part of the digestive tract, from the mouth to the anus. Patients with Crohn's disease experience severe abdominal pain, fever, intestinal obstruction, diarrhea, blood or mucus in the stool, or both. Extraintestinal symptoms include anemia, arthritis, and decreased bone density, with rare complications characterized by inflammation of the skin, eyes, and liver. Patients are also at increased risk of developing colon cancer. These painful symptoms significantly impact patients' quality of life, productivity, and healthy lifespan.

[0044] The prevalence of Crohn's disease in the United States was recently reevaluated based on a population of 61 to 63 million patients reported annually in U.S. medical databases. This study found that the overall prevalence of Crohn's disease among children in 2016 was 45.9 cases per 100,000, a 148% increase from 18.5 cases per 100,000 in 2007. Interestingly, the majority of pediatric cases were first diagnosed in the 10- to 17-year-old age group. The prevalence among adults was 197.7 cases per 100,000 in 2016, a 125% increase from 88.0 cases per 100,000 in 2007.

[0045] The risk of developing Crohn's disease is influenced by both environmental and genetic factors. Genetic factors are most prevalent, but only modestly increase risk, with odds ratios ranging from 1.1 to 1.2. A small subset of genes, including the pattern recognition receptor gene NOD2, the autophagy gene ATG16L1, and the IL-23 receptor gene IL23R, are involved in the risk locus for Crohn's disease. In Asian populations, TNFSF15 has the most significant associated risk, while NOD2 is more prevalent in Caucasian populations. Only 13.1% of disease heritability is explained by genetic factors, leaving non-genetic environmental and epigenetic factors as the major contributors to CD risk.

[0046] Smoking doubles the risk of developing CD and has been identified as the most important environmental factor for the disease. Oral contraceptives also show a strong positive association with disease onset, while the following show weak positive correlations: appendectomy, low vitamin D intake, NSAID use (which also has a strong positive association with disease progression), antibiotic use, depression, and psychological stress. Low dietary fiber intake is negatively associated with disease onset, while high fat and high protein intakes are not associated with disease onset.

[0047] Diagnosing Crohn's disease is a lengthy process, requiring several months and the involvement of multiple specialists, as many of its symptoms are shared with various other diseases. Diagnosis requires evaluation of the clinical history, physical examination, serum and stool biomarkers, cross-sectional and endoscopic imaging, and finally histological examination of biopsy samples. CD can be classified three ways based on its location in the large or small intestine. Approximately one-third of patients present with small bowel CD, one-third with large bowel CD, and one-third with ileocolonic CD. Currently, ileocolonoscopy is the gold standard for diagnosing CD, but this procedure can miss small bowel CD. Patients with a negative ileocolonoscopy but a strong suspicion of CD undergo small bowel video capsule endoscopy (VCE). The diagnostic yield of CD, i.e., the likelihood of providing sufficient information for a diagnosis, is higher with VCE than with ileocolonoscopy (47% vs. 21%, P = 0.009), with the significant advantage of VCE being able to better image the portion of the small intestine closer to the stomach.

[0048] Due to its similarities with ulcerative colitis, endoscopy has proven crucial in distinguishing between the two diseases. The key difference between the two is that CD is characterized by intermittent patches of inflammation, whereas ulcerative colitis occupies a continuous area of ​​the colon. While ulcerative colitis is treated and even cured with colon resection, there is currently no cure for CD. Instead, treatment focuses on immunomodulators or TNF agonists. Early treatment of CD is associated with reduced risk of bowel and perianal surgery and fewer complications, such as strictures. Unfortunately, current methods are insufficient for early detection of the disease. 40% of patients diagnosed with CD develop intestinal damage within one year due to delayed diagnosis, which is associated with poor outcomes, including high rates of surgery and hospitalization. Therefore, more sensitive and convenient diagnostic methods are needed for early detection of Crohn's disease to improve treatment outcomes.

[0049] Previous researchers have performed infrared imaging with capsule devices, but this was done at shorter near-infrared wavelengths (e.g., 700 nm to 2500 nm) and typically included an IR light source, resulting in reflected infrared light being detected. In contrast, the present disclosure uses longer IR wavelengths (e.g., from 7 or 8 μm to 14 or 15 μm) and does not use a light source. Instead, the IR sensor in this disclosure detects long IR light emitted by tissue, typically inflamed tissue, which is associated with increased tissue temperature and is referred to as thermal IR imaging.

[0050] The techniques of the present disclosure would not be possible without relatively recent advances in thermal IR detectors. These devices use less power and are more compact than previous generations. Older detectors were too large to fit into swallowable capsules and / or older thermal IR detectors typically required cooling with liquid nitrogen.

[0051] Given the untethered nature of the capsule, a method for tracking the capsule's location over time is needed to correlate image information with specific anatomical locations within the subject. According to embodiments of the present disclosure, this problem is addressed by using multiple antennas positioned around the subject (e.g., attached to a belt coupled to the subject) to collect information wirelessly transmitted from the device. In addition to collecting the transmitted image information itself, the relative signal strength at each antenna can be used to help determine the capsule's location through triangulation / trilateration, as disclosed herein. Thus, in various embodiments, the location tracking algorithm can use preset measurements of signal attenuation and depth to allow signal strengths received at different antennas to be used for trilateration based on the preset measurements. The use of such a catalog of preset measurements, and the catalog itself, along with correction algorithms, may be used in a variety of other capsule- or catheter-based tracking systems and is not limited to the thermal IR embodiments disclosed herein.

[0052] To facilitate more frequent and / or easier testing, embodiments of the capsule device may perform thermal IR imaging through the feces and use information about the depth or thickness of the feces (e.g., obtained using an ultrasound transducer within the capsule) to adjust the signal strength of the acquired image.

[0053] Thus, in various embodiments, the present disclosure provides devices, systems, and / or methods for detecting inflammation in the gastrointestinal tract. The device can include a capsule (see FIG. 1) containing a thermal imaging sensor and can be configured to be swallowed by a subject (e.g., by making the capsule appropriately small and / or shaped for easy swallowing, such as a pill with rounded ends, as disclosed herein). The thermal imaging sensor can be configured to detect infrared radiation emitted from the subject's tissue (see FIG. 1). In certain embodiments, the IR capsule can include a printed circuit board (PCB) housing a microcontroller, an IR sensor, a power regulator, and a radio frequency (RF) transmitter. The electronics can be encapsulated in a polycarbonate capsule with a custom thermal IR lens.

[0054] In some embodiments, the capsule can further include a controller (e.g., including a processor and memory) connected to the thermal imaging sensor. The controller can be configured to generate at least one image of infrared light emitted and detected from tissue of the subject. The capsule can also include a wireless transmitter, and the controller can be configured to transmit collected image data (e.g., the at least one image) to the wireless transmitter, which transmits the at least one image to an external antenna (see FIG. 7). An external device (e.g., a remote computing system) connected to the external antenna receives the image signals and processes them for analysis and / or display to facilitate diagnosis and / or treatment of the subject (see FIG. 1). In various embodiments, the wireless transmitter can be configured to transmit at a frequency ranging between 400 MHz and 500 MHz, and in certain embodiments, at a frequency of 433 MHz.

[0055] In certain embodiments, the controller can be further configured to generate multiple images of the infrared radiation detected and emitted from the subject's tissue, and in some embodiments, can be configured to generate at least one image per second of the infrared radiation detected and emitted from the subject's tissue.

[0056] In various embodiments, the capsule can further include a power source including at least one battery.

[0057] In certain embodiments, the thermal imaging sensor can be configured to detect infrared radiation including wavelengths in the range between 7 μm and 14 μm. In some embodiments, the thermal imaging sensor can include a thermopile sensor.

[0058] In some embodiments, the thermal imaging sensor can further include an ultrasound transducer connected to the controller. In various embodiments, the controller can be further configured to acquire data from the ultrasound transducer indicating the depth of the feces between the capsule and the tissue. In certain embodiments, the controller can be further configured to transmit data from the ultrasound transducer indicating the depth of the feces between the capsule and the tissue from the wireless transmitter to an external device. Information regarding the depth of the feces is used to adjust the thermal imaging data, facilitating acquisition of thermal information from the tissue without the subject undergoing preoperative bowel preparation.

[0059] In some embodiments, the thermal imaging sensor can be configured to detect infrared radiation after a delay period. That is, there is a period of time after the subject swallows the capsule before the controller within the capsule begins collecting thermal imaging information and transmitting the information via the transmitter to the external antenna. This delay period is at least two hours in various embodiments, allowing time for the capsule to reach the specific portion of the digestive tract (e.g., the ileum) from which data will be acquired. The delay period extends the device's battery life by not collecting data earlier than necessary.

[0060] In certain embodiments, the capsule can include an infrared-transparent window adjacent to the thermal imaging sensor, and in certain embodiments, the window can include a biocompatible material, and in some embodiments, can include low density polyethylene (LDPE) (see FIG. 2).

[0061] In various embodiments, the capsule can further include a reflector positioned adjacent to the thermal imaging sensor, and the reflector can be configured to redirect infrared light from the tissue toward the thermal imaging sensor. In certain embodiments, the reflector can be configured to redirect infrared light from a circumferential region around the capsule. For example, because a typical gastrointestinal sample is a luminal (i.e., tubular) sample, the reflector can redirect thermal IR light from a circumferential "ring" of sample adjacent the end of the capsule toward the IR sensor surface. The reflector can be a catadioptric reflector in some embodiments and can include a pyramidal shape, although in certain embodiments, the reflector can include an apex that includes a triangular wedge (see FIGS. 2-4). In other embodiments, the reflector can have a round shape (see FIG. 5).

[0062] In some embodiments, the at least one image can include multiple images, and the controller can be configured to average the multiple images and transmit the averaged image to a wireless transmitter for transmission to an external antenna. As disclosed herein, averaging two or more images improves the signal-to-noise ratio and therefore allows for the detection of small differences in thermal IR levels.

[0063] In various embodiments, a system for detecting inflammation in the gastrointestinal tract can include a capsule including a thermal imaging sensor and a wireless transmitter in communication with a controller. The system can also include multiple antennas in communication with the capsule, and the capsule can be configured to be swallowed by the subject. In some embodiments, the thermal imaging sensor can be configured to detect infrared radiation emitted from the subject's tissue, and the controller can be configured to generate at least one image of the detected infrared radiation emitted from the subject's tissue. In certain embodiments, the controller can be configured to transmit the at least one image to the wireless transmitter, and the wireless transmitter can transmit the at least one image to multiple antennas, and the multiple antennas can be configured to receive the at least one image from the wireless transmitter (see FIG. 7 ).

[0064] In some embodiments, the system can further include a computing system in communication with the plurality of antennas, the computing system can be configured to determine the location of the capsule based on the plurality of antennas receiving at least one image from the wireless transmitter. In various embodiments, the computing system can be further configured to determine the location of the capsule based on the amplitude of a signal received by each of the plurality of antennas. In certain embodiments, the computing system can be further configured to determine the location of the capsule with an uncertainty of 1 cm or less, while in other embodiments, the uncertainty can be 10 cm or less, 5 cm or less, 2 cm or less, 0.5 cm or less, or 0.1 cm or less.

[0065] In various embodiments, the plurality of antennas can include eight antennas. In other embodiments, the number of antennas ranges from 1 to 20 and can include 1, 2, 3, 4, 5, 10, 15, or other numbers of antennas. In some embodiments, the antennas can be coupled to a belt, and the belt can be configured to be coupled to the subject (see FIG. 6A). In other embodiments, the antennas can be attached to the subject using an adhesive (see FIG. 6B).

[0066] In some embodiments, the at least one image can include a plurality of images, each having a first image resolution, and the computing system can be further configured to process the plurality of images to obtain at least one super-resolution image having a second resolution higher than the first resolution. In particular embodiments, at least two of the plurality of images can correspond to at least two different positions of the capsule, and the computing system can be further configured to obtain the at least one super-resolution image based on interpolating at least two of the plurality of images corresponding to the at least two different positions of the capsule.

[0067] Thus, in various embodiments, the disclosed devices, methods, and systems can be used to detect deep-seated sites of inflammation that are not visible with visible light endoscopy. Thermal imaging has the potential to provide a more sensitive diagnostic tool that allows for more reliable identification of sites of inflammation than existing techniques.

[0068] Applications of this technology include, but are not limited to, the detection of all forms of inflammation in the gastrointestinal tract, including non-IBD-related colitis, IBD (e.g., Crohn's disease, ulcerative colitis associated with IBD), infections, ulcers, cancer, and diverticulitis. Furthermore, the disclosed technology can be used to detect and evaluate cancer and inflammatory conditions in other hollow organs. Embodiments of the disclosed device have applicability much broader than IBD and can be applied to very common conditions such as diverticulitis, cancer, and ulcers. They are also associated with many other infections, such as Helicobacter pylori (H. pylori), and may be useful for eosinophilic esophagitis and gastritis.

[0069] Considerations regarding the implementation of the various components of the system are disclosed below.

