Information processing device, information processing method, and storage medium

Abstract

An information processing device (100) according to the present disclosure comprises: an estimation unit (121) that estimates the state of a mammary gland tissue included in a breast image that has been input; a setting unit (122) that sets an image diagnosis method on the basis of the estimated state; and a diagnosis unit (123) that executes image diagnosis on the breast image by the image diagnosis method that has been set. Thus, for example, diagnostic information obtained by an image diagnostic method using a model generated by machine learning can be output, and support for user decision making can be provided.

Description

Information processing device, information processing method, and storage medium

[0001] The present disclosure relates to an information processing device, an information processing method, and a storage medium.

[0002] In recent years, technologies have become known for computer-aided diagnosis software and the like that automatically diagnose lesions such as breast masses and calcifications when breast images such as mammograms are input. For example, Patent Document 1 describes outputting pre-registered similar cases for a breast image to be diagnosed. Specifically, Patent Document 1 describes first storing breast images in a database in association with breast density information and feature values ​​of lesion candidates detected from the breast images. Then, using the breast image to be diagnosed, breast density information and feature values ​​of the lesion candidates are calculated, and breast images similar to the position information and / or breast density information of the lesion candidates in the diagnosis target are output from the database as similar cases.

[0003] JP 2010-000133 A

[0004] However, the technology described in Patent Document 1 suffers from a problem of reduced diagnostic accuracy for breast images with high breast density. This is because, when breast density is high, the breast is imaged overlapping with the lesion, which changes the imaging tendency of the lesion compared to when breast density is low, making it difficult to calculate the feature values ​​of the lesion candidate. Furthermore, in addition to the high or low breast density, factors such as the quality of the captured image can make it difficult to properly calculate the feature values ​​of the lesion candidate from the breast image, making it difficult to improve the diagnostic accuracy of breast images.

[0005] Therefore, an object of the present disclosure is to solve the above-mentioned problem of difficulty in improving diagnostic accuracy for breast images.

[0006] An information processing device according to one embodiment of the present disclosure is configured to include an estimation unit that estimates the state of mammary gland tissue contained in an input breast image, a setting unit that sets an imaging diagnostic method based on the estimated state, and a diagnosis unit that performs imaging diagnosis on the breast image using the set imaging diagnostic method.

[0007] Furthermore, an information processing method according to one embodiment of the present disclosure is configured to estimate the state of mammary gland tissue contained in an input breast image, set an imaging diagnostic method based on the estimated state, and perform imaging diagnosis on the breast image using the set imaging diagnostic method.

[0008] Furthermore, a program according to one embodiment of the present disclosure is configured to cause a computer to execute the following processes: estimate the state of mammary gland tissue contained in an input breast image; set an imaging diagnostic method based on the estimated state; and perform imaging diagnosis on the breast image using the set imaging diagnostic method.

[0009] With the above-described configuration, the present disclosure can improve diagnostic accuracy for breast images.

[0010] FIG. 1 is a block diagram showing a configuration of a first information processing device according to the present disclosure. FIG. 2 is a diagram showing a processing state by a first information processing device according to the present disclosure. FIG. 3 is a diagram showing a processing state by a first information processing device according to the present disclosure. FIG. 4 is a flowchart showing a processing operation of a first information processing device according to the present disclosure. FIG. 5 is a flowchart showing a processing operation of a second information processing device according to the present disclosure. FIG. 6 is a diagram showing a processing state by a third information processing device according to the present disclosure. FIG. 7 is a flowchart showing a processing operation of a third information processing device according to the present disclosure. FIG. 8 is a block diagram showing a configuration of a fourth information processing device according to the present disclosure. FIG. 9 is a flowchart showing a processing operation of the fourth information processing device according to the present disclosure. FIG. 10 is a block diagram showing a configuration of a fifth information processing device according to the present disclosure. FIG. 11 is a flowchart showing a processing operation of the fifth information processing device according to the present disclosure. FIG. 12 is a block diagram showing a hardware configuration of a sixth information processing device according to the present disclosure. FIG. 13 is a block diagram showing a configuration of the sixth information processing device according to the present disclosure.

[0011] First Embodiment A first embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings may be relevant to any embodiment.

[0012] [Configuration] The information processing device in the present disclosure can be used to perform image diagnosis on images of the human body, particularly breast images, taken using imaging devices such as mammography, breast tomosynthesis, PET (Positron Emission Tomography), and MRI (Magnetic Resonance Imaging).

[0013] The information processing device 10 in this embodiment is composed of one or more information processing devices each including a calculation device and a storage device. As shown in FIG. 1 , the information processing device 10 includes an image acquisition unit 11, a state estimation unit 12, a diagnostic technique setting unit 13, an image diagnosis unit 14, and a display processing unit 15. The functions of the image acquisition unit 11, the state estimation unit 12, the diagnostic technique setting unit 13, the image diagnosis unit 14, and the display processing unit 15 can be realized by the calculation device executing a program for realizing each function stored in the storage device. The information processing device 10 also includes an image storage unit 16 and a model storage unit 17. The image storage unit 16 and the model storage unit 17 are each configured as a storage device.

[0014] An imaging device 20 and a display device 30 are connected to the information processing device 10. The imaging device 20 is, for example, an X-ray imaging device that captures breast images. However, the imaging device 20 is not limited to being an X-ray imaging device, and may be an imaging device that captures breast images based on any principle. The display device 30 is a display that can display image data and text data, and displays diagnostic information to, for example, a diagnostician such as a doctor who performs image diagnosis or a patient whose breast image has been captured. However, the display device 30 may display diagnostic information in any form. Each component will be described in detail below.

[0015] The image acquisition unit 11 acquires breast images from the above-described imaging device 20 and stores them in the image storage unit 16. At this time, the image acquisition unit 11 stores the breast images in association with patient identification information (patient ID) that identifies the patient whose breast images were acquired, and may also store the breast images in association with patient data such as patient attributes. The image acquisition unit 11 may acquire one breast image for the same patient, or may acquire and store multiple breast images. The image acquisition unit 11 may also acquire breast images via a network from another information processing device that stores breast images.

[0016] The state estimation unit 12 (estimation unit) performs image processing on the breast image to estimate the state of the mammary gland tissue contained in the breast image. In this embodiment, the state of the breast tissue is estimated by estimating the extent to which normal mammary gland tissue is contained in the breast image, and the image is classified into classes according to the estimated extent to which normal mammary gland tissue is contained. Specifically, the state of the mammary gland tissue can be indicated, for example, by mammary gland density. Mammary gland density indicates the ratio of the area within the imaged breast region where the area is thought to have originally been occupied by mammary gland tissue to the area actually occupied by mammary gland tissue, where the denominator is the area of ​​the area.

