Critical patient chemotherapy assessment, monitoring method and system

Abstract

The disclosure provides a critical patient chemotherapy evaluation and monitoring method and system, and relates to the technical field of critical patient chemotherapy evaluation and monitoring. The critical patient chemotherapy evaluation method comprises the following steps: extracting a lesion mask image corresponding to a lesion from a preset part medical image of a critical patient to be chemotherapeutized; determining whether the lesion boundary of the lesion is clear and whether a spinous process sign exists on the lesion edge according to the lesion mask image; if the lesion boundary is blurred and the spinous process sign exists, then using the lesion mask image and an arterial vessel mask image corresponding to the preset part medical image to evaluate whether the lesion position exists a risk of invading the arterial vessel. The embodiment of the disclosure can realize critical patient chemotherapy evaluation and monitoring.

Description

Technical Field

[0001] This disclosure relates to the field of chemotherapy assessment and monitoring technology for critically ill patients, and in particular to a method and system for chemotherapy assessment and monitoring of critically ill patients. Background Technology

[0002] Assessing the risk of arterial invasion based on lesion location is a crucial step in clinical diagnosis and treatment, including analyzing the relationship between lesions and adjacent arteries, the course of blood vessels and lesion location, anatomical gaps and barriers, involvement of multiple organs, and postoperative prognosis.

[0003] For example, if a lesion is directly adjacent to an artery (such as a pancreatic tumor adjacent to the superior mesenteric artery, or a retroperitoneal tumor adjacent to the abdominal aorta), the risk of invasion increases significantly. For instance, in pancreatic ductal adenocarcinoma (PDAC), tumors in the pancreatic head are prone to invading the superior mesenteric artery and celiac trunk; when the contact angle is >180°, the invasion probability can reach 80%. Simultaneously, the course of the artery is closely related to the location of the lesion. If the lesion is located at the bend, bifurcation, or branch of an artery (such as the bifurcation of the hepatic artery or the origin of the renal artery), the risk of invasion is even higher due to changes in vessel wall tension and hemodynamics. Furthermore, normal anatomical spaces and barriers (such as the adventitia and fascia) can limit tumor invasion. If the lesion breaches these barriers (such as tumor invasion of the adventitia or penetration of the fascia), the risk of invasion increases. For example, when pancreatic cancer invades the adventitia of an artery, although it may be resected using subadventitial dissection techniques, the risk of postoperative recurrence is high. Finally, if the lesion also invades adjacent organs (such as pancreatic tumors invading the duodenum, stomach, etc.), it is often accompanied by arterial invasion. Because the involvement of multiple organs indicates that the tumor is highly invasive and easily breaks through the vascular barrier.

[0004] Based on the important reference value of the above-mentioned clinical diagnosis and treatment, and distinguishing it from existing technologies, there is an urgent need to propose a technical solution for lesion edge analysis and intelligent medical image processing. This solution aims to address at least one of the following technical problems: the need for manual determination of lesion location leads to excessive subjectivity in assessing the risk of arterial invasion; the lack of intelligent determination of lesion location results in a huge workload for doctors; and it prevents effective evaluation of the efficacy of radiotherapy and the development of effective radiotherapy strategies. Summary of the Invention

[0005] This disclosure presents a technical solution for a method and system for assessing and monitoring critically ill patients undergoing chemotherapy.

[0006] According to one aspect of this disclosure, a method for assessing chemotherapy in critically ill patients is provided, comprising: extracting a lesion mask image corresponding to the lesion from a medical image of a critically ill patient awaiting chemotherapy; determining, based on the lesion mask image, whether the lesion boundary is clear and whether there is a spike-like sign at the lesion edge; if the lesion boundary is blurred and there is a spike-like sign, then using the lesion mask image and the arterial blood vessel mask image corresponding to the medical image of the preset location, assessing whether there is a risk of invasion of arteries by the lesion location.

[0007] Preferably, the step of extracting the lesion mask image corresponding to the lesion from the medical image of the preset location of the critically ill patient awaiting chemotherapy includes: using a preset lesion segmentation model to segment the lesion in the medical image of the preset location to obtain the lesion mask image corresponding to the medical image of the preset location.

[0008] Preferably, before segmenting the medical image of the preset location using a preset lesion segmentation model to obtain the lesion mask image corresponding to the medical image of the preset location, the method includes: training a first preset deep learning segmentation network using a preset number of medical images of preset locations and their corresponding lesion mask training images to obtain a preset lesion segmentation model.

[0009] Preferably, determining whether the lesion boundary is clear based on the lesion mask image includes: performing an erosion operation on the lesion mask in the lesion mask image to obtain a lesion mask erosion image; subtracting the lesion mask erosion image from the lesion mask image to obtain a lesion mask processing image; mapping the lesion location coordinates in the lesion mask processing image to a preset site medical image; calculating multiple gradients corresponding to the lesion location coordinates in the preset site medical image; if the gradient magnitude values ​​corresponding to the multiple gradients are less than a preset gradient magnitude value, then the lesion boundary at the location corresponding to the lesion location less than the preset gradient magnitude value is determined to be blurred; otherwise, the lesion boundary at the location corresponding to the preset gradient magnitude value is determined to be clear.

[0010] Preferably, determining the gradient magnitude corresponding to the plurality of gradients includes: squaring the plurality of x-direction gradients corresponding to the lesion location coordinates to obtain a plurality of x-direction squared gradients; squaring the plurality of y-direction gradients corresponding to the lesion location coordinates to obtain a plurality of y-direction squared gradients; summing the plurality of x-direction squared gradients with their corresponding y-direction squared gradients to obtain a gradient sum corresponding to the plurality of lesion location coordinates; and taking the square root of the gradient sum corresponding to the plurality of lesion location coordinates to obtain the gradient magnitude corresponding to the plurality of gradients.

[0011] Preferably, the ratio of the long axis to the short axis of each lesion is calculated based on the long axis and short axis of each lesion in the lesion mask image corresponding to the medical image of the preset location; wherein, the medical image of the preset location is configured as a two-dimensional medical image; if the ratio of the long axis to the short axis is greater than or equal to a first preset ratio of the long axis to the short axis, then it is determined that the corresponding lesion has a spike sign.

[0012] Preferably, based on the major and minor axes of each three-dimensional lesion in the lesion mask image corresponding to the preset site medical image, multiple major-minor axis ratios corresponding to each three-dimensional lesion are calculated; if any one of the major-minor axis ratios is greater than or equal to a first preset major-minor axis ratio, then the corresponding lesion is determined to have a spike sign; wherein, the preset site medical image is configured as a three-dimensional medical image.

[0013] Preferably, determining whether a spiky sign exists at the lesion boundary based on the lesion mask image includes: determining whether the medical image of the preset location is a two-dimensional or three-dimensional medical image; if the medical image of the preset location is a two-dimensional medical image, then calculating the ratio of the long axis to the short axis of each lesion based on the long axis and short axis of each lesion in the lesion mask image corresponding to the preset location medical image; if the ratio of the long axis to the short axis is greater than or equal to a first preset ratio of the long axis to the short axis, then determining that the corresponding lesion has a spiky sign; otherwise, determining that the corresponding lesion does not have a spiky sign; if the medical image of the preset location is a three-dimensional medical image, then calculating multiple ratios of the long axis to the short axis of each three-dimensional lesion based on the long axis and short axis of each three-dimensional lesion in the lesion mask image corresponding to the preset location medical image; if any one of the ratios of the long axis to the short axis is greater than or equal to the first preset ratio of the long axis to the short axis, then determining that the corresponding lesion has a spiky sign.

[0014] Preferably, if the lesion boundary is blurred and a spiky sign is present, the risk of the lesion location invading the artery is assessed using the lesion mask image and the arterial mask image corresponding to the medical image of the preset location. This includes: extracting multiple spiky point coordinates corresponding to multiple spiky points in the lesion mask image and arterial mask edge coordinates corresponding to the arterial mask edge in the arterial mask image; calculating multiple distances between the multiple spiky point coordinates and the arterial mask edge coordinates; and determining that the spiky point corresponding to the lesion poses a risk of invading the artery if the minimum distance among the multiple distances is less than a preset distance.

[0015] Preferably, determining whether the spinous process corresponding to the lesion poses a risk of invading the artery based on the lesion mask and artery mask image corresponding to the medical image of the preset location includes: extracting multiple spinous process position coordinates corresponding to multiple spinous processes and artery mask edge position coordinates corresponding to the artery mask edge in the lesion mask and artery mask images; calculating multiple distances between the multiple spinous process position coordinates and the artery mask edge position coordinates respectively; if the minimum distance among the multiple distances is less than a preset distance, it is determined that the spinous process corresponding to the lesion poses a risk of invading the artery.

