Medical image processing device, medical image processing method, and program

Abstract

Provided are a medical image processing device, medical image processing method, and program in which useful distance information for lesion assessment can be presented with medical images. This medical image processing device according to one embodiment of the present disclosure comprises a processor and a storage device. The processor acquires a three-dimensional medical image by executing an instruction of a program stored in the storage device, accepts input of information indicating a lesion region contained in the medical image, determines a measurement reference plane serving as the measurement reference for lesion assessment from the medical image, three-dimensionally measures the distance between the lesion region and measurement reference plane, and displays, with the medical image, measurement results including information indicating at least one of the closest distance and farthest distance between the lesion region and measurement reference plane.

Description

Technical Field

[0001] The present disclosure relates to a medical image processing apparatus, a medical image processing method, and a program, and particularly relates to image processing technology and user interface technology that handle three-dimensional medical images. Background Art

[0002] Patent Document 1 describes a medical image processing apparatus that accurately determines infiltration of a tumor into tubular tissues such as bronchi or blood vessels. Patent Document 2 describes a method for representing an organ selected for medical observation or the like by three-dimensional rendering, and describes a method of measuring a distance or the like from a three-dimensional image and measuring a cut plane region as a useful method for monitoring a tumor or the like.

[0003] Patent Document 3 describes a medical image processing apparatus that extracts the contour of a lesion in a medical image and measures the length or the like of the lesion based on the contour of the lesion. Patent Document 4 describes an endoscopic image diagnosis support apparatus that displays a contour of the distance distribution from a bronchial wall to a lesion located outside the bronchus on a volume-rendered image. Prior Art Documents Patent Documents

[0004] Patent Document 1 Japanese Unexamined Patent Publication No. 2016-202918 Patent Document 2 Japanese National Publication of International Patent Application No. 10-507954 Patent Document 3 Japanese Unexamined Patent Publication No. 2009-072433 Patent Document 4 Japanese Unexamined Patent Publication No. 2016-39874 Summary of the Invention Problem to be Solved by the Invention

[0005] Cancers that originate from epithelial cells, especially those that occur in the digestive tract such as colorectal cancer, invade surrounding tissues as they progress. Cancer is classified into multiple stages according to its progression. The stage of progression is determined by how far the primary tumor has invaded several reference layers and other organs, and the treatment method is selected based on this. For example, in colorectal cancer, stages such as T1a, T1b, T2, T3, T4a, and T4b are classified according to the degree of invasion into reference areas such as the mucosa, submucosa, muscularis propria, subserosa, and other surrounding organs.

[0006] T1a indicates that the cancer is confined to the submucosa and has invaded less than 1 mm. T1b indicates that the cancer is confined to the submucosa and has invaded 1 mm or more, but has not reached the muscularis propria. T2 indicates that the cancer has invaded the muscularis propria but has not gone beyond it. T3 indicates that the cancer has invaded beyond the muscularis propria, and in areas with a serosal membrane, the cancer is confined to the subserosa, and in areas without a serosal membrane, the cancer is confined to the adventitia. T4a indicates that the cancer is in contact with the serosal surface or has broken through it and is exposed to the abdominal cavity. T4b indicates that the cancer has directly invaded other organs.

[0007] In rectal cancer, among cancers where the depth of invasion is determined in this way, attention is paid not only to whether or not the cancer has invaded the reference tissue, but also to the distance between the reference tissue and the cancer. Western guidelines recommend measuring the following indicators on high-resolution MRI (Magnetic Resonance Imaging) images.

[0008] [1]CRM (Circumferential resection merging): Surgical dissection stump CRM is the closest distance between the deepest part of the cancer and the surrounding mesentery (rectal dissection surface). A positive result is defined as a distance of 1 mm or less. CRM is considered a strong predictor of local recurrence.

[0009] [2]Extramural depth of tumor invasion Muscle invasion distance refers to the distance the cancer has traveled beyond the intestinal wall (muscle layer propria). This distance is used to classify cancers into three or four stages. A longer muscle invasion distance is associated with a poorer prognosis, and the need for chemotherapy is discussed in relation to this distance.

[0010] [Problem 1] As an indicator for determining the stage of cancer progression, CRM is evaluated based on the rectal mesentery, and the muscular infiltration distance is evaluated based on the muscularis propria. Thus, the tissue used as the basis for evaluation and the surface used as the basis for measurement (hereinafter referred to as the "measurement reference surface") differ depending on the stage of cancer progression. In this regard, the endoscopic image diagnostic support device described in Patent Document 4 aims to determine the distance between the tip of the endoscope and the region of interest when taking a tissue sample of the region of interest using a puncture needle provided at the tip of the endoscope, and generates a projected image in which the region of interest is projected onto the inner wall of the bronchus, with a specific point set inside the bronchus as the reference. The technology described in Patent Document 4 is configured to always measure the distance from the same specific reference to the region of interest, so it cannot be used for determining the stage of cancer progression, and adaptive distance measurement according to the stage of progression is difficult.

[0011] [Problem 2] When a physician determines the stage of cancer progression, it is desirable to confirm the positional relationship between the cancerous area and the surrounding tissue and measurement reference plane (especially the nearest and / or furthest points) on actual medical images such as CT (Computed Tomography) images or MRI images, and to confirm the distance using indicators such as CRM or muscle layer invasion distance. In this regard, the endoscopic image diagnostic support device described in Patent Document 4 is configured to display contours on a volume rendering image, and does not display numerical information indicating the measured distance and information indicating the measurement location on the actual medical image, making it difficult to grasp the appearance of areas where the distance between the cancer and the measurement reference plane is close on the actual medical image.

[0012] [Issue 3] Furthermore, the measurement reference plane is not limited to the outer edge of anatomically existing tissue or the boundary between tissues, but can also be used as any plane that a physician or other medical professional can freely designate. For example, when a physician is considering the resection plane in a pre-operative resection plan, they may designate a virtual resection plane on a medical image. In such cases, there is a need for a form of use that allows for prior confirmation of the distance from the arbitrarily designated plane to the cancer.

[0013] This disclosure is made in view of these circumstances and aims to provide a medical image processing device, a medical image processing method, and a program that can solve at least one of the above-mentioned problems and present useful distance information for lesion evaluation together with medical images. [Means for solving the problem]

[0014] A medical image processing device according to one aspect of the present disclosure comprises a processor and a storage device that stores a program executed by the processor, wherein the processor acquires a three-dimensional medical image by executing instructions from the program, accepts input of information indicating a lesion area contained in the medical image, determines a measurement reference plane that serves as a reference for measurement for lesion evaluation from the medical image, measures the distance between the lesion area and the measurement reference plane in three dimensions, and displays the measurement result, which includes information indicating at least one of the nearest distance and the farthest distance between the lesion area and the measurement reference plane, together with the medical image.

[0015] "Measurements for lesion evaluation" include, for example, measurements to determine the progression (malignancy) of the lesion, measurements to determine the stage of the lesion, and measurements to determine the legitimacy of the resection area. "Information indicating the lesion area" may be information about the entire lesion area or information about a part of the lesion area (partial area). For example, the information indicating the lesion area may be only the information about the area necessary for measurement.

[0016] According to this embodiment, it is possible to select an appropriate measurement reference plane according to the extent of the lesion, measure a three-dimensional distance useful for lesion evaluation, and display the distance information of the measurement result simultaneously with the medical image.

[0017] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to determine a first measurement reference plane outside the lesion region as one of the measurement reference planes, and to display measurement results including information indicating the nearest distance and nearest point between the first measurement reference plane and the lesion region.

[0018] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to determine a second measurement reference plane that intersects the lesion region as one of the measurement reference planes, and to display measurement results including information indicating the furthest distance and furthest point between the portion of the lesion region that crosses the second measurement reference plane and the second measurement reference plane.

[0019] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to determine a lesion-side measurement reference area from the lesion area, which will serve as a reference for measurements on the lesion side for lesion evaluation, and to measure the distance between the lesion-side measurement reference area and the measurement reference surface.

[0020] In a medical image processing apparatus according to another aspect of this disclosure, the lesion region-side measurement reference region may be a subregion of the lesion region.

[0021] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to determine a first measurement reference plane outside the lesion region and a second measurement reference plane intersecting the lesion region as measurement reference planes, to determine a lesion region-side measurement reference region that serves as the reference for the lesion region side of the measurement for lesion evaluation from a region within the lesion region that is inside the first measurement reference plane and outside the second measurement reference plane, and to measure the distance between at least one of the first measurement reference plane and the second measurement reference plane and the lesion region-side measurement reference region.

[0022] The lesion-region-side measurement reference region may be the entire region or a partial region that is inside the first measurement reference plane and outside the second measurement reference plane in the lesion region. For example, the lesion-region-side measurement reference region may be the outer edge surface of the region that is inside the first measurement reference plane and outside the second measurement reference plane in the lesion region.

[0023] In the medical image processing apparatus according to another aspect of the present disclosure, the processor may be configured to measure a distance between the first measurement reference plane and the lesion-region-side measurement reference region, and display a measurement result including information indicating the closest distance between the first measurement reference plane and the lesion-region-side measurement reference region together with a medical image.

[0024] In the medical image processing apparatus according to another aspect of the present disclosure, the lesion-region-side measurement reference region may be configured to be a region corresponding to at least a part of the outer edge surface of the lesion region.

