Method and system for touchless infection detection at the epidermis

Abstract

A touchless system for assessing a status of a target individual may include an optical component configured to image a patient sample, a Raman spectrometer subsystem configured to detect inelastically scattered light from the patient sample, and a laser-induced fluorescence spectrometer subsystem configured to detect fluorescence emissions of the sample; and a controller configured to receive the inelastically scattered light from the Raman spectrometer subsystem, receive the fluorescence emissions from the laser-induced fluorescence spectrometer subsystem, and determine a status of the sample based on the inelastically scattered light and the fluorescence emissions.

Description

METHOD AND SYSTEM FOR TOUCHLESS INFECTION DETECTION AT THE EPIDERMISCROSS-REFERENCE TO RELATED APPLICATIONS|0001| This application claims the benefit of U.S. provisional application Serial No. 63 / 518,686 filed August 10, 2023, the disclosure of which is hereby incorporated in its entirety by reference herein.TECHNICAL FIELD

[0002] Disclosed herein are systems and methods for touchless infection detection.BACKGROUND

[0003] Passive status detection currently uses infrared, radar, and ultrasound technologies to measure vital signs. For example, non-contact thermometers were used extensively as real-time health checks during the COVID-19 pandemic. Other approaches evaluate sleep patterns and gait by video and audio collection. However, these approaches are not specific to infection, and are not significantly predictive due to individual variability in disease course symptomology. Diagnostic tools such as antibody or polymerase chain reaction (PCR) assays with high sensitivity and specificity are routinely used. These require direct contact with the individual for sample collection. Such techniques also necessitate testing for specific, known pathogens and are unable to diagnose emerging pathogens with undefined etiology and genetic fingerprint. Alternatively, current tools rely on sensor contact, which increases the risk of spreading the infection, and requires active participation from the subject.SUMMARY|0004| A touchless system for assessing a status of a target individual may include an optical component configured to image a patient sample, a Raman spectrometer subsystem configured to detect inelastically scattered light from the patient sample, and a laser-induced fluorescencespectrometer subsystem configured to detect fluorescence emissions of the sample; and a controller configured to receive the inelastically scattered light from the Raman spectrometer subsystem, receive the fluorescence emissions from the laser-induced fluorescence spectrometer subsystem, and determine a status of the sample based on the inelastically scattered light and the fluorescence emissions.

[0005] A method for passive detection of a status of a target individual may include receiving data indicating an inelastically scattered light of a patient sample from a Raman spectrometer subsystem of a patient sample, receiving data indicating fluorescence emissions of the patient sample from a fluorescence spectrometer subsystem, and determining a status of the patient sample based on the inelastically scattered light and the fluorescence emissions.

[0006] A passive status system for assessing the status of a target individual may include an optical component configured to image a patient sample, at least one spectrometer configured to detect data indicated at least one of scattered light and fluorescence emissions of the patient sample; and a controller programmed to receive the data from the spectrometer representing an image of the patient sample, filter the data to remove spectral clutter; and determine status of the patient sample based on the filtered data.BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In the accompanying drawings, reference characters refer to the same parts throughout the different views. The drawings are not necessarily to scale; emphasis has instead been placed upon illustrating the principles of the invention. Of the drawings:

[0008] FIG. 1 illustrates a schematic drawing illustrating a patient and a clinician using a passive bio-intelligence system for passive patient status detection where the patient is uninfected;

[0009] FIG. 2 illustrates a schematic drawing illustrating a patient and a clinician using a passive bio-intelligence system for passive patient status detection where the patient is infected;

[0010] FIG. 3 illustrates a block diagram of the system of FIGs. 1 and 2;

[0011] FIG. 4 illustrates an example of a cross-sectional view of a Spatially Offset Raman Spectroscopy (SCORS) sample;(0012] FIG. 5 illustrates an example chart of a SORS scattering faction vs. depth of the sample; and[001.3] FIG. 6A-C illustrate an example charts showing the Shifted Difference Raman Spectroscopy (SDFR) illustrating fluorescence background rejecting.DETAILED DESCRIPTION[0014| As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention that may be embodied in various and alternative forms. The figures are not necessarily to scale; some features may be exaggerated or minimized to show details of particular components. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a representative basis for teaching one skilled in the art to variously employ the present invention.