[0070] (IR sensor) Thermal imaging detects light in the long-wave infrared regime (LWIR), between 8 and 14 microns. Early forms of thermal imaging required the sensor itself to be cooled by Peltier elements or liquid nitrogen to prevent the sensor's thermal radiation from interfering with the measurement. Driven by military contracts in the 1990s, modern uncooled focal plane arrays were developed, utilizing microbolometers, pyroelectric technology, and thermopiles. This development enabled uncooled thermal measurements in processes compatible with modern silicon manufacturing. As of 2010, microbolometers formed the majority of commercially available uncooled sensors, accounting for 95% of the market. Microbolometers rely on materials such as vanadium oxide that change resistance when exposed to LWIR radiation, while thermopiles contain micron-sized thermocouples that generate a voltage in response to heat and IR radiation. Currently, state-of-the-art miniature thermal imaging microbolometers achieve a sensitivity efficiency of 34 μW per pixel at a pixel size of 12 μm, and state-of-the-art thermopiles achieve 20.2 μW per pixel at a pixel size of 40 μm. Consequently, the choice of IR sensor array type depends on both the power and space budget of a device like Pilcam.

[0071] Thermography's ability to detect inflammation throughout the body has been documented by experts in the field. In rodent models, injection of 1% carrageenan into the pleural cavity, lower lip, and paw induced elevations in histamine, serotonin, prostaglandins, kinins, and interleukins, resulting in a temperature increase of at least 0.7°C at all injection sites. In rabbits, atherosclerotic plaques showed islands of macrophage-induced temperature increases of 0.5°C at locations less than 1 mm away from normal temperature zones. Similarly, surface thermography of the faces of patients with and without sinusitis demonstrated a 0.5°C temperature increase between the surface temperature of the nasal region and the axillary temperature. Finally, a human deep tissue incision model showed that inflammation resulting from a deep tissue incision (1.5 cm x 0.25 cm) caused a local temperature increase of 0.25°C to 0.9°C.

[0072] In various embodiments, the IR sensor can include a 16x16 pixel array, a 32x32 pixel array, a 64x64 pixel array, or other pixel configurations as required for a particular application.

[0073] (reflector) Figure 4 shows several embodiments of reflectors for reflecting light from the sample to the IR sensor, illustrating the degree to which each type of reflector covers the IR sensor. In the left panel of Figure 4, the bottom photograph shows an IR sensor with a conical reflector, and the top photograph shows the field of view of the IR sensor with a conical reflector, indicating the location of a "blind spot" on the IR sensor that does not receive reflected light. In the center panel of Figure 4, the bottom photograph shows an IR sensor with a wedge-shaped reflector, and the top photograph shows the field of view of the IR sensor with a wedge-shaped reflector, indicating the location of a "blind spot" on the IR sensor that does not receive reflected light. In the right panel of Figure 4, the bottom photograph shows the catadioptric reflector of Figures 2 and 3, and the top photograph shows the field of view of the IR sensor with a catadioptric reflector, indicating the location of a "blind spot" on the IR sensor that does not receive reflected light. As shown in the right panel, the catadioptric reflector minimizes blind spots and maximizes IR sensor utilization. Different types of reflectors can be used, but in all cases, the thermal IR energy reflected by the IR sensor can be mapped to the portion of tissue where the energy originated, identifying the location of elevated temperatures. This mapping is based, at least in part, on the assumption that the tissue of origin is a luminal (tube-like) structure surrounding the capsule. Combined with the time and position of the capsule when each image is taken, the image information can be mapped to the correct portion of the digestive tract.

[0074] (Battery Technology) One of the biggest limitations of IR sensors is their power consumption; for example, a state-of-the-art, single-pixel miniature thermopile consumes 20.2 μW. For comparison, a visible-light camera sensor in an endoscope consumes 300 nW per pixel. As a result, the battery must support a 20 mW power consumption for a full-sensor, independent of any additional technology that may be included in such a device. A typical 8-hour capsule endoscopy procedure requires 55 mAh from a 3 V battery to provide continuous imaging. Aqueous batteries are suitable for swallowable devices because they are resistant to thermal runaway and combustion. Silver-zinc (Ag-Zn) compositions offer the highest commercial power density of any aqueous battery. For reference, a size 312 Ag-Zn battery delivers 5–10 mA at 1.8 V and has a capacity of 35 mWh. Lithium iodide and lithium batteries are also used in many implants, such as pacemakers, allowing for higher current consumption and capacity. Taking up the same space as eight size 312 batteries, a size 2LZ6 coin cell provides 60-80mA at 3V and has a capacity of 480mWh, but requires temperature monitoring circuitry to prevent thermal runaway and combustion.

[0075] (wireless transmission through human tissue) Radio frequency (RF) attenuation in human tissue can be accurately modeled by approximating organs and tissues as homogeneous dielectric blocks. Using this model, two types of losses occur: reflection at dielectric boundaries and tissue absorption, which convert RF energy into thermal energy. The absorption coefficient (A) of radiation by human tissue is given by Equation (1), and the reflection coefficient (R) is given by Equation (2), assuming normal incidence and uniform permeability between tissues.

number

number

[0076] where k′ and k″ are the positive real and imaginary components of the wave vector, respectively, w is the angular frequency of the wave, z is the depth to which the wave has penetrated the tissue, μ and ε are the permeability and permittivity of the tissue, respectively, σ is the electrical conductivity of the tissue, and ε r1 , ε r2 is the permittivity of the two tissues that meet at the reflecting boundary. A comprehensive database for modeling lossy tissues has been established over the past decade and is used throughout the RF industry for finite-difference time-domain (FDTD) simulations. Figure 9 shows a dielectric model of a morbidly obese patient with a receiver 4.7 inches from the intestinal lumen.

[0077] (Preliminary data) Wireless Transmission. When working with RF signals in lossy environments such as human tissue, it is desirable to select a transmit power that ensures that the received power is sufficient for detection. Using the model shown in Figure 9, we calculated the reflection and transmission losses at 433 MHz for varying depths in visceral and subcutaneous fat, as shown in Figure 10. To verify the results, we sacrificed a 43 kg pig to perform the tissue model and implanted a 433 MHz MAX41464 transmitter in the omnidirectional half-dipole configuration within the ileocolonic region. We observed a loss of 22 dB at a depth similar to that of the model shown in Figures 9 and 10. Considering the receiver sensitivity of -45 dBm, a transmit power of 15 dBm fully meets the link budget. We also observed a 20° transmission cone before total reflection was observed. This result is consistent with previous studies.

[0078] [Table 2]

[0079] Table 2 shows the average voltage measured by a Heimann IR 2.1f 32p x 32p thermopile camera with a window substrate of different thicknesses immediately before the sensor. An IR black body source was used to generate temperatures in the expected biological range (see Figures 8A-8B). Figure 8A shows the experimental setup for generating a hot spot to perform ex vivo testing of the wireless thermal IR imaging capsule, and Figure 8B shows the thermal IR imaging results obtained by observing the hot spot with the capsule device through a resected section of ileum tissue.

[0080] (lens) Typical commercially available lens and window designs for long-wavelength infrared (LWIR) wavelengths use silicon, potassium bromide, zinc selenide, and germanium windows. Of these, only silicon is known to be biocompatible, and even then, it may exhibit mild toxicity. Furthermore, silicon windows are brittle and at risk of breakage due to pressure within the gastrointestinal tract. As a result, we sought to identify biocompatible, flexible polymers that could transmit LWIR light. We tested three materials commonly used in our laboratory prior to optical coherence tomography (OCT) capsule construction: polycarbonate (PC), polymethyl methacrylate (PMMA), and low-density polyethylene (LDPE). Based on previous literature, all three materials had passbands with different lengths in the 8-14 μm range. A calibrated black-body source (SR-33, manufactured by CI Systems) was used to display a temperature of 37-38 °C, followed by measuring the voltage recorded by a 32p × 32p thermopile array-based LWIR camera. Based on the results shown in Table 2 above, the LDPE lens has the lowest attenuation, indicating that its sharp stop band at 14um will have the least impact over the temperature range of interest.

[0081] (prototype) One embodiment of a prototype device (Figure 11) was built using a Heimann IR 32p x 32p thermopile array, a MAX41464 transmitter, and a MAX32630 microcontroller. The components were selected based on being the most power-efficient and compact unit on the market.

[0082] The IR sensor communicates with a 1.2mm x 1.2mm MAX32630 microcontroller via a two-wire 1MHz I2C bus. Using calibration data stored in the IR sensor's electrically erasable programmable read-only memory (EEPROM), the microcontroller performs initial IR image construction to interpret the thermopile's transient voltage, offset voltage, gradient, and ambient temperature. From there, the microcontroller transmits each frame via 400kHz I2C to a MAX41464 2mm x 5mm transmitter chip. The data is transmitted over a 433MHz solenoidal half-wave dipole using Gaussian FSK with a 200kHz bandwidth and a 100kHz baud rate. A Nooelec NESDR SMArt XR software-defined radio (SDR) receives the FSK over a 433MHz monopole at a 2MHz sampling rate. The data is processed in MATLAB® and SIMULINK® to display the video feed and store the image data for further processing. Figure 12 shows a block diagram of the device.

[0083] (electricity) Each component of the IR capsule was isolated during normal operation and its current was measured while the operating voltage was held at 3.3V. The resulting current and power consumption are recorded in Table 3. The MAX41464 transmitter exhibited the highest power consumption while transmitting, but since it transmits 16dBm (40mW), only 8.7mW is actually consumed by the device during operation.

[0084] [Table 3] Table 3 shows the measured power analysis of the components of the prototype IR capsule. The pull-up resistors required for I2C communication are summarized together with the microcontroller power.

[0085] We tested three types of batteries to power the device: ZPower Silver Zinc (AgZn) 312 cells, Energizer® Silver Oxide size 394 cells, and Li / MnO2 L76 size cells (see Table 4). We compared options using cells of the same volume, and Li / MnO2 provided the best performance. For initial pig trials, we plan to use the Li / MnO2 composition in 13 mm capsules, as we will be contracting with a third party to create smaller diameter, longer Li / MnO2 cells for the 11 mm capsules used in patient trials.

[0086] [Table 4] Table 4 shows the performance of implantable battery chemistries when used at the same volume.

[0087] (Ex-Vivo) For the ex vivo study, a 30 cm section of the large intestine from a 52 kg pig was cleaned with feces and sutured at one end to make it waterproof. The central 3 cm of the intestine (13.5 cm to 16.5 cm in length) was wrapped with a resistive heating element. A thermocouple was placed between the heating element and the tissue. The resistive heater and thermocouple were connected to a switching power supply thermostat (DROK Electronic Thermostat Controller). The thermostat was set to 38°C with a tolerance of + / - 0.2°C. The tissue and heating device were placed in a thermal bath heated to 37°C (see Figure 13). The device shown in Figure 12 was advanced toward the simulated inflammation site while images were wirelessly transmitted and received at a rate of 1 frame per second. A diagram of the experimental setup is shown in Figure 14, and the resulting images are shown in Figure 15.

[0088] We developed and validated a wireless infrared imaging capsule to detect and localize inflammation within the gastrointestinal tract.

[0089] The following sections describe the development and validation of an embodiment of a wireless thermal infrared imaging capsule that offers a significant advance in the diagnosis of various conditions, including Crohn's disease. The noninvasive capsule device is more sensitive to inflammatory activity than other imaging approaches (e.g., MRI, CT, endoscopy / VCE), provides information about inflammation deep within the bowel wall, and minimizes or eliminates preoperative bowel preparation.

[0090] The IR capsule is developed in our lab using an FDA-recommended, industry-standard design control process to ensure the device meets end-user needs and operates safely as intended. This process includes establishing design inputs, periodic design reviews, risk analysis, design verification, and validation, all documented in a design history file. Once the device is manufactured, it is validated in phantoms and preclinically in a porcine injury model of enteritis.

[0091] The design input specifications are as follows: Tables 4 and 5 show two initial target design input specifications for the wireless thermal imaging capsule, based on the specifications of existing VCE devices and our current understanding of temperature changes associated with tissue inflammation. Refinement of these specifications will occur as results are obtained from various gastrointestinal inflammation experiments.

[0092] [Table 5] Table 5 shows the wireless IR capsule input specifications.

[0093] [Table 6] Table 6 shows the IR wireless capsule input specifications.

[0094] High-level schematic diagrams of wireless infrared capsule embodiments are shown in Figures 16A and 16C (single IR sensor) and 16B (dual IR sensor). While the embodiments shown in Figures 16A-16C include a lens or round window to direct light to the IR sensor, other embodiments disclosed herein may use a catadioptric reflector placed in front of the IR sensor to direct light to the sensor (see, e.g., Figure 2). The IR sensor communicates with an RF transmitter chip, which is controlled by a microcontroller on a PCB and transmits data via a quarter-dipole coil antenna housed around the PCB. Similar to commercially available colonic VCE devices, certain capsule embodiments may include imaging detector arrays (sensors) at each end of the capsule to simultaneously acquire images in the anterior and posterior directions (see Figure 16B). Each IR sensor is associated with a microcontroller, transmitter, and battery mounted on a printed circuit board (PCB). All components are housed in a hermetically sealed 11 mm x 32 mm polymethyl methacrylate (PMMA) shell that is biocompatible and transparent to IR light. In various embodiments, the capsule will be the same size as the Given PillCam® Colon 2 VCE device.