[0025] In the medical image processing apparatus according to another aspect of the present disclosure, the processor determines the first measurement reference plane outside the lesion region as one of the measurement reference planes, and may be configured to, when the distance between the first measurement reference plane and the lesion-region-side measurement reference region is less than a first threshold, display information indicating that the distance is less than the first threshold together with a medical image.

[0026] In the medical image processing apparatus according to another aspect of the present disclosure, the processor determines the second measurement reference plane intersecting the lesion region as one of the measurement reference planes, and may be configured to, for a location where the distance between the second measurement reference plane and the lesion-region-side measurement reference region is equal to or greater than a second threshold, display information indicating that the distance is equal to or greater than the second threshold together with a medical image.

[0027] In the medical image processing apparatus according to another aspect of the present disclosure, the measurement result may be configured to include at least one of a numerical value indicating a distance, a color map representing the distance using colors, and information indicating a determination result of whether the distance exceeds a threshold.

[0028] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to perform lesion region extraction processing to automatically extract lesion regions from medical images and to acquire information indicating lesion regions.

[0029] In other embodiments of the present disclosure, the lesion region extraction process may be configured to include a process for extracting lesion regions by performing image segmentation using a model trained by machine learning.

[0030] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to accept input of information indicating a specified lesion region using an input device.

[0031] In other embodiments of the present disclosure, the measurement reference surface may be configured to be a surface corresponding to the edge surface of the tissue that serves as a reference for determining the progression of a lesion.

[0032] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to determine a measurement reference surface to be used for measurement from among a plurality of candidate measurement reference surfaces that can serve as measurement reference surfaces, according to the lesion area.

[0033] In a medical image processing apparatus according to another aspect of this disclosure, the multiple candidate reference planes may be configured to include planes corresponding to the edges of anatomical tissues.

[0034] In a medical image processing apparatus according to another aspect of this disclosure, the lesion region is the region of cancer originating from epithelial cells, and the processor can be configured to select the innermost uninvaded tissue, which is the tissue that has the region closest to the epithelial cells in the region outside the deepest part of the cancer, and to determine a measurement reference plane that serves as the basis for measuring the nearest neighbor distance based on the selected innermost uninvaded tissue.

[0035] In a medical image processing apparatus according to another aspect of the present disclosure, the processor may be configured to select the outermost invasive tissue, which is the tissue furthest from epithelial cells among the tissues that the cancer has penetrated in a region inside the deepest part of the cancer, and to determine a measurement reference plane that serves as the basis for measuring the furthest distance based on the selected outermost invasive tissue.

[0036] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to accept input of information indicating a specified reference plane using an input device.

[0037] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to display a numerical value of at least one of the measurement results of the nearest distance and the farthest distance.

[0038] In a medical image processing apparatus according to another aspect of the present disclosure, the processor may be configured to display a planar cross-sectional image including two points for which at least one of the nearest distance and the farthest distance has been measured.

[0039] In a medical image processing apparatus according to another aspect of this disclosure, the processor may be configured to generate a cross-sectional image of a plane including two points whose nearest-neighbor distance has been measured, and to display the cross-sectional image.

[0040] In a medical image processing device according to another aspect of this disclosure, the lesion region is the region of cancer occurring in a tubular organ, and the processor can be configured to present as a recommended cross-section a plane that passes through two points where the nearest nearest distance is measured and the cross-sectional area of ​​the tubular organ is smallest, or a plane that passes through two points where the nearest nearest distance is measured and the angle with the center line of the tubular organ is closest to 90 degrees.

[0041] Examples of tubular organs include the digestive tract, trachea, and blood vessels.

[0042] In a medical image processing apparatus according to another aspect of the present disclosure, the processor may be configured to, after presenting a recommended cross-section, accept an input from the user specifying a plane passing through two points, with the axis passing through the two points whose nearest-neighbor distance has been measured fixed, and generate a cross-sectional image of the specified plane.

[0043] A medical image processing method relating to another aspect of this disclosure includes a computer acquiring a three-dimensional medical image, receiving input of information indicating a lesion area contained in the medical image, determining a reference plane from the medical image to serve as a reference for measurement for lesion evaluation, measuring the distance between the lesion area and the reference plane in three dimensions, and displaying the measurement results, which include information indicating at least one of the nearest distance and the farthest distance between the lesion area and the reference plane, together with the medical image.

[0044] A program relating to another aspect of this disclosure is a program for a computer to implement the following functions: a function to acquire a three-dimensional medical image; a function to accept input of information indicating a lesion area contained in the medical image; a function to determine a reference plane that serves as a basis for measurement for lesion evaluation from the medical image; a function to measure the distance between the lesion area and the reference plane in three dimensions; and a function to display the measurement results, which include information indicating at least one of the nearest distance and the farthest distance between the lesion area and the reference plane, together with the medical image. [Effects of the Invention]

[0045] According to the present invention, a measurement reference plane can be adaptively selected according to the lesion area, and distance information for lesion evaluation can be displayed together with the medical image. [Brief explanation of the drawing]

[0046] [Figure 1] Figure 1 shows an example of CRM measurement from MRI images taken of a patient with rectal cancer. [Figure 2] Figure 2 shows an example of measuring the muscle layer invasion distance from MRI images taken of a patient with rectal cancer. [Figure 3]Figure 3 is a schematic diagram illustrating the relationship between cancer and the tissue layers that serve as criteria for determining the depth of invasion. [Figure 4] Figure 4 is a schematic diagram illustrating the progression of cancer. [Figure 5] Figure 5 is a functional block diagram of a medical image processing apparatus according to an embodiment. [Figure 6] Figure 6 is a schematic diagram illustrating an example of the selection of a measurement reference plane and distance measurement. [Figure 7] Figure 7 is a block diagram showing an example configuration of a medical image processing apparatus according to an embodiment. [Figure 8] Figure 8 is a flowchart showing an example of the operation of a medical image processing device according to the embodiment. [Figure 9] Figure 9 shows an example of a display screen shown using the medical image processing device according to this embodiment. [Figure 10] Figure 10 shows another example of a display screen displayed using the medical image processing device according to the embodiment. [Figure 11] Figure 11 shows an example of a display screen that shows a cross-section indicating the closest point to the CRM for a point selected by the user. [Figure 12] Figure 12 is a conceptual diagram illustrating a method for displaying a cross-section that clearly shows the measured distance, based on the results of measurements taken with respect to the nearest or furthest point, or a point entered by the user. [Figure 13] Figure 13 is a block diagram showing an example configuration of a medical information system including a medical image processing device according to an embodiment. [Figure 14] Figure 14 is a schematic diagram showing an example of a cross-sectional MRI image of rectal cancer. [Figure 15] Figure 15 is a schematic diagram showing another example of a cross-section of an MRI image of rectal cancer. [Figure 16] Figure 16 shows another example of a display screen that can be displayed using the medical image processing device according to the embodiment. [Modes for carrying out the invention]

[0047] Preferred embodiments of the present invention will be described below with reference to the attached drawings.

[0048] Examples of distance measurement in rectal cancer Figures 1 and 2 are examples of MRI images taken of a patient with rectal cancer. In Figures 1 and 2, different fill patterns are applied to each region to make the cancerous tissue (TU), muscularis propria (MP), and mesenteric ligament (ME) easier to see. Although the figures show two-dimensional images, actual MRI images are three-dimensional.

[0049] In modalities such as MRI or CT scanners, three-dimensional data representing the three-dimensional morphology of an object is obtained by sequentially acquiring two-dimensional slice images. In this specification, the term "three-dimensional image" includes the concept of a collection of sequentially acquired two-dimensional slice images (two-dimensional image sequence). The term "image" includes the meaning of image data.

[0050] Figure 1 shows an example of CRM measurement. The double-headed arrow A in Figure 1 represents the nearest neighbor (nearest point) where the cancerous tumor (TU) is closest to the rectal mesentery (ME). When determining the stage of cancer progression, the distance of this nearest neighbor (nearest point distance) in mm is one of the important parameters. A CRM positive result is indicated when the nearest neighbor distance is 1 mm or less.

[0051] Figure 2 shows an example of measuring the muscle layer invasion distance. The double-headed arrow B in Figure 2 represents the portion where the cancerous tumor (TU) extends the largest (longest) distance beyond the muscle layer (MP). Classification is performed based on how many millimeters the cancerous tumor (TU) extends beyond the muscular layer (MP).

[0052] FIG. 3 is a schematic image diagram schematically showing the relationship between cancer and tissue layers serving as criteria for depth of invasion determination. In FIG. 3, for simplification of illustration, three layers of A layer (LA), B layer (LB) and C layer (LC) and a peripheral organ (POR) outside the three layers are shown from the lumen of the intestinal tract toward the outside. In rectal cancer, cancer (TU) arises from epithelial cells in the lumen of the intestinal tract (IT), and infiltrates into outer tissues as the cancer (TU) progresses.

[0053] FIG. 4 is a schematic image diagram schematically showing how cancer (TU) progresses. For a doctor to determine the progression stage of cancer and decide a resection plane, it is necessary to three-dimensionally measure the distance between the cancer (TU) and its surrounding tissues. Hereinafter, for convenience of description, the positional relationship in which tissue A, tissue B, and tissue C are arranged in this order from the lumen of the intestinal tract toward the outside is expressed as "A<B<C". Further, the positional relationship when the deepest invasion site of cancer (TU) is located between tissue A and tissue B is expressed as "A<cancer<B".