[0016] Preferably, the method for assessing chemotherapy in critically ill patients further includes: if the spinous process corresponding to the lesion poses a risk of invading arteries, then the spinous process is determined to be a dangerous spinous process.

[0017] Preferably, determining the spike includes: detecting the edge of the lesion mask in the lesion mask image to obtain the lesion mask edge line; calculating the first pixel distance and the second pixel distance between any lesion mask edge pixel on the lesion mask edge line and its adjacent lesion mask edge pixels; if the first pixel distance and the second pixel distance are greater than a set pixel distance, then the arbitrary lesion mask edge pixel is configured as a spike.

[0018] According to one aspect of this disclosure, a method for monitoring critically ill patients is provided, comprising: using the aforementioned critically ill patient chemotherapy assessment method to assess whether there is a risk of lesion location in a preset location medical image of the critically ill patient to be treated for chemotherapy; if there is a risk of lesion location invading arteries, extracting one or more imaging features from the preset location medical image, such as the average gray value corresponding to the lesion, the ratio of the long diameter to the short diameter corresponding to the lesion, whether there is a risk of lesion location invading arteries, and whether there is a spike sign at the edge of the lesion, to predict the efficacy of radiotherapy.

[0019] Preferably, the step of predicting radiotherapy efficacy using one or more imaging features extracted from the medical image of the preset location, including the average gray value corresponding to the lesion, the ratio of the major axis to the minor axis corresponding to the lesion, whether the lesion location poses a risk of invading arteries, and whether the lesion edge has a spike-like sign, includes: determining whether the lesion type corresponding to the medical image of the preset location has a similar lesion type on the medical image of the preset location; if so, determining the imaging features used to distinguish the lesion type from the similar lesion type; and using the preset radiotherapy efficacy prediction model and the imaging features to predict the radiotherapy efficacy of the medical image of the preset location.

[0020] Preferably, the method further includes: using the above-mentioned critical patient chemotherapy assessment method to assess whether the lesion location of the critical patient undergoing chemotherapy poses a risk of invading arteries in the medical image of the preset site; if the lesion location poses a risk of invading arteries, then based on the lesion mask area corresponding to the lesion undergoing chemotherapy or surgery and the artery mask area corresponding to the artery, determining whether the artery passes through the lesion undergoing chemotherapy or surgery.

[0021] Preferably, determining whether the artery passes through the lesion to be treated or operated on, based on the lesion mask region corresponding to the lesion to be treated or operated on and the artery mask region corresponding to the artery, includes: extracting the lesion mask position coordinates corresponding to the lesion mask region of the lesion to be treated or operated on and the artery mask region of the artery to be treated, respectively; if the artery mask position coordinates overlap with the lesion mask position coordinates, then it is determined that the artery passes through the lesion to be treated or operated on; otherwise, it is determined that the artery does not pass through the lesion to be treated or operated on.

[0022] According to one aspect of this disclosure, a chemotherapy assessment system for critically ill patients is provided, comprising: a lesion mask image extraction unit, used to extract a lesion mask image corresponding to a lesion from a medical image of a critically ill patient to be treated with chemotherapy at a preset location; a first determination unit, used to determine whether the lesion boundary is clear and whether there is a spike-like sign at the edge of the lesion based on the lesion mask image; and a first assessment unit, used to assess whether there is a risk of invasion of arteries by the lesion location if the lesion boundary is blurred and there is a spike-like sign, using the lesion mask image and the arterial mask image corresponding to the medical image of the preset location.

[0023] According to one aspect of this disclosure, a chemotherapy assessment system for critically ill patients is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the aforementioned chemotherapy assessment method for critically ill patients.

[0024] According to one aspect of this disclosure, a chemotherapy assessment system for critically ill patients is provided, comprising: a computer-readable storage medium having a computer program / instructions and a bit stream stored thereon, wherein the computer program / instructions, when executed by a processor, generate the bit stream in accordance with the aforementioned chemotherapy assessment method for critically ill patients.

[0025] According to one aspect of this disclosure, a chemotherapy assessment system for critically ill patients is provided, comprising: a computer program product configured with a computer program / instruction that, when executed by a processor, implements the aforementioned chemotherapy assessment method for critically ill patients.

[0026] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a second assessment unit, used to assess whether there is a risk of lesion location in a preset location medical image of the critical patient undergoing chemotherapy using the aforementioned critical patient chemotherapy assessment method; and a radiotherapy efficacy prediction unit, used to extract one or more imaging features from the preset location medical image, such as the average gray value corresponding to the lesion, the ratio of the long diameter to the short diameter corresponding to the lesion, whether there is a risk of lesion location invading arteries, and whether there is a spike sign at the edge of the lesion, if there is a risk of lesion location invading arteries, to predict the radiotherapy efficacy.

[0027] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a third assessment unit, configured to assess whether there is a risk of lesion location in a preset site corresponding to the critical patient undergoing chemotherapy using the aforementioned critical patient chemotherapy assessment method; a second determination unit, configured to determine whether the artery passes through the lesion to be treated or the lesion to be operated on, based on the lesion mask area corresponding to the lesion to be treated or the lesion to be operated on and the artery mask area corresponding to the artery; and a radiotherapy unit, configured to, if the artery passes through the lesion to be treated or the lesion to be operated on, perform radiotherapy on the artery passing through the lesion to be treated or the lesion to be operated on under ultrasound image guidance with a first radiotherapy dose, and perform radiotherapy on the lesion outside the artery under ultrasound image guidance with a second radiotherapy dose less than the first radiotherapy dose.

[0028] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the aforementioned critical patient monitoring method.

[0029] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a computer-readable storage medium having a computer program / instructions and a bit stream stored thereon, wherein the computer program / instructions, when executed by a processor, implement the above-described critical patient monitoring method to generate the bit stream.

[0030] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a computer program product configured with a computer program / instruction, which, when executed by a processor, implements the aforementioned critical patient monitoring method.

[0031] In this disclosure, a technical solution for a chemotherapy assessment and monitoring method and system for critically ill patients is proposed to solve at least one of the following technical problems: the existing method requires manual determination of lesion location, which is too subjective in terms of the risk of arterial invasion; the lack of intelligent determination of lesion location, which results in a huge workload for doctors; and the inability to effectively assess the efficacy of radiotherapy and formulate effective radiotherapy strategies.

[0032] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0033] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0035] Figure 1 A flowchart illustrating a chemotherapy assessment method for critically ill patients according to an embodiment of this disclosure is shown; Figure 2 A flowchart illustrating a method for monitoring critically ill patients according to an embodiment of this disclosure is shown; Figure 3 A block diagram illustrating a chemotherapy assessment method for critically ill patients according to an embodiment of the present disclosure is shown; Figure 4 A block diagram of a method for monitoring critically ill patients according to an embodiment of the present disclosure is shown. Detailed Implementation

[0036] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0037] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0038] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0039] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0040] It is understood that the various patient chemotherapy assessment methods and critical patient monitoring methods mentioned in this disclosure can be combined with each other to form combined embodiments without violating the principles and logic. Due to space limitations, this disclosure will not elaborate further.

[0041] In addition, this disclosure also provides patient chemotherapy assessment methods and critical patient monitoring devices or systems, electronic devices, computer-readable storage media, and program products, all of which can be used to implement any of the patient chemotherapy assessment methods and critical patient monitoring methods provided in this disclosure. The corresponding technical solutions and descriptions are described in the relevant section on patient chemotherapy assessment methods and critical patient monitoring methods, and will not be repeated here.

[0042] Figure 1 A flowchart illustrating a chemotherapy assessment method for critically ill patients according to an embodiment of this disclosure is shown. Figure 1 As shown, the method for assessing chemotherapy in critically ill patients includes: Step S101: Extracting a lesion mask image corresponding to the lesion from a medical image of a pre-set location of the critically ill patient awaiting chemotherapy; Step S102: Determining whether the lesion boundary is clear and whether there is a spike-like sign at the lesion edge based on the lesion mask image; Step S103: If the lesion boundary is blurred and a spike-like sign is present, then using the lesion mask image and the arterial mask image corresponding to the pre-set location medical image, assessing whether the lesion location poses a risk of invading arteries. This addresses at least one of the following technical problems: the existing method requires manual determination of the lesion location's risk of invading arteries, which is too subjective; the lack of intelligent determination of the lesion location's risk of invading arteries results in a huge workload for doctors; and it prevents effective assessment of the subsequent efficacy of radiotherapy and the effective formulation of radiotherapy strategies.