[0095] Figure 17 shows an overview of the data stream for the thermal capsule and recording system. Data is transmitted from the capsule to the receiver belt and stored on two SD cards. The SD card on the front of the receiver belt's main module stores image data, while the SD card on the back stores location tracking data. The SD cards can be removed and replaced with new or identical cards at any time to monitor their contents and extract data such as the capsule's location. The antenna must be positioned on the subject relative to the xiphoid process, as shown in Figure 35. The receiver belt is then attached using a strap (e.g., like a purse), and the subject swallows the wireless thermal capsule. Briefly, N thermal images are captured and digitized by each IR sensor. The N frames are transferred to a microcontroller via an I2C serial communication protocol bus. The microcontroller includes a processor that averages the N frames to reduce noise and improve thermal detection sensitivity. The averaged images are transmitted from the capsule using a carrier RF frequency of 433 MHz. RF signals are transmitted wirelessly through the body and detected by multiple spatially offset receivers within a belt worn by the patient. The image data is then demodulated and stored by a recorder worn by the patient. The images are transferred from the recorder to a computer, where a custom super-resolution algorithm is applied, operating on M averaged frames, to reconstruct a final image with more pixels than the individual sensors. Data from the different receivers within the belt is also input into an algorithm that recovers the 3D position of the capsule for each image. The capsule is designed to turn off within its magnetic housing and begin transmitting within 5–6 seconds of being removed from the magnetic housing. These components and algorithms are described in detail below.

[0096] (sensor) Until recently, the power requirements and size of IR detector arrays hindered the development of wireless thermal imaging capsules. However, 32 x 32 pixel IR arrays are now in production, allowing their incorporation into thermal imaging capsules and facilitating the development of the disclosed capsule device. In some embodiments of the device, the sensor is a Heimann IR 32 x 32 array, which has a minimum commercial power consumption of 5-7 mA at 3 V and can operate from a non-flammable button cell battery. Two wide-field, sensor-mounted lenses (in embodiments using lenses to direct light to the sensors) at each end of the capsule allow for approximately 360° visualization of the luminal surface.

[0097] In some embodiments, the IR sensor may include two thermistor rings, each containing a thermistor array containing thermistor temperature sensors arranged along the capsule wall (see Figures 23, 24, 26A, and 26B). By collecting temperature readings from each thermistor in the array at specific intervals as the capsule passes through tissue, the collected data can be used to generate one or more images (e.g., two-dimensional images) of the heat radiating from the tissue. The precision contact thermistors are configured to measure temperature and convert it to a digital value via an onboard microcontroller. The capsule then wirelessly transmits the data to an external battery-powered receiver belt using Gaussian frequency shift keying in the 430-440 MHz frequency range, a frequency range with optimal electrodynamic characteristics for transmission through human tissue. The receiver belt may determine the capsule's location using relative signal strength across eight different antennas. The receiver belt may store both temperature and location data on two separate SD cards.

[0098] (sensitivity) One area of ​​interest is the development of methods to achieve high IR detection sensitivity, allowing for the measurement of small temperature changes. Because the detector array itself cannot be modified, a technique of averaging consecutive frames was used instead. This reduces thermal noise and increases sensitivity with the square root of the number of frames averaged. IR sensors have a pre-measured noise equivalent temperature difference (NETD), which is the standard deviation of pixel values ​​in milli-Kelvin. The Heimann sensor, selected for its low power requirements, compact packaging, and highest resolution, has a NETD of 340 mK. As noted above, frame averaging reduces the NETD by the inverse square root of the number of frames averaged, so approximately 12 frames must be averaged to achieve 100 mK. Therefore, in various embodiments, frame averaging is implemented in the capsule's microcontroller to achieve a target temperature resolution / variance of 0.1°C, which is within the range of temperature increases associated with inflammatory activity in other organ systems.

[0099] (Super resolution) Because the 32x32 pixel array produces relatively low-resolution images, we develop novel algorithms to improve resolution by multiplexing spatially offset images into a single high-resolution image. Because each successive average frame acquired by the array is slightly spatially offset (e.g., due to capsule movement between frames), we implement a super-resolution algorithm that acquires a set of M-shifted average images and interpolates them to obtain sub-pixel information. In various embodiments, acquisition of 16 consecutive 32x32 images can achieve VGA-level (512x512) resolution, similar to commercially available VCE devices.

[0100] (microcontroller) Highly efficient millimeter-sized microcontrollers and transmitters are commercially available that communicate via the I2C protocol and require minimal firmware development. In one embodiment, a prototype device using a MAX32630 microcontroller 1.2 mm x 1.2 mm chip has been built and used to perform 5-frame averaging while consuming only 200 μW peak power (see Figure 15).

[0101] (frame rate) The sensor and microcontroller are capable of 1MHz I2C communication, with each frame requiring 4224 to 5248 bits of information, yielding an average frame rate of 24 frames per second. The transmitter communicates over 400kHz I2C, transmitting at a baud rate of 100KHz. As a result, each frame takes 0.516 seconds, providing a frame rate of 1.94 frames per second.

[0102] (Battery power system) The highest energy density among commercially available aqueous button cells (aqueous cells are resistant to thermal runaway and combustion) is achieved with a silver-zinc (Ag-Zn) composition. For reference, a size 312 button Ag-Zn cell provides 5–10 mA at 1.8 V and has a capacity of 35 mWh. Two 312 Ag-Zn cells can provide 10 mA at 3.3 V with 20 mA bursts for transmission. For continuous imaging, the current design consumes an average of 21.96 mW, allowing for approximately 3.1 hours of continuous imaging. Device operation (including transmission) is delayed for a period of time after swallowing (e.g., approximately 2–3 hours in certain embodiments) to allow the device to reach the ileum. To extend battery life and enable ileocolonic recordings for 8 hours or more, some embodiments allow for imaging with an on-off cycle every 5 seconds. Based on the preliminary data presented in Tables 2 and 3, 30 mAh per hour is required from a typical Li-MnO2 3V battery. An 8-hour procedure requires 240mAh at 3V from the battery.

[0103] In some embodiments, the wireless capsule is powered by a lithium manganese oxide battery located near the rear cap of the capsule, which is capable of drawing an average current of approximately 6 mA and a peak current of 9 mA at 3 V (see Figures 24 and 30). This is less than 400% of the pulse current specification of lithium manganese oxide batteries commonly used in capsules. Lithium manganese oxide batteries are used in various embodiments due to their non-volatile composition, long life, and ability to drive medium current devices.

[0104] The capsule is further configured to check battery voltage both in hardware and software, initiating a graceful shutdown when the battery is nearing depletion. The software checks battery voltage using an ADC input on a GPIO pin. Since the battery is specified to operate at 2.0-3.0V, when the battery reaches 2.2V, the software triggers the shutdown process, turning off all microprocessor subsystems, and the capsule enters the off state.

[0105] The main regulator hardware checks if the battery is nearing depletion and, if so, performs a hardware cutoff of power. The capsule poses no risk to subjects when powered off, either gently at the end of battery life or suddenly by a hardware cutoff.

[0106] (Radio transmission) The MAX41464 transmitter transmits I2C image sensor data encoded at 433 MHz, providing a data rate of 200 kbps. When transmitting through the human body, RF signals are attenuated and reflected as they pass through different tissue layers. One approach to determining whether a wireless signal can be reliably received is to model human tissue as a layer of lossy dielectric (see Figure 9). Using this model, we estimated RF attenuation losses, calculated our link budget, and confirmed that a sufficiently strong signal could be transmitted through the body. For a 0 dBm (1 mW), 433 MHz signal, our model predicts a 27 dB transmission loss for a human, assuming the receiver is 4.7 inches from the intestinal lumen (see Figure 9). Furthermore, in a preliminary tissue model using a sacrificed 43 kg pig, we observed a 22 dB loss at a similar depth. Considering a conservative receiver sensitivity of -45 dBm, this data indicates that a transmit power of 0 dBm adequately meets the link budget.

[0107] (Printed Circuit Board (PCB)) In various embodiments, four components (sensor, microcontroller, battery, and transmitter) can be combined onto a single PCB prototype, as shown in Figures 13a, 14, and 17. In some embodiments, the board occupies 8.8 mm x 17 mm x 1.6 mm, reserving space for two 3 V batteries within the capsule housing. Figures 14 and 17 show internal block diagrams of how the different components on the board communicate with each other. The IR sensor communicates with the microcontroller via a two-wire I2C bus, which performs initial IR image processing, interprets thermopile information, and applies calibration data stored in the IR sensor's electrically erasable programmable read-only memory (EEPROM). From there, the microcontroller performs frame averaging, and the averaged image is transferred to the transmitter via another I2C line.

[0108] Further, as shown in FIGS. 23 and 24, in some embodiments, the capsule can include four printed circuit boards (PCBs) arranged around the thermistor ring, drug reservoir, and battery throughout the capsule. For example, PCB1 can be connected to and positioned around the thermistor ring array to improve thermal conductivity (see FIGS. 26 and 32). Furthermore, in some embodiments, more than one thermistor ring can be used. The thermistor sensors do not need to be perfectly aligned; in some embodiments, they can be offset from one another by rotating the individual rings of the thermistor by any amount, for example, any angle. Two PCBs, PCB2 and PCB3, can be configured to be located within the processing unit and wireless transmitter and further distally surrounded by the antenna and drug reservoir (see FIGS. 27-29). PCB4 can include a holder for contacting the back of the power source (see FIG. 31). PCB1-PCB4 can be connected to one another via a circuit board housing and configured to be folded and assembled within the capsule (see FIGS. 32 and 33).

[0109] (receiving belt) The receiving belt includes a main module, battery, antenna leads, and holster / belt. In certain embodiments, an eight-lead antenna configuration can be used to receive capsule image data, while other embodiments can use a variety of antenna numbers, such as one to twenty antennas. The eight antennas are located within a wearable belt that transmits data to a recorder and may be spaced 5 to 10 centimeters apart. The holster attaches to both the shoulder strap and the belt, ensuring it remains in place (see Figure 35). Capsule location tracking is achieved by triangulating the position from the amplitude of the received signal to the antenna lead array built into the belt. The main module continuously sweeps all eight antennas and records the signal strength to track the capsule's location. The antenna receiving the strongest signal strength is constantly updated and used to receive and record capsule data. Thermal data from the wireless thermal capsule is demodulated from baseband, decoded, and stored on an SD card located on the front of the main module. A second SD card is located on the back of the main module, which stores signal strength data for location tracking from the continuous sweep. Two serial ports for each SD card enable JTAG-to-USB serial access, allowing live streaming of thermal image data and capsule position. Data is transmitted encrypted and can be decrypted and displayed in real time for assessment of capsule position and device functionality. The current VCE capsule achieves a position tracking resolution of 3.8 cm. We believe that the position resolution is limited by high attenuation and variability in signal strength as the capsule moves. To achieve better resolution, we utilize a 16-bit analog-to-digital converter (ADC), enabling a resolution of 1 mdBm for an RF detector with a 70 dB dynamic range. This configuration should enable millimeter-level capsule position tracking resolution. Based on recent research conducted in our lab, we found that a 20° cone encompasses the entire transmitted signal.Therefore, to avoid signal dead zones, we configured the 8-lead receiver belt to collect RF data over this angular range for all capsule positions. The main module is powered by a 3.7 V rechargeable battery, with the PCB and battery held in separate compartments in a plastic case. The plastic case is encased in a fabric pouch attached to a shoulder strap, which provides vertical support and prevents shaking (see Figures 35A and 35B). The design is configured to hold the main module comfortably close to the subject during use and minimize the possibility of the antenna being pulled away from the subject. The main module of the receiver belt is reusable, while the antenna is disposable.

[0110] In various embodiments, the receiver belt may use a lithium polymer battery, with both hardware and software checking the battery voltage and initiating a graceful shutdown when the battery is nearing depletion.

[0111] The software checks the battery voltage using the ADC input on the GPIO pin. Since the battery is specified to operate from 3.7 to 2.2V, if the battery reaches 2.2V or below, the software triggers the shutdown process, turning off all microprocessor subsystems, and then the receiver enters the off state. The main voltage regulator also checks if the battery voltage is below 2.2V and, if so, cuts power to the device. In addition to this, lithium polymer batteries have built-in control circuitry that disconnects the battery if a short circuit condition is detected.