[0054] [Case 1] For example, when the positional relationship between cancer (TU) and its surrounding tissues is "A<cancer<B", it is necessary to three-dimensionally measure the closest distance between tissue B outside the cancer (TU) and the portion of the cancer (TU) region that has infiltrated beyond tissue A. In addition to measuring the closest distance, it is further desirable to three-dimensionally measure the farthest distance from tissue A when the cancer (TU) has invaded beyond tissue A. In this Case 1, for example, tissue A may be the proper muscle layer (MP) shown in FIG. 1, and tissue B may be the mesorectum (ME). The closest distance may also be rephrased as the shortest distance or the minimum distance, and the farthest distance may also be rephrased as the longest distance or the maximum distance. The closest distance can indicate the residual distance to the next tissue that cancer (TU) has not yet infiltrated, that is, how much margin exists to the nearest non-infiltrated tissue. On the other hand, the farthest distance can indicate the maximum distance that cancer (TU) has infiltrated beyond the reference plane, that is, how deeply cancer has infiltrated from the reference plane.

[0055] [Case 2] When the positional relationship between the cancer TU and its surrounding tissue is "A < B < cancer < C", it is necessary to three-dimensionally measure the closest distance between the tissue C outside the cancer TU and the portion of the cancer TU that has infiltrated beyond the tissue B. In addition to measuring this closest distance, it is also desirable to three-dimensionally measure the farthest distance from the tissue B when the cancer TU extends beyond the tissue B. In this Case 2, for example, the tissue B may be the mesorectal mesentery ME shown in FIG. 1, and the tissue C may be the peripheral organ POR.

[0056] <<Outline of Medical Image Processing Apparatus>> FIG. 5 is a functional block diagram showing the functions of a medical image processing apparatus 20 according to an embodiment of the present disclosure. The medical image processing apparatus 20 is implemented using computer hardware and software. Software is synonymous with a program. The medical image processing apparatus 20 includes an image acquisition unit 222, a lesion area extraction unit 224, a lesion area input reception unit 226, a measurement reference plane extraction unit 228, a measurement reference plane input reception unit 230, a distance measurement unit 232, and a display image generation unit 234. The medical image processing apparatus 20 is also connected to an input device 214 and a display device 216.

[0057] The image acquisition unit 222 acquires a medical image to be processed from an unillustrated image storage server or the like. Here, an MR image captured using an MRI apparatus is exemplified as the medical image to be processed, but the image is not limited thereto, and may be an image captured by another modality such as a CT apparatus.

[0058] In the present embodiment, since image diagnosis of cancer occurring in the digestive tract is assumed, the medical image acquired via the image acquisition unit 222 is, for example, a three-dimensional image obtained by capturing a region including the cancer and its surrounding tissue as one image. Further, since the medical image processing apparatus 20 three-dimensionally measures distances in millimeters, the target image is preferably high-resolution three-dimensional data of isotropic voxels.

[0059] The lesion region extraction unit 224 performs lesion region extraction processing to automatically extract lesion regions from medical images acquired via the image acquisition unit 222 by image recognition. In this embodiment, the lesion region is the region of cancer. The lesion region extraction unit 224 extracts lesion regions by performing image segmentation on the input medical image using a trained model that has been trained on the task of image segmentation using machine learning, such as deep learning.

[0060] For example, a Convolutional Neural Network (CNN) can be used as a learning model for image segmentation. The lesion region extraction unit 224 may be configured to perform segmentation that classifies the lesion region from other regions, or to classify each region of the lesion region from multiple surrounding tissues. For example, the lesion region extraction unit 224 may use a pre-trained model that has been trained to receive a 3D image as input and classify the cancerous region, mucosal layer, submucosa, muscularis propria, subserosa, and other surrounding organs into their respective regions, and output a segmentation result image with a mask pattern applied to each region. This model may then extract the lesion region and the surrounding regions.

[0061] The lesion area input receiving unit 226 accepts input of information about lesion areas automatically extracted by the lesion area extraction unit 224. The lesion area input receiving unit 226 also accepts input of information about lesion areas specified by the user using the input device 214. The user, a physician, can freely specify areas different from the lesion areas automatically extracted by the lesion area extraction unit 224 using the input device 214. For example, the physician can specify areas that were not automatically extracted as cancerous TUs, but are recognized as cancerous or suspected of being cancerous, using the input device 214.

[0062] The measurement reference plane extraction unit 228 performs adaptive extraction of a measurement reference plane from the medical image, based on information about the lesion area obtained via the lesion area input reception unit 226, according to the extent of the lesion area's spread. The digestive tract has a multilayer structure with multiple layers extending from the lumen outward, and other organs exist beyond the serosa. The measurement reference plane extraction unit 228 automatically selects tissue that serves as a reference for evaluating the progression of cancer based on the positional relationship between the cancerous TU (lesional lesion area) and the surrounding layers or other organs, and automatically extracts a measurement reference plane that serves as the basis for distance measurement. Since the extent of cancer spread changes depending on the stage of progression, an appropriate measurement reference plane is automatically extracted according to the stage of progression. The measurement reference plane may be a curved surface.

[0063] The measurement reference plane extraction unit 228 selects the innermost uninvaded tissue, which is the tissue with the innermost region (closest to epithelial cells) in the region outside the deepest part of the cancer TU, and the outermost invasive tissue, which is the tissue that the cancer TU has penetrated in the region inside the deepest part of the cancer TU, based on the positional relationship between the cancer TU and the surrounding tissue, and determines the measurement reference plane based on these tissues. In Figure 1, the rectal mesentery ME corresponds to the innermost uninvaded tissue, and the muscularis propria MP corresponds to the outermost invasive tissue.

[0064] For example, the outer edge of the innermost uninvaded tissue can serve as a reference surface for measuring the nearest neighbor distance. Similarly, the interface between the innermost uninvaded tissue and the outermost invaded tissue, or the outer edge of the outermost invaded tissue, can serve as a reference surface for measuring the furthest distance.

[0065] The measurement reference plane extraction unit 228 automatically extracts at least one reference plane from the medical image, based on the positional relationship between the cancerous tumor (TU) and the surrounding tissue in the region near the deepest part of the cancerous tumor (TU), which includes a first reference plane for measuring the nearest neighbor distance and a second reference plane for measuring the furthest distance. Due to clinical importance, it is preferable for the measurement reference plane extraction unit 228 to automatically extract at least the first reference plane, and it is even more preferable to extract both the first and second reference planes.

[0066] The measurement reference plane input receiving unit 230 accepts input of information on measurement reference planes automatically extracted by the measurement reference plane extraction unit 228. The measurement reference plane input receiving unit 230 also accepts input of information on measurement reference planes specified by the user using the input device 214. The user, a physician, can freely specify a reference plane different from the one automatically extracted by the measurement reference plane extraction unit 228 using the input device 214. The measurement reference plane to be used for measurement is determined based on the information input via the measurement reference plane input receiving unit 230.

[0067] For example, when a physician considers the resection surface before surgery, they can designate not only anatomically existing boundaries but also hypothetical surfaces within layers (non-existent virtual surfaces) as the planned resection surface. By using the planned resection surface as a reference plane for distance measurement, it becomes possible to determine the resection margins and other parameters.

[0068] The distance measurement unit 232 performs three-dimensional distance measurement from the measurement reference plane to the cancer TU based on the input medical image. The distance measurement unit 232 measures at least one of the nearest distance and the furthest distance. Preferably, the distance measurement unit 232 measures at least the nearest distance, and more preferably measures both the nearest distance and the furthest distance. The distance measurement unit 232 measures the nearest distance between the first measurement reference plane and the cancer, using the first measurement reference plane as a reference. The distance measurement unit 232 also measures the furthest distance between the second measurement reference plane and the cancer, using the second measurement reference plane as a reference. Furthermore, the distance measurement unit 232 measures at least one of the nearest distance and the furthest distance with respect to a measurement reference plane specified by the user.

[0069] Furthermore, if the user inputs a specified lesion area, it is possible to measure the distance from that specified area. Alternatively, the entire lesion area, including the automatically extracted lesion area and the lesion area specified by the user, can be grouped together and treated as a single lesion area for measuring the nearest and / or furthest distances. Preferably, the system is configured to allow selection of these measurement modes. When determining the progression of a lesion, it is preferable to measure the distance to the entire combined area of ​​the automatically extracted lesion area and the lesion area added manually by the user, and to evaluate the nearest and / or furthest distances.

[0070] As a method for measuring distance, for example, for each of the multiple points on the contour of the infiltrated portion of the lesion to be measured, the distance to the nearest point on the first measurement reference plane is calculated, and the distance between the two points with the shortest distance among them is obtained as the nearest-neighbor distance. Alternatively, for example, for each of the multiple points on the contour of the infiltrated portion of the lesion to be measured, the distance to the nearest point on the second measurement reference plane is calculated, and the distance between the two points with the longest distance among them is obtained as the farthest distance.

[0071] The display image generation unit 234 generates a display image to be displayed on the display device 216. The display image generation unit 234 generates a cross-sectional image (2D image) for display from the 3D image. The display image generation unit 234 generates at least one cross-sectional image from among axial cross-sectional images, coronal cross-sectional images, and sagittal cross-sectional images, and preferably generates all three types of cross-sectional images. The display image generation unit 234 also generates data necessary for display so that the distance and measurement location information of the distance measurement result by the distance measurement unit 232 are displayed together with the cross-sectional image.

[0072] When the distance measuring unit 232 measures the nearest-closest distance, text information including a numerical value indicating the nearest-closest distance, along with a mark such as an arrow pointing to the nearest-closest point where the nearest-closest distance was measured, is displayed on the screen of the display device 216 along with a cross-sectional image.

