Automatic lesion detection

Abstract

The present disclosure provides systems and methods for determining an outer elastic layer ("EEL") value of an intravascular image frame and using a predicted EEL to determine a plaque load for each image frame. The predicted EEL value may be determined based on a threshold number of image frames within the region of interest having a plaque load lower than the threshold plaque load. In some examples, the predicted EEL value may be determined as a function of intimal and medial thickness and an expected lumen diameter derived by an H-K model. The determined plaque load and visible EEL radians can be used to automatically identify lesions and suggest candidate treatment zones.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of the filing date of U.S. Provisional Patent Application No. 63 / 527,108, filed on July 17, 2023, the disclosure of which is incorporated herein by reference. Background Art

[0003] Based on the image data captured by the intravascular probe during the intravascular pullback, various measurements of the vessel can be automatically determined using computer software. However, the presence of plaque or other deposits in the vessel can hinder or increase the difficulty of automatically determining such measurements. This may result in incomplete vascular data obtained from the pullback. Incomplete data may cause problems in using the data to make further determinations (such as automatically selecting a candidate treatment area), or such further determinations may not be made automatically at all. This may cause the physician to manually enter or adjust clinical parameters (such as candidate treatment areas). Summary of the invention

[0004] The present disclosure generally relates to apparatus, methods, computer program codes, etc. for automatically estimating the external elastic layer ("EEL") value of an intravascular image frame. The estimated EEL can be used to determine the plaque burden of the image frame (for which the EEL value is estimated). The EEL value can be, for example, the EEL diameter or the EEL area. For example, plaque may be overgrown on a blood vessel, making it impossible to automatically determine the EEL value during pullback, or the EEL value cannot be seen by a user (e.g., an analyst or physician). For image frames where the EEL value is not detected and / or the EEL value is incorrectly measured, the EEL value can be predicted. The EEL value can be predicted for image frames within a region of interest. For example, the region of interest can be a vascular region between two side branches.

[0005] In one example, the region of interest may include a first set of frames and a second set of frames. The first set of frames may be image frames in which EEL values ​​are detected during pullback. The second set of frames may be image frames in which EEL values ​​are not detected during pullback. If the first set of frames includes a threshold number of image frames whose plaque load is lower than a threshold plaque load, at least the threshold number of frames may be used to predict the EEL value. For example, the threshold plaque load may be a healthy plaque load. The threshold plaque load may be a plaque load between approximately 0-50%. Representative values ​​of the EEL values ​​of the threshold number of image frames may be determined. For example, the representative EEL value may be an average, a median, or an EEL mean. The representative EEL value may be used as the predicted EEL value of the image frames in the second set of frames. According to some examples, the representative EEL value of the first set of frames may be used as the determined EEL value of each frame in the first subset of frames. For example, if some frames in the first subset of frames have erroneously measured EEL values, the determined representative EEL value may be used as the EEL value of the frame in the first subset of frames having an erroneous EEL value. An erroneous EEL value may be an EEL value that exceeds a standard deviation of the determined representative EEL value, an EEL value that is outside a predetermined range of the determined representative EEL value, and the like.

[0006] In another example, the EEL value of each frame in the region of interest can be predicted as a function of the intimal thickness and the media thickness. Continuing with the previous example, if the first set of frames does not include a threshold number of frames with a plaque load below a threshold plaque load, the EEL value can be predicted based on the intimal thickness and the media thickness. In some examples, the EEL value can be further based on the HK model. According to some examples, the EEL value can be predicted based on the intimal thickness, the media thickness and the HK model. According to some examples, if the EEL value of the blood vessel in the segment distal to the region of interest is greater than the predicted EEL value of the region of interest, the EEL value of the distal segment can be used as the predicted EEL value of the region of interest. The EEL value of the distal segment can be a representative EEL value of the distal segment. In some examples, if the EEL value of the blood vessel in the segment proximal to the region of interest is less than the predicted EEL value of the region of interest, the EEL value of the proximal segment can be used as the predicted EEL value of the region of interest. The EEL value of the proximal segment can be a representative EEL value of the proximal segment. The EEL value for the proximal or distal segment may be used based on the natural taper of the vessel from the proximal vessel segment to the distal vessel segment.

[0007] The predicted EEL value can be used to determine the plaque load of the corresponding image frame. For example, the predicted EEL value and the lumen area of ​​a given frame can be used to determine the plaque load. The determined plaque load can be used to identify lesions within a blood vessel. According to some examples, if the first lesion is within a threshold distance from the second lesion, the first and second lesions can be identified as a combined lesion. The identified lesions can be used to identify candidate treatment areas. For example, candidate treatment areas can be identified as corresponding to frames that are not within the identified lesions, are at a minimum distance from the identified lesions, have a plaque load less than a lesion load, have a visible EEL greater than or equal to an arc threshold, and so on.

[0008] One aspect of the present disclosure relates to a method, comprising: receiving, by one or more processors, vascular data including intravascular imaging data; identifying, by the one or more processors, a region of interest of the vessel based on the vascular data; identifying, by the one or more processors, a first subset of frames within the region of interest, the frames of the first subset having a plaque load below a threshold plaque load, the frames of the first subset including at least a threshold number of frames; determining, by the one or more processors, an external elastic layer ("EEL") value of the frames of the first subset; determining, by the one or more processors, a representative EEL value of the region of interest based on the EEL value of the frames of the first subset; and determining, by the one or more processors, a plaque load of a second subset of frames within the region of interest based on the representative EEL value, wherein the frames of the second subset are different from the frames of the first subset.

[0009] The region of interest may be defined between the first vessel branch and the second vessel branch. The EEL value may be an EEL diameter or an EEL area, and the representative EEL value may be a representative EEL diameter or a representative EEL area. The threshold plaque load may correspond to a plaque load of 0-50% or approximately 0-50%. The threshold number of frames may be at least three frames.

[0010] The plaque burden may be further determined based on the lumen area of ​​the corresponding frame. The determination of the plaque burden of the corresponding frame may include calculating 1-(lumen area / representative EEL value).

[0011] The method may further include: identifying, by the one or more processors, a lesion based on the determined plaque load. The method may further include: identifying, by the one or more processors, a candidate treatment zone based on the identified lesion. Identifying the candidate treatment zone may further include: identifying, by the one or more processors, proximal and distal frames of the identified lesion, wherein at least one of the plaque loads of the proximal and distal frames of the identified lesion is less than a threshold, or a visible EEL arc is greater than or equal to an arc threshold. When a first lesion is within a minimum gap distance from a second lesion, the method may further include: identifying, by the one or more processors, the first lesion and the second lesion as a combined lesion.

[0012] Another aspect of the present disclosure relates to a system, the system comprising one or more processors. The one or more processors may be configured to: receive vascular data including intravascular imaging data; identify a region of interest of the vessel based on the vascular data; identify a first subset of frames within the region of interest, the first subset of frames having a plaque load below a threshold plaque load, the first subset of frames comprising at least a threshold number of frames; determine an external elastic layer ("EEL") value of the first subset of frames; determine a representative EEL value of the region of interest based on the EEL values ​​of the first subset of frames; and determine a plaque load of a second subset of frames within the region of interest based on the representative EEL value, wherein the second subset of frames is different from the first subset of frames.

[0013] Yet another aspect of the present disclosure relates to a transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to: receive vascular data including intravascular imaging data; identify a region of interest of the vessel based on the vascular data; identify a first subset of frames within the region of interest, the frames of the first subset having a plaque load below a threshold plaque load, the frames of the first subset including at least a threshold number of frames; determine an external elastic layer ("EEL") value for the frames of the first subset; determine a representative EEL value for the region of interest based on the EEL values ​​for the frames of the first subset; and determine a plaque load for a second subset of frames within the region of interest based on the representative EEL value, wherein the frames of the second subset are different from the frames of the first subset.

[0014] One aspect of the present disclosure relates to a method, comprising: receiving, by one or more processors, vascular data including intravascular imaging data; identifying, by the one or more processors, a region of interest of the vessel based on the vascular data; determining, by the one or more processors, predicted external elastic layer ("EEL") values ​​of frames within the region of interest as a function of intima thickness and media thickness based on the vascular data; and determining, by the one or more processors, plaque load of frames within the region of interest based on the predicted EEL values.

[0015] The region of interest may be defined between the first vessel branch and the second vessel branch.The predicted EEL value may further be determined as a function of at least one of a lumen area or a lumen diameter obtained from the HK model.

[0016] The plaque burden may be further determined based on the lumen area of ​​the corresponding frame. The determination of the plaque burden of the corresponding frame may include calculating 1-(lumen area / predicted EEL value).

[0017] The method may further include: identifying, by the one or more processors, a lesion based on the determined plaque load. The method may further include: identifying, by the one or more processors, a candidate treatment zone based on the identified lesion. Identifying the candidate treatment zone may further include: identifying, by the one or more processors, proximal and distal frames of the identified lesion, wherein at least one of the plaque loads of the proximal and distal frames of the identified lesion is less than a threshold, or a visible EEL arc is greater than or equal to an arc threshold. When a first lesion is within a minimum gap distance from a second lesion, the method may further include: identifying, by the one or more processors, the first lesion and the second lesion as a combined lesion.

[0018] The method may further include: comparing, by the one or more processors, the predicted EEL value of the region of interest with a representative EEL value of a proximal segment of the blood vessel; and when the representative EEL value of the proximal segment is less than the predicted EEL value of the region of interest, determining the plaque burden of the region of interest based on the representative EEL value of the proximal segment.

[0019] The method may further include: comparing, by the one or more processors, the predicted EEL value of the region of interest with a representative EEL value of a distal segment of the blood vessel; and when the representative EEL value of the distal segment is greater than the predicted EEL value of the region of interest, determining the plaque burden of the region of interest based on the representative EEL value of the distal segment.

[0020] Another aspect of the present disclosure relates to a system, comprising one or more processors. The one or more processors may be configured to: receive vascular data including intravascular imaging data; identify a region of interest of a vessel based on the vascular data; determine a predicted external elastic layer ("EEL") value for a frame within the region of interest as a function of intima thickness and media thickness based on the vascular data; and determine a plaque load for a frame within the region of interest based on the predicted EEL value.

[0021] Yet another aspect of the present disclosure relates to a transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to: receive vascular data including intravascular imaging data; identify a region of interest of the vessel based on the vascular data; determine, based on the vascular data, a predicted external elastic layer ("EEL") value for a frame within the region of interest as a function of intima thickness and media thickness; and determine a plaque load for the frame within the region of interest based on the predicted EEL value. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The patent or patent application file contains at least one drawing printed in color. Copies of this patent or patent application publication with color drawings will be provided by the Office upon request and payment of the necessary fee.

[0023] Figure 1 is an exemplary system according to various aspects of the present disclosure.

[0024] Figure 2A is an exemplary intravascular image that can be used according to various aspects of the present disclosure. Figure 1 system capture.

[0025] Figure 2B is an exemplary annotated intravascular image that may be used according to various aspects of the present disclosure. Figure 1 system capture and / or annotation of the

[0026] Figure 2C is an exemplary vertical representation, which may be used according to various aspects of the present disclosure. Figure 1 system generated.

[0027] Figure 3 is an exemplary user interface that may be used according to various aspects of the present disclosure. Figure 1 system implementation.

[0028] Figure 4 is another exemplary user interface that can be used according to various aspects of the present disclosure. Figure 1 system implementation.

[0029] Figure 5 is an exemplary longitudinal representation for identifying lesions, which may be used according to aspects of the present disclosure. Figure 1 system generated.

[0030] Figure 6 is an exemplary user interface for identifying candidate treatment areas, which may be used according to various aspects of the present disclosure. Figure 1 system implementation.

[0031] Figure 7 is an exemplary user interface for stent planning, which may be used according to aspects of the present disclosure. Figure 1 system implementation.

[0032] Figure 8 is a flow chart showing a method for determining plaque burden based on average EEL values, which method can be used to provide Figure 3 , Figure 4 , Figure 6 and Figure 7 interface screen.