[0043] In the embodiments disclosed herein and other possible embodiments, the preset site medical training images and the preset site medical images are of the same type. For example, the preset site medical training images and the preset site medical images are configured as one or more of the following medical images: chest X-ray / CT / PET / MRI images, knee joint X-ray / CT / PET / MRI images, spine X-ray / CT / PET / MRI images, breast X-ray / CT / PET / MRI images, abdominal X-ray / CT / PET / MRI images, vertebral X-ray / CT / PET / MRI images, breast ultrasound images, and abdominal ultrasound images; and / or, the lesions corresponding to the preset site medical images are configured as one or more of the following medical images: pneumonia, tuberculosis, encephalitis, lung cancer, liver cancer, breast cancer, lipoma, fibroma, hamartoma, cavitary tuberculosis, cavitary lung abscess, nodule, fracture, cerebral contusion and laceration, and soft tissue injury.

[0044] In this embodiment of the disclosure, the step of extracting the lesion mask image corresponding to the lesion from the medical image of the preset location of a critically ill patient awaiting chemotherapy includes: using a preset lesion segmentation model to segment the lesion in the medical image of the preset location to obtain the lesion mask image corresponding to the medical image of the preset location.

[0045] In this embodiment of the disclosure, before segmenting the medical image of the preset location using a preset lesion segmentation model to obtain the lesion mask image corresponding to the medical image of the preset location, the method includes: training a first preset deep learning segmentation network using a preset number of medical images of preset locations and their corresponding lesion mask training images to obtain a preset lesion segmentation model.

[0046] In the embodiments disclosed herein and other possible embodiments, the lesions in the preset site medical image are configured as tumors or other possible lesions (e.g., lung nodules); the value corresponding to each lesion area in the lesion mask image is configured as 1, and the value corresponding to non-lesion areas is configured as 0.

[0047] In the embodiments of this disclosure and other possible embodiments, before training the first preset deep learning segmentation network using a preset number of preset site medical images and their corresponding lesion mask training images to obtain a preset lesion segmentation model, the method includes: using segmentation annotation software CasiaLabeler or Labelme to delineate lesions on a preset number of preset site medical images to obtain corresponding lesion mask training images.

[0048] In the embodiments disclosed herein and other possible embodiments, the preset deep learning segmentation network is configured as one or more deep learning segmentation networks such as Fully Convolutional Network (FCN), U-Net, DeepLab, and Pyramid Spatial Pooling Network (PSPNet).

[0049] The clarity of lesion boundaries is of significant reference value in clinical diagnosis and treatment, including: determining benign or malignant lesions, assessing inflammation and infection, and formulating treatment strategies. Unlike existing technologies, this disclosure proposes a technical solution for determining the clarity of lesion boundaries. This addresses at least one of the following technical problems: the need for manual determination of lesion edge clarity leads to excessive subjectivity; the lack of intelligent determination results in a heavy workload for doctors; and it prevents effective subsequent assessment of the efficacy of radiotherapy.

[0050] In this embodiment of the disclosure, determining whether the lesion boundary is clear based on the lesion mask image includes: performing an erosion operation on the lesion mask in the lesion mask image to obtain a lesion mask erosion image; subtracting the lesion mask erosion image from the lesion mask image to obtain a lesion mask processing image; mapping the lesion location coordinates in the lesion mask processing image to a preset site medical image; calculating multiple gradients corresponding to the lesion location coordinates in the preset site medical image; if the gradient magnitude values ​​corresponding to the multiple gradients are less than a preset gradient magnitude value, the lesion boundary at the location corresponding to the lesion location less than the preset gradient magnitude value is determined to be blurred; otherwise, the lesion boundary at the location corresponding to the preset gradient magnitude value is determined to be clear.

[0051] In this embodiment of the disclosure, determining the gradient magnitude corresponding to the plurality of gradients includes: squaring the plurality of x-direction gradients corresponding to the lesion location coordinates to obtain a plurality of x-direction squared gradients; squaring the plurality of y-direction gradients corresponding to the lesion location coordinates to obtain a plurality of y-direction squared gradients; summing the plurality of x-direction squared gradients with their corresponding y-direction squared gradients to obtain a gradient sum corresponding to the plurality of lesion location coordinates; and taking the square root of the gradient sum corresponding to the plurality of lesion location coordinates to obtain the gradient magnitude corresponding to the plurality of gradients.

[0052] In the embodiments of this disclosure and other possible embodiments, the step of calculating multiple gradients corresponding to the lesion location coordinates in the medical image of the preset location includes: determining multiple first position coordinates and multiple second position coordinates corresponding to both sides of the lesion location coordinates in the x-direction, and multiple third position coordinates and multiple fourth position coordinates corresponding to the y-direction, based on the lesion location coordinates; calculating the differences between the first pixel values ​​corresponding to the multiple first position coordinates and the second pixel values ​​corresponding to the multiple second position coordinates to obtain multiple x-direction gradients corresponding to the lesion location coordinates; calculating the differences between the third pixel values ​​corresponding to the multiple third position coordinates and the fourth pixel values ​​corresponding to the multiple fourth position coordinates to obtain multiple y-direction gradients corresponding to the lesion location coordinates; and configuring the multiple x-direction gradients and their corresponding multiple y-direction gradients as multiple gradients corresponding to the lesion location coordinates.

[0053] In the embodiments disclosed herein and other possible embodiments, determining multiple first position coordinates and multiple second position coordinates corresponding to both sides of the lesion position coordinates in the x-direction of the medical image of the preset site based on the lesion position coordinates includes: using the lesion position coordinates, determining multiple first position coordinates and multiple second position coordinates corresponding to both sides in the x-direction according to a preset distance; and / or, determining multiple third position coordinates and multiple fourth position coordinates corresponding to both sides of the lesion position coordinates in the y-direction of the medical image of the preset site based on the lesion position coordinates includes: using the lesion position coordinates, determining multiple third position coordinates and multiple fourth position coordinates corresponding to both sides in the x-direction according to a preset distance.

[0054] In the embodiments disclosed herein and other possible embodiments, those skilled in the art can configure the preset distance according to actual needs. For example, the lesion location coordinates can be configured as (x1, y1), (x2, y2), ..., (x... n ,y n ), respectively determine the coordinates of multiple first positions (x1+1, y1), (x2+1, y2), ..., (x2+1, y2) in the x-direction on both sides according to the 1 pixel value corresponding to the preset distance. n +1,y n ) and multiple second position coordinates (x1-1, y1), (x2-1, y2), ..., (x n -1,y n For example, the lesion location coordinates are configured as (x1, y1), (x2, y2), ..., (x... n ,y n ), respectively determine the coordinates of multiple first positions (x1, y1+1), (x2, y2+1), ..., (x2, y2+1) in the x-direction on both sides according to the 1 pixel value corresponding to the preset distance. n,y n +1) and multiple second position coordinates (x1, y1-1), (x2, y2-1), ..., (x n ,y n -1).

[0055] In the embodiments disclosed herein and other possible embodiments, those skilled in the art can configure the preset gradient magnitude value according to actual needs. For example, the preset gradient magnitude value can be configured as any value between 2 and 80 or other values.

[0056] In this embodiment of the disclosure, the ratio of the long axis to the short axis of each lesion is calculated based on the long axis and short axis of each lesion in the lesion mask image corresponding to the medical image of the preset location; wherein, the medical image of the preset location is configured as a two-dimensional medical image; if the ratio of the long axis to the short axis is greater than or equal to a first preset ratio of the long axis to the short axis, it is determined that the corresponding lesion has a spike sign.

[0057] The presence of a spiky sign at the lesion margin is of significant clinical importance in indicating the possibility of malignancy, assisting in differential diagnosis, and guiding further examination and treatment. Unlike existing technologies, this disclosure proposes a technical solution for determining the presence of a spiky sign at the lesion margin. This addresses at least one of the following technical problems: the current requirement for manual determination of the presence of a spiky sign at the lesion margin is too subjective; the lack of intelligent determination results in a heavy workload for doctors; and it prevents effective evaluation of subsequent radiotherapy efficacy predictions.

[0058] In this embodiment of the disclosure, based on the major and minor axes of each three-dimensional lesion in the lesion mask image corresponding to the preset site medical image, multiple major-minor axis ratios corresponding to each three-dimensional lesion are calculated; if any one of the major-minor axis ratios is greater than or equal to a first preset major-minor axis ratio, it is determined that the corresponding lesion has a spike sign; wherein, the preset site medical image is configured as a three-dimensional medical image.