[0112] Table 7 lists the specifications of the wireless thermal receiver belt. The receiver belt has a small footprint (e.g., occupies a volume of 7 cm x 7 cm x 2 cm or less) and is configured to fit into a cloth pouch worn by the subject. The total weight of the wireless thermal receiver belt is 1.1 lb (approximately 0.5 kg) or less, and the antenna is designed with a medical-grade adhesive to minimize skin irritation. For signal fidelity, a low-noise chipset with a noise floor of -120 dBm was selected to minimize the power required from the capsule. A frequency of 430–440 MHz was selected to minimize attenuation and interaction with the human body.

[0113] [Table 7] Table 7 shows the specifications of the wireless thermal receiving belt.

[0114] (Capsule location) Capsule localization is performed using triangulation of signal strength from the receiver belt. This means that each measurement requires an uncertainty of 1 / 3 cm for a final uncertainty of 1 cm. Considering preliminary data on a 22 dB loss in a pig model at a depth of 14.8 cm, a 0.5 dB difference needs to be resolved at a signal strength of around -15 dBm, requiring a noise floor higher than -26 dBm. To easily achieve this requirement, we built a receiver using a Nesdr Nooelec Smart radio with an inherent noise floor of -90 dBm and a sensitivity of -45 dBm.

[0115] (Verification of capsule performance) A blackbody source can be used to validate the capsule's thermal resolution / sensitivity and optimize the viewing angle. The capsule's temperature measurement capabilities in a blackbody radiation phantom and in a thermally conditioned porcine intestine ex vivo can be tested using a flexible thermoelectric generator (FlexTEG) device.

[0116] An extended-area blackbody source (SR-33, CI-Systems) is used to project a uniform temperature surface within an insulated temperature-controlled box, generating a two-dimensional mapping between the measured temperature and pixel values ​​and the ambient temperature. This is necessary because the thermopile voltage changes based on the ambient temperature. Once calibration is complete, an ex vivo study is performed in which the capsule images the lumen of a pig intestine. The pig intestine is sutured watertight on one side and immersed in a temperature-controlled water bath at 37 °C. Thermally regulated regions (with an increase of 0.5 °C to 1.5 °C) created from resistive and Peltier heaters simulate inflammatory spots. The temperature along the tissue and at the inflammatory site is measured with a non-metallic fiber-optic temperature sensor (TS5, Micronor).

[0117] (Animal research verification) The capsule prototype was introduced (using the AdvanceCE® Delivery Device) into the duodenum of three cohorts of adult pigs (50–75 kg) (pre-treated, minimally pre-treated, and no pre-treated) for 7 days after administration of DSS or TNBS-EtOH. A modified receiving / recording belt was attached to the pigs, and parameters were slightly adjusted to account for anatomical differences between pigs and humans. The pigs were allowed to recover and ambulate, and in vivo thermal images of the small and large intestines were recorded. Ileocolonic lesions associated with elevated temperatures were identified along with their corresponding locations within the intestine. The location of the capsule was confirmed by anterior-posterior and lateral X-rays taken every 30 minutes. After the capsule passed through the gastrointestinal tract, the pigs were sacrificed, the small and large intestines were dissected, and normal and elevated temperature lesions (determined by capsule location) were submitted for histological examination. The histology was evaluated by a pathologist blinded to the thermal imaging data. The temperatures of areas determined to be inflamed by pathology were compared with those of non-inflamed areas using a t-test.

[0118] (Validation of IR imaging capsule in a pig model) Inducing an inflammatory response along the pig intestine and identifying the site of inflammation confirms the IR capsule's ability to consistently detect the inflammatory response. In some embodiments, a pig injury model is used, involving intragastric administration of dextran sulfate sodium (DSS) or intraintestinal injection of 2,4,6-trinitrobenzene sulfonic acid (TNBS). Both methods have been established to induce transmural inflammation in pigs. The pigs are allowed a 7-day recovery period, after which the inflammatory site is examined using both a high-resolution IR borescope (TB-1710, Vividia) and a capsule device attached to a capsule deployment device (AdvanceCE® Delivery Device). The pigs are then sacrificed, and the small and large intestines are dissected. This study can be repeated in animals with minimal or no preoperative bowel preparation.

[0119] (Histopathological analysis) Standard H&E and immunohistochemical (IHC) processing was performed, including CD45 (leukocytes), CD3 (T lymphocytes, T helper cells), CD4 (T regulatory cells, monocytes, macrophages, and dendritic cells), CD68 (monocytes, macrophages, and dendritic cells), and metalloproteinase and cathepsin (lysosomal) enzyme stains. All of these IHC stains are known to be elevated during inflammatory processes. Slides were digitized using a whole-slide imaging system (Nanozoomer) and evaluated at different 100-micron depth intervals by two pathologists blinded to the thermal images. Inflammatory cell counts, areas of inflammatory / enzyme activity, and staining percentages were automatically calculated from the digitized slides and tabulated by depth.

[0120] (Statistical basis for animal numbers) Assuming a 1°C increase in temperature between inflamed and non-inflamed areas, a standard deviation of 1°C, and an intra-animal correlation coefficient of 0.5, 13 inflammatory lesions and 13 non-inflamed areas provide 90% power to detect differences between two groups using a two-tailed paired t-test with α = 0.05. Because we expect to image 2-3 clearly demarcated inflammatory lesions per animal, approximately 5 animals are required for each study (preoperative bowel preparation, minimal preoperative bowel preparation, and no preoperative bowel preparation). Therefore, a total of 15-20 animals will be used for preclinical device validation.

[0121] The sensitivity is insufficient. If the thermal noise in the image is too high, an adaptive frame averaging algorithm can be incorporated to increase or decrease the number of frames. The on-board microprocessor can calculate the standard deviation between the previous and current frame and calculate the number of frames required to achieve adequate image uniformity. If this is ineffective, a transceiver can be incorporated to allow the position tracking algorithm to determine the number of frames required based on the device's velocity and communicate the frame rate to the capsule.

[0122] Pig fecal content differs from that of humans. The pigs used in this study will be fed a human diet. However, thermal characteristics of pig feces will be collected and compared with human feces from colonoscopies with inadequate preoperative bowel preparation to confirm the validity of the pig model.

[0123] (Determining the optimal architecture for IR capsule endoscopy) Due to size and power limitations of IR sensor arrays, images are lower resolution than visible light sensors. Video capsule endoscopy is already limited in resolution due to similar size and power constraints, and neural networks have been shown to be a clinically successful method for improving diagnostic power by increasing resolution. While visible light images use a combination of RGB to generate color texture images with specific shapes, IR uses a single scalar value to present a more uniform image. As a result, many complexities can and should be eliminated to create an optimal super-resolution algorithm for IR capsule endoscopy.

[0124] We start with the prior art capsule endoscopy super-resolution system EndoL2h. It uses data collected using a high-resolution IR borescope and uses such images as a training set for an adversarial network, where the capsule images are input to the generator.

[0125] We adapt the EndoL2h loss function given in Eq. (3).

number

[0126] Because the capsule moves and its velocity is determined by triangulation of its position over time, interpolation between two or more images at a rate that depends on the device's velocity can enable high-resolution images on top of those generated by the GAN.

[0127] The center of the image is determined by the eccentricity of the content, and the radial velocity vector is assumed to point toward that center. Velocity determined from position tracking and the sensor's viewing angle indicates the velocity magnitude of the vector. Bicubic upsampling is then performed along the velocity vector, and subpixel values ​​are estimated from the subpixel velocities. Again, the images are evaluated using PSNR and SSIM, both with and without the GAN network.

[0128] Insufficient number of frames. Due to the low frame rate required to obtain low-noise images, it may not be possible to achieve enough frames to have sub-pixel velocity values. We have begun testing algorithms for this purpose, while other work is underway. If the frame rate is insufficient, we will consider image compression in the microcontroller as a means of increasing the frame rate.

[0129] A key step in the super-resolution algorithm is determining the subpixel shift in successively acquired images. If the device experiences periods of stationary motion, there is little subpixel information to use to reconstruct a high-resolution image. Alternatively, if the device moves rapidly over a large distance, successive images will be completely different, prohibiting the recovery of subpixel information. If we find that stationary or rapid capsule movement is a frequent problem, incorporating a receiver within the capsule allows us to control the sampling period and frame rate. We then use capsule position tracking velocity to control the capsule so that thermal images are acquired only when the speed of capsule movement is optimal for super-resolution reconstruction.

[0130] If temperature fluctuations due to intestinal inflammation are smaller than expected, temperature sensitivity can be increased by performing more frame averaging. For example, in some embodiments, 1 second of frame averaging should result in temperature sensitivity of approximately 0.1°C, while in other embodiments, 2 seconds of averaging increases sensitivity to 0.07°C. By using the receiver belt to reconstruct the capsule's position and velocity, we can determine a reasonable number of frames to average. As mentioned above, incorporating a receiver within the capsule allows us to adaptively change the frame rate during the procedure, resulting in lower thermal noise in the images when the device is moving more slowly. Alternatively, in other embodiments, a small Peltier element attached to the imaging sensor within the capsule can be used to actively cool the sensor and reduce background thermal noise.

[0131] Primary benchmarks of success include capsule design outputs meeting design input specifications (see Table 4 and Table 5) determined by validation and preclinical validation. Another benchmark of success is animal studies demonstrating the ability to detect a 1°C increase in gastrointestinal temperature corresponding to histological evidence of inflammation. [Example]

[0132] The following are non-limiting examples consistent with embodiments of the present disclosure.

[0133] (Example 1: Characterizing the relationship between inflammation and temperature in the gut) The temperature of inflamed tissue typically increases by 0.1–5°C due to increased blood flow and the metabolic rate of inflammatory cells. While this phenomenon has been studied in a variety of human diseases, little is known about the temperature changes observed in the inflamed intestinal wall. Therefore, to characterize temperature-based inflammatory changes in Crohn's disease and optimally design diagnostic thermal imaging capsules, a better understanding of the relationship between gastrointestinal temperature elevation and the underlying inflammatory signature is necessary. Because Crohn's disease is a transmural disease, it is even more important to understand how heat generated deep within the intestinal wall diffuses to the surface, where it emits IR radiation.

[0134] The temperature of inflamed porcine ileocolonic intestinal wall segments was measured in vivo and compared with quantitative immunohistochemistry (IHC) of inflammatory cell and enzyme activity and a histopathological inflammation scoring system. One potential advantage of IR thermal imaging is that heat caused by inflammation deep within the intestinal wall can diffuse to the surface and be detected. Therefore, in addition to determining overall inflammation, histopathology / IHC can be evaluated as a function of distance from the luminal surface to determine the relationship between intraluminal temperature and the depth of inflammatory activity.

[0135] (Animal model) Because heat generated by inflammation is a fundamental biophysical phenomenon maintained across vertebrates and inflammatory diseases, we study gastrointestinal temperature in an adult (50-75 kg) transmural porcine injury model of ileocolitis. Pigs also have similar anatomy and intestinal wall thickness to humans, making the results of this example more clinically transferable. Furthermore, the diameter of the porcine intestine allows for in vivo intraluminal thermography to be conducted using a commercially available infrared borescope, which is similar to an endoscope but typically used for industrial purposes.

[0136] Our swine injury model involves intragastric administration of dextran sulfate sodium (DSS) or intraintestinal injection of 2,4,6-trinitrobenzenesulfonic acid (TNBS)-EtOH, both of which have been established to induce transmural inflammation in pigs. Following chemical challenge, pigs are allowed to recover for 7 days, at which point a follow-up procedure is performed to measure intraluminal temperature along the gastrointestinal tract.

[0137] (Animal surgery) Seven days after DSS / TNBS administration, laparotomy is performed on preoperatively gut-prepared pigs. Temperature is measured intraluminally using an IR borescope inserted through incisions in the terminal ileum and colon. Conventional white-light endoscopy is also performed through the same intestinal segments. Electrocautery is used to mark areas containing both high and low / normal temperature images, as well as visibly normal and abnormal areas. The animals are then sacrificed, the ileum and colon are dissected, and histological sections are taken from the electrocautery-marked areas.

[0138] (Temperature Metric) To compare data across animals, we develop an algorithm to normalize elevated intestinal temperatures to the normal range. The primary temperature metrics are the mean and variance of normalized mucosal temperatures for different grades / metrics of inflammatory activity status and level. Additional parameters derived from thermal images, including spatial moments and features, will also be investigated.

[0139] (Histopathological analysis) Standard H&E and IHC processing is performed. IHC includes CD45, CD3, CD4, CD20, CD68, and enzyme stains (e.g., metalloproteinases, cathepsins, neutrophil elastase), which are known to be elevated during inflammatory processes. All slides are digitized using a whole-slide imaging system (Nanozoomer). Two pathologists blinded to the thermal images apply histological scoring at different depth intervals (e.g., 0–100, 100–200, etc., micrometers from the luminal surface) until consensus on the scoring is reached. Inflammatory cell counts and areas of inflammatory / enzyme activity expression are automatically calculated from the digitized histology / IHC slides, and cell counts / areas and percentage areas of staining are tabulated according to depth.