[0073] When the distance measuring unit 232 measures the maximum distance, character information including a numerical value indicating the maximum distance and a mark indicating the farthest location where the maximum distance is measured are displayed on the screen of the display device 216 together with the cross-sectional image. Note that items to be displayed can be selected via the input device 214, and the display content on the display screen can be switched by appropriately changing the display items.

[0074] Fig. 6 is a schematic image diagram illustrating an example of selection of a measurement reference plane and distance measurement. Fig. 6 exemplifies the case of the progression degree at the stage [4] in Fig. 4. The cancer TU illustrated in Fig. 6 infiltrates into the C-layer LC beyond the B-layer LB, and has a positional relationship of B-layer LB < cancer TU < C-layer LC. In this case, each of the C-layer LC and the B-layer LB can serve as a tissue serving as a reference for evaluating the progression degree of the cancer TU.

[0075] The outermost edge surface of the C-layer LC may be set as the first measurement reference plane Rp1, and the outermost edge surface of the B-layer LB may be set as the second measurement reference plane Rp2. Note that the outermost edge surface of the B-layer LB may also be understood as the boundary surface between the C-layer LC and the B-layer LB. The first measurement reference plane Rp1 is set on the outer side of the cancer TU. The second measurement reference plane Rp2 is set at a position intersecting the region of the cancer TU.

[0076] The medical image processing apparatus 20 identifies, from the image IM1 shown in the left diagram of Fig. 6, as shown in the right diagram of Fig. 6, the first measurement reference plane Rp1 and the contour surfaces C1a and C1b indicating the outer edge surface of the cancer TU in a region near the deepest part of the cancer TU, and three-dimensionally measures the distance between points on the first measurement reference plane Rp1 and points on the contour surfaces C1a and C1b. Then, the medical image processing apparatus 20 obtains the closest distance (the shortest distance) among the measured inter-point distances.

[0077] Further, the medical image processing apparatus 20 identifies measurement reference planes Rp2a and Rp2b, which are part of the second measurement reference plane Rp2, from the image IM1, and three-dimensionally measures the distance between points on the measurement reference planes Rp2a and Rp2b and points on the contour surfaces C1a and C1b. Then, the medical image processing apparatus 20 obtains the farthest distance (maximum distance) among the measured inter-point distances. Note that the measurement reference planes Rp2a and Rp2b are portions of the second measurement reference plane Rp2 invaded by the cancer TU.

[0078] In FIG. 6, the C layer LC is an example of the "innermost non-invaded tissue" in the present disclosure. Further, the B layer LB is an example of the "outermost invaded tissue" in the present disclosure. The contour surfaces C1a and C1b of the cancer TU are regions serving as references on the cancer TU side for measurement for progression evaluation, and are an example of the "lesion region-side measurement reference region" in the present disclosure.

[0079] In FIG. 6, an example of the positional relationship of B layer LB < cancer TU < C layer LC has been described; however, the region to be measured is the cancer TU and the surrounding region thereof, and the surrounding region to be measured changes depending on the degree of invasion of the cancer TU. The term "region" as used herein includes the concepts of "tissue" and "structure". In the case of colorectal cancer, the mucosa, submucosa, proper muscle layer, subserosa, serosa, or other surrounding organs such as the pancreas or liver can serve as reference tissues for evaluation. A plurality of measurement reference plane candidates that can serve as measurement reference planes are set corresponding to each of these tissues. The measurement reference plane extraction unit 228 determines the measurement reference plane to be used for measurement from among the plurality of measurement reference plane candidates according to the region of the cancer TU.

[0080] Figure 7 is a block diagram showing an example configuration of a medical image processing device 20. The medical image processing device 20 comprises a processor 202, a computer-readable medium 204 which is a non-temporary tangible object, a communication interface 206, and an input / output interface 208. The processor 202 is an example of a "processor" in this disclosure. The computer-readable medium 204 is an example of a "storage device" in this disclosure. The form of the medical image processing device 20 may be a server, a personal computer, a workstation, or a tablet terminal, etc.

[0081] The processor 202 includes a CPU (Central Processing Unit). The processor 202 may also include a GPU (Graphics Processing Unit). The processor 202 is connected to a computer-readable medium 204, a communication interface 206, and an input / output interface 208 via a bus 210. An input device 214 and a display device 216 are connected to the bus 210 via the input / output interface 208.

[0082] The input device 214 is comprised of, for example, a keyboard, mouse, multi-touch panel, or other pointing device, or an audio input device, or an appropriate combination thereof. The display device 216 is comprised of, for example, a liquid crystal display, an organic electro-luminescence (OEL) display, or a projector, or an appropriate combination thereof.

[0083] The computer-readable medium 204 includes memory, which is the main memory, and storage, which is the secondary memory. The computer-readable medium 204 may be, for example, semiconductor memory, a hard disk drive (HDD), or a solid state drive (SSD), or a combination of these.

[0084] The medical image processing device 20 is connected to a communication line (not shown) via a communication interface 206, and is capable of communicating with devices such as a DICOM (Digital Imaging and Communication in Medicine) server 40 and a viewer terminal 46 on the medical institution's internal network.

[0085] The computer-readable medium 204 stores multiple programs and data, including a medical image processing program 220 and a display control program 260. The processor 202 functions as an image acquisition unit 222, a lesion area extraction unit 224, a lesion area input receiving unit 226, a measurement reference plane input receiving unit 230, a distance measurement unit 232, and a display image generation unit 234 by executing instructions in the medical image processing program 220.

[0086] The display control program 260 generates display signals necessary for display output to the display device 216 and controls the display of the display device 216.

[0087] Examples of medical image processing methods Figure 8 is a flowchart illustrating an example of the operation of the medical image processing device 20. In step S12, the processor 202 acquires the medical image to be processed from the DICOM server 40 or the like.

[0088] Next, in step S14, the processor 202 automatically extracts lesion regions from the input medical image. The processor 202 extracts lesion regions by performing segmentation of the medical image using a trained model.

[0089] In step S16, the processor 202 automatically extracts a reference plane based on the identified lesion area.

[0090] In step S18, the processor 202 measures the distance between the identified reference plane and the lesion area. For example, the processor 202 measures the nearest distance between the reference plane and the lesion area. Preferably, the processor 202 measures both the nearest distance and the farthest distance.

[0091] In step S20, the processor 202 generates a display image for displaying distance information indicating the measurement result and marks such as arrows indicating the measurement location on the display device 216 along with the medical image. The distance information presented on the display image is preferably character information including numbers that show the measured value in millimeters.

[0092] In step S22, the processor 202 displays the generated display image on the display device 216. This superimposes annotations such as distance information onto the medical image.

[0093] Subsequently, in step S24, the processor 202 receives various instructions from the user. The user can input various information from the input device 214, such as specifying the lesion area and the measurement reference plane.

[0094] In step S26, the processor 202 determines whether there is input from the input device 214 specifying a lesion area. If the user performs an operation to specify a suspected lesion area in the medical image and information specifying a lesion area is input (resulting in a YES determination in step S26), the processor 202 proceeds to step S16 and extracts a measurement reference plane based on the specified lesion area.

[0095] On the other hand, if the result of step S26 is NO, that is, if there is no input specifying a lesion area, the processor 202 proceeds to step S28.

[0096] In step S28, the processor 202 determines whether or not there is input from the input device 214 to specify a measurement reference plane. If the user performs an operation to specify a measurement reference plane and information specifying the measurement reference plane is input (determined as YES in step S28), the processor 202 proceeds to step S18 and performs distance measurement based on the specified measurement reference plane.

[0097] On the other hand, if the result of step S28 is NO, that is, if no information is input to specify the measurement reference plane, the processor 202 proceeds to step S30.

[0098] In step S28, the processor 202 determines whether or not to terminate the display of the medical image. The termination condition may be a termination instruction input by the user or a termination command based on the program. If the termination condition is not met and the determination result in step S28 is NO, the processor 202 proceeds to step S22 and continues the display.

[0099] On the other hand, if the result of step S30 is YES, that is, if the termination condition is met, such as when the user closes the display window, the processor 202 terminates the display and exits the flowchart in Figure 8.

[0100] Furthermore, the processing functions of the medical image processing device 20 can also be implemented by sharing the processing among multiple computers.

[0101] Examples of user interfaces Figure 9 shows an example of a display screen shown using the medical image processing device 20. Figure 9 shows an example of a display screen when showing the portion with the longest muscle layer invasion distance within a single three-dimensional image. The display window 280 shown in Figure 9 includes a central main display area 282 and several sub-display areas 284a, 284b, and 284c arranged vertically to its left. In the example in Figure 9, an axial cross-sectional image is displayed in the main display area 282, and distance information showing the measurement results of CRM and muscle layer invasion distance, and an arrow indicating the furthest point (longest distance portion) where the muscle layer invasion distance was measured are superimposed on the cross-sectional image. Note that the background of the text may be a watermark (no fill). The text color and background presence may be set as appropriate from the viewpoint of visibility.

[0102] Similarly, the shortest distance in the CRM can also be displayed with annotations using arrows and distance information.

[0103] Sub-display area 284a displays a 3D multi-mask image. Sub-display area 284b displays a sagittal cross-sectional image, and sub-display area 284c displays a coronal cross-sectional image. The type of image displayed in each display area can be selected as appropriate.