[0059] In this embodiment of the disclosure, determining whether a lesion boundary exhibits a spike-like sign based on the lesion mask image includes: determining whether the medical image of a preset location is a two-dimensional or three-dimensional medical image; if the medical image of the preset location is a two-dimensional medical image, then calculating the ratio of the long axis to the short axis of each lesion in the lesion mask image corresponding to the preset location medical image; if the ratio of the long axis to the short axis is greater than or equal to a first preset ratio of the long axis to the short axis, then determining that the corresponding lesion exhibits a spike-like sign; otherwise, determining that the corresponding lesion does not exhibit a spike-like sign; if the medical image of the preset location is a three-dimensional medical image, then calculating multiple ratios of the long axis to the short axis of each three-dimensional lesion in the lesion mask image corresponding to the preset location medical image; if any one of the ratios of the long axis to the short axis is greater than or equal to the first preset ratio of the long axis to the short axis, then determining that the corresponding lesion exhibits a spike-like sign.

[0060] In the embodiments of this disclosure and other possible embodiments, determining the major axis corresponding to each three-dimensional lesion includes: performing three-dimensional reconstruction on each lesion mask in the first lesion mask image to obtain the three-dimensional mask lesion corresponding to each lesion mask; performing edge detection on the three-dimensional mask lesion of each lesion mask to obtain the three-dimensional lesion mask edge; selecting any three-dimensional edge pixel in the three-dimensional lesion mask edge; calculating multiple three-dimensional edge pixel distances between the arbitrary three-dimensional edge pixel and other three-dimensional edge pixel; selecting the maximum three-dimensional edge pixel distance from the multiple three-dimensional edge pixel distances; and configuring the maximum three-dimensional edge pixel distance as the major axis corresponding to each three-dimensional lesion.

[0061] In the embodiments of this disclosure and other possible embodiments, determining the short path corresponding to each lesion includes: performing three-dimensional reconstruction on each lesion mask in the first lesion mask image to obtain a three-dimensional mask lesion corresponding to each lesion mask; performing edge detection on the three-dimensional mask lesions of each lesion mask to obtain the three-dimensional lesion mask edges; selecting any three-dimensional edge pixel in the three-dimensional lesion mask edges; calculating multiple three-dimensional edge pixel distances between the arbitrary three-dimensional edge pixel and other three-dimensional edge pixel points; selecting the minimum three-dimensional edge pixel distance from the multiple three-dimensional edge pixel distances; and configuring the minimum three-dimensional edge pixel distance as the long path corresponding to each three-dimensional lesion.

[0062] In this disclosure and other possible embodiments, it is further included that: if the ratio of the major diameter to the minor diameter is less than the first preset ratio of the major diameter to the minor diameter, then it is determined that the corresponding lesion does not have a spiky sign.

[0063] In this embodiment and other possible embodiments, determining the lesion mask image corresponding to the preset site medical image includes: training a first preset deep learning segmentation network using a preset number of preset site medical training images and their corresponding lesion mask training images to obtain a preset lesion segmentation model; segmenting the lesions in the preset site medical image using the preset lesion segmentation model to obtain the corresponding lesion mask image; and segmenting the arteries using the preset artery segmentation model to obtain the corresponding artery mask image; wherein the lesions in the preset site medical image are configured as lesions to be treated with chemotherapy or lesions to be operated on.

[0064] In the embodiments disclosed herein and other possible embodiments, the mask value corresponding to each lesion region in the lesion mask image and the lesion mask training image is configured as 1, and the mask value corresponding to non-lesion regions is configured as 0.

[0065] In the embodiments of this disclosure and other possible embodiments, before training the first preset deep learning segmentation network using a preset number of preset site medical training images and their corresponding lesion mask training images, the method includes: using segmentation annotation software CasiaLabeler or Labelme to delineate lesions on the preset number of preset site medical training images to obtain corresponding lesion mask training images.

[0066] In the embodiments of this disclosure and other possible embodiments, if there is a spiky sign at the edge of the lesion, determining whether the lesion in the preset location medical image is a lesion to be treated with chemotherapy or a lesion to be operated on includes: detecting whether the boundary of the lesion in the lesion mask image corresponding to the preset location medical image is blurred; if the boundary of the lesion in the lesion mask image is blurred, then the lesion is configured as a lesion to be treated with chemotherapy or a lesion to be operated on.

[0067] In the embodiments disclosed herein and other possible embodiments, if the lesion edge has a spiky sign, determining whether the lesion in the preset location medical image is a lesion to be treated with chemotherapy or a lesion to be operated on includes: detecting whether the lesion boundary in the lesion corresponding to the preset location medical image and the lesion in the arterial mask image is blurred and whether the lesion edge has a spiky sign; if the lesion boundary in the lesion and the arterial mask image is blurred and the lesion edge has a spiky sign, then the lesion is configured as a lesion to be treated with chemotherapy or a lesion to be operated on.

[0068] In the embodiments of this disclosure and other possible embodiments, determining whether the lesion boundary is blurred includes: mapping the lesion location coordinates in the lesion masking image to a preset site medical image; calculating multiple gradients corresponding to the lesion location coordinates in the preset site medical image; if the gradient magnitude value corresponding to the multiple gradients is less than a preset gradient magnitude value, then the lesion boundary where the lesion location corresponding to the lesion location is less than the preset gradient magnitude value is determined to be blurred.

[0069] In the embodiments disclosed herein and other possible embodiments, if the gradient magnitude value corresponding to the plurality of gradients is greater than or equal to a preset gradient magnitude value, then the boundary of the lesion location corresponding to the lesion location that is greater than or equal to the preset gradient magnitude value is clearly determined.

[0070] In the embodiments of this disclosure and other possible embodiments, before mapping the lesion location coordinates in the lesion masking image to the preset site medical image, the method includes: performing an erosion operation on the lesion mask in the lesion masking image corresponding to the preset site medical image to obtain a lesion mask erosion image; and subtracting the lesion mask erosion image from the lesion masking image to obtain the lesion masking image.

[0071] In this embodiment of the disclosure, if the lesion boundary is blurred and a spiky sign is present, the risk of the lesion location invading the artery is assessed using the lesion mask image and the arterial mask image corresponding to the medical image of the preset location. This includes: extracting multiple spiky point coordinates corresponding to multiple spiky points in the lesion mask image and arterial mask edge coordinates corresponding to the arterial mask edge in the arterial mask image; calculating multiple distances between the multiple spiky point coordinates and the arterial mask edge coordinates; and determining that the spiky point corresponding to the lesion poses a risk of invading the artery if the minimum distance among the multiple distances is less than a preset distance.

[0072] In this embodiment of the disclosure, determining whether the spinous process corresponding to the lesion poses a risk of invading the artery based on the lesion mask and artery mask image corresponding to the medical image of the preset location includes: extracting multiple spinous process position coordinates corresponding to multiple spinous processes and artery mask edge position coordinates corresponding to the artery mask edge in the lesion mask and artery mask images; calculating multiple distances between the multiple spinous process position coordinates and the artery mask edge position coordinates respectively; if the minimum distance among the multiple distances is less than a preset distance, it is determined that the spinous process corresponding to the lesion poses a risk of invading the artery.

[0073] In this embodiment of the disclosure, the method for assessing chemotherapy in critically ill patients further includes: if the spinous process corresponding to the lesion poses a risk of invading arteries, then the spinous process is determined to be a dangerous spinous process.

[0074] In this embodiment of the disclosure, determining the spike includes: detecting the edge of the lesion mask in the lesion mask image to obtain the edge line of the lesion mask; calculating the first pixel distance and the second pixel distance between any lesion mask edge pixel on the edge line of the lesion mask and its adjacent lesion mask edge pixels; if the first pixel distance and the second pixel distance are greater than a set pixel distance, then the arbitrary lesion mask edge pixel is configured as a spike.

[0075] In this disclosure and other possible embodiments, determining whether the location of the lesion to be treated or operated on, based on the lesion mask image and the arterial mask image, poses a risk of invading the arterial vessels includes: calculating multiple positional distances between the arterial vessel edge mask coordinates corresponding to the arterial vessel mask image and the lesion edge mask coordinates corresponding to the lesion mask image; if the minimum positional distance among the multiple positional distances is less than or equal to a preset positional distance, it is determined that the lesion location poses a risk of invading the arterial vessels; otherwise, it is determined that the lesion location is far from the arterial vessels. The arterial vessel edge mask coordinates and the lesion edge mask coordinates corresponding to the lesion are respectively configured as the position coordinates of the arterial vessel edge in the arterial vessel edge mask image corresponding to the arterial vessel mask image and the position coordinates of the lesion edge mask in the lesion edge mask image corresponding to the lesion mask image.