[0033] Fig. 9 is a flow chart showing a method for determining plaque burden based on predicted EEL values, which method can be used to provide Figure 3 , Figure 4 , Figure 6 and Figure 7 interface screen. DETAILED DESCRIPTION

[0034] The present technology generally refers to automatically identifying lesions based on the plaque load within a blood vessel. The plaque load can be determined as a function of a lumen value and an external elastic layer ("EEL") value. For example, the EEL value can be an EEL diameter and / or an EEL area. The lumen value and the EEL value can be automatically determined based on intravascular image data obtained during pullback of the intravascular probe. In some examples, plaque may have overgrown in the blood vessel, making it impossible to determine the EEL value based on the image data. In some examples, plaque may cause the user to be unable to see the EEL value in the intravascular image data, or the EEL value to be incorrectly determined. The user can be, for example, an analyst, a physician, etc. In the event that the EEL value cannot be determined based on the image data obtained during pullback, the EEL value can be predicted.

[0035] For an area of ​​interest, such as a vascular area between two side branches, an EEL value can be predicted as a representative EEL value. According to some examples, a representative EEL value can be predicted as an average, median, mean, or mode EEL value. For clarity, representative EEL values ​​will be used throughout the disclosure. However, the representative EEL value can be replaced by a median EEL value, an average EEL value, and / or a mean EEL, and therefore, the use of the term "representative" does not mean limitation.

[0036] The representative EEL value may be determined based on a threshold number of frames within the region of interest. For example, the region of interest may have a first set of frames, wherein the plaque load of the image frames is lower than a threshold plaque load. The threshold plaque load may be approximately 0-50%. The first set of image frames may have a threshold number of image frames, such as at least three image frames. The region of interest may have a second set of image frames, wherein the plaque load is greater than the threshold plaque load, and the EEL value cannot be automatically determined (or similar situations). The representative EEL value may be determined based on the EEL value of the first set of frames. The representative EEL value may be used as a predicted EEL value for a frame in the second set of frames. According to certain examples, the representative EEL value may be used as the EEL value of at least one frame in the first set of frames. For example, the first set of frames may include one or more frames with an erroneously measured EEL value. The representative EEL value may be used for a frame in the first set of frames, the EEL value of the frame exceeds the standard deviation of the representative EEL value, that is, exceeds a predetermined range of the representative EEL value, or similar situations.

[0037] According to some examples, the EEL value can be predicted as a representative EEL value of a threshold number of frames based on the HK model. For example, when the HK model is applied, the HK model works under the assumption that the vessel size (eg, diameter, area, etc.) remains substantially constant between two side branches.

[0038] In some examples (where the region of interest does not include a threshold number of frames or visible EELs with a plaque load less than a threshold plaque load), the EEL values ​​of frames in the region of interest can be predicted as a function of the intima thickness and the media thickness. The intima thickness can be, for example, a minimum intima thickness, and the media thickness can be, for example, a minimum media thickness. The minimum intima thickness and the minimum media thickness can be determined based on histological observations of the blood vessels. For example, based on histological observations of the blood vessels, the intima thickness and the media thickness (with a standard deviation) can be determined. The minimum intima thickness and the minimum media thickness can be determined based on the low end of the standard deviation. For example, if the total thickness of the intima and the media is determined to be 427μm±190μm, the minimum total thickness of the intima and the media is 237μm. According to some examples, the predicted EEL value can be further determined as a function of the lumen area / diameter derived from the HK model.

[0039] The HK model assumes that the blood vessel naturally tapers from the proximal segment of the blood vessel to the distal segment of the blood vessel. In such an example, the predicted EEL value of the region of interest can be compared with the representative EEL value of the proximal segment of the region of interest. According to some examples, the proximal segment can be adjacent to the region of interest or closer than the region of interest. If the representative EEL value of the proximal segment is less than the predicted EEL value, the representative EEL value can be used as the predicted EEL value of the region of interest. In some examples, the predicted EEL value of the region of interest can be compared with the representative EEL value of the blood vessel segment at the distal end of the region of interest. In some examples, the distal segment can be adjacent to the region of interest or farther than the region of interest. If the representative EEL value of the distal segment is greater than the predicted EEL value of the region of interest, the representative EEL value of the distal segment can be used as the predicted EEL value of the region of interest.

[0040] Representative EEL values ​​and / or predicted EEL values ​​can be used to determine the plaque load of each frame in the region of interest. For example, the plaque load can be determined based on the EEL value (median or predicted EEL value) and the lumen area of ​​the corresponding frame. For example, the median or predicted EEL value can be the median or predicted EEL area. In some examples, the median or predicted EEL value can be the median or predicted EEL diameter. According to some examples, the plaque load can be determined by the following formula: 1-(lumen area / EEL value). The EEL value can be an average EEL value or a predicted EEL value.

[0041] Plaque load can be used to identify lesions. For example, an image frame with a maximum amount of plaque load can be identified. According to some examples, the identified image frame can be identified as an image frame that exceeds a disease threshold. The disease threshold can be, for example, a stenosis percentage, plaque load, etc. In some examples, the disease threshold can be, for example, a plaque load in a range of approximately 60-100%. According to some examples, the disease threshold can be a plaque load of approximately 70%. In some examples, the disease threshold can be determined based on disease characteristics, such as plaque load, stenosis percentage, etc., so that the percentage can be greater than or less than 70%, or within or outside the range of 60-100%.

[0042] The identified image frame may be an initial image frame for a given lesion. To determine the size and location of the lesion, the plaque load of the frames proximal and distal to the initial frame may be compared to a treatment zone threshold until the plaque load of an image frame proximal and distal to the initial frame is less than the treatment zone threshold. The treatment zone threshold may be approximately 50% plaque load. In some examples, the treatment zone threshold may be greater than or less than 50% plaque load. For example, the treatment zone threshold may correspond to approximately 45% plaque load. In some examples, the treatment zone threshold may be a range, such as approximately 0-50% plaque load. In some examples, the treatment zone threshold may be patient-specific, determined by a physician, and the like. In some examples, the treatment zone end frame may correspond to a visible EEL arc greater than or equal to an arc threshold. The arc threshold may be at least or approximately 180 degrees. Therefore, the exemplary treatment zone thresholds discussed herein are not limiting. Image frames between the identified proximal and distal frames are then marked as corresponding to the lesion.

[0043] According to some examples, the process of identifying lesions is repeated until all lesions within the blood vessel are identified. For example, an image frame with the next largest plaque load (excluding image frames from identified lesions) may be identified. Lesions (including image frames with the next largest plaque load) are determined by comparing the plaque load of frames proximal and distal to the image frame with the next largest plaque load with a treatment zone threshold. The plaque load of frames proximal and distal to the image frame with the next largest plaque load may be compared to the treatment zone threshold until the plaque load of image frames proximal and distal to the initial frame is less than the treatment zone threshold. Image frames between the identified proximal and distal frames are then marked as corresponding to lesions.

[0044] After identifying each lesion, a gap or distance between the lesions is determined. In examples where the gap is substantially equal to or less than a threshold distance, the lesions may be combined and identified as a single lesion. For example, when a first lesion is within a minimum gap distance of a second lesion (e.g., the gap between the first and second lesions is less than the threshold distance), the first and second lesions may be identified as a combined lesion. In examples where the gap is greater than the threshold distance, the lesions may be identified as separate lesions. According to some examples, a suggested or candidate treatment zone may be identified. For example, the treatment zone may be a stent landing zone, a balloon angioplasty zone, a laser atherectomy zone, or the like. In examples where the treatment zone is a stent landing zone, a stent landing zone for the stent may be identified based on the identified lesions.

[0045] By predicting the EEL values ​​for those image frames for which the EEL values ​​cannot be correctly determined during the pullback, the plaque load of a given frame can be determined. For example, by predicting the EEL values ​​of the image frames, the plaque load of each image frame obtained during the pullback can be determined. Compared with ignoring the image frames for which the EEL cannot be determined during the pullback, more accurate and complete vascular information can be obtained. Further, by determining the plaque load of the image frames during the pullback, the detected EEL values ​​and the predicted EEL values ​​can be used to more accurately identify the lesion location, length, severity, etc. Identifying lesions with higher accuracy can more accurately identify candidate treatment areas. For example, plaque load and lesion location can be used to determine a candidate treatment area end frame, which does not include a lesion and / or has a plaque load less than a threshold load. This reduces the need for user interaction to determine and / or adjust the treatment area (to a location outside the lesion or in a location where the plaque load is less than a threshold). According to some examples, the treatment area can be a stent landing area. In some examples, the treatment area can be used for balloon angioplasty, etc.

[0046] Figure 1 A data collection system 100 for collecting intravascular and extravascular data is shown. The system may include an intravascular data collection probe 104, an external imaging device 120, and a subsystem 108. The subsystem 108 may include an optical receiver 110, a computing device 112, and a display 118.

[0047] The data collection probe 104 can be, for example, an optical coherence tomography ("OCT") probe, an intravascular ultrasound ("IVUS") catheter, a micro-OCT probe, a near infrared spectroscopy (NIRS) sensor, optical frequency domain imaging ("OFDI"), or any other device that can be used to image the blood vessel 102. In some examples, the data collection probe 104 can be a pressure line, a flow meter, etc. The probe 104 can include a probe tip, one or more radiopaque markers, an optical fiber, and a torque line. In addition, the probe tip includes one or more data collection subsystems, such as a beam guide, an acoustic beam guide, a pressure probe sensor, other transducers or detectors, and combinations thereof.

[0048] Although the examples provided herein refer to intravascular imaging devices, such as OCT probes, it is not intended to limit the use of OCT probes. For example, an IVUS catheter, a pressure line, or another intravascular data collection device can be used in conjunction with or in place of an OCT probe. In general, the present disclosure can be applied to any intravascular data collection device that can be used to generate and receive signals including measurement information (such as image data) (related to the blood vessel in which they are used). These devices can include, but are not limited to, imaging devices, such as optical or ultrasound probes, pressure sensor devices, and other devices suitable for collecting data related to blood vessels or other components of the cardiovascular system.

[0049] A guidewire (not shown) may be used to introduce the probe 104 into the blood vessel 102. The probe 104 may be introduced along the length of the blood vessel and pulled back while data is collected.

[0050] The probe 104 may be connected to a subsystem 108 via an optical fiber 106. The subsystem 108 may include a light source (e.g., a laser), an interferometer having a sample arm and a reference arm, various optical paths, a clock generator, a photodiode, and other OCT, IVUS, micro-OCT, NIRS, and / or pressure line components.

[0051] The probe 104 may be connected to an optical receiver 110. According to some examples, the optical receiver 110 may be a balanced photodiode based system. The optical receiver 110 may be configured to receive light collected by the probe 104. The probe 104 may be coupled to the optical receiver 110 via a wired or wireless connection.

[0052] The system 100 may further include an external imaging device 120, or be configured to receive data from an external imaging device 120. For example, the external imaging device may be an imaging system based on angiography, fluoroscopy, X-ray, magnetic resonance imaging, computer-assisted tomography, etc. The external imaging device 120 may be configured to perform non-invasive imaging of the blood vessel 102. According to some examples, the external imaging device 120 may acquire one or more images before, during, and / or after the data collection probe 104 is pulled back. The external imaging device 120 may be used to image the patient in order to make clinical decisions and perform various possible treatment plans (such as stent placement). These and other imaging systems can be used to image the patient externally or internally to obtain raw data, which may include various types of image data.

[0053] The external imaging device 120 can communicate with the subsystem 108. According to some examples, the external imaging device 120 can be wirelessly connected to the subsystem 108 via a communication interface such as Wi-Fi or Bluetooth. In some examples, the external imaging device 120 can communicate with the subsystem 108 via a cable such as an optical fiber. In another example, the external imaging device 120 can be indirectly communicatively connected to the subsystem 108 or the computing device 112. For example, the external imaging device 120 can be connected to a separate computing device (not shown) that communicates with the computing device 112. For another example, image data from the external imaging device 120 can be transmitted to the computing device 112 using a computer-readable storage medium.