[0104] Figure 10 shows another example of a display screen shown using the medical image processing device 20. Figure 10 shows an example of a display screen that appears when the user places the cursor over a suspected lesion and measures the distance to it.

[0105] Figure 11 shows an example of displaying a cross-section in Figure 10 that shows the point closest to the CRM for a point selected by the user. When displaying the nearest and / or farthest distances, it is preferable to display the cross-section where each distance was measured, i.e., the plane containing the two points from which the distance was measured (see Figure 11).

[0106] Figure 11 shows an example where a plane is displayed that shows the measured distance based on the results of measurements taken for a point entered by the user. The same applies to automatically extracted lesion areas; a plane is displayed that shows the measured distance based on the results of measurements taken for the nearest or farthest point in the entire image.

[0107] Figure 12 is a conceptual diagram illustrating a method for displaying a cross-section that clearly shows the measured distance, based on the measurement results for the nearest or furthest point, or a point entered by the user. For example, the processor 202 determines the cross-section that best shows the measured distance from the set of planes determined by the two points P1 and P2 where the nearest or furthest distances were measured, and presents the cross-sectional image of the recommended cross-section first. As a method for determining the recommended cross-section, for example, the following rule 1 or rule 2 can be applied.

[0108] Rule 1: The recommended cross-section is the plane that passes through the two measured points and whose angle with the midline of the intestine is closest to 90 degrees.

[0109] Rule 2: The recommended cross-section is the plane that passes through the two measured points and minimizes the cross-sectional area of ​​the intestinal tract.

[0110] Furthermore, it is preferable that the processor 202, after presenting a cross-sectional image based on the recommended cross-section, accepts user input and is configured to allow the user to arbitrarily select a slice plane. In this case, the axis passing through the two points (the two-point axis) may be a fixed axis, and the system is configured to allow the user to arbitrarily select a plane from a group of planes that take the fixed axis.

[0111] The intestine is an example of a "luminal organ" in this disclosure, and the intestinal midline is an example of a "luminal organ midline" in this disclosure. Regarding the recommended cross-section, it is not limited to the plane described in Figure 12; the recommended cross-section may be determined from among several specific cross-sections, such as axial, coronal, and sagittal sections, that are closest to the plane of Rule 1 or Rule 2.

[0112] 《Example of system configuration》 Figure 13 is a block diagram showing an example configuration of a medical information system 100 including a medical image processing device 20. The medical information system 100 is a computer network built in a medical institution such as a hospital, and includes a modality 30 for capturing medical images, a DICOM server 40, a medical image processing device 20, an electronic medical record system 44, and a viewer terminal 46, and these elements are connected via a communication line 48. The communication line 48 may be an in-house communication line within the medical institution. Also, a portion of the communication line 48 may be a wide-area communication line.

[0113] Specific examples of modality 30 include CT scanners 31, MRI scanners 32, ultrasound diagnostic equipment 33, PET (Positron Emission Tomography) scanners 34, X-ray diagnostic equipment 35, X-ray fluoroscopy diagnostic equipment 36, and endoscopes 37. The types of modalities 30 connected to the communication line 48 can vary from one medical institution to another.

[0114] The DICOM server 40 is a server that operates according to the DICOM specification. The DICOM server 40 is a computer that stores and manages various data, including images captured using modality 30, and is equipped with a large-capacity external storage device and a database management program. The DICOM server 40 communicates with other devices via the communication line 48 and sends and receives various data, including image data. The DICOM server 40 receives image data and other various data generated by modality 30 via the communication line 48 and stores and manages them on a recording medium such as a large-capacity external storage device. The storage format of image data and communication between each device via the communication line 48 are based on the DICOM protocol.

[0115] The medical image processing device 20 can acquire data from a DICOM server 40 or the like via a communication line 48. The medical image processing device 20 can also send processing results to the DICOM server 40 and the viewer terminal 46. The processing functions of the medical image processing device 20 may be installed on the DICOM server 40 or on the viewer terminal 46.

[0116] Various data stored in the database of the DICOM server 40, as well as various information including processing results generated by the medical image processing device 20, can be displayed on the viewer terminal 46.

[0117] The viewer terminal 46 is an image viewing terminal called a PACS viewer or DICOM viewer. Multiple viewer terminals 46 may be connected to the communication line 48. The form of the viewer terminal 46 is not particularly limited; it may be a personal computer, a workstation, or a tablet terminal. The viewer terminal 46 may be configured to allow the specification of lesion areas and measurement reference planes from its input device.

[0118] Regarding programs that operate computers: The program for implementing the processing functions of the medical image processing device 20 on a computer can be recorded on a computer-readable medium, such as an optical disk, magnetic disk, or semiconductor memory, which is a tangible, non-temporary information storage medium, and the program can be provided through this information storage medium.

[0119] Alternatively, instead of providing programs by storing them on tangible, non-temporary computer-readable media, it is also possible to provide program signals as a download service using telecommunication lines such as the Internet.

[0120] Regarding the hardware configuration of each processing unit: The hardware structure of the processing unit that performs various processes in the medical image processing device 20, such as the image acquisition unit 222, lesion area extraction unit 224, lesion area input receiving unit 226, measurement reference plane extraction unit 228, measurement reference plane input receiving unit 230, distance measurement unit 232, and display image generation unit 234, is, for example, a variety of processors as shown below.

[0121] Various types of processors include CPUs, which are general-purpose processors that execute programs and function as various processing units; GPUs, which are processors specialized for image processing; Programmable Logic Devices (PLDs), such as FPGAs (Field Programmable Gate Arrays), which are processors whose circuit configuration can be changed after manufacturing; and Dedicated Electrical Circuits, such as ASICs (Application Specific Integrated Circuits), which are processors with circuit configurations specifically designed to perform particular processing.

[0122] A single processing unit may be composed of one of these various processors, or it may be composed of two or more processors of the same or different type. For example, a single processing unit may be composed of multiple FPGAs, or a combination of a CPU and an FPGA, or a combination of a CPU and a GPU. Alternatively, multiple processing units may be composed of a single processor. Examples of composing multiple processing units with a single processor include, firstly, a configuration where one or more CPUs and software are combined to form a single processor, and this processor functions as multiple processing units, as is typical of computers such as clients and servers. Secondly, a configuration where a processor is used that realizes the functions of the entire system, including multiple processing units, on a single IC (Integrated Circuit) chip, as is typical of System-on-a-Chip (SoC) systems. Thus, various processing units are configured, in terms of hardware structure, using one or more of the above-mentioned various processors.

[0123] Furthermore, the hardware structure of these various processors is, more specifically, an electrical circuit composed of circuit elements such as semiconductor devices.

[0124] 《Example of measurement target 1》 Figure 14 is a schematic diagram showing an example of a cross-sectional MRI image of rectal cancer. Figure 14 shows characteristic Muscle layer An example of cancerous tumor 1 (TU1) that has invaded beyond the mesorectal pressure point (MP) is shown. In Example 1 shown in Figure 14, the mesorectal fascia (MRF) surrounding the fatty layer of the mesorectal ligament (ME) outside the cancerous TU1 is set as the first reference plane Rp1. The edge of the muscularis propria (MP) intersecting the region of cancerous TU1 is set as the second reference plane Rp2.

[0125] In the evaluation of rectal cancer, the presence or absence of invasion of the mesorectal fascia (MRF) is one of the important considerations. If the distance between the invaded tumor TU1 and the mesorectal fascia is less than 1 mm, it is determined to be MRF-invasion positive (MRF involved).

[0126] When measuring the distance between cancer TU1 and the first measurement reference plane Rp1, the processor 202 may measure the distance to the first measurement reference plane Rp1 for all points within the region of cancer TU1, or it may extract a portion of the region of cancer TU1 as the measurement target region and measure the distance to the first measurement reference plane Rp1 for points within the extracted target region.

[0127] Of the cancerous TU1 region, the portion that is emphasized when measuring for progression assessment is the portion that has invaded beyond the second measurement reference plane Rp2. Therefore, the processor 202 may define the region TU1a of the cancerous TU1 region, which is inside the first measurement reference plane Rp1 and outside the second measurement reference plane Rp2, as the target region for measurement. In this case, the processor 202 may measure the distance from a point on the first measurement reference plane Rp1 to all points within the region TU1a that has invaded beyond the second measurement reference plane Rp2, or, as explained in Figure 6, it may extract the contour plane Ct1 of region TU1a and define only the contour plane Ct1 as the target region for measurement.

[0128] The process of extracting the contour plane Ct1 from the cancerous TU1 region involves, for example, determining whether adjacent voxels are classified as "cancer" or as normal tissue, and identifying the set of cancerous voxels that are in contact with non-cancer tissue. This allows for the identification of the interface (contour plane Ct1) between cancerous TU1 and normal tissue.

[0129] The processor 202 uses the contour surface Ct1 of region TU1a as the measurement reference region on the cancer TU1 side, measures the distance between a point on the contour surface Ct1 and a point on the first measurement reference surface Rp1, and determines the minimum value of the distance between points to identify the nearest nearest distance d1 and the nearest nearest location. The contour surface Ct1 is an example of the "lesion region side measurement reference region" in this disclosure.

[0130] Alternatively, the processor 202 may define the entire region TU1a that has invaded beyond the second reference plane Rp2 as the reference region on the cancer TU1 side, and determine the nearest neighbor distance d1 and the nearest neighbor location by finding the minimum distance between each point in region TU1a and a point on the first reference plane Rp1. In this case, the process of extracting the contour plane Ct1a may be unnecessary. Region TU1a, which is determined as the reference region on the cancer TU1 side, is an example of the "reference region on the lesion side" in this disclosure. The processor 202 may also extract only the lesion region necessary for measurement from the region sandwiched between the first reference plane Rp1 and the second reference plane Rp2.