[0015] Lack of a remote diagnostic that can evaluate characteristics of an individual that may indicate a status of the individual (e.g., a health, physical, bodily system, etc.) creates a vulnerability for the biosecurity field. In some cases, certain biometric markers of an individual or group of individuals can correlate to a status that may indicate presence of a pathogen, disease, symptom, or other anomalies. Pathogen outbreaks have the potential to cause acute damage to society and economy. Surveillance of individuals and populations for patterns of infection is a growing area of urgency to the US government and the medical field. Passive surveillance, such as wastewater and air sampling, allows data collection without self-reporting or symptomatic presentation. However, these methods rely on pathogen-specific assays, can only detect pathogens shed into the sampling milieu, and do not identify specific individual status. The invention described here could provide a passive detector of individual status, providing a pathogen agnostic solutions for both population and individual surveillance.

[0016] Generally, the present disclosure concerns the methods and systems for near and remote, such as at greater than 1 meter range, for the evaluation of -status or anomalies, such as the remote detection of infection based on detected changes of the skin microbiome.

[0017] In some aspects, the methods and system leverage the homeostasis between the host immune system and the microbiota to exploit skin microbes as an accessible and specific readout of immune status of individuals being assessed. The approach can employ Spatially Offset Raman Spectroscopy (SORS) and Shifted Difference Raman Spectroscopy (SDFR) instrumental and signal processing techniques to enhance sensitivity and specificity by differentiating the target signal from spectral clutter. This enables a system configured as a fieldable detector to diagnose a range of infectious diseases. This non-contact detection technology facilities remote patient monitoring by identifying infected individuals irrespective of symptoms, without relying on direct contact for sample collection, and using a fraction of the resources required for traditional detection. Moreover, this remote surveillance has broader implications for national security by providing continuous monitoring at the population-level for early evidence of an outbreak to drive readiness and response, or identification of infected individuals at ports of entry to slow spread of infectious pathogens.

[0018] The immune system and the microbiota are tightly linked, and disruption or imbalance of one often leads to disequilibrium of the other. Thus, the skin microbiota, as a particularly accessible feature, has been shown in some instances change (dysbiosis) when the host immune system is disrupted, such as during infection or inflammatory disease. This invention proposes the infection- or inflammation-driven dysbiosis will result in metabolite (small molecule) changes at the skin surface (microbe or host). In turn, some of these molecules may be specifically detectable at standoff, based on specific molecular structures. Specific spectroscopic methods can be employed to precisely interrogate the presence of these features. Raman spectroscopy, specifically Spatially Offset Raman Spectroscopy (SORS) and shifted Difference Raman Spectroscopy (SDRS), as well as Laser-Induced Fluorescence (LIF) methods. The concepts that support these chosen methods are described in the attached proposal.

[0019] In general, according to one aspect, the disclosed system assesses the status of a target individual. The system includes a Raman spectrometer subsystem and a laser-induced fluorescence spectrometer subsystem. The system analyses the target for skin metabolic changes in response to one or more pathogens.

[0020] In general, Raman spectroscopy (RS) and laser-induced fluorescence spectroscopy (LIF) are able to detect the molecular composition of biological tissue. Raman spectroscopy, for instance, has allowed for fast and accurate cancer diagnostics, including the in vivo analysis of breast, cervical, and skin tissues. Additionally, in vivo Raman spectroscopy of human skin has been reported to accurately diagnose patients with kidney failure with good sensitivity and specificity. Fluorescence spectroscopy of human skin has been used to identify subjects with psoriasis, even when non-lesional sites are investigated.