[0054] Subsystem 108 may include computing device 112. One or more steps may be performed automatically or without user input to browse images, enter information, make selections and / or interact with inputs, etc. In some examples, one or more steps may be performed based on receiving user input via mouse clicks, keyboard, touch screen, verbal commands, etc. Computing device 112 may include one or more processors 113, memory 114, instructions 115, data 116, and one or more modules 117.

[0055] The one or more processors 113 may be any conventional processor, such as a commercially available microprocessor. Alternatively, the one or more processors may be a dedicated device, such as an application specific integrated circuit (ASIC) or other hardware-based processor. Figure 1 The processor, memory, and other elements of device 110 are functionally illustrated as being within the same box, but one of ordinary skill in the art will appreciate that a processor, computing device, or memory may actually include multiple processors, computing devices, or memories, which may or may not be stored in the same physical housing. Similarly, the memory may be a hard drive or other storage medium located in a different housing than device 112. Therefore, references to a processor or computing device should be understood to include references to a collection of processors or computing devices or memories, which may or may not operate in parallel.

[0056] Memory 114 may store information accessible to the processor, including instructions 115 executable by processor 113, and data 116. Memory 114 may be a type of memory (including non-transitory computer-readable media) that stores information accessible to processor 113, or other media that stores data that can be read with the aid of an electronic device (e.g., a hard disk, a memory card, a read-only memory ("ROM"), a random access memory ("RAM"), an optical disk, and other writable and read-only memories). The subject matter disclosed herein may include different combinations of the above, with different portions of instructions 115 and data 116 stored on different types of media.

[0057] The memory 114 can be retrieved, stored or modified by the processor 113 according to the instructions 115. For example, although the present disclosure is not limited to a specific data structure, the data 116 can be stored in a computer register, in a relational database as a table with multiple different fields and records, an XML document or a flat file. The data 116 can also be formatted in a computer readable format, such as but not limited to binary values, ASCII or Unicode. By further example, the data 116 can be stored as a bitmap composed of pixels, stored in a compressed or uncompressed manner, or stored in various image formats (such as JPEG), vector-based formats (such as SVG) or computer instructions for drawing graphics. In addition, the data 116 can also include information sufficient to identify the relevant information, such as numbers, descriptive text, proprietary codes, pointers, references to data stored in other memories (including other network locations), or information used by functions to calculate related data.

[0058] Instructions 115 may be any set of instructions that are directly executed (e.g., machine code) or indirectly executed (e.g., scripts) by processor 113. In this regard, the terms "instructions," "applications," "steps," and "programs" are used interchangeably herein. Instructions may be stored in an object code format for direct processing by a processor, or in any other computing device language, including scripts or a collection of independent source code modules that are interpreted on demand or compiled in advance. The functions, methods, and routines of instructions are explained in more detail below.

[0059] According to some examples, the computing device 112 may receive data from the probe 104 via a wired connection or a wireless connection. For example, the data may include intravascular data, including intravascular imaging data, pressure data, temperature data, flow data, or the like. The data received by the computing device 112 from the probe 104 may be used to determine plaque burden, fractional flow reserve ("FFR") measurements at one or more locations along the vessel, calcium angles, EEL detection, calcium detection, proximal frames, distal frames, EEL-based metrics, stent / no-stent decisions, scoring, stripping recommendations and other procedures, evidence-based recommendations obtained by automatically detecting areas / features of interest, stent planning, etc.

[0060] The data obtained by the probe 104 and / or the external imaging device 120 may be processed by one or more modules to provide information about the vessel, including lumen contour, vessel diameter, vessel cross-sectional area, lumen area, EEL value, EEL diameter, EEL curvature, lesion location, lesion size, plaque load, VFR, FFR, landing zone, treatment zone, virtual stent surrounded by the landing zone, etc. According to some examples, the module 117 may include an EEL detection module 122, a lumen detection module 123, a lesion detection module 124, and a registration module.

[0061] The EEL detection module 122 may automatically detect and measure the EEL diameter of a given intravascular image frame acquired during a vessel pullback. The lumen detection module 123 may automatically detect and measure the lumen diameter of a given intravascular image frame acquired during a vessel pullback. The lesion detection module 124 may automatically detect lesions within a vessel based on the vessel data acquired from the probe 104 and / or the external imaging device 120. The side branch detection module 125 may process the vessel data acquired from the probe 104 and / or the external imaging device 120 to detect one or more side branches of the vessel.

[0062] The computing device 112 may be adapted to register the vascular data obtained during the pullback of the probe 104 with the intravascular image and / or the extraluminal image. For example, the computing device 112 may be configured to receive and store extraluminal image data, such as image data generated by the external imaging device 120 and acquired by the frame grabber. The computing device 112 may be configured to receive and store intravascular image data, such as image data generated by the probe 104 and acquired by the frame grabber. In some examples, the computing device 112 may access the registration module 121 to register the vascular data with the luminal image. The luminal image may be an extraluminal image, such as an angiogram, X-ray, etc. The registration module 121 may register the intravascular data, such as the intravascular image, plaque burden, EEL measurement, luminal diameter measurement, pressure reading, virtual flow reserve ("VFR"), fractional flow reserve ("FFR"), resting full cycle ratio ("RFR"), flow velocity, etc., with the extraluminal image. In some examples, the registration module 121 can register the intravascular data with an intraluminal image (eg, an intraluminal image captured by an OCT probe, an IVUS probe, a micro-OCT probe, or a link).

[0063] In one example, the registration module 121 can register the intraluminal data captured during the pullback with one or more extraluminal images. For example, the extraluminal image frame can be preprocessed. Various matrices such as convolution matrices, Hessian matrices, etc. can be applied to each pixel to change the intensity, remove or otherwise modify a given angiography image frame. As described herein, the preprocessing stage can enhance, modify and / or remove features of the extraluminal image to improve the accuracy, processing speed, success rate and other performance of the subsequent processing stage. The centerline of the blood vessel can be determined and / or calculated. In some examples, the centerline of the blood vessel can be superimposed or otherwise displayed relative to the preprocessed extraluminal image. According to some examples, the centerline of the blood vessel can represent the trajectory of the collection probe 104 through the blood vessel during the pullback process. In some examples, the centerline can be referred to as a trace. Additionally, or as another option, a marker band or a radiopaque marker can be detected in the extraluminal image frame. According to some examples, the extraluminal image frame and the data received by the collection probe 104 can be registered based on the determined marker band position.

[0064] According to some examples, these modules may additionally or alternatively include video processing software modules, preprocessing software modules, image file size reduction software modules, catheter removal software modules, shadow removal software modules, vascular enhancement software modules, speckle enhancement software modules, Laplacian of Gaussian filter or transform software modules, guidewire detection software modules, anatomical feature detection software modules, fixed marker detection software modules, background subtraction modules, Frangi vascular software modules, image intensity sampling modules, moving marker software detection modules, iterative centerline test software modules, background subtraction software modules, morphological closure operation software modules, feature tracking software modules, catheter detection software modules, bottom hat filter software modules, path detection software modules, Dijkstra software modules, Viterbi software modules, fast marching method-based software modules, vascular centerline generation software modules, vascular centerline tracking module software modules, Hesse software modules, intensity sampling software modules, image intensity overlay software modules and other suitable software modules described herein. According to some examples, modules may include software such as pre-processing software, transforms, matrices, and other software-based components for processing image data or responding to patient triggers (to facilitate registration of different types of image data through other software-based components or otherwise perform annotation of image data to generate ground truth values), as well as other software, modules, and functions suitable for implementing various embodiments of the present disclosure. The modules may include: lumen detection (using scan-line-based or image-based methods); stent detection (using scan-line-based or image-based methods); indicator generation; attachment strip generation (for stent planning); guidewire shadow indicators (to prevent confusion with foreign matter); side branches and missing data; and others.

[0065] In some examples, the module may be configured to process vascular data acquired by the probe 104 and / or external imaging device 120 using machine learning algorithms, artificial intelligence, and the like.

[0066] According to some examples, the computing device 112 may include a module for classifying different features within a blood vessel, such as a classification module. The module for classifying different features can be a machine learning system ("MLS"), which can be implemented by training a classifier to segment or manipulate an image to constitute tissues, tissue types, and other areas of interest that are detected and characterized based on type or another parameter. In one example, the lumen, intima, media, and plaque are detected and identified as having boundaries corresponding to these different tissues. Training a given MLS / neural network includes teaching the network using known inputs and known outputs.

[0067] The training data may include, for example, real data from the field, as well as image data elements (which may include various image formats, such as raw grayscale images) provided as input to the convolutional neural network ("CNN") of the MLS. The MLS is run in periods of full cycles until the training error is reduced, minimized, or otherwise below a threshold. In one embodiment, the period ranges from about 100 to about 1000 full cycles.

[0068] After a given MLS / CNN has been trained, it can then process raw images and output image segmentations including classified or characterized tissue. In one example, a pulled-back polar image from an intravascular imaging probe is run through the trained MLS to generate a classified image. According to some examples, various pre-processing steps / operations can be performed to further improve training and / or processing time.

[0069] The preprocessing step may include lumen detection using an MLS that has been previously trained using a training set with annotated lumen regions or segments. Preprocessing techniques may also be selected to speed up network training and / or prediction speed of the trained network during back propagation. Thus, the preprocessing step may also include: image data flattening, a periodic rotation process, a circular rotation process (wherein part of the image data is excluded, such as depth data below the noise floor, data removal may be performed in an alternating manner so that every other scan line of the image is removed or every other column is removed, pixels may be filtered to remove noise and increase regional uniformity) and other preprocessing steps.

[0070] In one example, the preprocessing step may include a normalization step. The normalization step may include normalizing the intensities of one or more or all of the image data, ground truth annotations, masks, frames, scan lines, neural network outputs, and other intensity-based data so that the intensities are normalized within a certain range (e.g., from about 0 to about 1, or another available range). In some examples, MLS training and prediction are performed on polar coordinate images, and after classification occurs, the polar coordinate view is converted to a Cartesian view, and the annotations generated by the trained MLS are displayed on the image using color coding or other suitable notation or visualization.

[0071] A given cost function can provide a measure for evaluating the output of a machine learning system by comparing the actual input / training set to the expected output when operating on patient data. The goodness of fit between the training data and the output data can be measured by a cost function. The output of the cost function can be a value corresponding to an error measure. This output is a comparative measure (e.g., a difference or gap) to summarize the success of the machine learning system or neural network or its other operational components in accurately predicting given the predictive results and the actual values ​​used for system training. If the output of the cost function is zero, the system will work perfectly and effectively. In this way, iterative changes to the system can be used to reduce the cost or error function of the system and improve its prediction accuracy.

[0072] In addition, a pixel-based cost function is defined to measure the gap between the predicted and actual values ​​or another suitable measure or score. In one embodiment, back propagation updates each weight in the network-based value derived from the cost function. In one embodiment, the partial derivative of the cost function is used to update the weights during the back propagation process. This weight update process has the benefit that the actual predictive results are closer to the actual values. This has the benefit of reducing or minimizing the error for each output neuron / node of the neural network.

[0073] In some examples, each annotated mask region corresponding to a series or group of pixels defines a ground truth mask for training one or more neural networks disclosed herein. Once the neural network is trained, a predictive or detection mask is generated that includes a series of pixels that correspond to user data regions and identifiers of features or categories of the regions, such as whether they are luminal, calcium, EEL, or other categories or features disclosed herein. In one example, predictive results are generated based on each category, and then all predictive results for a given image data input (e.g., an input frame of OCT, IVUS, or other image data) are compared at a pixel level to generate a final predictive result for all categories. In one example, the predictive results are displayed as an output image mask with regions corresponding to specific categories indicated by markers (e.g., colors and one or more legends summarizing which marker reflects which category).