[0131] The same applies when measuring the distance between cancer TU1 and the second reference plane Rp2. The processor 202 may measure the distance to the second reference plane Rp2 for all points within the region TU1a that has invaded beyond the second reference plane Rp2, or it may extract the contour plane Ct1 as the target area for measurement and measure the distance to the second reference plane Rp2 for points within the extracted target area.

[0132] For example, the processor 202 can identify the furthest distance d2 and the furthest location by using the contour surface Ct1 as the measurement reference area on the cancer TU1 side, measuring the distance between points on the contour surface Ct1 and points on the second measurement reference surface Rp2, and determining the maximum value of the distance between points. Alternatively, the processor 202 can identify the furthest distance d2 and the furthest location by using the entire region TU1a that has invaded beyond the second measurement reference surface Rp2 as the measurement reference area on the cancer TU1 side, and determining the maximum value of the distance between each point in region TU1a and points on the second measurement reference surface Rp2.

[0133] Example of measurement target 2 Figure 15 is a schematic diagram showing another example of a cross-section of an MRI image of rectal cancer. Figure 15 shows an example of cancer TU2 that has invaded beyond the muscularis propria (MP). In Figure 15, elements common to Figure 14 are denoted by the same symbols, and redundant explanations are omitted.

[0134] In Example 2 shown in Figure 15, when considering the entire region of cancer TU2, the point where the distance from cancer TU2 to the first measurement reference plane Rp1 is smallest is indicated by the symbol A1. However, the shortest distance d1a between cancer TU2 and the first measurement reference plane Rp1 at this proximity point A1 is measured across the second measurement reference plane Rp2. In other words, the portion of the cancer TU2 region corresponding to proximity point A1 remains inside the muscularis propria MP.

[0135] On the other hand, what is of particular importance in clinical practice is the distance from the first reference plane Rp1 to the region TU2a of the cancer TU2 that has invaded beyond the muscularis propria MP. Therefore, in order to measure this important distance, the processor 202 may be configured to set region TU2a, which is inside the first reference plane Rp1 and outside the second reference plane Rp2 of the cancer TU2, as the target region for measurement, and to measure the distance between region TU2a and the first reference plane Rp1.

[0136] In this case, the processor 202 may measure the distance between all points in the region TU2a that has infiltrated beyond the second measurement reference surface Rp2 and points on the first measurement reference surface Rp1, or it may extract the contour surface Ct2 of region TU2a and use only the contour surface Ct2 as the target area for measurement.

[0137] The processor 202 uses the contour surface Ct2 as the measurement reference area on the cancer TU2 side, measures the distance between a point on the contour surface Ct2 and a point on the first measurement reference surface Rp1, and determines the minimum value of the distance between points to identify the nearest neighbor distance d1b and the nearest neighbor location A2. The contour surface Ct2 is an example of the "lesion area side measurement reference area" in this disclosure.

[0138] Alternatively, the processor 202 may define the entire region TU2a that has invaded beyond the second reference plane Rp2 as the reference region on the cancer TU2 side, and determine the minimum value of the point-to-point distance d1c between each point in region TU2a and a point on the first reference plane Rp1, thereby identifying the nearest neighbor distance d1b and the nearest neighbor location A2. Region TU2a, which is determined as the reference region on the cancer TU2 side, is an example of a "reference region on the lesion side" in this disclosure.

[0139] Display Method of Measurement Results Figures 9 to 11 illustrate an example of displaying measurement results by showing a numerical value indicating distance. However, the display method of measurement results is not limited to numerical values. For example, the following display methods may be adopted instead of, or in combination with, the numerical display.

[0140] [Display Mode 1] The measurement results may be displayed as a color map that uses colors to represent distance. For example, distance information may be displayed using a color map in which the relationship between color and distance is defined so that the distance is represented by a stepless or stepwise change in color from red to blue, with red representing the closest distance and blue representing a farther distance. When the processor 202 displays the locations of two points where the nearest or furthest distance has been measured, it may display the measurement locations by changing the color according to the distance.

[0141] [Display Mode 2] The display of the measurement results may include information indicating whether or not the measured distance exceeds a threshold. For example, a first threshold is set in advance for the distance between a first measurement reference plane Rp1, which is set outside the lesion area, and the lesion area. The processor 202 may display a warning if the distance between the lesion area and the first measurement reference plane Rp1 is less than the first threshold. The processor 202 may also visually differentiate and display all locations or areas where the distance is less than the first threshold. In the case of CRM, the first threshold may be set to 1 mm. The processor 202 may perform display control to enhance the attention-grabbing effect, such as highlighting, flashing, or displaying with a thick line, when the distance between the cancer TU and the rectal mesentery ME is less than 1 mm. The processor 202 may also display a message to the effect that there are no locations where the distance is less than the first threshold, or it may not display the judgment result at all.

[0142] Similarly, for example, a second threshold may be set in advance for the distance between the lesion area and a second reference plane Rp2 that intersects the lesion area, and the processor 202 may display a warning if the distance between the lesion area and the second reference plane Rp2 is greater than or equal to the second threshold. The processor 202 may also visually differentiate and display all locations or areas where the distance is greater than or equal to the second threshold. In the case of muscle layer invasion distance, multiple values ​​corresponding to the stage classification may be set as the second threshold.

[0143] The processor 202 may perform display control to enhance the attention-grabbing effect, such as highlighting, flashing, or displaying with a thick line, when the muscle layer invasion distance is greater than or equal to a second threshold, or it may display a category classified based on the second threshold. Warning displays, differentiated displays, or category displays, or any appropriate combination thereof, based on the determination result of threshold determination using the first threshold and / or the second threshold are examples of "information indicating whether or not a threshold has been exceeded" in this disclosure.

[0144] The processor 202 may implement multiple display modes for the measurement results, such as a mode that displays numerical values, a mode that displays colors using a color map, a mode that displays information indicating the result of a threshold judgment, or a mode that is an appropriate combination thereof. The processor 202 may accept input instructions to specify the display mode for the measurement results and change the display mode according to the input instructions.

[0145] Other examples of user interfaces Figure 16 shows another example of a display screen displayed using the medical image processing device 20. Figure 16 shows an example of a display screen when a positive MRF infiltration (MRF involved) result is obtained. The display window 281 shown in Figure 16 includes a result display area 285 to the right of the main display area 282.

[0146] In the example in Figure 16, an axial cross-sectional image is displayed in the main display area 282, with the mesorectal ligament (ME), muscularis propria (MP), and cancerous tissue (TU) regions shown as masked areas. The main display area 282 also displays MRF invasion lines W1 and W2, indicating locations where the distance between the cancerous tissue (TU) and the MRF is less than 1 mm. In Figure 16, the MRF invasion lines W1 and W2 are drawn as thick lines along the outer edge of the mesorectal ligament (ME). The MRF invasion lines W1 and W2 may be displayed in red or other colors, or they may be displayed as blinking lines.

[0147] The judgment result display area 285 is an area that displays information indicating the result of threshold determination obtained by comparing the measured distance with the threshold, and includes the depth of invasion display area 286 and the MRF invasion evaluation display area 287. The depth of invasion display area 286 displays the category of depth of invasion classified based on the threshold determination. The MRF invasion evaluation display area 287 displays whether or not MRF invasion is present.

[0148] When displaying measurement results as shown in Figure 16, it is not necessarily required to identify the point where the distance between the cancer TU and the MRF is minimized, or to determine the minimum distance. However, it is clear that the minimum value (nearest neighbor distance) is included among the measurement values ​​that are determined to be below the threshold. The display of MRF invasion lines W1 and W2 is understood to include information on the nearest neighbor distance and the nearest neighbor location.

[0149] Advantages of this embodiment The medical image processing device 20 according to this embodiment has the following advantages.

[0150] [1] The medical image processing device 20 can adaptively select an appropriate measurement reference plane for lesion evaluation according to the positional relationship between the lesion area and the surrounding tissue, and measure three-dimensional distance. Furthermore, the medical image processing device 20 displays the distance information showing the measurement results on actual medical images such as MRI images, making it easier to understand the actual positional relationship between the lesion and its surroundings.

[0151] [2] The medical image processing device 20 can automatically measure the distance of nearby points in three dimensions for the input medical image, thereby reducing the chance of overlooking nearby points in three dimensions.

[0152] [3] In clinical settings, measurements are required to the nearest millimeter, and the medical image processing device 20 allows for measurements without inter-measurement errors, making statistical evaluation easier.

[0153] [4] In addition to the main cancer (primary tumor) that is automatically extracted, the physician can input information on suspected sites such as lymph node metastasis or vascular invasion via the input device 214, etc., to measure the distance and display the measurement results.

[0154] [5] The medical image processing device 20 allows for the examination of the legitimacy of the resection surface while confirming the distance between the resection surface and the lesion area on the medical image when planning a resection. Furthermore, the medical image processing device 20 allows physicians to freely specify not only anatomically existing surfaces but also virtual surfaces (non-existent surfaces) as measurement reference surfaces.