[0076] In this embodiment and other possible embodiments, determining whether the location of the lesion to be treated or operated on, based on the lesion mask and arterial mask images, poses a risk of invading arteries includes: calculating multiple distances between the arterial vessel edge mask coordinates and the lesion edge mask coordinates corresponding to the lesion mask and arterial mask images; if the minimum distance among the multiple distances is less than or equal to a preset distance, it is determined that the lesion location poses a risk of invading arteries; otherwise, it is determined that the lesion location is far from arteries. The arterial vessel edge mask coordinates and the lesion edge mask coordinates corresponding to the lesion are respectively configured as the arterial vessel edge coordinates in the arterial vessel edge mask and the lesion edge mask coordinates in the lesion edge mask.

[0077] In the embodiments disclosed herein and other possible embodiments, those skilled in the art can configure the preset position distance according to actual needs. For example, the preset position distance can be any value between 0 and 10 pixels or other values.

[0078] In the embodiments of this disclosure and other possible embodiments, the step of determining the lesion mask image and arterial mask image corresponding to the lesion to be treated or the lesion to be operated on using medical images of preset locations includes: training a first preset deep learning segmentation network using a preset number of preset location medical training images and their corresponding lesion mask training images to obtain a preset lesion segmentation model; training a second preset deep learning segmentation network using a preset number of preset location medical training images and their corresponding arterial mask training images to obtain a preset arterial segmentation model; segmenting the lesion to be treated or the lesion to be operated on in the preset location medical images using the preset lesion segmentation model to obtain the corresponding lesion mask image; and segmenting the arteries using the preset arterial segmentation model to obtain the corresponding arterial mask image.

[0079] In the embodiments disclosed herein and other possible embodiments, the step of determining the lesion mask and arterial mask images corresponding to the lesion to be treated or the lesion to be operated on using medical images of preset locations includes: training a preset deep learning segmentation network using a preset number of preset location medical training images and their corresponding lesion mask and arterial mask training images to obtain a preset lesion and arterial segmentation model; and segmenting the lesion to be treated or the lesion to be operated on and the arterial vessels using the preset lesion and arterial segmentation model to obtain the corresponding lesion mask and arterial mask images.

[0080] In the embodiments disclosed herein and other possible embodiments, the mask value corresponding to each lesion region in the lesion mask image and the lesion mask training image is configured as 1, and the mask value corresponding to the non-lesion region is configured as 0; similarly, the mask value corresponding to the artery in the artery mask image and the artery mask training image is configured as 1, and the mask value corresponding to the non-artery region is configured as 0.

[0081] In the embodiments disclosed herein and other possible embodiments, the mask value corresponding to each lesion region in the lesion mask and artery mask image and the lesion mask and artery mask training image is configured as 1, the mask value corresponding to the artery is configured as 2, and the mask value corresponding to the non-lesion region and non-artery region is configured as 0.

[0082] In the embodiments of this disclosure and other possible embodiments, before training the first preset deep learning segmentation network using a preset number of preset site medical training images and their corresponding lesion mask training images, the method includes: using segmentation annotation software CasiaLabeler or Labelme to delineate lesions on the preset number of preset site medical training images to obtain corresponding lesion mask training images.

[0083] In the embodiments of this disclosure and other possible embodiments, before training the second preset deep learning segmentation network using a preset number of preset site medical training images and their corresponding arterial blood vessel mask training images, the method includes: using segmentation annotation software CasiaLabeler or Labelme to delineate arteries and blood vessels in the preset number of preset site medical training images to obtain corresponding arterial blood vessel mask training images.

[0084] In the embodiments of this disclosure and other possible embodiments, before training the preset deep learning segmentation network using a preset number of preset site medical training images and their corresponding lesion masks and artery mask training images, the method includes: using segmentation annotation software CasiaLabeler or Labelme to delineate lesions and arteries in the preset number of preset site medical training images to obtain corresponding lesion masks and artery mask training images.

[0085] In the embodiments disclosed herein and other possible embodiments, the preset deep learning segmentation network, the first preset deep learning segmentation network and the second preset deep learning segmentation network are configured as one or more deep learning segmentation networks such as Fully Convolutional Network (FCN), U-Net, DeepLab, Pyramid Spatial Pooling Network (PSPNet).

[0086] Figure 2 A flowchart illustrating a method for monitoring critically ill patients according to an embodiment of this disclosure is shown. Figure 2 As shown, the critical patient monitoring method includes: Step 104: using the above-mentioned critical patient chemotherapy assessment method, assessing whether the lesion location of the critical patient undergoing chemotherapy poses a risk of invading arteries in the medical image of the preset site; Step 105: if the lesion location poses a risk of invading arteries, extracting one or more imaging features from the medical image of the preset site, such as the average gray value corresponding to the lesion, the ratio of the long diameter to the short diameter corresponding to the lesion, whether the lesion location poses a risk of invading arteries, and whether the lesion edge has a spiky sign, to predict the radiotherapy efficacy.

[0087] In this embodiment of the disclosure, the step of predicting radiotherapy efficacy using one or more imaging features extracted from the medical image of the preset location, including the average gray value corresponding to the lesion, the ratio of the major axis to the minor axis corresponding to the lesion, whether the lesion location poses a risk of invading arteries, and whether the lesion edge has a spike-like sign, includes: determining whether the lesion type corresponding to the medical image of the preset location has a similar lesion type on the medical image of the preset location; if so, determining the imaging features used to distinguish the lesion type from the similar lesion type; and using the preset radiotherapy efficacy prediction model and the imaging features to predict the radiotherapy efficacy of the medical image of the preset location.

[0088] In this embodiment of the disclosure, the critical patient monitoring method includes: using the above-mentioned critical patient chemotherapy assessment method to assess whether the lesion location of the critical patient undergoing chemotherapy poses a risk of invading arteries in a preset site medical image; if the lesion location poses a risk of invading arteries, then determining whether the artery passes through the lesion undergoing chemotherapy or surgery based on the lesion mask area corresponding to the lesion undergoing chemotherapy or surgery and the artery mask area corresponding to the artery.

[0089] In this embodiment of the disclosure, determining whether the artery passes through the lesion to be treated or operated on, based on the lesion mask region corresponding to the lesion to be treated or operated on and the artery mask region corresponding to the artery, includes: extracting the lesion mask position coordinates corresponding to the lesion mask region of the lesion to be treated or operated on and the artery mask region of the artery to be treated, respectively; if the artery mask position coordinates and the lesion mask position coordinates overlap, it is determined that the artery passes through the lesion to be treated or operated on; otherwise, it is determined that the artery does not pass through the lesion to be treated or operated on.

[0090] In the embodiments disclosed herein and other possible embodiments, if the artery passes through the lesion to be treated with chemotherapy or the lesion to be operated on, radiotherapy is performed on the artery passing through the lesion under ultrasound image guidance at a first radiotherapy dose, and radiotherapy is performed on the lesion outside the artery under ultrasound image guidance at a second radiotherapy dose lower than the first radiotherapy dose. This addresses the issue that tumor cells corresponding to the lesion may be affected by blood flow in the blood vessels, and the concentration of chemotherapy drugs in the local tumor area may be easily diluted, leading to reduced efficacy and increased risk of residual cancer cells and recurrence.

[0091] In the embodiments of this disclosure and other possible embodiments, determining the imaging features used to distinguish the lesion type from the similar lesion type includes: extracting multiple first imaging parameters to be distinguished from lesions in multiple first preset locations to be distinguished corresponding to the lesion type, and multiple second imaging parameters to be distinguished from lesions in multiple second preset locations to be distinguished corresponding to the similar lesion type; determining corresponding quantitative imaging parameters and count imaging parameters based on the multiple first imaging parameters to be distinguished and the multiple second imaging parameters to be distinguished; and using a feature filtering algorithm to filter the risk factor imaging parameters constructed from the quantitative imaging parameters and the count imaging parameters to obtain imaging features used to distinguish the lesion type from the similar lesion type.

[0092] For example, if the lesion type in the CT scan of the vertebral body corresponding to the preset site medical image is configured as osteoblastic bone metastasis, then the similar lesion type is configured as bone island. If the lesion type in the CT scan of the chest or X-ray scan of the chest corresponding to the preset site medical image is configured as pneumonia (common pneumonia), then the similar lesion type is configured as novel coronavirus infection. If the lesion type in the CT scan of the chest or X-ray scan of the chest corresponding to the preset site medical image is configured as ground-glass nodule, then the similar lesion type is configured as solid nodule or mixed ground-glass nodule. If the lesion type in the CT scan of the chest or X-ray scan of the chest corresponding to the preset site medical image is ground-glass nodule corresponding to lung inflammation, then the similar lesion type is configured as ground-glass nodule corresponding to early lung cancer.