[0074] According to some examples, the classification module can classify the type of plaque present. For example, the classification module can classify plaque according to calcification. In addition, if the presence of plaque and other detectable features in a given section of the artery can indicate the presence of narrowing (e.g., due to stenosis), another feature of the present disclosure can quickly and automatically obtain one or more scores associated with the given plaque or stenosis to facilitate decision-making by the end user. For example, a given score determined using image data and machine learning-based analysis thereof can help determine whether immediate action is not recommended, whether a stent should be placed for the stenosis, or whether cardiovascular surgery or other surgery (e.g., bypass surgery) is necessary.

[0075] For healthy patients, arteries have layers arranged in a consistent structure, including the intima, the media, and the adventitia. As a result of the atherosclerotic process, the intima becomes pathologically thickened and may contain plaques composed of different types of tissues (including fibers, proteoglycans, lipids and calcium, as well as macrophages and other inflammatory cells). When imaged using various imaging systems, these tissue types have different characteristics, which can be used to establish a series of training data for one or more machine learning systems of the present disclosure. It is believed that the most important plaque in pathology is the so-called vulnerable plaque, which is composed of a fibrous cap with an underlying lipid pool. Different atherosclerotic plaques have different geometric shapes. For example, foam cells often form band-like features on the shoulders of large lipid pools; the media presents a ring around the blood vessel, and so on. Shape information is currently used for qualitative evaluation of OCT images. In one example, a neural network is trained to identify a fibrous cap and / or a fibrous cap with an underlying lipid pool. In various embodiments, reference to calcium herein also includes, but is not limited to: calcified plaques and other calcium-containing tissues.

[0076] While the patient is still catheterized and preparing to receive a stent or other treatment option, the imaging procedure can be quickly performed on the patient and an arterial image can be obtained and then processed using a machine learning system, resulting in significant time savings and improved patient outcomes. The classification module can be similar to the classification method described in U.S. Patent No. 11,250,294, entitled "System and Method for Classification of Arterial Image Regions and Features Thereof," the contents of which are incorporated herein by reference in their entirety.

[0077] The subsystem 108 may include a display 118 for outputting content to a user. The display 118 may be integrated with the computing device 112 or may be a separate unit electronically connected to the computing device 112. The display 118 may output intravascular data related to one or more features detected in the vessel and / or obtained during aspiration. For example, the output may include, but is not limited to, cross-sectional scan data, longitudinal scans, three-dimensional representations generated based on intraluminal and / or extraluminal images, diameter maps, image masks, lumen boundaries, plaque size, plaque perimeter, visual indicia of plaque location, visual indicia of risk of stent expansion, flow rates, suggested treatment zones, or the like. The display 118 may identify features using text, arrows, colors, codes, highlights, contours, or other suitable human or machine readable indicia.

[0078] According to some examples, display 118 may include a graphical user interface ("GUI"). Display 118 may be a touch screen display, wherein a user may provide input to navigate images, enter information, make selections, and / or interact with inputs, etc. In some examples, display 118 and / or computing device 112 may include input devices, such as a touch pad, a mouse, a keyboard, etc., to allow a user to navigate images, enter information, make selections, and / or interact with inputs, etc. Display 118 by itself or in combination with computing device 112 may switch between one or more viewing modes in response to user input. For example, a user may switch between different intravascular data, images, etc. recorded during each pullback.

[0079] In some examples, display 118 by itself or in combination with computing device 112 may present one or more menus as output to the physician, in response to which the physician may provide input by selecting an item from the one or more menus. For example, a menu may allow a user to display or hide various features. As another example, there may be a menu for selecting which vascular features to display.

[0080] The output may include image data, such as a cross-sectional image obtained by the probe 104 during pullback and / or an external image obtained by the external imaging device 120. In some examples, the output may include a longitudinal representation of the vessel, a graphical representation of the vessel data, a three-dimensional representation of the vessel and / or vessel data, etc. The representation of the vessel may provide various viewing angles and cross-sectional views. In some examples, the EEL location, its diameter, or other EEL-based parameters may be output for display with respect to angle measurements, detected calcium arcs, plaque burden, etc.

[0081] In some examples, one or more visual representations of the image may include an indication of lesion location, lesion severity, lesion length, etc. Additionally, or alternatively, the indication of the lesion may be color coded, with each color representing severity, length, or other measurement associated with the lesion.

[0082] In some examples, the output may include candidate treatment zones. The candidate treatment zones may be, for example, candidate stent landing zones. For example, the output may include indications corresponding to candidate proximal landing zones for the stent and candidate distal landing zones for the stent. The candidate treatment zones may be determined based on determined plaque load, lesion location, lesion length, etc. The indications may be provided on any vessel representation, such as a three-dimensional representation, a longitudinal representation, a graphical representation, image data (e.g., an external image), etc.

[0083] According to some examples, the display 118 and / or the computing device 112 may be configured to receive one or more inputs corresponding to selections on one or more representations. For example, an input corresponding to a selection of an image frame on the longitudinal representation may be received. In response, other representations for providing output may be updated to display corresponding indications or image frames. For example, the extraluminal image may be updated to have an indication along the vessel corresponding to the location of the image frame selected in the longitudinal representation, a circumferential indication may be provided on the three-dimensional representation corresponding to the location of the image frame selected in the longitudinal representation, a cross-sectional image frame may be updated to correspond to the image frame selected in the longitudinal representation, and so on. In some examples, the vessel data associated with the selected location may be updated and provided for display.

[0084] Figure 2A is Figure 1 200A is an exemplary image frame obtained during the pullback of the probe 104. For example, multiple image frames can be obtained during the pullback of the probe 104. The image frame 200A can be an OCT image frame, an IVUS image frame, a NIRS image frame, an OFDI image frame, etc.

[0085] Image frame 200A may be processed using one or more modules 117 to determine vascular data. For example, the vascular data may include vascular measurements, such as EEL measurements, lumen measurements, plaque load, calcium load, intima thickness, media thickness, etc. For example, EEL detection module 122 may automatically determine an EEL value for an image frame including image frame 200A. Lumen detection module 123 may automatically determine a lumen area for an image frame including image frame 200A. Lesion detection module 124 may automatically determine a plaque load for an image frame including image frame 200A. In some examples, the plaque load for a given image frame may be determined based on the determined EEL value and lumen area for the given image frame.

[0086] Figure 2B is an exemplary annotated image frame. Image frame 200B may be similar to image frame 200A in that image frame 200B may also be obtained during pullback of probe 104. Therefore, image frame 200B may be an OCT image frame, an IVUS image frame, a NIRS image frame, an OFDI image frame, and the like.

[0087] Image frame 200B may be processed similarly to image frame 200A to determine vessel measurements. In some examples, an image frame (e.g., image frame 200B) may be processed to identify different features in image frame 200B. For example, image frame 200B may be processed to identify probe 104, vessel wall W, adventitia AD, lumen L, etc. In some examples, image frame 200B may be processed to identify EEL, plaque, calcium plaque, calcium angle, etc. According to some examples, output 118 may include an indication of the identified vessel wall W, adventitia AD, lumen L, calcium angle, plaque load, etc.

[0088] The lumen L may be identified by the lumen detection module 123. In some examples, the lumen L may be automatically identified and used to determine the lumen area of ​​the blood vessel in a given image frame. The lumen area may be used to determine the plaque load in the image frame. For example, the EEL detection module 122 may determine an EEL value for a given frame, and the plaque load of the frame may be determined as follows: plaque load = 1-(lumen area / EEL value). In the formula, the EEL value may be, for example, an EEL area or an EEL diameter, etc.

[0089] According to some examples, an EEL value may not be automatically determined for a frame, such as when plaque load reduces visibility of the EEL. In another example, the plaque load may be greater than a threshold. For example, when the plaque load is greater than a threshold, the plaque load may be considered unhealthy. In some examples, such as when the EEL is not visible enough to be measured, the EEL value may be measured incorrectly. In examples where the EEL value cannot be determined or the plaque load is greater than a threshold, the EEL value may be predicted to determine the plaque load for a given frame.

[0090] Figure 2C An exemplary longitudinal representation of a blood vessel is shown. The longitudinal representation 200C may be generated based on image frames acquired by the probe 104 during pullback, for example, by Figure 1The longitudinal representation 200C may include an indication "P" corresponding to the proximal end of the pullback and an indication "D" corresponding to the distal end of the pullback. According to some examples, the longitudinal representation 200C may include an indication corresponding to the location of a side branch "SB" along the vessel. The longitudinal representation 200C may be color-coded, shaded, or include some type of indication between different tissue types within the vessel. For example, areas of calcium "Ca" may be coded with a first color, while areas without calcium may be coded with another color.

[0091] The longitudinal representation 200C may include an indication of an area or image frame, wherein the image frame contains an EEL value. For example, the longitudinal representation 200C may include a dotted line along the length of the representation, indicating a frame or area in which the EEL value is measured or detected. According to some examples, the longitudinal representation 200C may include an area where the EEL value is not measured and / or the plaque load is above a threshold. If the visibility of the EEL is insufficient for measurement, the EEL value may not be measured or the measurement may be incorrect. For example, the plaque load of the areas "ME1" and "ME2" may be above the threshold. There are no dotted lines in the areas ME1 and ME2, which indicates that the plaques in these areas ME1 and ME2 may have overgrown so that the EEL is not detected and / or the detected level cannot meet the threshold describing the EEL value. For example, the EEL value may be the EEL area and / or the EEL diameter. In some examples, the absence of dotted lines representing the EEL area may indicate that the EEL values ​​of these image frames cannot be determined.

[0092] According to some examples, a region of interest may be identified. The region of interest 230, 232, 234 may be a vessel region between side branches SB. The region of interest 230, 232, 234 may include sub-regions 236, 238, 240 where the EEL value is not determined and / or the EEL value is below a threshold. In these regions 236, 238, 240, the EEL value may be predicted.

[0093] According to some examples, the EEL values ​​detected or determined in the regions of interest 230, 232, 234 may be used to predict the EEL values ​​in the respective sub-regions 236, 238, 240. For clarity, the description herein will be directed to the region of interest 232 and the sub-region 238. However, the methods described herein may also be applied to the regions of interest 230, 234 and the respective sub-regions 236, 240. Therefore, the use of the region of interest 232 and the sub-region 238 is only an example and is not limiting.

[0094] The region of interest 232 may be located between the two side branches SB. One or more modules 117 may be used to process image frames within the region of interest 232 obtained during the pullback. For example, the EEL value, lumen area value, and plaque load may be automatically determined. As described above, the EEL value may not be determined within the sub-region 238, and / or the plaque load reduces the visibility of the EEL, so that the EEL value is not suitable for use in determining the plaque load. In this case, the EEL value of the image frame in the sub-region 238 can be predicted.

[0095] In some examples, the predicted EEL value may be determined based on the EEL values ​​determined in the remaining image frames within region 232. For example, region 232 may include multiple image frames. A first subset of these image frames may have a plaque load less than a threshold plaque load. The EEL value may be determined for at least the first subset of image frames. A second subset of image frames, such as image frames within subregion 238, has a plaque load higher than the threshold plaque load. In some examples, the EEL values ​​of the frames of the second subset may be measured incorrectly due to plaque load or EEL values ​​that cannot be detected due to plaque load. In an example where the image frames of the first subset include a threshold number of frames with a plaque load lower than the threshold plaque load, the EEL values ​​of these threshold number of frames may be determined. The representative EEL value may be determined based on the EEL values ​​of the image frames of the first subset with a plaque load lower than the threshold plaque load. For example, the threshold plaque load may be between about 0-50%. For example, the threshold plaque load may be about 40%, 45%, etc. In some examples, the threshold plaque load may be greater than or less than about 0-50%. In another example, the threshold plaque burden can be a range, be patient-specific, be determined by a physician, and so on.

[0096] According to some examples, the representative EEL values ​​of the image frames in the first subset of image frames may be used as the EEL values ​​of those image frames in the first subset of image frames that have EEL values ​​that are erroneously measured. For example, the EEL values ​​of some image frames in the first set of image frames may be greater than the standard deviation of the representative EEL value, or outside a predetermined range of the representative EEL value, etc. In such examples, for example, when the EEL value is erroneously measured, the representative EEL value of the first set of frames may be used as the EEL value of the erroneously measured frame.