[0017] The state estimation unit 12 performs classification of breast density using, for example, a classification model using a trained neural network or the like. In this case, classification criteria include a four-value classification based on BI-RADS, known as the international comprehensive guideline for breast imaging diagnosis, and a binary classification that classifies breasts as dense or thin (fatty) breasts. In this embodiment, the state estimation unit 12 estimates whether the breast density is dense or thin.

[0018] Here, the classification model using a neural network or the like is generated in advance by supervised learning in a format in which a breast image is input and a classification label is output, and is stored in the model storage unit 17. However, the classification of breast tissue state, i.e., mammary gland density, performed by the state estimation unit 12 is not limited to being performed using the model described above, and may be performed by any method. Furthermore, as will be described in other embodiments, the estimation of breast tissue state by the state estimation unit 12 is not necessarily limited to performing classification of mammary gland density, and may instead estimate the value of mammary gland density.

[0019] In this embodiment, the state estimation unit 12 estimates the mammary gland density as the state of the mammary gland tissue (hereinafter also referred to as the mammary gland state), but the state of the mammary gland tissue may be estimated using other indices. For example, the state estimation unit 12 may use the extent of mammary gland expansion as an index and estimate a numerical value representing the extent of the mammary gland expansion or a classification based on the extent of the expansion. The extent of the mammary gland expansion may be, for example, a numerical value representing the degree to which the mammary glands are distributed uniformly within the breast or whether they are distributed in clusters in specific areas, or a classification based on such a numerical value. However, the state of the mammary gland tissue may be any information about the mammary gland tissue obtained from a breast image.

[0020] The diagnostic technique setting unit 13 (setting unit) sets an imaging diagnostic technique for breast images based on the class of mammary gland condition classified by the above-mentioned condition estimation unit 12. In this embodiment, a preset model (diagnostic model) that outputs diagnostic information in response to input of a breast image is used as the imaging diagnostic technique, and the diagnostic technique setting unit 13 selects the model to be used in accordance with the class.

[0021] Here, multiple models to be selected are stored in advance in the model storage unit 17. Each model corresponds to a class related to mammary gland conditions and has been trained in advance as a model that provides the highest diagnostic accuracy for breast images classified into the corresponding class. In this embodiment, the model is trained to output, as diagnostic information, the malignancy score, the type of lesion, and the corresponding location within the image (e.g., a rectangular display) for an input breast image. As an example, the model may be one in which neural network parameters are optimally trained by fine-tuning or the like using training data in which breast images belonging to the corresponding class are associated with the malignancy score, the type of lesion, and a rectangular display of the corresponding location within the breast image, either in image units or in lesion candidate regions, as training data; one in which the network structure itself is designed for each class; or one that combines multiple of these models. In this embodiment, since the classes classified based on breast density are binary, high density and low density, two corresponding models, a high density model and a low density model, are selectable.

[0022] Note that the diagnostic procedure setting unit 13 is not limited to setting an imaging diagnostic procedure by selecting a model according to a class as described above, and may set an imaging diagnostic procedure by other methods. For example, the diagnostic procedure setting unit 13 may set an imaging diagnostic procedure by setting, according to a class, an output rule for a model that outputs diagnostic information according to input breast images. As an example, when a final diagnostic result is output using a model that calculates the malignancy score described above and a preset threshold for the malignancy score, the output rule may be set by adjusting the threshold using a function of a predesigned mammary gland condition class. Alternatively, when a malignancy score S is output as a diagnostic result, a specific function f(S) for calculating the malignancy score S may be set according to a mammary gland condition class. However, the diagnostic procedure set by the diagnostic procedure setting unit 13 described above is merely an example, and any diagnostic procedure may be set according to a class.

[0023] The diagnostic imaging unit 14 (diagnostic unit) performs a diagnosis on a breast image using the diagnostic imaging method set by the diagnostic method setting unit 13. In this embodiment, the diagnostic imaging unit 14 inputs a breast image into a model selected according to the class of breast density estimated from the breast image as described above, and acquires information output from the model as a diagnostic result. For example, the diagnostic imaging unit 14 acquires diagnostic information from the model, such as the malignancy score, the type of lesion suspected to develop (e.g., mass, architectural distortion, local asymmetric shadow, calcification), the region of the lesion in the breast image, the malignancy score for each region, and the characteristics of the lesion shape, and passes this information to the display processing unit 15. At this time, the diagnostic imaging unit 14 also passes information such as the breast image and patient ID to the display processing unit 15.

[0024] The display processor 15 outputs the diagnostic information and the like received from the diagnostic imaging unit 14 to the display device 30. For example, as shown in FIG. 2 , the display processor 15 displays a breast image G, along with the class "Breast Density: D" D1, which is the estimated breast condition, the selected diagnostic imaging method "Diagnostic Mode: High (High Density Diagnostic Mode)" D2, "Malignancy Score: 90%" D3, and the type of suspected lesion "Diagnostic Result: Mass" D4. Note that in this embodiment, the breast condition is classified into two classes, such as "high density" or "low density," so a model corresponding to "high density" is selected as the diagnostic imaging method, and the selected model is displayed in the "Diagnostic Mode" D2 field. That is, in the example of FIG. 2 , the character "high," indicating that a model corresponding to "high density" has been selected, is displayed highlighted. In addition, as shown in Figure 2, the display processing unit 15 may display on the breast image G the type of lesion suspected to have developed, "tumor" D4, and the area of ​​the lesion (dotted rectangle) A1, and may also display the characteristics of the lesion shape, etc., such as "Note: circular" D5.

[0025] The display processing unit 15 may simultaneously display the diagnostic information of multiple patients, etc., passed from the diagnostic imaging unit 14, in a list format, as shown in Fig. 3. In this case, the display processing unit 15 does not necessarily display breast images or areas corresponding to lesions on the screen, as shown in Fig. 3. However, when displaying the diagnostic information of multiple patients, the display processing unit 15 may display breast images or areas corresponding to lesions on the screen.

[0026] [Operation] Next, a description will be given of the operation of the above-mentioned information processing device 10. The image acquisition unit 11 acquires breast images from the imaging device 20, an image storage medium, etc. (Step S11 in FIG. 4). The acquired images are output to the condition estimation unit 12, the image diagnosis unit 14, and the display processing unit 15 for use, as will be described later.

[0027] Next, the state estimation unit 12 estimates the state of the mammary gland tissue contained in the breast image. In this embodiment, the density values ​​of the mammary gland tissue are classified into classes (step S12 in FIG. 4). Here, it is assumed that the density values ​​of the mammary gland tissue are classified into the high density class out of the two classes of high density and low density. The state estimation unit 12 then outputs the estimated results of the mammary gland density to the diagnostic technique setting unit 13, the image diagnosis unit 14, and the display processing unit 15.

[0028] Next, the diagnostic method setting unit 13 sets an image diagnostic method according to the classification result of the mammary gland condition. In this embodiment, a diagnostic model corresponding to the class is selected (step S13 in FIG. 4). Here, it is assumed that a model corresponding to the high density class is selected.