[0021] One challenge in non-contact detection is the differentiation of the signal from spectral clutter due to background. Spectral signals due to the molecular components of skin, naturally produced skin compounds, and compounds layered onto the skin can obscure the spectrum of the targeted biomarker. To extract the diagnostically relevant spectrum from background, the controller 120 employs both instrumental and signal processing techniques utilized to enhance sensitivity and specificity to remove spectral clutter. Such techniques may include SORS and SDFR as explained herein.

[0022] FIG. 1 and FIG. 2 illustrate a schematic drawing illustrating a patient 102 and a clinician 104 using a passive bio-intelligence system 106 for passive status detection. The system 106 may detect and classify the patient 102 as an uninfected patient, as illustrated in FIG. 1, or an infected patient, as illustrated in FIG. 2. The passive bio-intelligence system 106 may detect anomalies in the patient 102 via touchless infection detection at the epidermis (TIDE) via imaging of a patient sample. The system 106 may include an optical sensor to gather patient data. This data be used to detect certain infections by leveraging discernable changes of the skin microbiome. Certain alterations of the skin may identifies infections.

[0023] As explained, some systems may use infrared, radar, and ultrasonic technologies to measure vital signals. This may include non-contact thermometers. Other passive-related detectionmethods may include evaluating sleep patterns, gait, etc. However, these approaches are not specific to infection, and are not significantly predictive due to individual variability in disease course symptomology. Where antibody and PCR assays are used, such methods require direct contact with the patient and are still unable to diagnose emerging pathogens with undefined etiology and genetic fingerprint. Thus, current tools rely on physical patient contact, which may lead to an increased risk in the spreading of infection.

[0024] This system 100 may include a display user interface 116 that would display the determined status of the patient 102. Often, the status would be either uninfected or infected in the case where the system 100 was used to search for individuals infected with a certain pathogen.

[0025] FIG. 3 illustrates a block diagram of the system 106 of FIGs. 1 and 2. In this example, the system 106 may include at least one of each of a Raman spectrometer subsystem 112 and a laser-induced fluorescence spectrometer subsystem 114. Both subsystems are configured to interrogate the patient 102 via projection and collection optics 110.

[0026] The Raman spectrometer subsystem 112 includes a Raman spectrometer configured to detect low-frequency light through Raman scattering. The Raman spectrometer may include a laser configured to excite a sample (e.g., the patient’s skin). When the laser light interacts with the epidermis molecule, most of the light is elastically scattered. The remining light is inelastically scattered and possesses a different energy. The light is then filtered to remove the elastically scattered light and is then dispersed by a spectrometer. The results are a unique Raman spectrum that can be analyzed.