[0093] For example, the imaging features used to distinguish the type of lesion from the similar lesion types are configured as one or more imaging features corresponding to the imaging features used to differentiate osteogenic bone metastases from bone islands, such as the average effective atomic number value, the average CT value corresponding to the lesion, the ratio of the long axis to the short axis of the lesion with the largest cross-sectional area, whether the lesion boundary is clear, whether the lesion location is adjacent to the bone cortex, and whether there is a spinous process sign at the edge of the lesion.

[0094] Osteoblastic bone metastases commonly occur in tumors such as prostate cancer, breast cancer, and kidney cancer, accounting for 10% of all bone metastases. Bone metastases are classified into osteolytic metastases, osteoblastic metastases, and mixed metastases. Among these, diagnosing osteoblastic bone metastases is a challenge in current imaging diagnostics, as it is easily confused with diseases such as bone islands. Symptoms of bone metastases include persistent and severe bone pain, pathological fractures and limited mobility, severe hypercalcemia, and compression of adjacent spinal cords and nerves. Failure to make a clear diagnosis and treat bone metastases in a timely manner can pose a significant risk to the patient's life and reduce their quality of life. Currently, bone metastases are often diagnosed through a clear history of the primary tumor, commonly used imaging diagnostic techniques (DR, CT, MR), emission CT (ECT), or positron emission tomography (PET). The shortcomings of existing technologies are summarized as follows: (1) Osteolytic and mixed metastatic bone metastases both appear as bone destruction on DR (Digital Radiography) and CT (Computed Tomography). The bone destruction is shown as a low-density or mixed low-density lesion, and soft tissue masses may be present around the bone destruction; (2) Osteolytic and mixed metastatic bone metastases often appear as long T1 and long T2 signals on MR (Magnetic Resonance Imaging). Diffusion-restricted areas can be seen on diffusion sequences, and enhanced MR scans can show different degrees of enhancement of bone destruction and surrounding soft tissue masses. However, osteoblastic bone metastases and bone islands are very similar in imaging. These lesions are high-density on both DR and CT (CT has higher image resolution), while they are generally low-signal on various MR sequences. Therefore, it is often difficult to accurately diagnose and differentiate osteoblastic bone metastases and bone islands using MR.

[0095] Currently, the main treatment for bone metastases is symptomatic drug therapy. If a clear therapeutic effect is not achieved, radiotherapy, chemotherapy, and immunotherapy are required. Chemotherapy for bone metastases often fails to completely cure the tumor and can only be used to relieve symptoms and improve the patient's quality of life. For significant therapeutic effects on local bone metastases, local radiotherapy to the metastatic area is often necessary. When assessing the effectiveness of local radiotherapy, osteolytic and mixed metastatic bone metastases can be evaluated by changes in the size of the corresponding tumor lesion; however, this assessment method is not applicable to osteoblastic bone metastases. After radiotherapy, although the internal tumor tissue of osteoblastic bone metastases has undergone necrosis, changes in the size and density of the corresponding tumor lesion are often not significant due to ossification or bone hyperplasia. Therefore, current technology cannot accurately assess the radiotherapy effect on osteoblastic bone metastases.

[0096] Furthermore, while radionuclide imaging (CT) can diagnose all bone metastases, including osteoblastic bone metastases, it requires intravenous injection of radiolabeled phosphate compounds. PET scans also require the injection of radioactive drugs and are very expensive. Therefore, these techniques are not suitable for patients with bone metastases who are allergic to radiopharmaceuticals, pregnant or breastfeeding women, have severe cardiopulmonary or hepatic / renal insufficiency, or are financially disadvantaged. In addition, radioactive drugs pose a risk not only to the patient's own healthy tissues but also to the surrounding environment and the general population.

[0097] In the embodiments of this disclosure and other possible embodiments, determining the corresponding quantitative and count parameters based on the plurality of first and second radiographic parameters to be differentiated includes: grouping the plurality of first and second radiographic parameters to be differentiated according to quantitative and count principles to obtain a first group of quantitative radiographic parameters to be processed and a second group of count radiographic parameters to be processed; performing an independent samples t-test on the first group of quantitative radiographic parameters to be processed and the second group of count radiographic parameters to be processed, and selecting quantitative radiographic parameters with a significance level less than or equal to a first preset significance level from the first group of quantitative radiographic parameters to be processed or the second group of count radiographic parameters to be processed; performing a chi-square test on the first group of quantitative radiographic parameters to be processed and the second group of count radiographic parameters to be processed, and selecting count radiographic parameters with a significance level less than or equal to a second preset significance level from the first group of quantitative radiographic parameters to be processed or the second group of count radiographic parameters to be processed; wherein the feature selection algorithm is configured as a multi-factor logistic regression analysis algorithm or a LASSO (Least Absolute Shrinkage and Selection Operator) algorithm.

[0098] In the embodiments disclosed herein and other possible embodiments, the imaging features used to distinguish the lesion type from the similar lesion type include: the average gray value corresponding to the lesion, the ratio of the long diameter to the short diameter corresponding to the lesion, whether the lesion location poses a risk of invading arteries, and whether the lesion edge has a spiky sign, or one or more of these imaging features.

[0099] In the embodiments of this disclosure and other possible embodiments, determining the average gray value corresponding to the lesion includes: performing a pixel-level multiplication operation on the medical image of the preset location and its corresponding lesion mask image to obtain a lesion medical image; calculating the average pixel value of the lesion medical image to obtain the average gray value corresponding to the lesion.

[0100] In the embodiments of this disclosure and other possible embodiments, when the preset site medical image is configured as a preset site spectral CT scan image, the imaging features used to distinguish the lesion type from the similar lesion type further include: the average effective atomic number value.

[0101] In the embodiments of this disclosure and other possible embodiments, extracting the average effective atomic number value corresponding to the lesion includes: using an energy spectrum CT atomic number analysis module configured with energy spectrum CT images to extract the average effective atomic number value corresponding to the lesion based on the energy spectrum CT scan image of the preset location and the corresponding lesion mask image.

[0102] In the embodiments of this disclosure and other possible embodiments, the spectral CT atomic number analysis module configured using spectral CT images extracts the average effective atomic number value corresponding to the lesion based on the spectral CT scan image of the preset location and its corresponding lesion mask image. This includes: using the spectral CT atomic number analysis module configured using spectral CT images to extract quantitative bar charts of atomic number corresponding to each component within each lesion generated from the spectral CT scan image of the preset location and its corresponding lesion mask image; determining the effective atomic number value of each component within each lesion based on multiple peak values ​​corresponding to the quantitative bar charts of atomic number corresponding to each component within each lesion; and averaging the effective atomic number values ​​of all components within all lesions to determine the average effective atomic number value of all components within the lesion corresponding to the spectral CT scan image of the preset location.

[0103] In the embodiments of this disclosure and other possible embodiments, the step of extracting a quantitative bar chart of the atomic number corresponding to each component within each lesion generated from the spectral CT scan image of the preset location based on each first spectral CT scan vertebral body image and its corresponding lesion mask image in the spectral CT scan image of the preset location includes: performing pixel-level multiplication operations on the spectral CT scan image of the preset location and its corresponding lesion mask image to obtain the spectral CT scan lesion image; and obtaining a quantitative bar chart of the atomic number corresponding to each component within each lesion generated from the spectral CT scan vertebral body image based on the spectral CT scan lesion image.

[0104] In the embodiments of this disclosure and other possible embodiments, the average CT value corresponding to the lesion is extracted based on the preset site spectral CT scan image and the lesion mask image, including: performing pixel-level multiplication operations on the preset site spectral CT scan image and its corresponding lesion mask image to obtain a first spectral CT scan lesion image corresponding to the preset site spectral CT scan image; calculating the CT value of each lesion corresponding to the first spectral CT scan lesion image; and averaging the CT values ​​of each lesion to determine the average CT value corresponding to the lesion.

[0105] In the embodiments of this disclosure and other possible embodiments, determining the preset radiotherapy efficacy prediction model includes: obtaining a preset number of imaging features corresponding to a first time moment for distinguishing the lesion type from the similar lesion type and radiotherapy efficacy prediction labels corresponding to a second time moment after the first time moment; training a preset prediction network or a preset predictor to obtain the preset radiotherapy efficacy prediction model.