[0140] (Data analysis method) Temperatures are compared with the percentage area staining and enzyme expression of inflammatory cells from corresponding digitized slides using linear regression with repeated measurements. Nonlinear associations between temperature and histological scoring are estimated using Spearman correlation. Analysis is performed throughout the entire intestinal wall and at different depths from the luminal surface. Furthermore, normalized temperature thresholds for the diagnosis of inflammation (mild to moderate-severe) are determined, and sensitivity and specificity are retrospectively evaluated. The smallest detectable inflammatory foci are determined as a function of thermal detection sensitivity.

[0141] A statistical rationale for the number of animals is provided. If three inflammatory areas are identified in each animal, and the correlation coefficient between histopathological metrics (e.g., CD45% area staining) and temperature is 0.6, with an intra-animal correlation of 0.5, data simulations show that, using a two-tailed test with α = 0.05 in a random effects model, 10 animals would provide greater than 80% power to detect a correlation between temperature and histopathological metrics.

[0142] Here, we chose a simple injury-induced inflammation model because it is simple and can be generated in pigs with human-like anatomy; however, if we find that the temperature changes seen in injury models are not present in Crohn's disease, we could consider a more complex model that more closely resembles Crohn's disease.

[0143] If the inflammation is too heterogeneous, it can be difficult to match the thermal image with the histology. In this case, DSS or TNBS can be used to stimulate only a limited area of ​​the intestine by dispensing a toxic agent between two inflated balloons.

[0144] If the DSS or TNBS model does not produce sufficient changes in depth-dependent inflammation, consider modifying the protocol to endoscopically inject DSS, TNBS, or lipopolysaccharide (LPS) at different depths within the intestinal wall.

[0145] A key indicator of success will be demonstrating that elevated temperatures reflect histological indicators of inflammation in the small and large intestine. A secondary benchmark will be demonstrating that elevated temperatures can identify inflammation beneath the surface of the intestinal wall.

[0146] (Preliminary results from early animal studies) Two pig studies were conducted and analyzed. The first study (Pig Study 1) demonstrated an increase in intestinal wall temperature of 0.7 to 1.2 degrees Celsius. Another study demonstrated that forward-facing infrared imaging can detect inflammation in the intestinal wall. The second study (Pig Study 2) tested a catadioptric lens and demonstrated its ability to image tissue. It also demonstrated that a 15 cm distance between the imaging site and the laparoscope incision is necessary for evaporative cooling. Furthermore, it was determined that additional improvements were needed in the mirror / reflector design.

[0147] Example 2: Determining the capacity of mucosal temperature measurement through fecal content Because stool is primarily composed of water, which readily transmits heat, stool temperature should reflect the temperature of the intestinal wall. Therefore, a potential advantage of thermal imaging is its ability to diagnose intestinal wall inflammation through fecal content. This possibility could potentially allow for the detection of colonic inflammation without requiring patients to undergo a complete preoperative bowel preparation. Here, we investigate this possibility by measuring the temperature of the intestinal wall through different thicknesses of fecal content.

[0148] (Experimental Strategy) Segments of clean porcine distal ileum and colon are heated ex vivo to known temperatures. The temperature of the intestinal surface is measured via IR thermal imaging. Varying thicknesses of fecal content are then applied to the luminal surface of the intestine, and the IR imaging temperature measurements are repeated. The equivalence of temperatures measured with and without fecal coverage is determined for different intestinal temperatures and fecal loads.

[0149] (Animal model) The pig intestine serves as an ideal model for this study because it is readily available and anatomically similar to the human intestine. After sacrificing adult pigs (50-75 kg) fed a human diet, the terminal ileum and colorectal segments (cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum) are dissected. Because the composition of fecal content depends on the intestinal segment, feces are collected and separated based on their anatomical origin.

[0150] (Experimental equipment) Because measuring fecal thickness is much easier in flat specimens, each intestinal segment is cut longitudinally, cleaned, fixed flat, and placed luminal side up on a Peltier thermoelectric heating plate (see Figure 18). Temperature is monitored at the luminal surface using a thermocouple, a common and reliable electronic device for temperature measurement. The voltage to the Peltier cooler is controlled to maintain a constant intestinal wall temperature using feedback from the thermocouple. The entire temperature-regulating apparatus is placed in a controlled humidity environment at 37 °C to simulate intraluminal conditions.

[0151] (temperature measurement) Thermal imaging is performed to measure the temperature of each cleansed intestinal segment in the absence of feces. Next, a layer of feces from the same anatomical segment is placed between the mucosal surface and the thermal camera and covered with a glass plate. The thickness of the feces is measured using high-frequency (>30 MHz) ultrasound. Thermal images of the intestine with different thicknesses of fecal content and a temperature range representative of presumed mild to severe ileocolitis (e.g., 37–42°C) are acquired in approximately 0.1°C increments. Thermal equilibration, determined to occur when the thermal image no longer changes, is performed before each temperature measurement.

[0152] The mean and standard deviation of temperatures obtained from the thermal images are calculated. Temperature equivalence with and without fecal layers of different thicknesses is determined using Student's t-tests or trimmed t-tests assuming unequal variances, where appropriate. If present, a cutoff fecal layer thickness below which equivalence is no longer demonstrated is identified as a function of thermal detection sensitivity.

[0153] Assuming a standard deviation of 0.1°C for temperature measurements, if there is truly no difference in temperatures measured with or without feces, 22 paired measurements for each segment (with and without feces) would provide 80% power to provide a two-sided 90% confidence interval that excludes mean differences of more than 0.1°C. We estimate that approximately 10 pigs would be needed to obtain 22 paired measurements for each intestinal segment.

[0154] Although the pigs used in this study will be consuming a human diet, it is possible that the model may not fully replicate human fecal content. To investigate this factor, we could obtain stool from volunteers or collect human feces from endoscopic procedures with inadequate preoperative bowel preparation and repeat a subset of the study described here to determine whether equivalence thresholds are similar.

[0155] Furthermore, fecal thermal diffusion may depend on diet and other physiological conditions. To investigate this potential confounding factor, we measured the thermal diffusion of feces from pigs fed various diets and from different anatomical sites to determine whether there was significant variation in fecal thermal diffusion due to these variables.

[0156] The primary criterion for success in this example is demonstrating that the surface temperature of clinically relevant fecal deposits is equivalent to the surface temperature of the intestinal wall, which may pave the way for using thermal capsules to diagnose inflammation in patients without the need for bowel preparation.

[0157] (Example 3: Conduct a pilot clinical trial using a wireless thermal imaging capsule in Crohn's disease patients) In this example, we will demonstrate the feasibility of a thermal imaging capsule in detecting inflammation in patients with Crohn's disease, with or without bowel preparation, and conduct a pilot clinical trial to obtain an estimate of efficacy.

[0158] (Experimental Strategy) Patients with Crohn's disease who underwent bowel preparation swallowed a thermal imaging capsule, and thermal imaging data, along with the capsule's position, were continuously recorded. Then, normothermic and hyperthermic bowel wall areas were endoscopically biopsied. The capsule-based thermal images were correlated with quantitative histological findings obtained from the corresponding biopsies. A similar study was conducted in patients who did not undergo bowel preparation. The capacity of capsule imaging to capture thermal images corresponding to intestinal inflammation was compared between the two groups.

[0159] (patient) Patients with moderate to severe ileocolonic Crohn's disease (n = 20) were enrolled in this study. Inclusion criteria were: 1) a confirmed diagnosis of ileocolonic Crohn's disease, 2) ability to consent, 3) age 18-75 years, and 4) moderate to severe Crohn's disease, defined as a Crohn's disease activity index (CDAI) score of 220 or greater but less than 450. Exclusion criteria were: 1) evidence of active infection, 2) a history of ileocolic resection, 3) evidence of small bowel or colonic stricture or obstruction, 4) evidence of small bowel or colonic fistula, 5) presence of intra-abdominal abscess, 6) a diagnosis of ulcerative colitis or atypical colitis, or 7) pregnancy.

[0160] (protocol) To confirm the absence of stricture due to capsule obstruction, subjects first swallow a patent capsule (e.g., Pillcam® patent capsule), followed by an abdominal x-ray 24 hours later to confirm capsule passage. Subjects (10 subjects who received a 4-L divided-dose PEG-ELS bowel preparation and 10 subjects who did not receive a bowel preparation) swallow the thermal imaging capsule disclosed herein. Subjects wear a receiver / recorder belt for 8-10 hours as the capsule passes through the entire gastrointestinal tract, recording corresponding thermal images of the ileocolon and the capsule's location. After capsule administration, hypothermic / normothermic and hyperthermic areas are identified and their location within the intestine is recorded. Patients then undergo ileocolonoscopy under sedation 2-3 days after thermal capsule imaging. During the endoscopy, biopsies are taken from the sites identified by thermal capsule imaging.

[0161] (Data Analysis) Biopsy slides will be assessed for inflammation as described in Example 1. Thermal capsule signatures of histologically determined normal and inflamed areas will be compared using t-tests. The sensitivity and specificity of thermal capsule imaging to distinguish inflamed from non-inflamed bowel walls will be determined using histology as the gold standard. The sensitivity / specificity of cohorts with and without bowel preparation will be compared using Fisher's exact test. Receiver operating characteristic (ROC) curves will be used to assess the classification power of the proposed method.

[0162] (Statistical basis for number of patients) Assuming a mean temperature difference between inflamed and non-inflamed bowel walls of 1°C and a standard deviation of 1°C, a total of 13 normal bowel segments and 13 inflamed segments provides greater than 80% power to detect a difference using a two-tailed t-test with α = 0.05. Assuming an average of three inflamed bowel wall areas per patient and an estimated sensitivity / specificity of capsule thermography in diagnosing inflammation of 90%, enrolling 10 patients per cohort would provide a 95% confidence interval of ±11% for lesion-specific analyses.

[0163] We recognize that inflammation in sites other than the terminal ileum may be difficult to identify on capsule and confirm by colonoscopy. If it is difficult to distinguish inflammation in the terminal ileum from inflammation in the proximal colon, we will register inflammation in the ileum alone or in the colon alone and perform stratified analyses by site.

[0164] Furthermore, the capsule can be located with an accuracy of 1 cm, whereas it may be more difficult to locate by endoscopy. The location is recorded on a patent radiograph for the surgeon's reference, but imaging such as ultrasound or X-ray may be required to confirm the exact location detected by position tracking during ileocolonoscopy.

[0165] If sufficient gastrointestinal inflammation is not observed in patients with a CDAI of 220–450, we can narrow the enrollment criteria and include only patients with elevated inflammatory markers such as ESR, CRP, and fecal calprotectin, or patients with active ileocolonic disease confirmed by endoscopy. If there are insufficient areas of normal bowel, we can enroll an age- and sex-matched cohort of patients without Crohn's disease for comparison.

[0166] (Expected results / results) The primary outcome of these studies is to verify that the capsule can detect inflammatory activity in patients with Crohn's disease, with or without bowel preparation. We expect to see a high correlation between temperature measurements and histological activity, which will significantly improve the resolution of this technique compared to other currently available imaging modalities (e.g., CT, MRI, or VCE).

[0167] (Example 4: Development of super-resolution neural network for IR image enhancement) Determining the optimal architecture for IR capsule endoscopy: The current gold standard, a generative adversarial network (GAN) machine learning architecture common to endoscopic super-resolution of color images, is applied to IR images, evaluated on datasets obtained using embodiments of the disclosed capsule, and compared to baseline high-resolution IR borescope data. The resulting resolution gains are expected to improve the diagnostic capabilities of IR capsules, enabling the detection of small, early-stage intestinal lesions at the millimeter scale.

[0168] (Implementation of time-of-flight pixel tracking) Position tracking of a capsule endoscopy system is investigated to help further predict velocity vectors for analyzing sub-pixel information in order to add to a GAN-based super-resolution network to further improve resolution.

[0169] In machine learning, super-resolution refers to the concept of generating high-resolution images from low-resolution images. The two most successful methods in endoscopy are time-of-flight (ToF) and generative adversarial networks (GANs). ToF methods rely on rapidly capturing low-resolution (LR) images with known shifts in position and interpolating between them to recover subpixel information. Previous endoscopic reconstruction techniques estimated these displacements using the optical flow of RGB data from the endoscopic camera. While ToF requires multiple images to generate a single super-resolution image, GAN networks have a 1:1 input-to-output image ratio. GAN networks work by training two competing networks: a generative network that creates a high-resolution version of a low-resolution image, and a discriminative network that simultaneously attempts to determine whether the generated image is the generated high-resolution image or the reference high-resolution image captured initially. These competing networks are capable of generating images with an accurate 10–12x resolution improvement in one dimension.