[0029] Next, the image diagnosis unit 14 receives the set image diagnosis method, performs image diagnosis on the breast image using the image diagnosis method, and outputs the diagnosis results to the display processing unit 15. In this embodiment, the breast image is input to a model corresponding to the high density class, and diagnostic information is output from the model (step S14 in FIG. 4).

[0030] The display processing unit 15 then outputs the diagnostic information from the diagnostic imaging unit 14 to the display device 30 (step S15 in FIG. 4). In this embodiment, as shown in FIG. 2, the display processing unit 15 outputs the breast image G together with the estimated breast density class (breast density), the model (diagnostic mode) D2 selected as the diagnostic imaging method, the malignancy score D3 output by the model, and the diagnostic result D4, etc.

[0031] As described above, in this embodiment, an imaging diagnostic method is set according to the state of the mammary gland tissue contained in the breast image, and imaging diagnosis is performed using this method. This allows an appropriate imaging diagnostic method to be applied to breasts with various states of mammary gland density, etc., enabling highly accurate diagnosis.

[0032] The tendency for lesions to be imaged on breast images varies significantly depending on the amount of glandular tissue contained in the breast. Therefore, when using a diagnostic method that does not explicitly consider differences in lesion image tendencies due to differences in glandular conditions, such as glandular density, it is difficult to perform a uniform diagnosis with high accuracy on all breast images. For example, research has shown that when a CNN (convolutional neural network) model that performs image diagnosis using large amounts of data is trained and used, the diagnostic accuracy of malignant lesions decreases by approximately 10% in dense breasts compared to low-density breasts. To address this issue, highly accurate diagnoses can be achieved by setting a diagnostic method that corresponds to differences in glandular conditions, such as glandular density, as in the present embodiment.

[0033] Furthermore, in this embodiment, information indicating the actually selected diagnostic imaging technique is displayed along with the diagnostic results. This allows the diagnostician and the patient being diagnosed to be presented with information regarding the reliability of the displayed diagnostic results and the criteria for judgment. For example, if a diagnostician performs imaging diagnosis using a diagnostic imaging technique specialized for high-density breasts on a breast image that the diagnostician determines to be a high-density breast, the diagnostician can have confidence in the diagnostic results obtained by the device. On the other hand, if a diagnostician performs imaging diagnosis using a diagnostic imaging technique specialized for low-density breasts on a breast image that the diagnostician determines to be a high-density breast, the diagnostician can take action such as immediately rejecting the diagnostic results obtained by the device, thereby improving the final diagnostic accuracy throughout the diagnostic process performed by the diagnostician.

[0034] Second Embodiment A second embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings may be relevant to any of the embodiments.

[0035] [Configuration] The information processing device 10 in this embodiment has a configuration substantially similar to that of the information processing device described in the above-mentioned embodiment 1. That is, as shown in FIG. 1 , the information processing device 10 includes an image acquisition unit 11, a state estimation unit 12, a diagnostic technique setting unit 13, an image diagnosis unit 14, a display processing unit 15, an image storage unit 16, and a model storage unit 17. The information processing device 10 in this embodiment further differs from embodiment 1 in the configuration described below. Below, the configuration that differs from embodiment 1 described above will be mainly described in detail.

[0036] Similarly to the above, the state estimation unit 12 performs image processing on the breast image to estimate the state of the mammary gland tissue contained in the breast image, and particularly estimates an index related to the mammary gland state using a continuous value. For example, the state estimation unit 12 obtains a mammary gland density value by inputting the breast image into a regression model using a trained neural network or the like. Such a neural network is obtained by supervised learning using training data in which a breast image is input and continuous values ​​between 0 and 1 are associated with mammary gland density values. Note that the state estimation unit 12 is not necessarily limited to outputting a mammary gland density value, and may output a continuous value representing another state of the mammary gland using another model.

[0037] The diagnostic technique setting unit 13 receives the breast density value output from the state estimation unit 12 and sets a diagnostic technique. For example, the diagnostic technique setting unit 13 may classify the received breast density value based on a preset threshold and set an imaging diagnostic technique corresponding to the class classification, as in the first embodiment. The diagnostic technique setting unit 13 may also set an imaging diagnostic technique corresponding to the received breast density value. Alternatively, the diagnostic technique setting unit 13 may set an imaging diagnostic technique by setting, according to the class, an output rule in a model that outputs diagnostic information in response to input breast images. As an example, for a diagnostic technique that makes a final diagnosis using a model trained under supervision to output a malignancy score and a threshold related to the malignancy score, the imaging diagnostic technique may be set by setting the threshold related to the malignancy score using a predefined function of the breast density value. However, the diagnostic technique set by the diagnostic technique setting unit 13 described above is merely an example, and any diagnostic technique may be set according to the breast density value.

[0038] The image diagnosis unit 14 performs a diagnosis on a breast image using the image diagnosis method set by the diagnostic method setting unit 13. At this time, the image diagnosis unit 14 inputs breast images and mammary gland density values ​​to a neural network used as a model set as the image diagnosis method as described above, and obtains information output from the neural network as a diagnostic result. In this case, the neural network is obtained by supervised learning so as to input mammary gland density values ​​and breast images and output a diagnostic result.

[0039] Similarly to the above, the display processing unit 15 outputs the diagnostic information and the like received from the diagnostic imaging unit 14 to be displayed on the display device 30. At this time, the display processing unit 15 may display the mammary gland density value estimated by the condition estimation unit 12 in addition to the diagnostic mode indicating the diagnostic imaging technique set together with the breast image and the diagnostic result, as shown in FIG.

[0040] [Operation] Next, a description will be given of the operation of the above-mentioned information processing device 10. The image acquisition unit 11 acquires breast images from the imaging device 20, an image storage medium, etc. (step S21 in FIG. 5 ). The acquired images are output to the condition estimation unit 12, the image diagnosis unit 14, and the display processing unit 15 for use, as will be described later.

[0041] Next, the state estimation unit 12 estimates the state of the mammary gland tissue contained in the breast image using a continuous mammary gland density value (step S22 in FIG. 5 ), and outputs the mammary gland density value to the diagnostic technique setting unit 13, the image diagnosis unit 14, and the display processing unit 15.

[0042] Next, the diagnostic technique setting unit 13 sets an image diagnostic technique according to the mammary gland density value. In this embodiment, a diagnostic model corresponding to the mammary gland density value is selected (step S23 in FIG. 5). Here, it is assumed that a model corresponding to high density is selected based on the mammary gland density value.

[0043] Next, the image diagnosis unit 14 receives the set image diagnosis method, performs image diagnosis on the breast image using the image diagnosis method, and outputs the diagnosis results to the display processing unit 15. In this embodiment, the breast image and the mammary gland density value are input to a model corresponding to high density, and diagnostic information is output from the model (step S24 in FIG. 5).