[0106] In the embodiments of this disclosure and other possible embodiments, the radiotherapy efficacy prediction label can be configured as a radiotherapy efficacy prediction grading label. For example, when predicting the grading of radiotherapy efficacy for osteoblastic bone metastases, the radiotherapy efficacy prediction label can be configured as one or more of complete remission (CR), partial remission (PR), stable disease (SD), and progressive disease (PD). Complete remission (CR) is characterized by X-ray, CT, or MRI showing complete sclerosis of the osteoblastic lesion, normalized bone density, normalized bone signal intensity, and normalized bone imaging tracer uptake; clinically, it is characterized by complete disappearance of pain, no need for analgesics, and basic functional recovery. Partial remission (PR) is characterized by X-ray, CT, or MRI showing sclerosis or partial sclerosis filling at the edge of the osteoblastic lesion, or a measurable lesion shrinkage of ≥50%, or a subjective shrinkage of ≥50% for unmeasurable lesions; a subjective reduction of ≥50% in bone imaging tracer uptake; and clinically, it is characterized by significant pain reduction, reduced use of analgesics, and partial functional recovery. Stable disease (SD) is characterized by an increase of <25% or decrease of <50% in measurable lesion size on imaging, an increase of ≤25% and a decrease of ≤50% in unmeasurable lesion size, and no new bone metastases. Clinically, pain is not significantly changed or slightly improved, and function is basically stable. Progressive disease (PD) is characterized by an increase of ≥25% in measurable lesion size on X-ray, CT, or MRI, a subjective increase of ≥25% in unmeasurable lesion size, or an increase of ≥25% in bone scintigraphy tracer uptake. New bone metastases may also be present. Clinically, pain may worsen, function may deteriorate, or new bone-related events (such as pathological fractures or spinal cord compression) may occur.

[0107] In the embodiments disclosed herein and other possible embodiments, the preset prediction network or preset predictor may be configured as one or more of the following: decision tree classifier, random forest classifier, fully connected neural network (FCN), recurrent neural network (RNN), support vector machine (SVM), K-nearest neighbor algorithm (KNN).

[0108] The execution entity for patient chemotherapy assessment and critical patient monitoring methods can be an image processing device. For example, these methods can be executed by a terminal device, server, or other processing equipment. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, vehicle-mounted device, wearable device, etc. In some possible implementations, these methods can be implemented by a processor calling computer-readable instructions stored in memory.

[0109] Those skilled in the art will understand that in the above-described methods for assessing chemotherapy in critically ill patients and for monitoring critically ill patients in specific embodiments, the order in which each step is written does not imply a strict order of execution and does not constitute any limitation on the implementation process. The specific order of execution of each step should be determined by its function and possible internal logic.

[0110] Figure 3 A block diagram illustrating a chemotherapy assessment method for critically ill patients according to an embodiment of this disclosure is shown. Figure 3 As shown, the critical patient chemotherapy assessment system includes: a lesion mask image extraction unit 10, used to extract the lesion mask image corresponding to the lesion from a preset site medical image of a critically ill patient to be treated with chemotherapy; a first determination unit 11, used to determine whether the lesion boundary is clear and whether there is a spike sign at the edge of the lesion based on the lesion mask image; and a first assessment unit 12, used to assess whether there is a risk of invasion of arteries by the lesion location if the lesion boundary is blurred and there is a spike sign, using the lesion mask image and the arterial blood vessel mask image corresponding to the preset site medical image.

[0111] According to one aspect of this disclosure, a chemotherapy assessment system for critically ill patients is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the aforementioned chemotherapy assessment method for critically ill patients.

[0112] According to one aspect of this disclosure, a chemotherapy assessment system for critically ill patients is provided, comprising: a computer-readable storage medium having a computer program / instructions and a bit stream stored thereon, wherein the computer program / instructions, when executed by a processor, generate the bit stream in accordance with the aforementioned chemotherapy assessment method for critically ill patients.

[0113] According to one aspect of this disclosure, a chemotherapy assessment system for critically ill patients is provided, comprising: a computer program product configured with a computer program / instruction that, when executed by a processor, implements the aforementioned chemotherapy assessment method for critically ill patients.

[0114] Figure 4 A block diagram illustrating a method for monitoring critically ill patients according to an embodiment of this disclosure is shown. Figure 4 As shown, the critical patient monitoring system includes: a second assessment unit 13, used to assess whether there is a risk of lesion location in the preset site medical image of the critical patient to be treated for chemotherapy using the above-mentioned critical patient chemotherapy assessment method; and a radiotherapy efficacy prediction unit 14, used to extract one or more imaging features from the preset site medical image, such as the average gray value corresponding to the lesion, the ratio of the long diameter to the short diameter corresponding to the lesion, whether there is a risk of lesion location invading arteries, and whether there is a spike sign at the edge of the lesion, if there is a risk of lesion location invading arteries, to predict the radiotherapy efficacy.

[0115] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a third assessment unit, configured to assess whether there is a risk of lesion location in a preset site corresponding to the critical patient undergoing chemotherapy using the aforementioned critical patient chemotherapy assessment method; a second determination unit, configured to determine whether the artery passes through the lesion to be treated or the lesion to be operated on, based on the lesion mask area corresponding to the lesion to be treated or the lesion to be operated on and the artery mask area corresponding to the artery; and a radiotherapy unit, configured to, if the artery passes through the lesion to be treated or the lesion to be operated on, perform radiotherapy on the artery passing through the lesion to be treated or the lesion to be operated on under ultrasound image guidance with a first radiotherapy dose, and perform radiotherapy on the lesion outside the artery under ultrasound image guidance with a second radiotherapy dose less than the first radiotherapy dose.

[0116] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the aforementioned critical patient monitoring method.

[0117] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a computer-readable storage medium having a computer program / instructions and a bit stream stored thereon, wherein the computer program / instructions, when executed by a processor, implement the above-described critical patient monitoring method to generate the bit stream.

[0118] According to one aspect of this disclosure, a critical patient monitoring system is provided, comprising: a computer program product configured with a computer program / instruction, which, when executed by a processor, implements the aforementioned critical patient monitoring method.

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0120] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for assessing chemotherapy in critically ill patients, characterized in that, include: Extract the lesion mask image corresponding to the lesion from medical images of preset sites in critically ill patients awaiting chemotherapy; Based on the lesion mask image, determine whether the lesion boundary is clear and whether there is a spiky sign at the edge of the lesion; If the lesion has blurred boundaries and exhibits a spike-like appearance, the lesion mask image and the arterial mask image corresponding to the preset site medical image are used to assess whether the lesion location poses a risk of invading the arterial vessels.

2. The method for assessing chemotherapy in critically ill patients according to claim 1, characterized in that, The step of extracting the lesion mask image corresponding to the lesion from a preset medical image of a critically ill patient awaiting chemotherapy includes: segmenting the preset medical image using a preset lesion segmentation model to obtain the lesion mask image corresponding to the preset medical image; and / or, Before segmenting the medical image of the preset location using the preset lesion segmentation model to obtain the lesion mask image corresponding to the medical image of the preset location, the method includes: training a first preset deep learning segmentation network using a preset number of medical images of the preset location and their corresponding lesion mask training images to obtain the preset lesion segmentation model.

3. The method for assessing chemotherapy in critically ill patients according to any one of claims 1 or 2, characterized in that, Determining whether the lesion boundary is clear based on the lesion mask image includes: performing an erosion operation on the lesion mask in the lesion mask image to obtain an eroded lesion mask image; subtracting the eroded lesion mask image from the lesion mask image to obtain a processed lesion mask image; mapping the lesion location coordinates in the processed lesion mask image to a preset medical image; calculating multiple gradients corresponding to the lesion location coordinates in the preset medical image; if the gradient magnitude values ​​corresponding to the multiple gradients are less than a preset gradient magnitude value, the lesion boundary at the location corresponding to the lesion location with a gradient magnitude value less than the preset gradient magnitude value is determined to be blurred; otherwise, the lesion boundary at the location corresponding to the preset gradient magnitude value is determined to be clear; and / or, Determining the gradient magnitude corresponding to the plurality of gradients includes: squaring the plurality of x-direction gradients corresponding to the lesion location coordinates to obtain a plurality of x-direction squared gradients; squaring the plurality of y-direction gradients corresponding to the lesion location coordinates to obtain a plurality of y-direction squared gradients; summing the plurality of x-direction squared gradients with their corresponding y-direction squared gradients to obtain a gradient sum corresponding to the plurality of lesion location coordinates; and taking the square root of the gradient sum corresponding to the plurality of lesion location coordinates to obtain the gradient magnitude corresponding to the plurality of gradients.