[0155] "others" The embodiments of the present invention described above can be modified, added to, or deleted as appropriate without departing from the spirit of the invention. The present invention is not limited to the embodiments described above, and many modifications are possible within the technical concept of the present invention by those with ordinary skill in the art. [Explanation of Symbols]

[0156] 20 Medical imaging processing equipment 22 Image acquisition unit 30 Modalities 31 CT device 32 MRI machine 33. Ultrasound diagnostic equipment 34 PET equipment 35 X-ray diagnostic equipment 36 X-ray fluoroscopy diagnostic equipment 37 Endoscopic equipment 40 DICOM Servers 46 Viewer terminals 48 Communication lines 100 Medical Information Systems 202 processors 204 Computer-readable media 206 Communication Interfaces 208 Input / Output Interfaces 210 Bus 214 Input device 216 Display device 220 Medical Image Processing Programs 222 Image acquisition unit 224 Lesion area extraction section 226 Lesion Area Input Reception Unit 228 Measurement reference plane extraction unit 230 Measurement Reference Surface Input Reception Unit 232 Distance measurement unit 234 Display Image Generation Unit 260 Display Control Program 280, 281 Display Window 282 Main display area 284a Sub-display area 284b Sub-display area 284c Sub-display area 285 Judgment Result Display Area 286 Invasion depth display area TU, TU1, TU2 cancer TU1a, TU2a area C1a contour surface C1b contour surface Ct1, Ct2 contour surface d1 nearest distance d2 furthest distance A1 Proximity d1a Shortest distance d1b nearest neighbor distance A2 Nearest point d1c distance between points IM1 Image LA A layer LB B layer LC C layer ME rectal mesentery MP muscularis propria POR surrounding organs Rp1 First measurement reference plane Rp2 Second measurement reference plane Rp2a, Rp2b measurement reference plane P1, P2 points S12-S30 Steps demonstrating the operation of the medical image processing device.

Claims

1. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned processor, From among a plurality of candidate measurement reference surfaces that can serve as the aforementioned measurement reference surface, the measurement reference surface to be used for the measurement is determined according to the extent of the lesion area. Medical image processing equipment.

2. The aforementioned multiple candidate measurement reference planes include planes corresponding to the outer edges of anatomical tissues. The medical image processing apparatus according to claim 1.

3. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned lesion area is the area of ​​cancer that originates from epithelial cells. The processor selects the innermost uninvaded tissue, which is the tissue that has the region closest to the epithelial cells in the region outside the deepest part of the cancer. Based on the selected innermost uninvaded tissue, the measurement reference plane that serves as the basis for measuring the nearest neighbor distance is determined. Medical image processing equipment.

4. The aforementioned processor, In the region inside the deepest part of the cancer, the outermost invasive tissue, which is the tissue furthest from the epithelial cells among the tissues that the cancer has penetrated, is selected. Based on the selected outermost invading tissue, the measurement reference plane that serves as the basis for the measurement of the furthest distance is determined. The medical image processing apparatus according to claim 3.

5. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned processor, A cross-sectional image of a plane is displayed, which includes two points where at least one of the nearest distance and the farthest distance has been measured. Medical image processing equipment.

6. The aforementioned processor, A cross-sectional image of a plane including the two points for which the nearest neighbor distance was measured is generated. To display the aforementioned cross-sectional image, The medical image processing apparatus according to claim 5.

7. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned medical images are images obtained by photographing tubular organs. The aforementioned lesion area is the area of ​​cancer that has developed in the tubular organ. The aforementioned processor, The recommended cross-section is the plane that passes through the two points where the nearest nearest distance is measured and where the cross-sectional area of ​​the tubular organ is smallest, or the plane that passes through the two points where the nearest nearest distance is measured and where the angle with the centerline of the tubular organ is closest to 90 degrees. Medical image processing equipment.

8. After presenting the recommended cross-section, the processor then The system accepts an input from the user specifying a plane passing through two points, with the axis passing through the two points whose nearest-neighbor distance has been measured fixed, using an input device. A cross-sectional image of the specified plane is generated. The medical image processing apparatus according to claim 7.

9. The aforementioned processor, A first measurement reference surface is determined outside the lesion area as one of the aforementioned measurement reference surfaces. The measurement results are displayed, including information indicating the nearest distance and nearest point between the first measurement reference plane and the lesion area. A medical image processing apparatus according to any one of claims 1 to 8.

10. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned processor, A first measurement reference surface is determined outside the lesion area as one of the aforementioned measurement reference surfaces. The measurement results are displayed, including information indicating the nearest distance and nearest point between the first measurement reference plane and the lesion area. Medical image processing equipment.

11. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned processor, The input device accepts input of information indicating the specified measurement reference plane, A first measurement reference surface is determined outside the lesion area as one of the aforementioned measurement reference surfaces. The measurement results are displayed, including information indicating the nearest distance and nearest point between the first measurement reference plane and the lesion area. Medical image processing equipment.

12. The aforementioned processor, A second measurement reference surface intersecting the lesion area is determined as one of the aforementioned measurement reference surfaces. The measurement results are displayed, including information indicating the furthest distance and the furthest point between the portion of the lesion area that has deeply infiltrated beyond the second measurement reference plane and the second measurement reference plane. A medical image processing apparatus according to any one of claims 1 to 11.

13. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned processor, A second measurement reference surface intersecting the lesion area is determined as one of the aforementioned measurement reference surfaces. The measurement results are displayed, including information indicating the furthest distance and the furthest point between the portion of the lesion area that has deeply infiltrated beyond the second measurement reference plane and the second measurement reference plane. Medical image processing equipment.

14. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned processor, The input device accepts input of information indicating the specified measurement reference plane, A second measurement reference surface intersecting the lesion area is determined as one of the aforementioned measurement reference surfaces. The measurement results are displayed, including information indicating the furthest distance and the furthest point between the portion of the lesion area that has deeply infiltrated beyond the second measurement reference plane and the second measurement reference plane. Medical image processing equipment.

15. The aforementioned processor, From the lesion area, a reference measurement area on the lesion side is determined, which serves as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between the measurement reference area on the lesion side and the measurement reference surface is measured. A medical image processing apparatus according to any one of claims 1 to 8.

16. The aforementioned measurement reference region on the lesion side is a sub-region of the lesion. The medical image processing apparatus according to claim 15.

17. The aforementioned processor, As the aforementioned measurement reference surfaces, a first measurement reference surface is determined outside the lesion area, and a second measurement reference surface is determined that intersects with the lesion area. From the region of the lesion area that exists between the first measurement reference plane and the second measurement reference plane, a lesion area-side measurement reference region is determined to serve as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between at least one of the first measurement reference surface and the second measurement reference surface and the measurement reference area on the lesion side is measured. A medical image processing apparatus according to any one of claims 1 to 8.

18. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned processor, As the aforementioned measurement reference surfaces, a first measurement reference surface is determined outside the lesion area, and a second measurement reference surface is determined that intersects with the lesion area. From the region of the lesion area that exists between the first measurement reference plane and the second measurement reference plane, a lesion area-side measurement reference region is determined to serve as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between at least one of the first measurement reference surface and the second measurement reference surface and the measurement reference area on the lesion side is measured. Medical image processing equipment.

19. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned processor, The input device accepts input of information indicating the specified measurement reference plane, As the aforementioned measurement reference surfaces, a first measurement reference surface is determined outside the lesion area, and a second measurement reference surface is determined that intersects with the lesion area. From the region of the lesion area that exists between the first measurement reference plane and the second measurement reference plane, a lesion area-side measurement reference region is determined to serve as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between at least one of the first measurement reference surface and the second measurement reference surface and the measurement reference area on the lesion side is measured. Medical image processing equipment.

20. The aforementioned processor, The distance between the first measurement reference surface and the measurement reference area on the lesion side is measured. The measurement results, including information indicating the nearest distance between the first measurement reference plane and the measurement reference region on the lesion side, are displayed together with the medical image. A medical image processing apparatus according to any one of claims 17 to 19.

21. The aforementioned measurement reference region on the lesion side is a region corresponding to at least a part of the outer edge surface of the lesion. A medical image processing apparatus according to any one of claims 15 to 20.

22. The aforementioned processor, A first measurement reference surface is determined outside the lesion area as one of the aforementioned measurement reference surfaces. When the distance between the first measurement reference plane and the measurement reference region on the lesion side is less than a first threshold, information indicating that the distance is less than the first threshold is displayed together with the medical image. The medical image processing apparatus according to claim 15 or 16.

23. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned processor, From the lesion area, a reference measurement area on the lesion side is determined, which serves as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between the measurement reference area on the lesion side and the measurement reference surface is measured. A first measurement reference surface is determined outside the lesion area as one of the aforementioned measurement reference surfaces. When the distance between the first measurement reference plane and the measurement reference region on the lesion side is less than a first threshold, information indicating that the distance is less than the first threshold is displayed together with the medical image. Medical image processing equipment.

24. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned processor, The input device accepts input of information indicating the specified measurement reference plane, From the lesion area, a reference measurement area on the lesion side is determined, which serves as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between the measurement reference area on the lesion side and the measurement reference surface is measured. A first measurement reference surface is determined outside the lesion area as one of the aforementioned measurement reference surfaces. When the distance between the first measurement reference plane and the measurement reference region on the lesion side is less than a first threshold, information indicating that the distance is less than the first threshold is displayed together with the medical image. Medical image processing equipment.

25. The aforementioned processor, When the distance between the first measurement reference plane and the measurement reference region on the lesion side is less than a first threshold, information indicating that the distance is less than the first threshold is displayed together with the medical image. A medical image processing apparatus according to any one of claims 17 to 20.