[0027] In one embodiment, the Raman spectrometer subsystem 112 uses Spatially Offset Raman Spectroscopy (SORS) and Shifted Difference Raman Spectroscopy (SDFR). Generally, SORS achieves greater chemical specificity by relying on a spatial separation between illumination and collection zones, which enables control of skin penetration depth. SDFR improvises sensitivity by rejecting target-obscuring background fluorescence emissions. In SDFR, two single-frequency lasers are used to generate a Raman spectrum of the same sample, which provides for nearly identical penetration and molecular interaction and gives rise to slightly shifted, identical spectra. Dividing the two spectra provides a well-resolved target spectrum free of backgroundfluorescence. In other examples, the Raman spectrometer subsystem 112 uses Coherent AntiStokes Raman Spectroscopy (CARS), and Resonance Raman Spectroscopy (RRS).(0028] FIG. 4 illustrates an example of a cross-sectional view of a Spatially Offset Raman Spectroscopy (SCORS) sample. FIG. 5 illustrates an example chart of a SORS scattering faction vs. depth of the sample. The sample may be human skin.|0029| FIG. 6A-C illustrate example charts showing the SDFR) illustrating fluorescence background rejecting.[0030| Returning to FIG. 3, the laser-induced fluorescence spectrometer subsystem 114 may include a LIF to measure the fluorescence emissions by a sample excited by a laser. The LIF subsystem 114 may include a detector configured to detect the energy from the laser and collect the emitted fluorescence. A spectrometer disperses the light into its component wavelengths and detects the intensity at each wavelength. LIF subsystem 114 enables the remote detection of biological substances and offers high sensitivity for skin-safe laser powers. Enhancement of LIF specificity is gained by combining a multispectral approach with temporal resolution. Such a LIF detection subsystem acquires both spectral and time-resolved fluorescence. Excitation by multiple laser wavelengths provides for broad spectral emission that is measured by a spectrometer. A highspeed detector, operating in tandem, enables time-resolved measurements of the fluorescence emission.(0031 ] The projection and collection optics 110 may be an optical sensor configured to image, illuminate, and sense patient skin microbes. The optics 110 may include various lenses, mirrors, lights, sensors, etc., to project and collect light. This collection may in turn be used to evaluate the microbes.100321 A controller 120 is configured to analyze the data from the Raman spectrometer subsystem 112 and the laser-induced fluorescence spectrometer (LIF) subsystem 114 in order to determine the existence of a disease state of the target individual. The determined information may be presented to the user via the display 116. The controller 120 may include a memory 122, a non-volatile storage 124, and a processor 126. The non-volatile memory 124 may be configuredto maintain profiles and biomarkers associated with diagnosis profiles and may be configured to be updated to continually improve such profiles for better detection.(0033] The memory 122 may include a single memory device or a number of memory devices including, but not limited to, random access memory (RAM), volatile memory, non-volatile memory, static random access memory (SRAM), dynamic random access memory (DRAM), flash memory, cache memory, or any other device capable of storing information. The non-volatile storage 124 may include one or more persistent data storage devices such as a hard drive, optical drive, tape drive, non-volatile solid-state device, cloud storage or any other device capable of persistently storing information.10034] The processor 126 may include one or more microprocessors, micro-controllers, digital signal processors, microcomputers, central processing units (CPU), graphical processing units (GPU), tensor processing units (TPU), field programmable gate arrays, programmable logic devices, state machines, logic circuits, analog circuits, digital circuits, or any other devices that manipulate signals (analog or digital) based on computer-executable instructions residing in memory 122.10035] The processor 126 may be configured to read into memory 122 and execute computerexecutable instructions residing in the non-volatile storage 124. Upon execution by the processor 126, the computer-executable instructions may cause the system 106 to perform one or more of the algorithms and / or methodologies disclosed herein. This may include, but is not limited to, exciting the microbes via the optics 110 and receiving data via the spectrometers 112, 114 to determine whether the microbes indicate an infection.

[0036] Preferably, the controller 120, via the processor 126, analyzes the information from the Raman spectrometer subsystem 112 and the LIF subsystem 114 using both artificial intelligence and machine learning techniques. In general, an aggregated statistical classification combined with AI / ML helps to distinguish infection by the presence of spectral anomalies apparent between uninfected and diseased subjects. The key is obtaining nominally identical spectra for a large sample size for both infected and uninfected specimens. In any case, highly sophisticated signalprocessing methods, including principal component analysis (PCA) and partial least squares (PLS) regression, are useful.(0037] In one training approach, the chemical and metatranscriptomic data obtained from animal samples establish an integrated, predictive in silico model. A proportionality network is appropriate for identifying “co expression” patterns of metabolites and pathways, and interquartile log ratios will be used for normalization. Total RNA read counts mapped to assembled orthogroups (OGs) will inform potential infection of specific genes and pathways. This step can be informative even in the absence of insightful annotation; hypothetical proteins can be associated with mass spectra of unknown compounds. Machine learning strategies will train Generalized Linear Models with 2 / 3rds of the data, with subsequent testing on l / 3rd to determine model accuracy. The proportionality network will be used as a method for feature selection, allowing the data to drive empirical identification of important interactions.(0038] The display 116, as also shown in FIGs. 1 and 2, may be a screen or other form of display for presenting a user interface. The display 116 may be a liquid crystal (LCD), light emitting diode (LED), organic light emitting diode (OLED), quantum dot display (QLED), e-paper display (EPD), plasma display panel (PDP), microLED, etc. Further, the display 116 may be configured to receive user input and may be a touchscreen or include other user interfaces such as buttons, slides, etc. The display 116 may also be a projection display configured to project the user interface onto a surface remote from the system 106, or a heads-up display (HUD).|0039| The display 116 may be configured to present information relative to the analysis of the data acquired by the system 106. For example, the display 116 may be configured to provide a reading of the data. This may be in response to the determinations performed by the controller 120 and may directly reflect the findings relative to the signals and data from the spectrometers 112, 114. In some examples, the display 116 may be configured to provide a visual diagnosis or prognosis in response to detecting an infection in the microbes of the skin.10040] Although not shown, the system 106 may include a wireless transceiver configured to transmit and / or receive wireless signals carrying data. Such transceiver may allow the system 106 to communicate with a remote system to receive updates, analyze data, etc. Further, the system106 may interface with other systems, such as health provider systems, to provide results directly to such systems. Such integration may further permit continual machine learning and better facilitate infection detection.