[0170] Previous studies have applied a variety of loss functions to medical images. Pixel loss evaluates the pixel-by-pixel difference between a generated super-resolution (SR) image and its corresponding reference high-resolution (HR) image via an L1 loss function. Content loss evaluates the feature maps of the SR image to the HR image using the Euclidean distance between feature representations, typically using feature maps extracted from pre-trained, off-the-shelf feature extractors such as VGG or ResNet. Texture loss is defined as the Gram matrix formed by the dot product of vectorized feature maps of a specific convolutional layer. This helps introduce directional correlation into the learning process. Finally, adversarial losses have been shown to increase stability during training and result in better convergence. Previous studies outside of endoscopy have used these losses individually to characterize super-resolution algorithms, but capsule endoscopy showed greatest success when all losses were used with their respective optimized weighted hyperparameters. While video endoscopic images are information-rich and noise-free, thermal images of the small intestine present unique challenges, and preliminary data show that the images are largely homogeneous. As a result, it is unclear whether the same complexity is required to generate a complete image.

[0171] (Computational System) Turning to FIG. 19 , an example of a system 1900 (e.g., a data collection and processing system) for detecting gastrointestinal inflammation is shown in accordance with some embodiments of the disclosed subject matter. As shown in FIG. 19 , a computing device 1910 can receive thermal IR data from the thermal IR capsule 1900. In some embodiments, the computing device 1910 can execute at least a portion of a system for detecting gastrointestinal inflammation based on the thermal IR data received from the thermal IR capsule 1900. Additionally or alternatively, in some embodiments, the computing device 1910 can transmit information regarding the thermal IR data received from the thermal IR capsule 1900 to a server 1920 via the communications network 1906, thereby executing at least a portion of a system for detecting gastrointestinal inflammation based on the thermal IR data. In some such embodiments, the server 1920 can return information indicative of the output of the system for detecting gastrointestinal inflammation 1904, such as thermal IR information, to the computing device 1910 (and / or other suitable computing devices). This information may be transmitted and / or presented to a user (e.g., a researcher, operator, clinician, etc.) and / or may be stored (e.g., as part of a research database or as a medical record associated with the subject).

[0172] In some embodiments, the computing device 1910 and / or the server 1920 can be any suitable computing device or combination of devices, such as a desktop computer, a laptop computer, a smartphone, a tablet computer, a wearable computer, a server computer, a virtual machine running on a physical computing device, etc. As described herein, the system for detecting gastrointestinal inflammation 1904 can present information regarding the thermal IR data and / or thermal IR information to a user (e.g., a researcher and / or a physician).

[0173] In some embodiments, thermal IR capsule 1900 can include IR sensor 1902, which is a sensor suitable for detecting IR, such as a thermopile sensor. In other embodiments, IR sensor 1902 can be associated with computing device 1910. For example, IR sensor 1902 can be combined with computing device 1910 (e.g., computing device 1910 can be configured as part of a capsule for obtaining thermal IR information). As another example, IR sensor 1902 can be connected to computing device 1910 by a cable, a direct wireless link, or the like. Additionally or alternatively, in some embodiments, IR sensor 1902 can be located locally and / or remotely from computing device 1910 and transmit information to computing device 1910 (and / or server 1920) via a communications network (e.g., communications network 1906).

[0174] In some embodiments, communications network 1906 can be any suitable communications network or combination of communications networks. For example, communications network 1906 can include a Wi-Fi network (which may include one or more wireless routers, one or more switches, etc.), a peer-to-peer network (e.g., a Bluetooth network), a cellular network (e.g., a 4G network, a 5G network, etc., conforming to suitable standards such as CDMA, GSM, LTE, LTE Advanced, WiMAX, etc.), a wired network, etc. In some embodiments, communications network 1906 can be a local area network, a wide area network, a public network (e.g., the Internet), a private or semi-private network (e.g., a corporate or university intranet), any other suitable type of network, or a combination of suitable networks. The communications links shown in FIG. 19 can each be any suitable communications link or combination of communications links, such as a wired link, an optical fiber link, a Wi-Fi link, a Bluetooth link, a cellular link, etc.

[0175] FIG. 20 illustrates example hardware 2000 that can be used to implement a computing device 1910 and a server 1920 in accordance with some embodiments of the disclosed subject matter. As shown in FIG. 20 , in some embodiments, the computing device 1910 can include a processor 2002, a display 2004, one or more inputs 2006, one or more communication systems 2008, and / or memory 2010. In some embodiments, the processor 2002 can be a suitable hardware processor or combination of processors, such as a central processing unit, a graphics processing unit, or the like. In some embodiments, the display 2004 can include a suitable display device, such as a computer monitor, a touchscreen, a television, or the like. In some embodiments, the input 2006 can include a suitable input device and / or sensor that can be used to receive user input, such as a keyboard, a mouse, a touchscreen, a microphone, or the like.

[0176] In some embodiments, communications system 2008 may include suitable hardware, firmware, and / or software for communicating information over communications network 1906 and / or other suitable communications networks. For example, communications system 2008 may include one or more transceivers, one or more communications chips and / or chipsets, etc. As a more specific example, communications system 2008 may include hardware, firmware, and / or software that can be used to establish a Wi-Fi® connection, a Bluetooth® connection, a cellular connection, an Ethernet connection, etc.

[0177] In some embodiments, memory 2010 may include a suitable storage device or device that can be used to store instructions, values, etc., which processor 2002 can use to present content using display 2004, to communicate with server 1920 via communication system 2008, etc. Memory 2010 may include suitable volatile memory, non-volatile memory, storage, or a suitable combination thereof. For example, memory 2010 may include RAM, ROM, EEPROM, one or more flash drives, one or more hard disks, one or more solid-state drives, one or more optical drives, etc. In some embodiments, memory 2010 may be encoded with a computer program for controlling the operation of computing device 1910. In such embodiments, processor 2002 may execute at least a portion of the computer program to present content (e.g., images, user interfaces, graphics, tables, etc.), receive content from server 1920, and send information to server 1920.

[0178] In some embodiments, server 1920 may include a processor 2012, a display 2014, one or more inputs 2016, one or more communication systems 2018, and / or memory 2020. In some embodiments, processor 2012 may be a suitable hardware processor or combination of processors, such as a central processing unit, a graphics processing unit, etc. In some embodiments, display 2014 may include a suitable display device, such as a computer monitor, a touchscreen, a television, etc. In some embodiments, input 2016 may include a suitable input device and / or sensor that can be used to receive user input, such as a keyboard, a mouse, a touchscreen, a microphone, etc.

[0179] In some embodiments, communications system 2018 may include suitable hardware, firmware, and / or software for communicating information over communications network 1906 and / or other suitable communications networks. For example, communications system 2018 may include one or more transceivers, one or more communications chips and / or chipsets, etc. As a more specific example, communications system 2018 may include hardware, firmware, and / or software that can be used to establish a Wi-Fi® connection, a Bluetooth® connection, a cellular connection, an Ethernet connection, etc.

[0180] In some embodiments, memory 2020 may include any suitable storage device or device that can be used to store instructions, values, etc., which processor 2012 can use to present content using display 2014, communicate with one or more computing devices 1910, etc. Memory 2020 may include any suitable volatile memory, non-volatile memory, storage, or any suitable combination thereof. For example, memory 2020 may include RAM, ROM, EEPROM, one or more flash drives, one or more hard disks, one or more solid-state drives, one or more optical drives, etc. In some embodiments, memory 2020 may be encoded with a server program for controlling the operation of server 1920. In such embodiments, processor 2012 may execute at least a portion of the server program to send information and / or content (e.g., tissue identification and / or classification results, user interfaces, etc.) to one or more computing devices 1910, receive information and / or content from one or more computing devices 1910, and receive instructions from one or more devices (e.g., personal computers, laptop computers, tablet computers, smartphones, etc.).

[0181] In some embodiments, any suitable computer-readable medium may be used to store instructions for performing the functions and / or processes described herein. For example, in some embodiments, the computer-readable medium may be transitory or non-transitory. For example, non-transitory computer-readable media may include media such as magnetic media (hard disks, floppy disks, etc.), optical media (compact disks, digital video disks, Blu-ray disks, etc.), semiconductor media (RAM, flash memory, electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.), any suitable medium that does not lack transitory or permanent properties during transmission, and / or any suitable tangible medium. As another example, transitory computer-readable media include signals on a network, wires, conductors, optical fiber, circuits, or any suitable medium that is transitory and has no permanent properties during transmission, and / or any suitable intangible medium.

[0182] In some embodiments, the optical signals are detected by a photodiode array. It should be appreciated that any optoelectronic conversion device can be used to perform this detection function, including, but not limited to, photodetectors, photodiodes, line scan and two-dimensional cameras, photodiode arrays, and the like.

[0183] It should be noted that the term mechanism as used herein may encompass hardware, software, firmware, or any suitable combination thereof.

[0184] 21 illustrates an example process 1200 for detecting gastroenteritis in accordance with some embodiments of the disclosed subject matter. As shown in FIG. 21, at 2102, process 2100 can provide a capsule including a thermal imaging sensor, which can be configured to be swallowed by a subject. Finally, at 2104, process 2100 can detect infrared radiation emitted from tissue of the subject using the thermal imaging sensor.

[0185] FIG. 22 illustrates an example process 2200 for detecting gastroenteritis in accordance with some embodiments of the disclosed subject matter. As shown in FIG. 22 , at 2202, process 2200 can provide a capsule including a thermal imaging sensor, a wireless transmitter, and multiple antennas in communication with a controller, wherein the capsule can be configured to be swallowed by a subject. At 2204, process 2200 can detect infrared radiation emitted from the subject's tissue by the thermal imaging sensor. At 2206, process 2200 can generate, by the controller, at least one image of the detected infrared radiation emitted from the subject's tissue. At 2208, process 2200 can transmit, by the controller, the at least one image to the wireless transmitter, which transmits the at least one image to multiple antennas. Finally, at 2210, process 2200 can receive, by the multiple antennas, the at least one image from the wireless transmitter.

[0186] It should be understood that the above-described steps in the processes of Figures 21 and 22 are not limited to the order and sequence shown and described, but may be performed or executed in any order or sequence. Also, some of the above-described steps in the processes of Figures 21 and 22 may be performed or executed substantially simultaneously or in parallel where appropriate, thereby reducing latency and processing time.

[0187] FIG. 34 shows a system block diagram illustrating the operation of an embodiment of the device, from capsule measurement transmission to reception, processing, and storage between the capsule and the receiving belt. As shown in FIG. 34, in step 37, the capsule's thermistor sensor array measures the user's lumen temperature. In step 38, the capsule's onboard controller processes and encrypts the data. Following step 38, in step 40, the capsule wirelessly transmits the data through the tissue to an external receiver in an antenna array on the receiving belt. In step 48, the external receiver sweeps and stores all antenna amplitudes from the signal, and in step 50 updates the receiving antenna to record the signal as the highest fidelity input. Simultaneously with step 40, the external receiver also receives and stores data in step 42. In some embodiments, the receiver processes the data with a neural network to determine the capsule's location in step 44. Finally, in step 46, the receiver transmits a signal back to the capsule to perform one or more functions, such as releasing a drug payload, providing location information, or adjusting the sensitivity and filter settings of the thermal measurement. In some embodiments, the data is processed by the receiver belt and sends signals back to the wireless capsule to adjust sensor settings and frame rate, as well as to guide further actions such as releasing a drug payload or informing the capsule of its current location.

[0188] For machine learning, two networks are used within the thermal wireless capsule system. As shown in Figure 36, the first network (Network 1) is configured to analyze tissue thickness and determine the capsule's location. This is accomplished by taking the antenna signal amplitude input 62 from the receiving belt and outputting, via a neural network, the tissue thickness 64 of the region along the signal path between the capsule and the patient's body surface. The network also outputs the capsule's location and rotation in an (x,y,z) coordinate system 64.

[0189] The neural network for the capsule is trained using a data set that simulates the electromagnetic fields 58 generated by the capsule for various tissue depths, capsule angles, and capsule positions relative to the antenna. Simultaneously, multi-antenna measurements are generated using the input antenna configuration. This is achieved by iterating through predicted capsule positions to generate antenna fields for all antennas 60. Based on the input number and positions of antennas, the observed fields from the entire antenna array are extrapolated. These extrapolations are then used to train the network to learn capsule position, rotation, and various tissue depths for a given field strength pattern.

[0190] Figure 37 shows a second network (Network 2) configured to determine tissue inflammation and lesion severity 68. The second network uses capsule location, calculated local tissue thickness, and temperature measurements to determine the depth and / or severity of lesions in tissue 66. When run post-procedure, the network can use past, present, and future measurements to calculate all inputs at once. When run during treatment, only past and present inputs are available for a particular new data point.

[0191] The second neural network is trained by simulating thermal fields generated by varying the size, intensity, depth, heat type, and location of the lesion in tissue and propagating them through the capsule body 70. These thermal fields vary with tissue thickness, capsule position, and rotation, and are controlled by any combination of current, past, and present measurements. The rationale for each input is described below.

[0192] Inputs from the initial network include capsule location and tissue thickness, as well as past, current, and, if evaluated, future post-operative inputs. Tissue thickness helps determine heat diffusion and analyze depth, calculating thermal physics to determine site depth and severity. Location helps determine if the capsule is near major heat sinks, such as arteries, or thermally significant organs due to metabolism or perfusion, such as the heart, thyroid, kidneys, liver, or bladder. Past and current thermal measurements serve as inputs to determine ambient temperature and help determine if the capsule contains significant lesions. Future inputs are also processed if evaluated post-operatively.