26. The aforementioned processor, A second measurement reference surface intersecting the lesion area is determined as one of the aforementioned measurement reference surfaces. For locations where the distance between the second measurement reference plane and the measurement reference region on the lesion side is greater than or equal to the second threshold, information indicating that the distance is greater than or equal to the second threshold is displayed together with the medical image. The medical image processing apparatus according to claim 15 or 16.

27. ​​A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned processor, From the lesion area, a reference measurement area on the lesion side is determined, which serves as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between the measurement reference area on the lesion side and the measurement reference surface is measured. A second measurement reference surface intersecting the lesion area is determined as one of the aforementioned measurement reference surfaces. For locations where the distance between the second measurement reference plane and the measurement reference region on the lesion side is greater than or equal to the second threshold, information indicating that the distance is greater than or equal to the second threshold is displayed together with the medical image. Medical image processing equipment.

28. A medical image processing device, Processor and The system comprises a storage device in which a program executed by the processor is stored, The processor executes the instructions of the program, By acquiring three-dimensional medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image. From the aforementioned medical images, a reference plane is determined to serve as the basis for measurement for lesion evaluation. The distance between the lesion area and the measurement reference plane is measured in three dimensions. The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. It is a medical image processing device, The aforementioned processor, The input device accepts input of information indicating the specified measurement reference plane, From the lesion area, a reference measurement area on the lesion side is determined, which serves as the reference for the measurement on the lesion side for the evaluation of the lesion. The distance between the measurement reference area on the lesion side and the measurement reference surface is measured. A second measurement reference surface intersecting the lesion area is determined as one of the aforementioned measurement reference surfaces. For locations where the distance between the second measurement reference plane and the measurement reference region on the lesion side is greater than or equal to the second threshold, information indicating that the distance is greater than or equal to the second threshold is displayed together with the medical image. Medical image processing equipment.

29. The aforementioned processor, For locations where the distance between the second measurement reference plane and the measurement reference region on the lesion side is greater than or equal to the second threshold, information indicating that the distance is greater than or equal to the second threshold is displayed together with the medical image. A medical image processing apparatus according to any one of claims 17 to 20.

30. The measurement results include at least one of the following: a numerical value indicating distance, a color map representing distance using color, and information indicating whether or not a threshold has been exceeded. A medical image processing apparatus according to any one of claims 1 to 29.

31. The aforementioned processor, A lesion region extraction process is performed to automatically extract the lesion region from the medical image, and information indicating the lesion region is obtained. A medical image processing apparatus according to any one of claims 1 to 30.

32. The lesion region extraction process includes a process of extracting the lesion region by performing image segmentation using a model trained by machine learning. The medical image processing apparatus according to claim 31.

33. The aforementioned processor, The system accepts input of information indicating the lesion area specified using an input device. A medical image processing apparatus according to any one of claims 1 to 32.

34. The aforementioned processor, The system displays the numerical value of at least one of the measurement results for the nearest distance and the furthest distance. A medical image processing apparatus according to any one of claims 1 to 33.

35. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned computer, This includes determining the measurement reference surface to be used for the measurement from among a plurality of candidate measurement reference surfaces that can serve as the measurement reference surface, according to the extent of the lesion area. Medical image processing methods.

36. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned lesion area is the area of ​​cancer that originates from epithelial cells. The aforementioned computer, The innermost uninvaded tissue is selected, which is the tissue that is closest to the epithelial cells in the region outside the deepest part of the aforementioned cancer. This includes determining the measurement reference plane that serves as the basis for measuring the nearest neighbor distance based on the selected innermost uninvaded tissue, Medical image processing methods.

37. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned computer, This includes displaying a cross-sectional image of a plane that includes two points from which the nearest distance and the farthest distance have been measured. Medical image processing methods.

38. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned medical images are images obtained by photographing tubular organs. The aforementioned lesion area is the area of ​​cancer that has developed in the tubular organ. The aforementioned computer, The method includes presenting as a recommended cross-section a plane that passes through the two points where the nearest nearest distance is measured and where the cross-sectional area of ​​the tubular organ is smallest, or a plane that passes through the two points where the nearest nearest distance is measured and where the angle with the center line of the tubular organ is closest to 90 degrees. Medical image processing methods.

39. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned computer, One of the aforementioned measurement reference surfaces is determined to be a first measurement reference surface located outside the lesion area, The method includes displaying the measurement results, which include information indicating the nearest distance and nearest point between the first measurement reference plane and the lesion area. Medical image processing methods.

40. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned computer, The input device accepts input of information indicating the measurement reference plane specified by the input device, One of the aforementioned measurement reference surfaces is determined to be a first measurement reference surface located outside the lesion area, The method includes displaying the measurement results, which include information indicating the nearest distance and nearest point between the first measurement reference plane and the lesion area. Medical image processing methods.

41. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned computer, One of the aforementioned measurement reference surfaces is to determine a second measurement reference surface that intersects with the lesion area, The measurement results include displaying information indicating the furthest distance and the furthest point between the portion of the lesion area that has deeply infiltrated beyond the second measurement reference plane and the second measurement reference plane, Medical image processing methods.

42. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned computer, The input device accepts input of information indicating the measurement reference plane specified by the input device, One of the aforementioned measurement reference surfaces is to determine a second measurement reference surface that intersects with the lesion area, The measurement results include displaying information indicating the furthest distance and furthest point between the portion of the lesion area that has deeply infiltrated beyond the second measurement reference plane and the second measurement reference plane, Medical image processing methods.

43. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned computer, The aforementioned measurement reference surfaces are determined to be a first measurement reference surface located outside the lesion area and a second measurement reference surface intersecting the lesion area. From the region of the lesion area that exists between the first measurement reference plane and the second measurement reference plane, a measurement reference area on the lesion side that serves as the reference for the measurement for the evaluation of the lesion is determined. This includes measuring the distance between at least one of the first measurement reference plane and the second measurement reference plane and the measurement reference region on the lesion side. Medical image processing methods.

44. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned computer, The input device accepts input of information indicating the measurement reference plane specified by the input device, The aforementioned measurement reference surfaces are determined to be a first measurement reference surface located outside the lesion area and a second measurement reference surface intersecting the lesion area. From the region of the lesion area that exists between the first measurement reference plane and the second measurement reference plane, a measurement reference area on the lesion side that serves as the reference for the measurement for the evaluation of the lesion is determined. This includes measuring the distance between at least one of the first measurement reference plane and the second measurement reference plane and the measurement reference region on the lesion side. Medical image processing methods.

45. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned computer, Determining a measurement reference area on the lesion side that serves as the reference for the measurement on the lesion side for the evaluation of the lesion from the lesion area, The distance between the measurement reference area on the lesion side and the measurement reference surface is measured, One of the aforementioned measurement reference surfaces is determined to be a first measurement reference surface located outside the lesion area, The method includes displaying information indicating that the distance between the first measurement reference plane and the measurement reference region on the lesion side is less than a first threshold, along with the medical image. Medical image processing methods.

46. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned computer, The input device accepts input of information indicating the measurement reference plane specified by the input device, Determining a measurement reference area on the lesion side that serves as the reference for the measurement on the lesion side for the evaluation of the lesion from the lesion area, The distance between the measurement reference area on the lesion side and the measurement reference surface is measured, One of the aforementioned measurement reference surfaces is determined to be a first measurement reference surface located outside the lesion area, The method includes displaying information indicating that the distance between the first measurement reference plane and the measurement reference region on the lesion side is less than a first threshold, along with the medical image. Medical image processing methods.

47. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned measurement reference surface is a surface that corresponds to the tissue edge surface that serves as a reference when determining the progression of the lesion. The aforementioned computer, Determining a measurement reference area on the lesion side that serves as the reference for the measurement on the lesion side for the evaluation of the lesion from the lesion area, The distance between the measurement reference area on the lesion side and the measurement reference surface is measured, One of the aforementioned measurement reference surfaces is to determine a second measurement reference surface that intersects with the lesion area, This includes displaying information indicating that the distance between the second measurement reference plane and the measurement reference region on the lesion side is greater than or equal to the second threshold, along with the medical image, for locations where the distance is greater than or equal to the second threshold. Medical image processing methods.

48. A medical image processing method, Computers Acquiring 3D medical images, The system accepts input of information indicating the lesion area contained in the aforementioned medical image, To determine a reference plane from the aforementioned medical images that will serve as the basis for measurement for lesion evaluation, The distance between the lesion area and the measurement reference plane is measured in three dimensions, The measurement results, which include information indicating at least one of the nearest and farthest distances between the lesion area and the measurement reference plane, are displayed together with the medical image. Includes, The aforementioned computer, The input device accepts input of information indicating the measurement reference plane specified by the input device, Determining a measurement reference area on the lesion side that serves as the reference for the measurement on the lesion side for the evaluation of the lesion from the lesion area, The distance between the measurement reference area on the lesion side and the measurement reference surface is measured, One of the aforementioned measurement reference surfaces is to determine a second measurement reference surface that intersects with the lesion area, This includes displaying information indicating that the distance between the second measurement reference plane and the measurement reference region on the lesion side is greater than or equal to the second threshold, along with the medical image, for locations where the distance is greater than or equal to the second threshold. Medical image processing methods.

49. A program that causes a computer to execute the medical image processing method described in any one of claims 35 to 48.

50. A non-temporary and computer-readable recording medium on which the program described in claim 49 is recorded.

Images