[0044] The display processing unit 15 then outputs the diagnostic information from the diagnostic imaging unit 14 to the display device 30 (step S15 in FIG. 4). In this embodiment, the display processing unit 15 outputs the breast image G together with the estimated breast density value, the model selected as the diagnostic imaging method, the malignancy score and the diagnostic result that are the output results of the model, and the like.

[0045] As described above, in this embodiment, the mammary gland condition is estimated as a continuous value by regression, and an imaging diagnostic method is set according to the continuous value. This makes it possible to set an imaging diagnostic method that is more appropriate according to the mammary gland condition, and to perform a diagnosis with even higher accuracy.

[0046] Third Embodiment A third embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings may be relevant to any of the embodiments.

[0047] [Configuration] The information processing device 10 in this embodiment has a configuration similar to that of the information processing device described in the above-described embodiment. That is, as shown in FIG. 1 , the information processing device 10 includes an image acquisition unit 11, a state estimation unit 12, a diagnostic technique setting unit 13, an image diagnosis unit 14, a display processing unit 15, an image storage unit 16, and a model storage unit 17. The information processing device 10 in this embodiment further differs from other embodiments in the following configuration. Below, the configuration that differs from the above-described other embodiments will be mainly described in detail.

[0048] The state estimation unit 12 performs image processing on the breast image as described above and estimates a mammary gland density value as the state of mammary gland tissue in the entire breast image. In this embodiment, the state estimation unit 12 estimates local mammary gland conditions within the breast image. For example, the state estimation unit 12 sets partial regions in the breast image on a pixel-by-pixel basis or on a region-by-region basis consisting of multiple adjacent pixels, and estimates a mammary gland density value for each partial region. Specifically, the state estimation unit 12 generates a mammary gland density value map in which a mammary gland density value is set for each pixel of the breast image using a model having a supervised trained neural network that outputs mammary gland density values ​​on a pixel-by-pixel basis. The mammary gland density value map is corrected for each pixel according to the mammary gland density value of the entire image, and is output as local mammary gland density information. The state estimation unit 12 is not limited to estimating local mammary gland density values, and may estimate any value representing the local mammary gland condition, such as the probability that a mammary gland has ever been present at that location.

[0049] Furthermore, the state estimation unit 12 calculates a threshold from the breast density value of the entire breast image and performs binary class classification for each pixel in the breast image based on the threshold and the breast density value map. Specifically, when calculating the threshold, for example, T is the area of ​​the region with a breast density value equal to or greater than the threshold, B is the area of ​​the entire breast region obtained by Otsu's binarization method or the like, and D is the breast density value of the entire image. The correspondence between these is defined as T / B = g(D) using a function g, and the threshold is adjusted to achieve T for which the above equation holds. Furthermore, the threshold used for breast density classification for each pixel may be set using a pre-fixed value rather than the breast density value of the entire image. The state estimation unit 12 is not limited to classifying partial regions, such as pixels, into binary classes; it may also classify into more classes, or it may calculate continuous values ​​of breast density values ​​on a pixel-by-pixel or region-by-region basis. However, the processing by the state estimation unit 12 described above is merely exemplary, and other methods may be used to locally estimate the state of the mammary glands.

[0050] The diagnostic technique setting unit 13 receives input of the locally estimated mammary gland state as described above and locally sets a diagnostic technique. For example, when multi-class classification is performed for mammary gland density for each pixel or region, the diagnostic technique setting unit 13 sets, for each pixel or region, an imaging diagnostic technique corresponding to the mammary gland density class for each pixel or region. Note that the setting of an imaging diagnostic technique according to the class classification is similar to the method described above. Alternatively, when mammary gland density for each pixel or region is estimated using continuous values, the diagnostic technique setting unit 13 may set an imaging diagnostic technique according to the continuous values ​​estimated for each pixel or region.

[0051] The image diagnosis unit 14 diagnoses breast images based on the image diagnosis method set by the diagnostic method setting unit 13. For example, if the diagnostic method setting unit 13 sets an image diagnosis method for each region, the diagnosis is performed using the image diagnosis method set for each region. The diagnostic results calculated for each region are then aggregated for the entire image. When aggregating, the lesions detected in each region may be output together, or the malignancy scores calculated for each region may be added up and one malignancy score may be output for one breast image.

[0052] As an example, when the diagnostic imaging method is set for each region or pixel in the diagnostic method setting unit 13, the diagnostic imaging unit 14 may perform diagnostic processing according to the following method. First, the diagnostic imaging unit 14 detects candidate lesion regions using all of the lesion detection methods set in the diagnostic method setting unit 13. At this time, for example, detection is performed using rectangular display or segmentation using a supervised learning model. After that, for example, the mammary gland condition class that accounts for the largest proportion of pixels included in the lesion region detected by the diagnostic imaging method corresponding to class A is regarded as the mammary gland condition class X of that region. At this time, if class X does not match class A, the detected lesion region is rejected and is not output as a diagnostic result.

[0053] As another example, when the diagnostic imaging technique setting unit 13 sets an imaging technique corresponding to continuous breast density values, the diagnostic imaging unit 14 may input breast images and breast density values ​​to a model set for each region, as described above, to output a diagnostic result. Alternatively, the diagnostic imaging unit 14 may input the spatial map itself containing local breast information and obtain a diagnostic result by inputting the spatial map described above to a supervised trained model that outputs a local diagnostic result. Note that the diagnostic imaging process described above by the diagnostic imaging unit 14 is merely an example, and any other method may be used for the diagnostic imaging process.

[0054] The display processor 15 outputs the diagnostic information, etc., received from the diagnostic imaging unit 14 to the display device 30 for display. For example, as shown in FIG. 6 , the display processor 15 displays a breast image G, along with the estimated breast density and classification class "Breast Density: 9.85 (D)" D1, the selected diagnostic imaging method "Diagnostic Mode" D2, "Malignancy Score: 95%" D3, and the suspected lesion type "Diagnostic Result: Mass" D4. In this embodiment, the display processor 15 may define a color or the like corresponding to local breast information (breast density) and highlight each pixel on the breast image G. For example, in the example of FIG. 6 , if the breast density of each partial region is classified into two classes, the region R1 of pixels belonging to the high breast density class may be highlighted using a first display method, and the region R2 of pixels belonging to the low breast density class may be highlighted using a second display method. Furthermore, the display processing unit 15 may display, for each region R1, R2, a "diagnosis mode" D21, D22, a type of lesion suspected of developing D41, D42, and a region A1, A2 of the lesion, as shown in Fig. 6. In the example of Fig. 6, for region R1 of the high glandular density class, a diagnostic mode D21 specialized for dense breasts is set, and the detected lesion is displayed as "mass 1" D41. For region R2 of the low glandular density class, a diagnostic mode D22 specialized for low-density breasts is set, and the detected lesion is displayed as "calcification 1" D42. However, the display method of the various information described above by the display processing unit 15 is merely an example, and other display methods or other information may be used.