[0097] The threshold number of frames may be determined based on the number of frames for the region of interest. For example, for a larger region of interest, the threshold number of frames may be greater than the threshold number of frames for a smaller region of interest. In some examples, regardless of the size of the region of interest, the threshold number of frames may be three image frames.

[0098] The predicted EEL value and lumen area can be used to determine the plaque load for frames where the EEL value is not automatically determined, the plaque load is greater than a threshold plaque load, the EEL value is erroneously measured, etc. In such an example, the plaque load for a given frame can be determined as 1-(lumen area / predicted EEL value). In this formula, the predicted EEL value can be the predicted EEL area and / or the predicted EEL diameter.

[0099] According to some examples, the predicted EEL value can be determined as a function of the intimal thickness and the media thickness. The intimal thickness can be, for example, the minimum intimal thickness, and the media thickness can be, for example, the minimum media thickness. The minimum intimal thickness and the minimum media thickness can be determined based on typical blood vessels. For example, a typical blood vessel with a plaque load value below a threshold value can be used to determine the average value of the minimum intimal thickness and the minimum media thickness. In one example, the combined minimum intimal thickness and the minimum media thickness can be 0.237 mm. In some examples, the respective minimum intimal thickness and the minimum media thickness can be 0.198 mm. The total combined thickness of the minimum intimal and media of 0.237 mm and the respective minimum intimal and media thickness of 0.198 mm are just some examples and are not limiting. For example, the combined thickness can be greater than or less than about 0.237 mm, and the respective thickness can be greater than or less than about 0.198 mm. In some examples, the respective minimum intimal thickness and the minimum media thickness can be the same value or different values. According to some examples, the minimum intima thickness and the minimum media thickness can be based on histological observations of the blood vessels. For example, based on the histological observations of the blood vessels, the intima thickness and the media thickness (with a standard deviation) can be determined. The minimum intima thickness and the minimum media thickness can be determined based on the low end of the standard deviation. For example, if the total thickness of the intima and the media is determined to be 427μm±190μm, the minimum total thickness of the intima and the media is 237μm. The total thickness of the intima and the media may change based on factors such as the size of the data set study, the patients involved in the study, etc. Therefore, although a minimum total combined thickness of the intima and the media of 0.237mm is used, the minimum total combined thickness of the intima and the media can be any value determined by histological observations.

[0100] The predicted EEL value can be further determined as a function of the HK model, where the HK model predicts an expected lumen diameter. One assumption of the HK model is that the size of the vessel within the region of interest 232 (e.g., between side branches) is substantially constant. For example, the HK model predicts the lumen diameter based on the assumption that the diameter, circumference, and / or area of ​​the vessel is substantially constant along the region of interest. According to some examples, if the vessel is healthy, the HK model can provide a prediction of the lumen diameter of the vessel in a given image frame. A healthy vessel can be a vessel with a plaque load below a threshold plaque load, a vessel with a lumen diameter above a threshold diameter, and so on.

[0101] According to some examples, the predicted EEL may be determined using the following formula:

[0102] Predicted EEL value = (expected lumen diameter) + 2 × (minimum intima thickness + minimum media thickness)

[0103] In the formula, the predicted EEL value may be a predicted EEL area and / or a predicted EEL diameter. For example, the expected lumen diameter may be a lumen diameter determined using the HK model.

[0104] Since the EEL is outside the lumen, additional distance can be added in the form of minimum intima thickness and minimum media thickness to predict the EEL value. For example, the minimum intima thickness and minimum media thickness can compensate for the additional width between the lumen and the EEL. The minimum intima thickness and minimum media thickness can be added and multiplied by 2 to compensate for the additional width on both sides of the vessel. The predicted EEL value can be determined by adding 2 times the minimum intima thickness and minimum media thickness to the expected lumen diameter predicted by the HK model.

[0105] The predicted EEL value and lumen area can be used to determine plaque burden for frames where the EEL value was not automatically determined and / or was incorrectly determined. In this example, the plaque burden for a given frame can be determined as 1-(lumen area / predicted EEL value).

[0106] Figure 3 Shown in Figure 1 1. An exemplary user interface for use on the display 118 of the probe 104. The user interface 300 may include an upper portion "UP" of the interface and a lower portion "LP" of the interface. The upper portion UP may include image frames, such as a cross-sectional image of a vessel acquired during pullback, and the lower LP may include a longitudinal representation 350 of the vessel. The longitudinal representation 350 may be generated using image frames captured by the probe 104 during the pullback process.

[0107] In the upper part UP of the interface 300, there can be three image frames corresponding to: an image frame or a specific view or slice of the blood vessel at the proximal reference 151, a selected frame 153 corresponding to the image frame with a diamond 165 in the longitudinal representation 350, and a view at the distal reference frame 155.

[0108] The proximal and distal reference frames 151, 155 show the lumen of the blood vessel in the image frame (one or more dashed lines pass through the lumen L). The values ​​from the measurements made on these lines can be applied to the measured or detected EEL positions, points, or pixels. According to some examples, these values ​​can be used to generate measured EEL values, such as EEL diameter or average EEL diameter. Some exemplary EEL diameter measurements are shown as approximately 3.8 mm (proximal) and approximately 3.4 mm (distal). According to some examples, the measured EEL values ​​can be used to predict the EEL values ​​for one or more frames where the EEL values ​​cannot be determined.

[0109] The lower portion LP of the interface 300 may illustrate a combination of calcium "Ca" and EEL as a longitudinal representation 350. The longitudinal representation 350 may be similar to the longitudinal representation 200C in that the longitudinal representation 350 may include an indication of one or more side branches SB, EEL values, calcium regions, etc. According to some examples, the interface 300 may include an indication of one or more regions of interest 332, such as a region of a blood vessel located between two side branches. In some examples, the interface 300 may include an indication of a sub-region 338, where the EEL values ​​of image frames within the sub-region cannot be determined. When there are a threshold number of image frames (these image frames have a plaque load less than a threshold plaque load and / or have a visible EEL arc greater than or equal to an arc threshold), the EEL values ​​of the image frames within the sub-region 338 may be predicted as the median of the EEL values ​​within the region 332. For example, the arc threshold may be at least 180 degrees or approximately 180 degrees. For example, the threshold plaque load may be a healthy plaque load. In some examples, the healthy plaque load may correspond to a plaque load between 0-50%. In some examples, a healthy plaque load may correspond to a plaque load between 35-50%. In other examples, a healthy plaque load may correspond to a plaque load range greater than 50%. Thus, plaque loads between 0-50% and 35-50% are merely examples and are not intended to be limiting.

[0110] In some examples, the EEL values ​​of the image frames within the sub-region 338 may be predicted as a function of the HK model, the minimum intimal thickness, and the minimum media thickness. For example, when there are not enough image frames with a plaque load below a threshold plaque load, the EEL values ​​of the image frames may be predicted as a function of the HK model, the minimum intimal thickness, and the minimum media thickness.

[0111] According to some examples, the predicted EEL value (determined as a function of the HK model) may be compared with the EEL value of the proximal segment and / or the distal segment of the blood vessel. The proximal segment and / or the distal segment of the blood vessel may be a segment of the blood vessel adjacent to the region of interest, or closer and / or farther than the region of interest. For example, there may be a distance between the proximal segment and the region of interest and / or between the distal segment and the region of interest. In some examples, the EEL value of the proximal segment and / or the distal segment of the blood vessel may be a representative EEL value of the proximal and / or distal segment of the blood vessel. If the predicted EEL value is less than the representative EEL value of the distal segment, the representative EEL value of the distal segment may be used to determine the plaque load of the frame within the region of interest. Since the HK model assumes that the blood vessel has a natural taper from the proximal blood vessel segment to the distal blood vessel segment, the representative EEL value of the distal segment may be used when the predicted EEL value is less than the representative EEL value of the distal segment. If the predicted EEL value is greater than the representative EEL value of the proximal segment, the representative EEL value of the proximal segment can be used to determine the plaque burden of the frame within the region of interest. Since the HK model assumes that the blood vessel has a natural taper from the proximal vessel segment to the distal vessel segment, the representative EEL value of the proximal segment can be used when the predicted EEL value is greater than the representative EEL value of the proximal segment.

[0112] Figure 4 Shown in Figure 1 1. Another exemplary user interface for use on display 118 of FIG. User interface 400 may be similar to user interface 300, with an upper portion "UP" and a lower portion "LP". The difference between interface 300 and interface 400 may be the representation output for display. For example, the longitudinal representation 350 provided for display in interface 300 may be a lumen outline, while the longitudinal representation 450 provided for display in interface 400 may be a transverse representation of the vessel, such as an L-view representation.

[0113] As shown, the upper portion UP of the interface 400 includes three frames, with the middle one being a user-selectable frame. Upon receiving input corresponding to the selection and / or movement of the marker "US", the user-selected frame 153 may be updated. In addition, the vascular data associated with the user-selected frame 153 may also be updated to correspond to the selected frame. This allows for consideration of different EELs and lumen diameters for the proximal and distal references 151, 155. A bookmark BKM is also shown, which the user may set using the GUI to quickly move between frames. Another marker shows the frame with the minimum lumen diameter MLD, and in other cases, the MLA or minimum lumen area may also be displayed.

[0114] Figure 5An exemplary longitudinal representation of a blood vessel that can be generated using computing device 112 is shown. According to some examples, longitudinal representation 500 and / or data used to generate longitudinal representation 500 can be used to automatically identify lesions. For example, lesions can be identified based on the plaque load of each frame. Plaque load can be determined as a function of the EEL value and the lumen area of ​​a given frame. In some examples, a determined EEL value can be used, and in some examples, a predicted EEL value can be used to determine the plaque load. Plaque load can be determined as 1-(lumen area / EEL value), where the EEL value is a determined EEL value or a predicted EEL value of the image frame. Frames with plaque loads above a threshold plaque load can be marked or indicated as part of a lesion. For example, the threshold plaque load can be a plaque load of 70%. In some examples, the threshold plaque load can be a plaque load of, for example, 25%, 50%, etc. The threshold plaque load may vary from patient to patient. In some examples, the threshold plaque load can be adjusted by a physician to correspond to any value or percentage of plaque load. Therefore, the 70% example is just an example and is not limiting.

[0115] As shown in the vertical representation 500, two different lesions L1, L2 may be identified. According to some examples, the lesions L1, L2 may be identified as a single lesion LC based on the proximity of each lesion L1, L2 to each other.

[0116] In order to identify the lesion L1, an image frame M1 having a plaque load greater than a threshold plaque load can be identified. According to some examples, an image frame with a maximum plaque load can be identified. In some examples, an image frame having a plaque load greater than a disease threshold can be identified. The plaque load of each frame in the proximal and distal directions of the identified image frames can be determined and compared with the treatment zone threshold until the proximal image frame P1 and the distal image frame D1 are identified as having a plaque load less than the treatment zone threshold. For example, the treatment zone threshold can be a plaque load of approximately 0-50%. The treatment zone end frame can also be defined as a frame P1, D1 where the plaque load is less than the treatment zone threshold and / or the visible arc of the EEL is greater than or equal to the arc threshold. For example, the arc threshold can be at least or approximately 180 degrees. The lesion L1 can be identified as extending between the identified proximal and distal image frames P1, D1.

[0117] This process may be repeated until all lesions, such as lesion L2, are identified for the pullback. For example, an image frame with the next highest plaque load may be identified from the remaining image frames (e.g., image frames other than the image frame identified as lesion L1). For example, the next highest plaque load may be M2. According to some examples, an image frame having a plaque load greater than a disease threshold may be identified from the remaining image frames. Similar to identifying lesion L1, identifying lesion L2 may be performed by comparing the plaque loads of the proximal and distal image frames until a proximal image frame P2 and a distal image frame D2 are identified whose plaque load is less than the treatment zone threshold and / or whose visible EEL arc is greater than or equal to an arc threshold. For example, the arc threshold may be at least or approximately 180 degrees. Although only two lesions L1, L2 are identified in the longitudinal representation 500, more or fewer lesions may be determined for a given pullback.