[0041] Accordingly disclosed herein is a system configured to detect infection without active sampling and performing pathogean-specific analysis. The system leverages the homeostasis between a host immune system and microbial to exploit skin mibrobes as an accessible and specific readout of immune status.

[0042] Various aspects of the current embodiments may be embodied as a system, a method, or a computer program product. Therefore, various aspects of the present disclosure may take the following forms: a complete hardware embodiment, a complete software embodiment (including firmware, resident software, microcode, etc.), or a combination of software and hardware embodiments, which may be all regarded as "module" or "system" generally herein. In addition, any hardware and / or software technology, process, function, component, engine, module, or system described in the present disclosure may be implemented as a circuit or a group of circuits. In addition, various aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media on which computer-readable program code is embodied.

[0043] Any combination of one or more computer-readable media may be utilized. The computer- readable mediums may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media may include each of the following: an electrical connection with one or more wires, a portable computer floppy disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable CD-ROM, an optical storage apparatus, a magnetic storage apparatus, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium that can contain orstore a program for use by an instruction execution system, device, or apparatus or in combination with the instruction execution system, device, or apparatus.(0044] The aspects of the present disclosure are described above with reference to flowchart illustrations and / or block diagrams of methods, devices (systems) and computer program products according to the implementations of the present disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams and combinations of blocks in the flowchart illustrations and / or block diagrams may be implemented by computer program instructions. These computer program instructions may be provided to processors of general purpose computers, special purpose computers, or other programmable data processing devices to produce machines. When the instructions are executed via the processors of the computers or other programmable data processing devices, the functions / actions specified in the flowchart and / or block diagram block or multiple blocks can be realized. These processors m be, but are not limited to, general purpose processors, special purpose processors, special application processors, or field programmable gate arrays.

[0045] The flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, section, or part of code, and the code includes one or more executable instructions for implementing prescribed logical functions. It should also be noted that in some alternative implementations, the functionality described in the blocks may occur out of the order described in the drawings. For example, two blocks shown in succession may actually be executed substantially simultaneously, or the blocks may sometimes be executed in the reverse order depending on the functionality involved. It should also be noted that each block in the block diagram and / or flowchart illustration and the combination of the blocks in the block diagram and / or flowchart illustration can be implemented by a dedicated hardware-based system or dedicated hardware and computer instructions that perform the specified functions or actions.

[0046] Although the foregoing content is directed to the embodiments of the present disclosure, other and additional embodiments of the present disclosure may be conceived without departing from the basic scope of the present disclosure, and the scope of the present disclosure is determined by the appended claims.

[0047] While exemplary embodiments are described above, it is not intended that these embodiments describe all possible forms of the invention. Rather, the words used in the specification are words of description rather than limitation, and it is understood that various changes may be made without departing from the spirit and scope of the invention. Additionally, the features of various implementing embodiments may be combined to form further embodiments of the invention.