[0055] [Operation] Next, a description will be given of the operation of the information processing device 10. The image acquisition unit 11 acquires breast images from the imaging device 20, an image storage medium, etc. (step S31 in FIG. 7 ). The acquired images are output to the condition estimation unit 12, the image diagnosis unit 14, and the display processing unit 15 for use, as described below.

[0056] Next, the state estimation unit 12 infers the state of the mammary gland tissue contained in the breast image in a class classification format. In this embodiment, the mammary gland density value is estimated for each pixel or region in the entire breast image, and the density values ​​are classified into classes for each region (step S32 in FIG. 7). Here, it is assumed that the density value of the mammary gland tissue is classified into the high-density class out of the two-value classes of high density and low density. The state estimation unit 12 then outputs the inference results to the diagnostic technique setting unit 13, the image diagnosis unit 14, and the display processing unit 15.

[0057] Next, the diagnostic technique setting unit 13 sets an imaging diagnostic technique according to the classification result of the mammary gland condition. In this embodiment, an imaging diagnostic technique is set according to the class classified for each pixel or each region (step S33 in FIG. 7). Here, it is assumed that a model corresponding to the high-density class is set for the first region R1 in FIG. 6, and a model corresponding to the low-density class is set for the second region R2.

[0058] Next, the diagnostic imaging unit 14 receives the diagnostic imaging method set for each region, performs diagnostic imaging on the breast image using the diagnostic imaging method set for each region, and outputs the diagnostic results to the display processing unit 15 (step S34 in FIG. 7 ). In this embodiment, for the first region R1 in FIG. 6 , the breast image of the first region R1 is input to a model corresponding to the high-density class, and for the second region R2, the breast image of the second region R2 is input to a model corresponding to the low-density class, thereby obtaining diagnostic information for each region R1 and R2. The diagnostic imaging unit 14 also aggregates the diagnostic results for each region R1 and R2 (step S35 in FIG. 7 ). For example, the diagnostic imaging unit 14 may aggregate only lesions set as more serious among the lesions in each region R1 and R2, or only lesions with a high probability of being diagnosed based on the output diagnostic results.

[0059] The display processing unit 15 then outputs the diagnostic information from the image diagnostic unit 14 to the display device 30 (step S36 in FIG. 7). In this embodiment, as shown in FIG. 6, the display processing unit 15 outputs the diagnostic information from the image diagnostic unit 14 to display, together with the breast image G, each of the regions R1 and R2, the class (color coding) of the breast density for each region, the model that is the diagnostic method for each region, the diagnostic result for each region, the overall malignancy score and diagnostic result, and the like.

[0060] As described above, in this embodiment, diagnosis is performed by setting a diagnostic method for each region in a breast image. Therefore, even in breast images where the breast density is not uniform, highly accurate diagnosis can be performed for each region. As a result, diagnostic accuracy can be further improved even when the location of a lesion varies.

[0061] Fourth Embodiment A fourth embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings may be relevant to any of the embodiments.

[0062] [Configuration] The information processing device 10 in this embodiment has substantially the same configuration as the information processing device described in the above-mentioned embodiments. That is, as shown in FIG. 8 , the information processing device 10 includes an image acquisition unit 11, a state estimation unit 12, a diagnostic technique setting unit 13, an image diagnosis unit 14, a display processing unit 15, an image storage unit 16, and a model storage unit 17. The information processing device 10 in this embodiment further includes an image correction unit 18 as shown in FIG. 8 . The image correction unit 18 is realized by the arithmetic unit of the information processing device 10 executing a program. Below, the configuration that differs from the other embodiments described above will be mainly described in detail.

[0063] The image corrector 18 (corrector) corrects breast images for diagnostic imaging based on the estimated mammary gland condition. In this embodiment, the image corrector 18 converts breast images according to the class of mammary gland density estimated by the condition estimator 12 as described above.

[0064] Examples of the breast image conversion process include brightness correction using the Contrast Limited Adaptive Histogram Equalization (CLAHE) method and image conversion using a deep learning generation model such as a generative adversarial network (GAN). The deep learning generation model is, for example, CycleGAN, which is trained to convert a high-density breast image into a low-density breast image when it is input.

[0065] For example, when the state estimation unit 12 classifies breast images into two classes based on breast density, the image correction unit 18 may perform brightness correction using the CLAHE method for classes corresponding to high density, and perform identity conversion without correction for low-density breasts. Furthermore, when the state estimation unit 12 classifies breast images into multiple classes (three or more values) based on breast density, the image correction unit 18 may perform image conversion using a deep learning generative model, such as CycleGAN, that has been appropriately trained for each class. Furthermore, when the state estimation unit 12 estimates continuous values ​​of breast density, the image correction unit 18 may also use the breast density values ​​as input for the model used for image conversion. In this case, the model used in the image correction unit 18 is trained to convert a high-density image and breast density values ​​into a low-density breast image, for example. However, the image correction unit 18 may perform correction processing, such as image conversion, using any method.

[0066] The image diagnosis unit 14 performs image diagnosis on the breast image corrected by the image correction unit 18, using the diagnostic method set by the diagnostic method setting unit 13. At this time, the model used for diagnosis may be a model trained using the image corrected by the image correction unit 18.

[0067] 2 and 6, the display processing unit 15 displays and outputs information such as breast images, estimated breast density, the selected imaging diagnostic method, and diagnostic results. Furthermore, the display processing unit 15 may display breast images corrected by the image corrector 18, and in this case, the corrected breast images may be displayed together with the uncorrected breast images, or only the corrected breast images may be displayed without displaying the uncorrected breast images.

[0068] Here, the image correction unit 18 may perform image conversion for each region of the breast image according to the mammary gland condition of that region, as described above. For example, the image correction unit 18 performs image correction processing for each region according to the mammary gland density class estimated for that region, and generates an image I(J) for that region corresponding to class J. The image diagnosis unit 14 then performs detection of potential lesion regions in the corrected image I(J) using the diagnostic technique M(J) set for the mammary gland density class J for that region in the diagnostic technique setting unit 13. This may be performed for all classes J, and for potential lesion regions detected in the image I(J) for each region using the mammary gland density for that region, if the representative mammary gland density class for that region does not match the estimated class J, the lesion region may be rejected.

[0069] [Operation] Next, a description will be given of the operation of the above-described information processing device 10. The image acquisition unit 11 acquires breast images from the imaging device 20, an image storage medium, etc. (step S41 in FIG. 9 ). The acquired images are output to and used by the condition estimation unit 12, the image diagnosis unit 14, the display processing unit 15, and the image correction unit 18, as will be described later.

[0070] Next, the state estimation unit 12 infers the state of the mammary gland tissue contained in the breast image. In this embodiment, the density values ​​of the mammary gland tissue are classified into classes (step S42 in FIG. 9 ). Here, it is assumed that the density values ​​of the mammary gland tissue are classified into the high-density class out of the two-value classes of high density and low density. The state estimation unit 12 then outputs the inference results to the diagnostic technique setting unit 13, the image diagnosis unit 14, the display processing unit 15, and the image correction unit 18.