[0118] According to some examples, after identifying one or more individual lesions L1, L2, these lesions may be merged into a single lesion LC. For example, when the distance between the individual lesions is less than a threshold distance, one or more individual lesions may be merged into a single lesion. The distance between the lesions may be measured based on the number of image frames between the distal end of the first lesion and the proximal end of the other lesion. In some examples, the distance between the lesions may be measured in millimeters or any other form of distance measurement. The threshold distance may be patient-specific, updated by a doctor, preset, and the like. In some examples, the threshold distance between the lesions may be between approximately 5-10 mm. According to some examples, the threshold distance may be between approximately 8-10 mm. In other examples, the threshold distance may be less than approximately 5 mm or greater than approximately 10 mm. In some examples, the threshold distance may be patient-specific, doctor-preferred, and the like. Therefore, the threshold distance between approximately 5-10 mm is just an example and is not limiting.

[0119] by Figure 5 Taking the lesions L1 and L2 in the image as an example, the distance between the distal image frame D1 of the lesion L1 and the proximal image frame P2 of the lesion L2 can be determined. If the distance between the distal image frame D1 of the lesion L1 and the proximal image frame P2 of the lesion L2 is less than the threshold distance, the lesions L1 and L2 can be merged. As shown in the figure, the distance between the lesions L1 and L2 is less than the threshold. Therefore, the lesions L1 and L2 are merged into a single lesion LC.

[0120] By merging lesions (the gap or distance between them is less than a threshold distance), the treatment zone end frame can be prevented from being placed in the gap between lesions. For example, by merging separate lesions into a single combined lesion, the system can automatically identify that the treatment zone end frame is located at the proximal and distal positions of the combined lesion, rather than in the gap between two lesions.

[0121] Figure 6 Another exemplary user interface that can be output on the display 118 is shown. The user interface 600 shows a candidate treatment zone end frame "TZ". The candidate treatment zone end frame TZ can be located at the proximal and distal positions of the identified lesion LC. For example, the candidate treatment zone end frame TZ for the stent can be determined based on the comparison of the plaque load of the image frames proximal and distal to the lesion LC with the treatment zone threshold. For example, the treatment zone threshold can be a plaque load of approximately 0-50%. When the plaque load of the image frames proximal and distal to the lesion LC is identified to be substantially consistent with or less than the treatment zone threshold and / or its visible EEL arc is greater than or equal to the arc threshold, the image frame can be determined as a candidate treatment zone end frame for the stent. For example, the arc threshold can be at least or approximately 180 degrees. The candidate treatment zone can be provided as an output on the longitudinal display 650 or any other registered representation of the blood vessel. For example, an indication of the candidate treatment zone end frame TZ can be provided as an output on a registered external image frame 660 (e.g., an angiography image frame).

[0122] Interface 600 may include a cross-sectional representation of a vessel, such as a cross-sectional image frame of the vessel. Cross-sectional image 662 may include an indication identifying the EEL location (e.g., a dashed line) and an indication identifying the lumen "L" (e.g., a solid line). Corresponding vessel data, such as an EEL value and a lumen diameter value, may be provided for output with image frame 662. For example, cross-sectional image 662 may correspond to image frame 662 selected on longitudinal representation 650. As shown, selected image frame 662 has an EEL diameter of 2.61 mm and a lumen diameter of 2.50 mm. According to some examples, interface 600 may include an indication of the EEL curvature. For example, interface 600 may output an indication of the EEL curvature on an intravascular image, a longitudinal representation, etc. In some examples, interface 600 may provide the output of the EEL curvature as a value, such as a percentage.

[0123] These EEL values ​​and lumen values ​​can be used to help select stents or other therapeutic devices. For example, based on the EEL values ​​and lumen values, the physician can then evaluate the candidate treatment zones TZ automatically suggested by the system. According to some examples, the longitudinal representation is registered with the extraluminal image so that the candidate treatment zone is displayed on both the longitudinal representation and the extraluminal image, which helps to evaluate and assess the candidate treatment zone.

[0124] According to some examples, the cross-sectional representation may include an indication of plaque load, calcium load, etc. For example, the cross-sectional representation may include an arc identifying plaque load, calcium load, etc. In some examples, the indication may be color-coded to identify different categories identified in the cross-sectional representation. For example, the types of categories may include intima, media, adventitia, lumen, external elastic layer (EEL), internal elastic layer (IEL), plaque, calcium, calcium plaque, side branch, guidewire, stent tendon, stent, imprisoned stent, bioresorbable vascular scaffold (BVS), drug eluting stent (DES), fibrous, halo artifact, pressure wire, lipid, atherosclerotic plaque, stenosis, calcium, calcified plaque, calcium-containing tissue, lesion, fat, poorly set stent, under-expanded stent, over-expanded stent, radio-opaque markers, branching angles of the arterial tree, probe calibration element, doped membrane, light scattering particles, sheath, doped sheath, fiducial alignment point, diameter measurement, radial measurement, guide catheter, shadow area, guidewire segment, length or thickness.

[0125] Additionally, or alternatively, the indications may be color coded to correspond to severity of plaque, lesions, calcium accumulation, etc. In some examples, the color coding used as output on the cross-sectional representation may also be used as output on the longitudinal representation and / or extraluminal images.

[0126] According to some examples, interface 600 may include a three-dimensional ("3D") representation of a vessel (including a region of interest). The three-dimensional representation may be in addition to or in lieu of one of the other various representations of the vessel. For example, interface 600 may include one or more of an extraluminal image, a cross-sectional image frame, a longitudinal representation, a three-dimensional representation, and the like. In some examples, the longitudinal representation may be symmetrical about a longitudinal axis of the vessel and / or the representation. In another example, the longitudinal representation may be a carpet view of the vessel. Each representation of the vessel (e.g., an extraluminal image, a cross-sectional image, a three-dimensional representation, a longitudinal representation, and the like) may be configured to be color-coded, include annotations and / or indications, and the like.

[0127] Figure 7 Another exemplary user interface that can be provided as an output on the display 118 is shown. The user interface 700 can be used to support stent planning through a virtual stent. In some examples, the virtual stent can correspond to a treatment zone end frame TZ that is automatically identified based on the detected lesions. A description or indication of the virtual stent can be provided on one or more representations of the blood vessel. For example, similar to the interface 600, the interface 700 can include one or more representations of the blood vessel, including an extraluminal image 770, a cross-sectional image 772, and a longitudinal representation 750. An indication of the virtual stent can be provided as an output on the extraluminal image 770 and / or the longitudinal representation 750.

[0128] According to some examples, interface 700 can output vascular data, such as EEL value, lumen value, VFR value, MLA value, diameter stenosis percentage, etc. Interface 700 can include pre-stent value and predicted post-stent value. For example, the pre-stent VFR value can be 0.75, and the predicted post-stent VFR value can be 0.90. Similarly, although not shown, interface 700 can output pre-stent EEL value, lumen diameter value, etc., and corresponding predicted post-stent value. The predicted value can be determined using machine learning or a neural network (trained for predictive analysis).

[0129] Figure 8 A flow chart showing an exemplary process for automatically determining plaque load for frames within a region of interest, which may be implemented using computing device 112. The following operations do not have to be performed in the exact order described below. Instead, various operations may be processed in a different order or simultaneously, and operations may be added or omitted.

[0130] In block 810, vascular data including intravascular imaging data may be received. For example, the intravascular imaging data may be one or more image frames obtained by the probe during pullback through the vessel. The one or more image frames may be OCT image frames, IVUS image frames, etc. In some examples, the vascular data may be values ​​or measurements associated with the vessel in a given image frame. For example, the vascular data may be an EEL value (such as an EEL diameter), a lumen value (such as a lumen area or diameter), etc. In some examples, the vascular data may include a pressure value, a VFR value, an IMR value, etc.

[0131] In block 820, a region of interest of the vessel may be identified based on the vessel data. For example, the vessel data may include an indication of one or more side branches. The region of interest may be defined as a region between a first side branch and a second side branch.

[0132] In block 830, a first subset of frames in the region of interest may be identified whose plaque load is below a threshold plaque load. For example, the threshold plaque load may be between 0-45%. The first subset of frames may include a threshold number of frames. The threshold number of frames may be at least three frames.

[0133] In block 840, an EEL value may be determined for the first subset of frames. According to some examples, an EEL value may be determined for each frame in the first subset of frames. In another example, an EEL value may be determined for a threshold number of frames in the first subset of frames. The EEL values ​​for the first subset of frames may be automatically determined based on the vascular data. For example, the EEL value may be an EEL diameter and / or an EEL area.

[0134] In block 850, a representative EEL value of the region of interest may be determined based on the EEL values ​​of the frames of the first subset. For example, the representative EEL value of the region of interest may be a median EEL value, an average EEL value, an EEL mean, and / or a mode EEL value. For example, the median of the EEL values ​​of the frames of the first subset may be determined. The determined representative EEL values ​​of the frames of the first subset may be used as predicted EEL values ​​of the frames of the second subset in the region of interest. According to some examples, the determined representative EEL values ​​of the frames of the first subset may be used as predicted EEL values ​​of some of the frames of the first subset. For example, if some of the frames of the first subset have erroneously measured EEL values, the determined representative EEL values ​​may be used as predicted EEL values ​​of those frames in the first subset that have erroneous EEL values. The erroneous EEL value may be an EEL value that exceeds the standard deviation of the determined representative EEL value, an EEL value that exceeds a predetermined range of the determined representative EEL value, and the like.

[0135] The frames of the second subset may be different from the frames of the first subset. The frames of the second subset may be those frames in the region of interest for which the EEL value is not automatically determined when pulling back. In some examples, the frames of the second subset may be those frames in the region of interest for which the EEL value is incorrectly measured or not visible.

[0136] In block 860, the plaque burden for each frame within the region of interest may be determined based on the representative EEL value. The plaque burden may be further based on the lumen area of ​​the corresponding frame. For example, the plaque burden may be determined per frame using the following formula: 1-(lumen area / representative EEL value). In this formula, the representative EEL value may be a representative EEL area and / or a representative EEL diameter.

[0137] According to some examples, the plaque load of each frame can be used to identify lesions within a vessel. For example, a lesion can be identified by identifying an image frame with a maximum plaque load. According to some examples, a lesion can be identified by identifying an image frame with a plaque load greater than a disease threshold. For example, the disease threshold can be a plaque load disease threshold. For example, the plaque load disease threshold can be about 70%. In some examples, the plaque load disease threshold can be greater than or less than 70%. For example, the plaque load disease threshold can be patient-specific, determined by a physician, and the like.

[0138] Using the identified image frame as an initial frame, the plaque load of the frames proximal and distal to the initial frame can be compared to the treatment zone threshold until an image frame proximal and distal to the initial frame has a plaque load less than the treatment zone threshold. In some examples, the treatment zone threshold can be greater than or less than 50% of the plaque load. For example, the treatment zone threshold can correspond to a plaque load of approximately 45%. In some examples, the treatment zone threshold can be a range, such as a plaque load of approximately 0-50%. In some examples, the treatment zone threshold can be patient-specific, determined by a physician, and the like. In addition, or alternatively, the treatment zone end frame can correspond to a frame where the visible EEL arc is greater than or equal to the arc threshold. According to some examples, the arc threshold can be at least or approximately 180 degrees. In some examples, the arc threshold can be greater than or less than 180 degrees. For example, the arc threshold can be patient-specific, determined by a physician, and the like, so that the arc threshold can be any predetermined value.