[0193] While the present invention has been described in terms of one or more preferred embodiments, it should be understood that many other equivalents, alternatives, variations, and modifications, aside from those already described, may be similarly constructed and fall within the scope of the invention.

Claims

1. a capsule containing at least one temperature sensor; the capsule is configured to be swallowed by a subject; the at least one temperature sensor is configured to sense ambient heat radiated by tissue of the subject; A device for detecting gastrointestinal lesions.

2. the at least one temperature sensor includes a thermistor including a thermistor ring having a plurality of thermistors disposed around a cylindrical wall of the capsule; the plurality of thermistors in the thermistor ring are configured to sense a spatial pattern of heat radiated by the tissue of the subject.

10. The apparatus of claim 1.

3. The apparatus of claim 2 , wherein the plurality of thermistors are disposed partially or completely around the cylindrical wall of the capsule.

4. the thermistor ring includes a first thermistor ring; the plurality of thermistors includes a first plurality of thermistors; the at least one temperature sensor further comprising a thermistor having a second thermistor ring comprising a second plurality of thermistors disposed about the cylindrical wall of the capsule.

3. The apparatus of claim 2.

5. 5. The apparatus of claim 4, wherein the second plurality of thermistors are disposed partially or completely around the cylindrical wall of the capsule.

6. 5. The apparatus of claim 4, wherein the second plurality of thermistors of the second thermistor ring are arranged in a spatially offset manner from the first plurality of thermistors of the first thermistor ring.

7. the first plurality of thermistors and the second plurality of thermistors are configured to sense the spatial pattern of heat radiated by the tissue of the subject; Data relating to the spatial pattern of detected heat includes: improving the spatial resolution of an image formed using said data; and determining a rate of movement of the capsule within the tissue of the subject; reducing the amount of noise associated with transmission of said data; and and 7. The apparatus of claim 6.

8. the cylindrical wall of the capsule comprises a thermally conductive material; at least one of the first plurality of thermistors or the second plurality of thermistors is in thermal contact with the thermally conductive material of the cylindrical wall of the capsule; 7. The apparatus of claim 6.

9. further comprising a flexible printed circuit board; At least one of the first thermistor ring or the second thermistor ring is coupled to the printed circuit board.

9. The apparatus of claim 8.

10. 10. The device of claim 9, further comprising a battery in electrical contact with the flexible printed circuit board.

11. further comprising a controller in communication with the at least one temperature sensor; the controller is configured to acquire data from the at least one temperature sensor relating to the heat detected and radiated from the tissue of the subject; 11. Apparatus according to any one of claims 1 to 10.

12. The apparatus of claim 11 , wherein the controller is further configured to encrypt the data obtained from the at least one temperature sensor.

13. further comprising a wireless transmitter and antenna in communication with the controller; the controller transmits the data to an external device via the wireless transmitter and the antenna, and at least one of stores and analyzes the transmitted data; 12. The apparatus of claim 11.

14. The apparatus of claim 13 , wherein the controller is further configured to generate at least one image based on the data obtained from the at least one temperature sensor.

15. the controller is further configured to generate a plurality of images based on the data obtained from the at least one temperature sensor; the plurality of images are based on data acquired at a data acquisition rate from the at least one temperature sensor; 14. The apparatus of claim 13.

16. The controller further comprises: receiving a signal from the external device; configured to adjust at least one of the data capture rate from the at least one temperature sensor or an operational setting of the at least one temperature sensor based on the signal from the external device.

16. The apparatus of claim 15.

17. further comprising a drug reservoir; The controller further comprises: receiving a signal from the external device; configured to release a drug payload from the drug reservoir upon receiving the signal from the external device.

14. The apparatus of claim 13.

18. further comprising a drug reservoir; The controller further comprises: detecting a target site within the tissue based on the detected heat radiated from the tissue of the subject; configured to release a drug payload from the drug reservoir based on detecting the target site.

14. The apparatus of claim 13.

19. The controller further receives a signal from the external device; the signal received from the external device includes information regarding the current location of the capsule within the subject; 14. The apparatus of claim 13.

20. 14. The apparatus of claim 13, wherein the radio transmitter is configured to transmit at a frequency in the range comprised between 430 MHz and 440 MHz.

21. further comprising a thermal imaging sensor; the thermal imaging sensor is configured to detect infrared radiation emitted by the tissue of the subject; 14. The apparatus of claim 13.

22. the capsule includes a cylindrical housing; the thermal imaging sensor is disposed at an end of the cylindrical housing; 22. The apparatus of claim 21.

23. 22. The apparatus of claim 21, wherein the thermal imaging sensor is configured to detect infrared radiation having a wavelength in the range comprised between 7 μm and 14 μm.

24. 22. The apparatus of claim 21, wherein the thermal imaging sensor comprises a thermopile sensor.

25. 22. The apparatus of claim 21, wherein the thermal imaging sensor further comprises an ultrasonic transducer coupled to the controller.

26. 26. The apparatus of claim 25, wherein the ultrasound transducer is configured to acquire data indicative of a depth of feces between the capsule and the tissue of the subject.

27. 26. The apparatus of claim 25, wherein the controller is configured to obtain data from the ultrasound transducer indicative of a depth of feces between the capsule and the tissue of the subject.

28. 28. The device of claim 27, wherein the controller is configured to transmit the data from the ultrasound transducer indicative of the depth of feces between the capsule and the tissue of the subject to the external device using the wireless transmitter and the antenna.

29. the capsule has a window that is transparent to infrared light; the window is adjacent to the thermal imaging sensor; 22. The apparatus of claim 21.

30. further comprising a reflector adjacent to the thermal imaging sensor; the reflector is configured to redirect infrared light from the tissue to the thermal imaging sensor.

22. The apparatus of claim 21.

31. 31. The apparatus of claim 30, wherein the reflector is configured to redirect the infrared radiation from a peripheral region around the capsule.

32. 31. The apparatus of claim 30, wherein the reflector has a pyramidal shape.

33. 33. The apparatus of claim 32, wherein the pyramidal shape has an apex that includes a triangular wedge.

34. 34. The apparatus of claim 1, wherein the at least one temperature sensor comprises at least one of a thermistor, a thermocouple, a semiconductor-based sensor, or a resistance-based temperature sensor.

35. A capsule including at least one temperature sensor, the capsule is configured to be swallowed by a subject; a capsule, wherein the at least one temperature sensor is configured to sense ambient heat radiated by tissue of the subject; a receiving belt configured to be coupled to the subject's body; A system for detecting gastrointestinal pathology, comprising:

36. the at least one temperature sensor includes a thermistor including a thermistor ring having a plurality of thermistors disposed around a cylindrical wall of the capsule; the plurality of thermistors in the thermistor ring are configured to sense a spatial pattern of heat radiated by the tissue of the subject.

36. The system of claim 35.

37. 37. The system of claim 36, wherein the plurality of thermistors are disposed partially or completely around the cylindrical wall of the capsule.

38. the thermistor ring includes a first thermistor ring; the plurality of thermistors includes a first plurality of thermistors; the at least one temperature sensor further comprising a thermistor having a second thermistor ring comprising a second plurality of thermistors disposed about the cylindrical wall of the capsule.

37. The system of claim 36.

39. 39. The system of claim 38, wherein the second plurality of thermistors are disposed partially or completely around the cylindrical wall of the capsule.

40. 39. The system of claim 38, wherein the second plurality of thermistors of the second thermistor ring are arranged in a spatially offset manner from the first plurality of thermistors of the first thermistor ring.

41. the first plurality of thermistors and the second plurality of thermistors are configured to sense the spatial pattern of heat radiated by the tissue of the subject; Data relating to the spatial pattern of detected heat includes: improving the spatial resolution of an image formed using said data; and determining a rate of movement of the capsule within the tissue of the subject; reducing the amount of noise associated with transmission of said data; and and 41. The system of claim 40.

42. the cylindrical wall of the capsule comprises a thermally conductive material; at least one of the first plurality of thermistors or the second plurality of thermistors is in thermal contact with the thermally conductive material of the cylindrical wall of the capsule; 41. The system of claim 40.

43. the capsule further includes a flexible printed circuit board; At least one of the first thermistor ring or the second thermistor ring is coupled to the printed circuit board.

43. The system of claim 42.

44. 44. The system of claim 43, wherein the capsule further comprises a battery in electrical contact with the flexible printed circuit board.

45. the capsule further includes a controller in communication with the at least one temperature sensor; the controller is configured to acquire data from the at least one temperature sensor relating to the heat detected and radiated from the tissue of the subject; 45. A system according to any one of claims 35 to 44.

46. 46. ​​The system of claim 45, wherein the controller is further configured to encrypt the data obtained from the at least one temperature sensor.

47. the capsule further includes an antenna in communication with the controller; the controller transmits the data to an external device via the antenna, and at least one of stores and analyzes the transmitted data; 46. ​​The system of claim 45.

48. 48. The system of claim 47, wherein the external device is coupled to the receiving belt.

49. 49. The system of claim 48, wherein the receiver belt includes a plurality of receiver belt antennas for communicating with the external device.

50. The receiving belt includes a waist belt and a shoulder strap; the waist belt and the shoulder straps are configured to hold the plurality of receiving belt antennas in a fixed position relative to the body of the subject; 50. The system of claim 49.

51. The controller further comprises: receiving a signal from the external device; configured to adjust at least one of the data capture rate from the at least one temperature sensor or an operational setting of the at least one temperature sensor based on the signal from the external device.

48. The system of claim 47.

52. the capsule further comprises a drug reservoir; The controller further comprises: receiving a signal from the external device; configured to release a drug payload from the drug reservoir upon receiving the signal from the external device.

48. The system of claim 47.

53. the capsule further comprises a drug reservoir; The controller further comprises: detecting a target site within the tissue based on the detected heat radiated from the tissue of the subject; configured to release a drug payload from the drug reservoir based on detecting the target site.

48. The system of claim 47.

54. The controller further receives a signal from the external device; the signal received from the external device includes information regarding the current location of the capsule within the subject; 50. The system of claim 49.

55. 55. The system of claim 54, wherein the information regarding the current location of the capsule within the subject is determined based on information from the plurality of receiving belt antennas.

56. 56. The system of claim 55, wherein the information regarding the current location of the capsule within the subject is determined based on a comparison of information from the plurality of receiving belt antennas with data regarding antenna signal attenuation versus tissue depth.

57. the information from the plurality of receiving belt antennas is processed by a first neural network to identify at least one of tissue type or tissue thickness between the capsule and a surface of the subject adjacent the plurality of receiving belt antennas; the current position of the capsule is determined based on at least one of the type of tissue or the thickness of the tissue.

56. The system of claim 55.

58. 58. The system of claim 57, wherein the current location of the capsule, at least one of the tissue type and tissue thickness, and the data obtained from the at least one temperature sensor are processed by a second neural network to determine at least one of a lesion depth, a lesion type, or a lesion severity within the tissue of the subject.

59. 50. The system of claim 49, wherein information from the plurality of receiving belt antennas is processed to identify at least one of tissue type or tissue thickness between the capsule and a surface of the subject adjacent the plurality of receiving belt antennas.

60. 60. The system of any one of claims 35 to 59, wherein the at least one temperature sensor comprises at least one of a thermistor, a thermocouple, a semiconductor-based sensor, or a resistance-based temperature sensor.

61. A capsule including at least one temperature sensor, the capsule is configured to be swallowed by a subject; providing a capsule wherein the at least one temperature sensor is configured to sense ambient heat radiated by tissue of the subject; circumferentially sensing heat radiated by tissue of the subject with the at least one temperature sensor; A method for detecting gastrointestinal lesions.

62. the at least one temperature sensor includes a thermistor including a thermistor ring having a plurality of thermistors disposed around a cylindrical wall of the capsule; Providing a capsule further includes providing the capsule including the plurality of thermistors in the thermistor ring disposed about the cylindrical wall of the capsule; circumferentially sensing the heat radiated by the tissue of the subject further comprises circumferentially sensing a spatial pattern of heat radiated by the tissue of the subject using the plurality of thermistors in the thermistor ring.

62. The method of claim 61.

63. 63. The method of claim 62, wherein the plurality of thermistors are disposed partially or completely around the cylindrical wall of the capsule.

64. the thermistor ring includes a first thermistor ring; the plurality of thermistors includes a first plurality of thermistors; the at least one temperature sensor further includes a thermistor having a second thermistor ring comprising a second plurality of thermistors disposed about the cylindrical wall of the capsule; providing a capsule further includes providing the capsule including the second plurality of thermistors in the second thermistor ring disposed about the cylindrical wall of the capsule; circumferentially sensing the heat radiated by the tissue of the subject further comprises circumferentially sensing a spatial pattern of heat radiated by the tissue of the subject using the second plurality of thermistors in the second thermistor ring.