[0071] Next, the image corrector 18 performs a correction process on the breast image according to the classified class (step S43 in FIG. 9). For example, the image corrector 18 performs a luminance correction process on the breast image.

[0072] Next, the diagnostic method setting unit 13 sets an image diagnostic method according to the classification result of the mammary gland condition. In this embodiment, a diagnostic model corresponding to the class is selected (step S44 in FIG. 9).

[0073] Next, the image diagnosis unit 14 receives the set image diagnosis method, performs image diagnosis on the breast image corrected by the image diagnosis method, and outputs the diagnosis result to the display processing unit 15 (step S45 in FIG. 9).

[0074] The display processing unit 15 then outputs the diagnostic information from the diagnostic imaging unit 14 to the display device 30 (step S46 in FIG. 9 ). At this time, the display processing unit 15 outputs the estimated state of breast density, the model selected as the diagnostic imaging method, the malignancy score and diagnostic result output by the model, and the like, together with the breast image G, as described above, and may also display and output the corrected breast image.

[0075] As described above, in this embodiment, breast images are corrected according to the state of the mammary glands, and image diagnosis is performed using the corrected breast images. For example, the image correction unit 18 can improve the detection accuracy of lesions that overlap with the mammary gland tissue by performing contrast enhancement processing using the CLAHE method only on high-density breasts. Furthermore, performing contrast enhancement processing using the CLAHE method on low-density breasts, in which lesions are clearly imaged, can result in a decrease in diagnostic accuracy due to information loss caused by image preprocessing. However, by using information about the mammary gland density estimated in advance, it is possible to avoid a decrease in diagnostic accuracy due to excessive image preprocessing. Thus, in this embodiment, by appropriately correcting input breast images according to not only the diagnostic technique but also the mammary gland density, it is possible to perform image diagnosis with even higher accuracy for mammary gland density.

[0076] Fifth Embodiment A fifth embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings may be relevant to any of the embodiments.

[0077] [Configuration] The information processing device 10 in this embodiment has substantially the same configuration as the information processing device described in the above-mentioned embodiments. That is, as shown in FIG. 10 , the information processing device 10 includes an image acquisition unit 11, a state estimation unit 12, a diagnostic technique setting unit 13, an image diagnosis unit 14, a display processing unit 15, an image storage unit 16, and a model storage unit 17. The information processing device 10 in this embodiment further includes an update unit 19 as shown in FIG. 10 . The update unit 19 is realized by the arithmetic unit of the information processing device 10 executing a program. An input device 40, such as a keyboard or a mouse, capable of inputting information is also connected to the information processing device 10. Hereinafter, the configuration that is different from the other embodiments described above will be mainly described in detail.

[0078] 2 and 6, the display processing unit 15 mainly displays the breast image G, the estimated mammary gland condition D1 (mammary gland density and class), the set imaging diagnostic technique D2 (diagnostic mode), the diagnostic result D4, etc. on the display device 30. At this time, the display processing unit 15 displays the estimated mammary gland condition D1 (mammary gland density and class) and the set imaging diagnostic technique D2 (diagnostic mode) in a manner that allows them to be modified. This allows the diagnostician performing the imaging diagnosis to check the displayed mammary gland condition, imaging diagnostic technique, diagnostic result, etc., and, if necessary, operate the input device 40 to input modification information for the mammary gland condition D1 (mammary gland density and class) and the imaging diagnostic technique D2 (diagnostic mode) displayed on the display device 30.

[0079] The update unit 19 (input unit) receives correction information for the estimated mammary gland condition D1 (mammary gland density and class) and the set imaging diagnostic method D2 (diagnostic mode) input by the diagnostician via the input device 40 as described above, and updates the estimated mammary gland condition D1 (mammary gland density and class) and the set imaging diagnostic method D2 (diagnostic mode) with the correction information. At this time, the update unit 19 passes the input correction information to the corresponding processing units. For example, when the mammary gland condition, i.e., the mammary gland density or class, is corrected, the update unit 19 passes the correction information to the condition estimation unit 12, and when the imaging diagnostic method is corrected, the update unit 19 passes the correction information to the diagnostic method setting unit 13.

[0080] When the state estimation unit 12 receives correction information for the mammary gland density or class, which is the mammary gland state, from the update unit 19, it estimates the state of the breast image to the mammary gland density or class corresponding to the correction information. That is, when it receives correction information for the mammary gland density, it assumes that it has estimated the mammary gland density corresponding to the correction information and performs class classification according to the mammary gland density, or when it receives correction information for the class, it assumes that it has estimated the class corresponding to the correction information. As an example, even if the estimated class before correction was the low-density class, if the correction information indicates the high-density class, it estimates the class of the breast image to be the high-density class. The state estimation unit 12 then passes the new mammary gland density or class based on the correction information to the diagnostic technique estimation unit 13 and the display processing unit 15.

[0081] When a new breast density or class is estimated by the state estimation unit 12 based on the correction information, the diagnostic method setting unit 13 newly sets an imaging diagnostic method corresponding to the new breast density or class. For example, the diagnostic method setting unit 13 selects a model corresponding to the new breast density or class, or sets an output rule by the model to correspond to the new breast density or class. As an example, even if a low-density class model was selected before correction, when a high-density class is newly estimated based on the correction information, the diagnostic method setting unit 13 selects a high-density class model as the imaging diagnostic method for the corresponding breast image.

[0082] Furthermore, when the diagnostic technique setting unit 13 receives correction information for the diagnostic imaging technique from the update unit 19, it sets the diagnostic imaging technique corresponding to the correction information. As an example, even if a low-density class model was selected before the correction, if the correction information has corrected it to a high-density class, it selects a high-density class model as the diagnostic imaging technique for the corresponding breast image.

[0083] The image diagnosis unit 14 performs diagnosis on the breast image using the image diagnosis method newly set by the diagnostic method setting unit 13 based on the correction information as described above. As an example, even if image diagnosis was performed using a low-density class model before the correction, if a high-density class model is set by the above-mentioned correction, image diagnosis is performed on the corresponding breast image using the high-density class model.

[0084] The display control unit 15 then displays the mammary gland condition D1 (mammary gland density and class) and image diagnostic method D2 (diagnostic mode) based on the input correction information, or the image diagnostic method D2 newly set from the mammary gland condition D1 based on the correction information, as well as the diagnostic result D4 based on the corrected image diagnosis.

[0085] The above-described configuration can also be applied to all of the other embodiments described above. For example, if the mammary gland density value, which is the mammary gland state estimated by the state estimation unit 12, is a continuous value, such continuous value can be used as correction information. In this case, the mammary gland density value may be input in a seek bar format. Furthermore, if the state estimation unit 12 estimates a class by classifying continuous values ​​such as mammary gland density values, a threshold value for the continuous value can be used as correction information. In this case, too, the threshold value may be input in a seek bar format, for example.