[0139] Image frames between the identified proximal and distal frames are then marked as corresponding to lesions. The process is repeated for image frames with the next largest plaque load, regardless of image frames that have been identified as corresponding to lesions. After each lesion is identified, a gap or distance between lesions is determined. In examples where the gap is substantially equal to or less than a distance threshold, the lesions may be merged and identified as a single lesion. For example, when a first lesion is within a minimum gap distance of a second lesion (e.g., the gap between the first and second lesions is less than a distance threshold), the first and second lesions may be identified as a combined lesion. In examples where the gap is greater than the distance threshold, the lesions may be identified as separate lesions. According to some examples, a recommended or candidate treatment area for a stent may be identified based on the identified lesions.

[0140] Fig. 9 A flow chart of an exemplary process for automatically determining plaque load of a frame within a region of interest is shown, which can be implemented using computing device 112. The following operations do not have to be performed in the exact order described below. Instead, various operations can be processed in a different order or simultaneously, and operations can be added or omitted.

[0141] In block 910, vascular data including intravascular imaging data may be received. For example, the intravascular imaging data may be one or more image frames obtained by the probe during pullback through the vessel. The one or more image frames may be OCT image frames, IVUS image frames, etc. In some examples, the vascular data may be values ​​or measurements associated with the vessel in a given image frame. For example, the vascular data may be an EEL value (such as an EEL diameter), a lumen value (such as a lumen area or diameter), etc. In some examples, the vascular data may include a pressure value, a VFR value, an IMR value, etc.

[0142] In block 920, a region of interest of the vessel may be identified based on the vessel data. For example, the vessel data may include an indication of one or more side branches. The region of interest may be defined as a region between a first side branch and a second side branch.

[0143] In block 930, the predicted EEL value of the frame within the region of interest may be determined as a function of the intimal thickness and the media thickness. According to some examples, the predicted EEL value may be a representative EEL value of the frame within the region of interest. In another example, the predicted EEL value of each frame within the region of interest may be determined frame by frame. For example, a predicted EEL value may be determined for each frame within the region of interest. In some examples, respective predicted EEL values ​​may be determined for at least some frames within the region of interest. According to some examples, the intimal thickness may be a minimum intimal thickness, and the media thickness may be a minimum media thickness. The minimum intimal thickness and the minimum media thickness may be determined based on histological observations of the blood vessels. For example, based on histological observations of the blood vessels, the intimal thickness and the media thickness (with a standard deviation) may be determined. The minimum intimal thickness and the minimum media thickness may be determined based on the low end of the standard deviation.

[0144] According to some examples, the predicted EEL can be further determined as a function of the HK model. The HK model predicts the lumen diameter based on the assumption that the diameter, circumference and / or area of ​​the blood vessel is substantially constant along the region of interest. For example, the predicted EEL can be determined using the following formula:

[0145] Predicted EEL value = (expected lumen diameter) + 2 × (minimum intima thickness + minimum media thickness)

[0146] In the formula, the predicted EEL value may be a predicted EEL area and / or a predicted EEL diameter. For example, the expected lumen diameter may be a lumen diameter determined using the HK model.

[0147] According to some examples, the predicted EEL value (determined as a function of the HK model) may be compared with the EEL value of the proximal segment and / or the distal segment of the blood vessel. In some examples, the EEL value of the proximal segment and / or the distal segment of the blood vessel may be a representative EEL value of the proximal and / or distal segment of the blood vessel. For example, the representative EEL value of the region of interest may be a median EEL value, an average EEL value, an EEL mean, and / or a mode EEL value. If the predicted EEL value is less than the representative EEL value of the distal segment, the representative EEL value of the distal segment may be used to determine the plaque burden of the frame within the region of interest. Since the HK model assumes that the blood vessel has a natural taper from the proximal blood vessel segment to the distal blood vessel segment, the representative EEL value of the distal segment may be used when the predicted EEL value is less than the representative EEL value of the distal segment. If the predicted EEL value is greater than the representative EEL value of the proximal segment, the representative EEL value of the proximal segment may be used to determine the plaque burden of the frame within the region of interest. Since the HK model assumes that the blood vessel has a natural taper from the proximal blood vessel segment to the distal blood vessel segment, the representative EEL value of the proximal segment may be used when the predicted EEL value is greater than the representative EEL value of the proximal segment.

[0148] In block 940, the plaque load for each frame within the region of interest may be determined based on the predicted EEL value. The plaque load may be further based on the lumen area of ​​the corresponding frame. For example, the plaque load may be determined per frame using the following formula: 1-(lumen area / predicted EEL value).

[0149] With reference Figure 8 Similar to the exemplary process described, the plaque load of each frame can be used to identify lesions within a vessel. For example, a lesion can be identified by identifying an image frame with a maximum plaque load. According to some examples, a lesion can be identified by identifying an image frame with a plaque load greater than a disease threshold. For example, the disease threshold can be a plaque load disease threshold. For example, the plaque load disease threshold can be about 70%. In some examples, the plaque load disease threshold can be greater than or less than 70%. For example, the plaque load disease threshold can be patient-specific, determined by a physician, and so on.

[0150] Using the image frame as an initial frame, the plaque load of the frames proximal and distal to the initial frame can be compared to the treatment zone threshold until an image frame proximal and distal to the initial frame has a plaque load less than the treatment zone threshold and / or the curvature of the visible EEL is above the curvature threshold. Then, the image frames between the identified proximal frame and the distal frame are marked as corresponding to the lesion. The process is repeated for the image frame with the next largest plaque load without considering the image frame that has been identified as corresponding to the lesion. After each lesion is identified, the gap or distance between the lesions is determined. In examples where the gap is substantially equal to or less than the distance threshold, the lesions can be merged and identified as a single lesion. For example, when the distance between the first lesion and the second lesion is within the minimum gap distance (e.g., the gap between the first and second lesions is less than the distance threshold), the first and second lesions can be identified as a combined lesion. In examples where the gap is greater than the distance threshold, the lesions can be identified as separate lesions. According to some examples, a recommended or candidate treatment zone. According to some examples, the recommended or candidate treatment zone can be a stent landing zone. The stent landing zone for the stent can be identified based on the identified lesions. In some examples, the treatment area may be used for balloon angioplasty, laser atherectomy, or the like.

[0151] According to some examples, the EEL value of a given frame during the pullback may not be determined due to plaque overgrowth or other obstacles during the pullback. In such examples, predicting the EEL values ​​of these image frames can provide more vascular information for determination. For example, by averaging the EEL values ​​or predicting the EEL values ​​as a function of the intima thickness, media thickness, and HK model, the plaque load can be determined frame by frame. The determined plaque load can be used to more accurately identify the location, length, severity, etc. of the lesion. In addition, by using the predicted EEL values ​​to determine the plaque load of those frames where the EEL is not detected or the EEL is measured incorrectly, the candidate treatment area can be more accurately identified. For example, the candidate treatment area is often adjusted by the physician during the stent planning stage. In contrast, by automatically determining or predicting the EEL value and using the determined EEL value to determine the plaque load, the frame at the end of the candidate treatment area can be automatically identified (by identifying the location where the plaque load is below a threshold and / or the visible EEL arc is at or above the arc threshold). This reduces the need for user intervention and can improve accuracy because the predicted EEL value can provide a more informed decision-making process.

[0152] In general, the systems and methods disclosed herein provide various automated clinical tools to help physicians determine whether a particular patient should be treated, and if so, which lesion / stenosis should be treated. The system can treat the most important lesions based on physiological guidance. In addition, detailed information about plaque type and other MLS detected features can be used to select the shortest stent (providing the greatest blood flow restoration). In addition, virtual stenting can be implemented, which provides interactive planning to tailor a plan for stent placement in an artery based on tissue classification and other measurements disclosed herein.

[0153] The various aspects, features and examples of the present disclosure are illustrative in every sense and are not intended to limit the disclosure of the present invention, the scope of which is limited only by the claims. Other examples, modifications and uses are obvious to those skilled in the art and will not depart from the spirit and scope of the present invention.

[0154] Throughout this application, when a composition is described as having, including, or comprising particular ingredients, or when a method is described as having, including, or comprising particular method steps, it is contemplated that the compositions taught by the present invention also consist of or consist essentially of the stated ingredients, and that the methods taught by the present invention consist of or consist essentially of the stated method steps.

[0155] In this application, when an element or component is said to be included in and / or selected from a list of listed elements or components, it should be understood that the element or component can be any one of the listed elements or components, and can be selected from a group consisting of two or more of the listed elements or components. In addition, it should be understood that the elements and / or features of the compositions, devices or methods described herein can be combined in a variety of ways without departing from the spirit and scope of the teachings of the present invention (whether explicit or implicit).

[0156] The use of the terms "including", "having" and "having" should generally be construed as open ended and non-limiting unless specifically stated otherwise.

[0157] Unless otherwise specifically stated, the singular forms used herein include the plural (and vice versa). In addition, the singular forms "a", "an" and "the" also include the plural forms, unless the context clearly dictates otherwise. In addition, when the term "approximately" is used before a quantitative value, the specific quantitative value itself is also included unless otherwise specifically stated. As used herein, the term "approximately" refers to a variation of ±10% compared to the nominal value. All numerical values ​​and ranges disclosed herein are deemed to include "approximately" before each numerical value.

[0158] It should be understood that the order of steps or the order in which certain operations are performed is not important as long as the present invention remains operable. In addition, two or more steps or operations may be performed simultaneously.

[0159] Where a range of values ​​or a list of values ​​is provided, each intermediate value between the upper and lower limits of the range of values ​​or the list of values ​​is considered separately and is included in the present invention as if each value were specifically listed herein. In addition, smaller ranges between and including the upper and lower limits of a given range are also contemplated by the present invention. Listing exemplary values ​​or ranges is not a disclaimer of other values ​​or ranges between and including the upper and lower limits of a given range.

Claims

1. A method comprising: Receiving, via one or more processors, vascular data including intravascular imaging data; identifying, by the one or more processors, a region of interest of a blood vessel based on the blood vessel data; identifying, by the one or more processors, a first subset of frames within the region of interest, the first subset of frames having a plaque load below a threshold plaque load, the first subset of frames comprising at least a threshold number of frames; determining, by the one or more processors, outer elastic layer ("EEL") values ​​for the first subset of frames; determining, by the one or more processors, a representative EEL value for the region of interest based on the EEL values ​​of the frames of the first subset; as well as Determining, by the one or more processors, a plaque load of a second subset of frames within the region of interest based on the representative EEL value, wherein the second subset of frames is different from the first subset of frames. 2 . The method of claim 1 , wherein the representative EEL value is at least one of a mean EEL value, an average EEL value, a median EEL value, or a mode EEL value. The method according to claim 1 , wherein the region of interest is defined between a first vessel branch and a second vessel branch.

4. A method according to any preceding claim, wherein: The EEL value is the EEL diameter or the EEL area, and The representative EEL value is a representative EEL diameter or a representative EEL area.

5. The method of any preceding claim, wherein the threshold plaque load corresponds to a plaque load of at or about 0-50%.

6. A method according to any preceding claim, wherein the threshold number of frames is at least three frames.

7. The method according to any of the preceding claims, wherein the plaque burden is further determined based on the lumen area of ​​the corresponding frame.

8. The method of claim 6, wherein determining the plaque burden for the corresponding frame comprises calculating 1-(luminal area / representative EEL value).

9. The method according to any preceding claim, further comprising: Lesions are identified, by the one or more processors, based on the determined plaque burden.

10. The method according to claim 9, further comprising: A candidate treatment volume is identified, by the one or more processors, based on the identified lesions.

11. The method of claim 10, wherein identifying the candidate treatment area further comprises: Frames proximal and distal to the identified lesion are identified, by the one or more processors, wherein at least one of the plaque load of the frames proximal and distal to the identified lesion is less than a threshold or a visible EEL arc is greater than or equal to an arc threshold.

12. The method of claim 9, wherein when the first lesion is within a minimum clearance distance from the second lesion, the method further comprises: The first lesion and the second lesion are identified, by the one or more processors, as a combined lesion.