63. The method of claim 62.

65. 65. The method of claim 64, wherein the second plurality of thermistors are disposed partially or completely around the cylindrical wall of the capsule.

66. 65. The method of claim 64, wherein the second plurality of thermistors of the second thermistor ring are arranged in a spatially offset manner from the first plurality of thermistors of the first thermistor ring.

67. the first plurality of thermistors and the second plurality of thermistors are configured to sense the spatial pattern of heat radiated by the tissue of the subject; The method further comprises processing data relating to the spatial pattern of detected heat; improving the spatial resolution of an image formed using said data; and determining a rate of movement of the capsule within the tissue of the subject; reducing the amount of noise associated with transmission of said data; and performing at least one of the following:

67. The method of claim 66.

68. the cylindrical wall of the capsule comprises a thermally conductive material; at least one of the first plurality of thermistors or the second plurality of thermistors is in thermal contact with the thermally conductive material of the cylindrical wall of the capsule; 67. The method of claim 66.

69. the capsule further includes a controller in communication with the first plurality of thermistors and the second plurality of thermistors; The method includes, using the controller, first acquiring data related to heat sensed from the tissue of the subject by the first plurality of thermistors and the second plurality of thermistors.

69. The method of claim 68.

70. the capsule further includes an antenna in communication with the controller; The method further includes transmitting, with the controller, the data via the antenna to an external device for at least one of storing and analyzing the transmitted data; the external device is coupled to a receiver belt including a plurality of receiver belt antennas for communicating with the external device; 70. The method of claim 69.

71. 71. The method of claim 70, further comprising: determining a first position of the capsule at a first time based on information from the plurality of receiving belt antennas.

72. 72. The method of claim 71, further comprising generating a first image of the tissue of the subject at the first location of the capsule on the subject based on the data from the first plurality of thermistors and the second plurality of thermistors related to heat sensed radiating from the tissue of the subject at a first time.

73. using the controller to acquire data from the first plurality of thermistors and the second plurality of thermistors related to heat sensed radiating from the tissue of the subject at a second time; determining a second position of the capsule at a second time based on information from the plurality of receiving belt antennas; generating a second image of the tissue of the subject at the second location of the capsule on the subject based on the data from the first and second plurality of thermistors related to heat sensed radiating from the tissue of the subject at a second time.

73. The method of claim 72.

74. 74. The method of claim 73, further comprising generating a map of heat radiated from the tissue of the subject based on the first image at the first location and the second image at the second location.

75. 75. The method of claim 74, further comprising determining at least one of the first location of the capsule or the second location of the capsule based on a comparison of the information from the plurality of receiving belt antennas and data regarding a relationship between antenna signal attenuation versus tissue depth.

76. 76. The method of any one of claims 61 to 75, wherein the at least one temperature sensor comprises at least one of a thermistor, a thermocouple, a semiconductor-based sensor, or a resistance-based temperature sensor.

77. a capsule containing a thermal imaging sensor; the capsule is configured to be swallowed by a subject; the thermal imaging sensor is configured to detect infrared radiation emitted by tissue of the subject; A device for detecting gastrointestinal lesions.

78. 78. The apparatus of claim 77, wherein the capsule further comprises a controller coupled to the thermal imaging sensor and configured to generate at least one image of the detected infrared radiation emitted by the tissue of the subject.

79. the capsule further includes a wireless transmitter; 79. The apparatus of claim 78, wherein the controller is configured to transmit the at least one image to the wireless transmitter, which transmits the image to an external antenna.

80. 80. The apparatus of claim 79, wherein the radio transmitter is configured to transmit at a frequency in the range comprised between 400 MHz and 500 MHz.

81. 81. The apparatus of claim 80, wherein the wireless transmitter is configured to transmit at a frequency of 433 MHz.

82. 79. The apparatus of claim 78, wherein the controller is configured to generate a plurality of images of the detected infrared radiation emitted by the tissue of the subject.

83. 83. The apparatus of claim 82, wherein the controller is further configured to generate at least one image per second of the detected infrared radiation emitted by the tissue of the subject.

84. 78. The device of claim 77, wherein the capsule further comprises a power supply comprising at least one battery.

85. 78. The apparatus of claim 77, wherein the thermal imaging sensor is configured to detect infrared radiation having a wavelength in a range comprised between 7 μm and 14 μm.

86. 86. The apparatus of claim 85, wherein the thermal imaging sensor comprises a thermopile sensor.

87. 80. The apparatus of claim 79, wherein the thermal imaging sensor further comprises an ultrasonic transducer coupled to the controller.

88. 88. The apparatus of claim 87, wherein the controller is further configured to obtain data from the ultrasound transducer indicative of a depth of feces between the capsule and the tissue.

89. 89. The apparatus of claim 88, wherein the controller is further configured to transmit the data from the ultrasound transducer indicating the depth of feces between the capsule and the tissue of the subject via the wireless transmitter to the external device.

90. 78. The apparatus of claim 77, wherein the thermal imaging sensor is configured to detect infrared radiation after a delay period.

91. 91. The apparatus of claim 90, wherein the delay period is at least two hours.

92. the capsule has a window that is transparent to infrared light; the window is adjacent to the thermal imaging sensor; 78. The apparatus of claim 77.

93. 93. The device of claim 92, wherein the window comprises a biocompatible material.

94. 94. The device of claim 93, wherein the window comprises low density polyethylene (LDPE).

95. further comprising a reflector adjacent to the thermal imaging sensor; the reflector is configured to redirect infrared light from the tissue to the thermal imaging sensor.

78. The apparatus of claim 77.

96. 96. The apparatus of claim 95, wherein the reflector is configured to divert the infrared radiation from a peripheral region around the capsule.

97. 96. The apparatus of claim 95, wherein the reflector has a pyramidal shape.

98. 98. The apparatus of claim 97, wherein the pyramidal shape has an apex that includes a triangular wedge.

99. the at least one image includes a plurality of images; the controller is configured to average the images together to generate an average image and send the average image to the wireless transmitter for transmission to the external antenna.

80. The apparatus of claim 79.

100. a capsule including a thermal imaging sensor in communication with a controller and a wireless transmitter; a plurality of antennas in communication with the capsule; the capsule is configured to be swallowed by a subject; the thermal imaging sensor is configured to detect infrared radiation emitted by tissue of the subject; the controller is configured to generate at least one image of the detected infrared radiation emitted by the tissue of the subject; the controller is configured to transmit the at least one image to the wireless transmitter, which transmits the at least one image to the plurality of external antennas; the plurality of external antennas are configured to receive the at least one image from the wireless transmitter. A system for detecting gastrointestinal lesions.

101. further comprising a computing system in communication with the plurality of antennas; the computing system is configured to determine a location of the capsule based on the plurality of antennas receiving the at least one image from the wireless transmitter.

101. The system of claim 100.

102. 102. The system of claim 101, wherein the computing system is further configured to determine the location of the capsule based on an amplitude of a signal received by each of the plurality of antennas.

103. 103. The system of claim 102, wherein the computing system is further configured to determine the position of the capsule with an uncertainty of one centimeter or less.

104. 101. The system of claim 100, wherein the plurality of antennas includes eight antennas.

105. each of the plurality of antennas is coupled to a belt; the belt is configured to be coupled to the subject; 101. The system of claim 100.

106. the at least one image includes a plurality of images, each having a first image resolution; the computing system is further configured to process the plurality of images to obtain at least one super-resolution image having a second resolution higher than the first resolution.

102. The system of claim 101.

107. at least two of the plurality of images correspond to at least two different positions of the capsule; the computing system is further configured to obtain the at least one super-resolution image based on interpolating at least two of the plurality of images corresponding to the at least two different positions of the capsule.

107. The system of claim 106.

108. providing a capsule configured to be swallowed by a subject, the capsule including a thermal imaging sensor; detecting infrared radiation emitted by tissue of the subject with the thermal imaging sensor. A method for detecting gastrointestinal lesions.

109. 109. The method of claim 108, further comprising generating, with a controller coupled to the thermal imaging sensor, at least one image of the detected infrared radiation emitted by the tissue of the subject.

110. the capsule further includes a wireless transmitter; The method further includes using the controller to transmit the at least one image to the wireless transmitter, which transmits the at least one image to an external antenna. The method of claim 109.

111. 111. The method of claim 110, wherein the wireless transmitter is configured to transmit the at least one image to the external antenna in a signal having a frequency in the range comprised between 400 MHz and 500 MHz.

112. 112. The method of claim 111, wherein the wireless transmitter is configured to transmit the at least one image to the external antenna at a frequency of 433 MHz.

113. 110. The method of claim 109, further comprising generating, by the controller, a plurality of images of the detected infrared radiation emitted by the tissue of the subject.

114. 114. The method of claim 113, further comprising generating, by the controller, at least one image per second of the detected infrared radiation emitted by the tissue of the subject.

115. 109. The method of claim 108, wherein the capsule further comprises a power supply comprising at least one battery.

116. 109. The method of claim 108, wherein detecting infrared radiation further comprises detecting infrared radiation having a wavelength in a range comprised between 7 μm and 14 μm using the thermal imaging sensor.

117. 117. The method of claim 116, wherein the thermal imaging sensor comprises a thermopile sensor.

118. the thermal imaging sensor further includes an ultrasonic transducer coupled to the controller; 111. The method of claim 110, further comprising obtaining data from the ultrasound transducer indicative of a depth of feces between the capsule and the tissue.

119. 119. The method of claim 118, further comprising transmitting, by the controller, the data from the ultrasound transducer indicating the depth of feces between the capsule and the tissue via the wireless transmitter to an external device.

120. 109. The method of claim 108, wherein detecting infrared radiation further comprises detecting infrared radiation after a delay period.

121. 121. The method of claim 120, wherein the delay period is at least 2 hours.

122. the capsule includes a window adjacent to the thermal imaging sensor; 109. The method of claim 108, further comprising transmitting the infrared radiation through the window to the thermal imaging sensor.

123. 123. The method of claim 122, wherein the window comprises a biocompatible material.

124. 124. The method of claim 123, wherein the window comprises low density polyethylene (LDPE).

125. further comprising a reflector adjacent to the thermal imaging sensor; 109. The method of claim 108, further comprising redirecting infrared radiation from the tissue to the thermal imaging sensor with the reflector.

126. 126. The method of claim 125, wherein diverting infrared radiation from the tissue to the thermal imaging sensor further comprises diverting infrared radiation from a peripheral region around the capsule to the thermal imaging sensor.

127. 126. The method of claim 125, wherein the reflector has a pyramidal shape.

128. 128. The method of claim 127, wherein the pyramidal shape has an apex that includes a triangular wedge.

129. the at least one image includes a plurality of images; the method further comprising averaging the images together to generate an average image and transmitting the average image to the wireless transmitter for transmission to the external antenna. The method of claim 110.

130. providing a capsule configured to be swallowed by a subject, the capsule including a thermal imaging sensor, a wireless transmitter, and a plurality of antennas in communication with a controller; detecting infrared radiation emitted by tissue of the subject with the thermal imaging sensor; generating, by the controller, at least one image of the detected infrared radiation emitted by the tissue of the subject; transmitting, by the controller, the at least one image to the wireless transmitter, which transmits the at least one image to the plurality of antennas; receiving the at least one image from the wireless transmitter by the plurality of antennas; A method for detecting gastrointestinal lesions.

131. providing a computing system in communication with the plurality of antennas; and determining, using the computing system, a location of the capsule based on the at least one image received by the plurality of antennas from the wireless transmitter. The method of claim 130.

132. 132. The method of claim 131, further comprising: using the computing system to determine the location of the capsule based on the amplitude of signals received by each of the plurality of antennas.

133. 133. The method of claim 132, further comprising using the computing system to determine the position of the capsule with an uncertainty of one centimeter or less.

134. 131. The method of claim 130, wherein the plurality of antennas comprises eight antennas.

135. each of the plurality of antennas is coupled to a belt; 131. The method of claim 130, further comprising coupling the plurality of antennas to the subject using the belt.

136. the at least one image includes a plurality of images, each having a first image resolution; The method further includes processing, with the computing system, the plurality of images to obtain at least one super-resolution image having a second resolution greater than the first resolution. The method of claim 131.

137. at least two of the plurality of images correspond to at least two different positions of the capsule; obtaining the at least one super-resolution image further includes obtaining, with the computing system, the at least one super-resolution image based on interpolating at least two of the plurality of images corresponding to the at least two different positions of the capsule. The method of claim 136.

138. the capsule further includes an ultrasonic transducer coupled to the controller; The method further comprises: using the controller to obtain data from the ultrasound transducer indicative of a depth of feces between the capsule and the tissue; using the controller to transmit the data from the ultrasound transducer indicating the depth of feces between the capsule and the tissue via the plurality of antennas and the wireless transmitter to the computing system; adjusting the at least one image using the computing system to compensate for the depth of the feces. The method of claim 131.

Images