[0086] Furthermore, when the state estimation unit 12 estimates the mammary gland state for each region of the breast image, or when the diagnostic imaging method setting unit 13 sets the diagnostic imaging method for each region of the breast image, the mammary gland state (density value or class) or diagnostic imaging method (model or output rule) for each region of the breast image can be used as correction information. In this case, when the mammary gland state (density value or class) or diagnostic imaging method (model or output rule) is corrected for each region of the breast image, the corrected information is used to estimate the mammary gland state for each region, set the diagnostic imaging method, and perform image diagnosis and display output. Furthermore, when the information processing device 10 is equipped with the image correction unit 18 described above, the breast image is corrected using a correction method corresponding to the corrected mammary gland state, such as the corrected mammary gland density value.

[0087] [Operation] Next, we will explain the operation of the above-mentioned information processing device 10. First, as described above, it is assumed that the mammary gland condition is estimated from a breast image, image diagnosis is performed using a diagnostic model corresponding to the mammary gland condition, and diagnostic results, etc. are output (steps S51 to S55 in FIG. 11). At this time, the display processing unit 15 displays the estimated mammary gland condition and the set image diagnosis method so that they can be modified.

[0088] Subsequently, when the diagnostician performing the imaging diagnosis inputs correction information for the mammary gland state or imaging diagnostic technique (Yes in step S56 of FIG. 11 ), the update unit 19 updates the mammary gland state and imaging diagnostic technique using the input correction information (step S57 of FIG. 11 ). The state estimation unit 12 then newly estimates the mammary gland density value and class, which represent the state of the mammary gland tissue contained in the breast image, based on the content of the correction information (step S52 of FIG. 11 ). In response, the diagnostic technique setting unit 13 sets the imaging diagnostic technique based on the newly estimated mammary gland density value and class (step S53 of FIG. 11 ). Alternatively, the diagnostic technique setting unit 13 newly sets the imaging diagnostic technique for the breast image based on the content of the correction information (step S53 of FIG. 11 ).

[0089] Next, the diagnostic imaging unit 14 receives the newly set diagnostic imaging technique and performs diagnostic imaging on the breast image using the newly set diagnostic imaging technique (step S54 in FIG. 11). The display processing unit 15 then outputs the diagnostic results from the diagnostic imaging unit 14, as well as information on the mammary gland condition and diagnostic imaging technique updated by the correction information, to the display device 30 (step S55 in FIG. 11).

[0090] As described above, in this embodiment, such information can be corrected using correction information for the mammary gland state and imaging diagnostic technique input by the diagnostician, etc. This makes it possible to set an appropriate imaging diagnostic technique through correction even when the reliability of the mammary gland state estimation result by the state estimation unit 12 is low or the quality of the breast image is poor, thereby further improving the final accuracy of the imaging diagnosis.

[0091] Sixth Embodiment Next, a sixth embodiment of the present disclosure will be described with reference to the drawings. This embodiment shows an outline of the configuration of the information processing device described in the above-mentioned embodiments. Note that Figures 12 and 13 are diagrams for explaining the configuration, and these diagrams may be relevant to any of the embodiments.

[0092] First, the hardware configuration of the information processing device 100 will be described with reference to Fig. 12. The information processing device 100 is configured as a general information processing device, and is equipped with the following hardware configuration, for example: CPU (Central Processing Unit) 101 (arithmetic unit); ROM (Read Only Memory) 102 (storage device); RAM (Random Access Memory) 103 (storage device); programs 104 loaded into RAM 103; storage device 105 storing programs 104; drive device 106 for reading and writing data from and to a storage medium 110 external to the information processing device; communication interface 107 for connecting to a communication network 111 external to the information processing device; input / output interface 108 for inputting and outputting data; and bus 109 for connecting the various components.

[0093] 12 shows an example of the hardware configuration of the information processing device 100, and the hardware configuration of the information processing device is not limited to the above-described case. For example, the information processing device may be configured with only a part of the above-described configuration, such as excluding the drive device 106. Furthermore, the information processing device may use a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating Point Number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof, instead of the above-described CPU.

[0094] The information processing device 100 can be equipped with an estimation unit 121, a setting unit 122, and a diagnosis unit 123 shown in FIG. 13 by having the CPU 101 acquire and execute the program group 104. The program group 104 is stored in advance in the storage device 105 or the ROM 102, for example, and is loaded into the RAM 103 and executed by the CPU 101 as needed. The program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in advance in the storage medium 110, and the drive device 106 may read and supply the programs to the CPU 101. However, the estimation unit 121, the setting unit 122, and the diagnosis unit 123 described above may be constructed using dedicated electronic circuits for realizing such means.

[0095] The estimation unit 121 estimates the state of mammary gland tissue contained in the input breast image. The setting unit 122 sets an imaging diagnostic technique based on the estimated state. The diagnosis unit 123 performs imaging diagnosis on the breast image using the set imaging diagnostic technique.

[0096] With the above-described configuration, the present disclosure sets an imaging diagnostic method according to the state of mammary gland tissue contained in a breast image and performs imaging diagnosis using the imaging diagnostic method, thereby enabling the application of an appropriate imaging diagnostic method to breasts with various states, such as mammary gland density, and enabling highly accurate diagnosis.

[0097] In addition, at least one or more of the functions of the above-mentioned estimation unit 121, setting unit 122, and diagnosis unit 123 may be executed by an information processing device installed and connected anywhere on the network, that is, they may be executed by so-called cloud computing.

[0098] The above-described program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-RWs, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program can also be supplied to a computer by various types of transitory computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer-readable media can be supplied to a computer via wired communication paths such as electric wires and optical fibers, or via wireless communication paths.

[0099] Although the present disclosure has been described above with reference to the above-described embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each of the above-described embodiments can be combined with other embodiments as appropriate.