13. A system comprising: One or more processors configured to: receiving vascular data including intravascular imaging data; identifying a region of interest of a blood vessel based on the blood vessel data; identifying a first subset of frames within the region of interest, the first subset of frames having a plaque load below a threshold plaque load, the first subset of frames comprising at least a threshold number of frames; determining outer elastic layer ("EEL") values ​​for the first subset of frames; determining a representative EEL value of the region of interest based on the EEL values ​​of the frames of the first subset; as well as A plaque burden of a second subset of frames within the region of interest is determined based on the representative EEL value, wherein the second subset of frames is different from the first subset of frames.

14. The system of claim 13, wherein the representative EEL value is at least one of a mean EEL value, an average EEL value, a median EEL value, or a mode EEL value.

15. The system of claim 13 or 14, wherein the region of interest is defined between a first vessel branch and a second vessel branch.

16. A system according to any one of claims 13 to 15, wherein: The EEL value is the EEL diameter or the EEL area, and The representative EEL value is a representative EEL diameter or a representative EEL area.

17. The system of any one of claims 13 to 16, wherein the threshold plaque load corresponds to a plaque load of at or about 0-50%.

18. The system of any one of claims 13 to 17, wherein the threshold number of frames is at least three frames.

19. The system of any one of claims 13 to 18, wherein the plaque burden is further determined based on the lumen area of ​​the corresponding frame.

20. The system of claim 19, wherein determining the plaque burden for the corresponding frame comprises calculating 1 - (luminal area / representative EEL value).

21. The system of any one of claims 13 to 20, wherein the one or more processors are further configured to identify lesions based on the determined plaque burden.

22. The system of claim 21, wherein the one or more processors are further configured to identify a candidate treatment volume based on the identified lesion.

23. A system according to claim 22, wherein when the candidate treatment area is identified, the one or more processors are further configured to identify frames proximal and distal to the identified lesion, wherein at least one of the plaque loads of the frames proximal and distal to the identified lesion is less than a threshold, or the visible EEL arc is greater than or equal to an arc threshold.

24. The system of claim 21, wherein when a first lesion is within a minimum clearance distance from a second lesion, the one or more processors are further configured to identify the first lesion and the second lesion as a combined lesion.

25. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to: receiving vascular data including intravascular imaging data; identifying a region of interest of a blood vessel based on the blood vessel data; identifying a first subset of frames within the region of interest, the first subset of frames having a plaque load below a threshold plaque load, the first subset of frames comprising at least a threshold number of frames; determining outer elastic layer ("EEL") values ​​for the first subset of frames; determining a representative EEL value for the region of interest based on the EEL values ​​of the frames of the first subset; and A plaque burden of a second subset of frames within the region of interest is determined based on the representative EEL value, wherein the second subset of frames is different from the first subset of frames.

26. The non-transitory computer-readable medium of claim 25, wherein the representative EEL value is at least one of a mean EEL value, an average EEL value, a median EEL value, or a mode EEL value.

27. The non-transitory computer readable medium of claim 25 or 26, wherein the region of interest is defined between a first vessel branch and a second vessel branch.

28. The non-transitory computer readable medium of any one of claims 25 to 27, wherein: The EEL value is the EEL diameter or the EEL area, and The representative EEL value is a representative EEL diameter or a representative EEL area.

29. The non-transitory computer-readable medium of any one of claims 25 to 28, wherein the threshold plaque load corresponds to a plaque load of at or about 0-50%.

30. The non-transitory computer-readable medium of any one of claims 25 to 29, wherein the threshold number of frames is at least three frames.

31. The non-transitory computer readable medium of any one of claims 25 to 30, wherein the plaque burden is further determined based on a lumen area of ​​a corresponding frame.

32. The non-transitory computer readable medium of claim 31, wherein the determination of the plaque burden for the corresponding frame comprises calculating 1 - (luminal area / representative EEL value).

33. The non-transitory computer readable medium of any one of claims 25 to 32, wherein the one or more processors are further configured to identify lesions based on the determined plaque burden.

34. The non-transitory computer readable medium of claim 33, wherein the one or more processors are further configured to identify a candidate treatment volume based on the identified lesion.

35. The non-transitory computer-readable medium of claim 34, wherein when the candidate treatment area is identified, the one or more processors are further configured to identify frames proximal and distal to the identified lesion, wherein at least one of the plaque loads of the frames proximal and distal to the identified lesion is less than a threshold, or a visible EEL arc is greater than or equal to an arc threshold.

36. The non-transitory computer readable medium of claim 33, wherein when a first lesion is within a minimum clearance distance from a second lesion, the one or more processors are further configured to identify the first lesion and the second lesion as a combined lesion.

37. A method comprising: Receiving, via one or more processors, vascular data including intravascular imaging data; identifying, by the one or more processors, a region of interest of a blood vessel based on the blood vessel data; determining, by the one or more processors, a predicted external elastic layer ("EEL") value for a frame within the region of interest based on the vascular data as a function of intima thickness and media thickness; as well as A plaque load of a frame within the region of interest is determined, by the one or more processors, based on the predicted EEL value.

38. The method of claim 37, wherein the region of interest is defined between a first vessel branch and a second vessel branch.

39. The method of claim 37 or 38, wherein the predicted EEL value is further determined as a function of at least one of the lumen area or lumen diameter obtained from the HK model.

40. The method of any one of claims 37 to 39, wherein the plaque burden is further determined based on the lumen area of ​​the corresponding frame.

41. The method of claim 40, wherein determining the plaque burden for the corresponding frame comprises calculating 1 - (luminal area / predicted EEL value).

42. The method according to any one of claims 37 to 41, further comprising: Lesions are identified, by the one or more processors, based on the determined plaque burden.

43. The method of claim 42, further comprising: A candidate treatment volume is identified, by the one or more processors, based on the identified lesions.

44. The method of claim 43, wherein identifying the candidate treatment area further comprises: Frames proximal and distal to the identified lesion are identified, by the one or more processors, wherein at least one of the plaque load of the frames proximal and distal to the identified lesion is less than a threshold or a visible EEL arc is greater than or equal to an arc threshold.

45. The method of claim 44, wherein when the first lesion is within a minimum clearance distance from the second lesion, the method further comprises: The first lesion and the second lesion are identified, by the one or more processors, as a combined lesion.

46. ​​The method according to any one of claims 37 to 45, further comprising: comparing, by the one or more processors, the predicted EEL value of the region of interest with a representative EEL value of a proximal segment of the blood vessel; and When the representative EEL value of the proximal segment is less than the predicted EEL value of the region of interest, the plaque burden of the region of interest is determined based on the representative EEL value of the proximal segment.

47. The method according to any one of claims 37 to 46, further comprising: comparing, by the one or more processors, the predicted EEL value of the region of interest with a representative EEL value of a distal segment of the blood vessel; and When the representative EEL value of the distal segment is greater than the predicted EEL value of the region of interest, the plaque burden of the region of interest is determined based on the representative EEL value of the distal segment.

48. The method of claim 46 or 47, wherein the representative EEL value is at least one of a mean EEL value, an average EEL value, a median EEL value, or a mode EEL value.

49. A system comprising: One or more processors configured to: receiving vascular data including intravascular imaging data; identifying a region of interest of a blood vessel based on the blood vessel data; determining, based on the vascular data, a predicted external elastic layer ("EEL") value for a frame within the region of interest as a function of intima thickness and media thickness; as well as The plaque load of the frame within the region of interest is determined based on the predicted EEL value.

50. The system of claim 49, wherein the region of interest is defined between a first vessel branch and a second vessel branch.

51. The system of claim 49 or 50, wherein the predicted EEL value is further determined as a function of at least one of a lumen area or a lumen diameter obtained from a HK model.

52. The system of any one of claims 49 to 51, wherein the plaque burden is further determined based on the lumen area of ​​the corresponding frame.

53. The system of claim 52, wherein determining the plaque burden for the corresponding frame comprises calculating 1 - (luminal area / predicted EEL value).

54. The system of any one of claims 49 to 53, wherein the one or more processors are further configured to identify lesions based on the determined plaque burden.

55. The system of claim 54, wherein the one or more processors are further configured to identify a candidate treatment volume based on the identified lesion.

56. A system according to claim 55, wherein when the candidate treatment area is identified, the one or more processors are further configured to identify frames proximal and distal to the identified lesion, wherein at least one of the plaque loads of the frames proximal and distal to the identified lesion is less than a threshold, or the visible EEL arc is greater than or equal to an arc threshold.

57. The system of claim 56, wherein when a first lesion is within a minimum clearance distance from a second lesion, the one or more processors are further configured to identify the first lesion and the second lesion as a combined lesion.

58. A system according to any one of claims 49 to 57, wherein: The one or more processors are further configured to compare the predicted EEL value of the region of interest with a representative EEL value of a proximal segment of the blood vessel; and When the representative EEL value of the proximal segment is less than the predicted EEL value of the region of interest, the plaque burden of the region of interest is determined based on the representative EEL value of the proximal segment.

59. A system according to any one of claims 49 to 58, wherein: The one or more processors are further configured to compare the predicted EEL value of the region of interest with a representative EEL value of a distal segment of the blood vessel; and When the representative EEL value of the distal segment is greater than the predicted EEL value of the region of interest, the plaque burden of the region of interest is determined based on the representative EEL value of the distal segment.

60. The system of claim 58 or 59, wherein the representative EEL value is at least one of a mean EEL value, an average EEL value, a median EEL value, or a mode EEL value.

61. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to: receiving vascular data including intravascular imaging data; identifying a region of interest of a blood vessel based on the blood vessel data; determining, based on the vascular data, predicted external elastic layer ("EEL") values ​​for frames within the region of interest as a function of intima thickness and media thickness; and The plaque load of the frame within the region of interest is determined based on the predicted EEL value.

62. The non-transitory computer readable medium of claim 61, wherein the region of interest is defined between a first vessel branch and a second vessel branch.

63. The non-transitory computer readable medium of claim 61 or 62, wherein the predicted EEL value is further determined as a function of at least one of a lumen area or a lumen diameter obtained from a HK model.

64. The non-transitory computer readable medium of any one of claims 61 to 63, wherein the plaque burden is further determined based on a lumen area of ​​a corresponding frame.

65. The non-transitory computer readable medium of claim 64, wherein determining the plaque burden for the corresponding frame comprises calculating 1 - (luminal area / predicted EEL value).

66. The non-transitory computer readable medium of any one of claims 61 to 65, wherein the one or more processors are further configured to identify lesions based on the determined plaque burden.

67. The non-transitory computer readable medium of claim 66, wherein the one or more processors are further configured to identify a candidate treatment volume based on the identified lesion.

68. A non-transitory computer-readable medium according to claim 67, wherein when the candidate treatment area is identified, the one or more processors are further configured to identify frames proximal and distal to the identified lesion, wherein at least one of the plaque loads of the frames proximal and distal to the identified lesion is less than a threshold and / or the visible EEL arc is greater than or equal to a arc threshold.

69. The non-transitory computer readable medium of claim 68, wherein when a first lesion is within a minimum clearance distance from a second lesion, the one or more processors are further configured to identify the first lesion and the second lesion as a combined lesion.

70. The non-transitory computer readable medium of any one of claims 61 to 69, wherein: The one or more processors are further configured to compare the predicted EEL value of the region of interest with a representative EEL value of a proximal segment of the blood vessel; and When the representative EEL value of the proximal segment is less than the predicted EEL value of the region of interest, the plaque burden of the region of interest is determined based on the representative EEL value of the proximal segment.

71. The non-transitory computer readable medium of any one of claims 61 to 70, wherein: The one or more processors are further configured to compare the predicted EEL value of the region of interest with a representative EEL value of a distal segment of the blood vessel; and When the representative EEL value of the distal segment is greater than the predicted EEL value of the region of interest, the plaque burden of the region of interest is determined based on the representative EEL value of the distal segment.

72. The non-transitory computer-readable medium of claim 70 or 71, wherein the representative EEL value is at least one of a mean EEL value, an average EEL value, a median EEL value, or a mode EEL value.

Images