4. The method for assessing chemotherapy in critically ill patients according to any one of claims 1-3, characterized in that, Based on the major and minor axes of each lesion in the lesion mask image corresponding to the medical image of the preset location, the ratio of the major axis to the minor axis for each lesion is calculated; wherein, the medical image of the preset location is configured as a two-dimensional medical image; if the ratio of the major axis to the minor axis is greater than or equal to a first preset ratio of the major axis to the minor axis, then the corresponding lesion is determined to have a spike sign; or, Based on the major and minor axes of each three-dimensional lesion in the lesion mask image corresponding to the preset site medical image, calculate multiple major-to-minor axis ratios for each three-dimensional lesion; if any one of the major-to-minor axis ratios is greater than or equal to a first preset major-to-minor axis ratio, then the corresponding lesion is determined to have a spike-like sign; wherein, the preset site medical image is configured as a three-dimensional medical image; or, Determining whether a spiky sign exists at the lesion boundary based on the lesion mask image includes: determining whether the medical image of the preset site is a two-dimensional or three-dimensional medical image; if the medical image of the preset site is a two-dimensional medical image, then calculating the ratio of the long axis to the short axis of each lesion based on the long axis and short axis of each lesion in the lesion mask image corresponding to the preset site medical image; if the ratio of the long axis to the short axis is greater than or equal to a first preset ratio of the long axis to the short axis, then determining that the corresponding lesion has a spiky sign; otherwise, determining that the corresponding lesion does not have a spiky sign; if the medical image of the preset site is a three-dimensional medical image, then calculating multiple ratios of the long axis to the short axis of each three-dimensional lesion based on the long axis and short axis of each three-dimensional lesion in the lesion mask image corresponding to the preset site medical image; if any one of the ratios of the long axis to the short axis is greater than or equal to the first preset ratio of the long axis to the short axis, then determining that the corresponding lesion has a spiky sign.

5. The method for assessing chemotherapy in critically ill patients according to any one of claims 1-4, characterized in that, If the lesion boundary is blurred and a spiky sign is present, then the risk of lesion invasion of arteries is assessed using the lesion mask image and the arterial mask image corresponding to the medical image of the preset location. This includes: extracting multiple spiky point coordinates corresponding to multiple spiky points in the lesion mask image and arterial mask edge coordinates corresponding to the arterial mask edge in the arterial mask image; calculating multiple distances between the multiple spiky point coordinates and the arterial mask edge coordinates; if the minimum distance among the multiple distances is less than a preset distance, it is determined that the spiky point corresponding to the lesion poses a risk of arterial invasion; or, The method of determining whether the spinous process corresponding to the lesion poses a risk of invading the artery based on the lesion mask and artery mask image corresponding to the preset site medical image includes: extracting multiple spinous process position coordinates corresponding to multiple spinous processes and artery mask edge position coordinates corresponding to the artery mask edge in the lesion mask and artery mask images; calculating multiple distances between the multiple spinous process position coordinates and the artery mask edge position coordinates respectively; if the minimum distance among the multiple distances is less than a preset distance, it is determined that the spinous process corresponding to the lesion poses a risk of invading the artery.

6. The method for assessing chemotherapy in critically ill patients according to claim 5, characterized in that, Also includes: If the spinous process corresponding to the lesion poses a risk of invading arteries, then the spinous process is determined to be a dangerous spinous process. And / or, Determining the thorn includes: detecting the edge of the lesion mask in the lesion mask image to obtain the lesion mask edge line; calculating the first pixel distance and the second pixel distance between any lesion mask edge pixel on the lesion mask edge line and its adjacent lesion mask edge pixels; if the first pixel distance and the second pixel distance are greater than a set pixel distance, then the arbitrary lesion mask edge pixel is configured as a thorn.

7. A method for monitoring critically ill patients, characterized in that, include: The method for assessing chemotherapy in critically ill patients according to any one of claims 1-6 is used to assess whether there is a risk of lesion location to invade arteries in the medical images of the critically ill patients to be treated with chemotherapy; If the lesion location poses a risk of invading arteries, one or more imaging features are extracted from the medical image of the preset location: the average gray value corresponding to the lesion, the ratio of the long diameter to the short diameter corresponding to the lesion, whether the lesion location poses a risk of invading arteries, and whether the lesion edge has a spiky sign, to predict the efficacy of radiotherapy.

8. The method for monitoring critically ill patients according to claim 7, characterized in that, The method of predicting radiotherapy efficacy using one or more imaging features extracted from the medical image of the preset location, including the average gray value corresponding to the lesion, the ratio of the long axis to the short axis corresponding to the lesion, whether the lesion location poses a risk of invading arteries, and whether the lesion edge has a spike-like sign, includes: determining whether the lesion type corresponding to the medical image of the preset location has a similar lesion type on the medical image of the preset location; if so, determining the imaging features used to distinguish the lesion type from the similar lesion type; using the preset radiotherapy efficacy prediction model and the imaging features to predict the radiotherapy efficacy of the medical image of the preset location; and / or, It also includes: determining whether the artery passes through the lesion to be treated or operated on based on the lesion mask region corresponding to the lesion to be treated or operated on and the artery mask region corresponding to the artery; and / or, determining whether the artery passes through the lesion to be treated or operated on based on the lesion mask region corresponding to the lesion to be treated or operated on and the artery mask region corresponding to the artery includes: extracting the lesion mask position coordinates corresponding to the lesion mask region of the lesion to be treated or operated on and the artery mask region corresponding to the artery; if the artery mask position coordinates overlap with the lesion mask position coordinates, then it is determined that the artery passes through the lesion to be treated or operated on; otherwise, it is determined that the artery does not pass through the lesion to be treated or operated on.

9. A chemotherapy assessment system for critically ill patients, characterized in that, include: The lesion mask image extraction unit is used to extract the lesion mask image corresponding to the lesion from the medical image of the preset site of the critically ill patient to be treated with chemotherapy; The first determining unit is used to determine, based on the lesion mask image, whether the lesion boundary is clear and whether there is a spike-like sign at the lesion edge; the first evaluating unit is used to, if the lesion boundary is blurred and a spike-like sign is present, to evaluate whether there is a risk of lesion location invading arteries using the lesion mask image and the arterial vessel mask image corresponding to the preset site medical image; or, The method comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the chemotherapy assessment method for critically ill patients according to any one of claims 1-6; or, it comprises: a computer-readable storage medium having a computer program / instructions and a bit stream stored thereon, wherein the computer program / instructions, when executed by a processor, implement the chemotherapy assessment method for critically ill patients according to any one of claims 1-6 to generate the bit stream; or, it comprises: a computer program product having a computer program / instructions configured to implement the chemotherapy assessment method for critically ill patients according to any one of claims 1-6 when executed by a processor.

10. A critical patient monitoring system, characterized in that, include: The second assessment unit is used to assess whether there is a risk of lesion location in the medical image of the critically ill patient to be treated for chemotherapy using the chemotherapy assessment method for critically ill patients according to any one of claims 1-6; the radiotherapy efficacy prediction unit is used to extract one or more imaging features from the medical image of the preset location, such as the average gray value corresponding to the lesion, the ratio of the long diameter to the short diameter corresponding to the lesion, whether there is a risk of lesion location invading arteries, and whether there is a spike sign at the edge of the lesion, if there is a risk of lesion location invading arteries, to predict the radiotherapy efficacy. or, The third assessment unit is used to assess whether there is a risk of lesion location in the medical image of the critically ill patient undergoing chemotherapy according to any one of claims 1-6, based on the lesion mask area corresponding to the lesion to be treated or the lesion to be operated on, and the artery mask area corresponding to the artery; the second determination unit is used to determine whether the artery passes through the lesion to be treated or the lesion to be operated on, based on the lesion mask area corresponding to the lesion to be treated or the lesion to be operated on, and the artery mask area corresponding to the artery; the radiotherapy unit is used to, if the artery passes through the lesion to be treated or the lesion to be operated on, perform radiotherapy on the artery passing through the lesion to be treated or the lesion to be operated on under ultrasound image guidance with a first radiotherapy dose, and perform radiotherapy on the lesion outside the artery under ultrasound image guidance with a second radiotherapy dose less than the first radiotherapy dose; or The method comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to execute the critical patient monitoring method of claim 7 or 8; or, it comprises: a computer-readable storage medium having a computer program / instructions and a bit stream stored thereon, wherein the computer program / instructions, when executed by a processor, implement the critical patient monitoring method of claim 7 or 8 to generate the bit stream; or, it comprises: a computer program product having a computer program / instructions configured thereon, wherein the computer program / instructions, when executed by a processor, implement the critical patient monitoring method of claim 7 or 8.

Images