[0100] <Supplementary Notes> Some or all of the above embodiments may also be described as in the following supplementary notes. Below, an outline of the configurations of an information processing device, an information processing method, and a program according to the present disclosure will be described. However, the present disclosure is not limited to the following configurations. (Supplementary Note 1) An information processing device comprising: an estimation unit that estimates the state of mammary gland tissue contained in an input breast image; a setting unit that sets an imaging diagnostic method based on the estimated state; and a diagnosis unit that performs imaging diagnosis on the breast image using the set imaging diagnostic method. (Supplementary Note 2) The information processing device according to Supplementary Note 1, wherein the setting unit selects a pre-set diagnostic model that outputs diagnostic information in response to input of the breast image based on the estimated state, and the diagnosis unit uses the selected diagnostic model to perform imaging diagnosis based on the diagnostic information output in response to input of the breast image. (Supplementary Note 3) The information processing device according to Supplementary Note 2, wherein the setting unit selects at least one diagnostic model from a plurality of diagnostic models based on the estimated state, and the diagnostic unit performs image diagnosis using the selected at least one diagnostic model based on the diagnostic information output in response to the input of the breast image. (Supplementary Note 4) The information processing device according to Supplementary Note 1, wherein the setting unit sets, based on the estimated state, an output rule for a predetermined diagnostic model that outputs diagnostic information in response to the input of the breast image, and the diagnostic unit uses the diagnostic model to perform image diagnosis based on the diagnostic information output according to the set output rule in response to the input of the breast image. (Supplementary Note 5) An information processing device according to Supplementary Note 1, wherein the estimation unit estimates the state of mammary gland tissue contained in each partial region set within the breast image, the setting unit sets the imaging diagnosis method for each partial region based on the estimated state, and the diagnosis unit performs imaging diagnosis on the partial region of the breast image using the set imaging diagnosis method for each partial region, and also performs imaging diagnosis on the breast image.(Supplementary Note 6) The information processing device according to Supplementary Note 1, comprising a correction unit that performs correction processing on the breast image based on the estimated state, and the diagnosis unit performs image diagnosis on the breast image that has been corrected using the set image diagnosis method. (Supplementary Note 7) The information processing device according to Supplementary Note 1, comprising an output unit that outputs the breast image, the estimated state, the set image diagnosis method, and the result of the image diagnosis. (Supplementary Note 8) The information processing device according to Supplementary Note 5, comprising an output unit that outputs the breast image, the partial regions set within the breast image, the estimated state for each partial region, the image diagnosis method set for each partial region, and the result of the image diagnosis. (Supplementary Note 9) The information processing device according to Supplementary Note 6, comprising an output unit that outputs the breast image and / or the breast image that has been corrected, the estimated state, the set image diagnosis method, and the result of the image diagnosis. (Supplementary Note 10) The information processing device according to Supplementary Note 1, comprising an input unit that accepts input of the diagnostic imaging technique, wherein the diagnostic unit performs diagnostic imaging on the breast image using the diagnostic imaging technique for which input has been accepted. (Supplementary Note 11) The information processing device according to Supplementary Note 5, comprising an input unit that accepts input of the diagnostic imaging technique for each partial region of the breast image, wherein the diagnostic unit, for each partial region, performs diagnostic imaging on the partial region of the breast image using the diagnostic imaging technique for which input has been accepted, and also performs diagnostic imaging on the breast image. (Supplementary Note 12) The information processing device according to Supplementary Note 1, comprising an input unit that accepts input of the state, wherein the setting unit sets the diagnostic imaging technique based on the state for which input has been accepted. (Supplementary Note 13) The information processing device according to Supplementary Note 5, comprising an input unit that accepts input of the state for each partial region of the breast image, wherein the setting unit sets the diagnostic imaging technique for each partial region based on the state for which input has been accepted.(Supplementary Note 14) The information processing device according to Supplementary Note 6, comprising an input unit that accepts input of the state, wherein the correction unit performs correction processing of the breast image based on the accepted input of the state. (Supplementary Note 15) The information processing device according to Supplementary Note 1, wherein the state is mammary gland density. (Supplementary Note 16) The information processing device according to Supplementary Note 1, wherein the setting unit sets a model generated by machine learning based on the estimated state, and the diagnosis unit performs image diagnosis by inputting the breast image into the set model and obtains information related to decision-making output from the model. (Supplementary Note 17) An information processing method that estimates the state of mammary gland tissue contained in an input breast image, sets an image diagnosis method based on the estimated state, and performs image diagnosis on the breast image using the set image diagnosis method. (Supplementary Note 18) A computer-readable storage medium storing a program for causing a computer to execute the following processes: estimating the state of mammary gland tissue contained in an input breast image; setting an image diagnosis method based on the estimated state; and performing image diagnosis on the breast image using the set image diagnosis method.

[0101] REFERENCE SIGNS LIST 10 Information processing device 11 Image acquisition unit 12 State estimation unit 13 Diagnostic technique setting unit 14 Image diagnosis unit 15 Display processing unit 16 Image storage unit 17 Model storage unit 18 Image correction unit 19 Update unit 20 Image capturing device 30 Display device 40 Input device 100 Information processing device 101 CPU 102 ROM 103 RAM 104 Program group 105 Storage device 106 Drive device 107 Communication interface 108 Input / output interface 109 Bus 110 Storage medium 111 Communication network 121 Estimation unit 122 Setting unit 123 Diagnosis unit

Claims

1. An estimation unit that estimates the state of the mammary gland tissue contained in the input breast image, A setting unit that sets an image diagnostic method based on the estimated state, A diagnostic unit that performs image diagnosis on the breast image using the configured image diagnosis method, Equipped with an information processing device.

2. An information processing apparatus according to claim 1, The setting unit selects a pre-configured diagnostic model that outputs diagnostic information in response to the input of the breast image, based on the estimated state. The diagnostic unit uses the selected diagnostic model to perform image diagnosis based on the diagnostic information output in response to the input of the breast image. Information processing device.

3. An information processing apparatus according to claim 2, The setting unit selects at least one of the diagnostic models from the plurality of diagnostic models based on the estimated state, The diagnostic unit performs image diagnosis based on the diagnostic information output in response to the input of the breast image, using at least one selected diagnostic model. Information processing device.

4. An information processing apparatus according to claim 1, The estimation unit estimates the state of the mammary gland tissue included in each partial region set within the breast image, The setting unit sets the image diagnostic method for each of the partial regions based on the estimated state, The diagnostic unit performs image diagnosis on each of the partial regions of the breast image using the set image diagnosis method, and also performs image diagnosis on the breast image. Information processing device.

5. An information processing apparatus according to claim 1, The system includes a correction unit that performs correction processing on the breast image based on the estimated state, The diagnostic unit performs image diagnosis on the breast image that has undergone correction processing using the configured image diagnosis method. Information processing device.

6. An information processing apparatus according to claim 4, The system includes an input unit that receives input of the state for each of the partial regions of the breast image, The setting unit sets the image diagnostic method for each of the subregions based on the state that has been received as input. Information processing device.

7. An information processing device according to claim 5, It includes an input unit that accepts input of the aforementioned state, The correction unit performs correction processing on the breast image based on the state that it has received as input. Information processing device.

8. An information processing apparatus according to claim 1, The setting unit sets a model generated by machine learning based on the estimated state, The diagnostic unit performs image diagnosis by inputting the breast image into the configured model and obtains information related to decision-making output from the model. Information processing device.

9. The information processing device is The state of the mammary gland tissue contained in the input breast image is estimated. Based on the estimated state, set up an image diagnostic method. The image diagnosis of the breast image is performed using the image diagnosis method that has been set. Information processing methods.

10. The state of the mammary gland tissue contained in the input breast image is estimated. Based on the estimated state, set up an image diagnostic method. The image diagnosis of the breast image is performed using the image diagnosis method that has been set. A program that causes a computer to perform a process.