Claims

WHAT IS CLAIMED IS:

1. A touchless system for assessing a status of a target individual, comprising: an optical component configured to image a patient sample; a Raman spectrometer subsystem configured to detect inelastically scattered light from the patient sample; and a laser-induced fluorescence spectrometer subsystem configured to detect fluorescence emissions of the sample; and a controller configured to receive the inelastically scattered light from the Raman spectrometer subsystem, receive the fluorescence emissions from the laser-induced fluorescence spectrometer subsystem, and determine a status of the sample based on the inelastically scattered light and the fluorescence emissions.

2. The system of claim 1, further comprising a display user interface for displaying the determined status of the target individual.

3. The system of claim 1, wherein the controller is programmed to assess the inelastically scattered light and the fluorescence emissions using machine learning or artificial intelligence.

4. The system of claim 1, wherein the Raman spectrometer subsystem uses at least one of Spatially Offset Raman Spectroscopy (SORS) and Shifted Difference Raman Spectroscopy (SDFR).

5. The system of claim 1, wherein the laser-induced fluorescence spectrometer subsystem acquires both spectral and time-resolved fluorescence.

6. The system of claim 1, wherein the laser-induced fluorescence spectrometer subsystem excites by multiple laser wavelengths to provide for broad spectral emission that is measured by a spectrometer.

7. The system of claim 1, wherein the Raman spectrometer subsystem uses at least one of Coherent Anti-Stokes Raman Spectroscopy (CARS) and Resonance Raman Spectroscopy (RRS).

8. A method for passive detection of a status of a target individual, comprising: receiving data indicating an inelastically scattered light of a patient sample from aRaman spectrometer subsystem of a patient sample, receiving data indicating fluorescence emissions of the patient sample from a fluorescence spectrometer subsystem, and determining a status of the patient sample based on the inelastically scattered light and the fluorescence emissions.

9. The method of claim 8, further comprising instructing a display user interface to display the determined status of the target individual.

10. The method of claim 9, wherein the determining a status includes assessing the data indicating the inelastically scattered light and the fluorescence emissions using machine learning or artificial intelligence.

11. The method of claim 9, wherein the Raman spectrometer subsystem uses Spatially Offset Raman Spectroscopy (SORS).

12. The method of claim 9, wherein the Raman spectrometer subsystem uses Shifted Difference Raman Spectroscopy (SDFR).

13. The method of claim 9, further comprising acquiring spectral and time- resolved fluorescence via the laser-induced fluorescence spectrometer subsystem.

14. The method of claim 9, further comprising exciting multiple laser wavelengths at the laser-induced fluorescence spectrometer subsystem to provide for broad spectral emission.

15. The method of claim 9, wherein the Raman spectrometer subsystem uses Coherent Anti-Stokes Raman Spectroscopy (CARS)16. The method of claim 9, wherein the Raman spectrometer subsystem uses Resonance Raman Spectroscopy (RRS).

17. A passive status system for assessing the status of a target individual, comprising: an optical component configured to image a patient sample; at least one spectrometer configured to detect data indicated at least one of scattered light and fluorescence emissions of the patient sample; and a controller programmed to receive the data from the spectrometer representing an image of the patient sample; filter the data to remove spectral clutter; and determine status of the patient sample based on the filtered data.

18. The system of claim 17, further comprising a Raman spectrometer and a laser-induced fluorescence spectrometer configured to filter the data.

19. The system of claim 18, wherein the Raman spectrometer subsystem uses at least one of Spatially Offset Raman Spectroscopy (SORS), Shifted Difference Raman Spectroscopy (SDFR), Coherent Anti-Stokes Raman Spectroscopy (CARS) and Resonance Raman Spectroscopy (RRS).

20. The system of claim 18, further comprising a laser-induced fluorescence spectrometer subsystem to filter the data.

Images