_xcalculated for each training image 21 in which the inclusion relationship between the cancer region 201 and the muscularis propria region 202 is the partial inclusion relationship by the number of these images, can be used. As the average value A2, a value, which is obtained by dividing a total value of the probability sum ΣP_xcalculated for each training image 21 in which the inclusion relationship between the cancer region 201 and the muscularis propria region 202 is the complete inclusion relationship by the number of these images, can be used. It should be noted that the average value A1 is an example of a first average value according to the disclosed technology, and the average value A2 is an example of a second average value according to the disclosed technology.

E1=(A2+α)/(A1+A2+β) (1)

Expression (2) is an example of the loss L including the evaluation value E1 represented by Expression (1), as one of the elements. In Expression (2), an evaluation value E2 is another element of the loss L, W1 is a weight constant with respect to the evaluation value E1, and W2 is a weight constant with respect to the evaluation value E2. The evaluation value E1 mainly plays a role of improving the estimation accuracy of the inclusion relationship between the regions, and the evaluation value E2 mainly plays a role of improving the segmentation accuracy.

L=E1×W1+E2×W2 (2)

Expression (3) is an example of the evaluation value E2. As shown in Expression (3), soft dice loss can be used as the evaluation value E2. In Expression (3), G_ais a correct answer value for each pixel based on the range information 22A, 1 is added to the pixel that is the cancer region 201, and 0 is added to the pixel that is not the cancer region 201. P_ais a probability that the pixel is the cancer region 201, which is calculated by the estimation model 30. G_bis a correct answer value for each pixel based on the range information 22B, 1 is added to the pixel that is the muscularis propria region 202, and 0 is added to the pixel that is not the muscularis propria region 202. P_bis a probability that the pixel is the muscularis propria region 202, which is calculated by the estimation model 30. G_cis a correct answer value for each pixel based on the range information 22C, 1 is added to the pixel that is the mesorectum region 203, and 0 is added to the pixel that is not the mesorectum region 203. P_cis a probability that the pixel is the mesorectum region 203, which is calculated by the estimation model 30. γ, δ, and ε are weight constants for each class (cancer region 201, muscularis propria region 202, and mesorectum region 203), respectively. It should be noted that the evaluation value E2 is not limited to the soft dice loss represented by Expression (3), and other values that contribute to the improvement of the segmentation accuracy can also be used.

$\begin{matrix} E 2 = 1 - \frac{2}{γ + δ + ε} (\frac{\sum (G_{a} * P_{a})}{\sum G_{a} + \sum P_{a}} \times γ + \frac{\sum (G_{b} * P_{b})}{\sum G_{b} + \sum P_{b}} \times δ + \frac{\sum (G_{c} * P_{c})}{\sum G_{c} + \sum P_{c}} \times ε) & (3) \end{matrix}$

Whether the inclusion relationship between the cancer region 201 and the muscularis propria region 202 included in the training image 21 is the complete inclusion relationship or the partial inclusion relationship can be grasped by the range information 22A and 22B as the correct answer mask added to the training image 21. In a case in which the estimation model 30 is ideal, the average value A1 should be a relatively large value, which is larger than zero, and the average value A2 should be zero. Therefore, by training the estimation model 30 such that the loss L is reduced, the loss L including, as one of elements, the evaluation value E1 in which the average value A1 is included in a denominator and the average value A2 is included in a numerator, the estimation model 30 that appropriately performs the segmentation of the cancer region 201 and the muscularis propria region 202 while appropriately specifying the inclusion relationship between these regions can be constructed.

FIG. 5 is a diagram showing an example of a functional configuration of the information processing apparatus 10 in an operation phase. In the operation phase, the information processing apparatus 10 operates the trained estimation model 30 to perform the segmentation for the plurality of regions included in the target image. The information processing apparatus 10 includes an acquisition unit 13, a specifying unit 14, and a display control unit 15.

The acquisition unit 13 acquires the target image including the plurality of regions that are the targets of the segmentation. Hereinafter, as an example, a case will be described in which the target image is the tomographic image similar to the training image 21 shown in FIG. 4, the cancer region, the muscularis propria region, and the mesorectum region are included in the target image, and the segmentation is performed for each of these regions.

The specifying unit 14 inputs the target image acquired by the acquisition unit 13 to the trained estimation model 30. The estimation model 30 performs the segmentation for each pixel of the target image. Specifically, the estimation model 30 calculates, for each pixel of the target image, the probability P_athat the pixel is the cancer region and the probability P_bthat the pixel is the muscularis propria region. Further, the estimation model 30 calculates, for each pixel of the target image, P_a×(1−P_b) as the probability P_xin which the pixel is the portion of the cancer region that is not included in the muscularis propria region (portion of the cancer region that has invaded the mesorectum region).

The specifying unit 14 specifies the region consisting of pixels in which the probability P_ais equal to or larger than a predetermined threshold value as the cancer region, and specifies the region consisting of pixels in which the probability P_bis equal to or larger than the predetermined threshold value as the muscularis propria region. In addition, the specifying unit 14 specifies a region consisting of pixels in which the probability P_x(=P_a×(1−P_b)) is equal to or larger than the predetermined threshold value as the portion of the cancer region that is not included in the muscularis propria region (portion of the cancer region that has invaded the mesorectum region).

The display control unit 15 performs control of displaying each region specified by the specifying unit 14 in a discriminable manner. For example, as shown in FIG. 6, the display control unit 15 performs control of displaying color-coded label images indicating ranges in which the cancer region, the muscularis propria region, and the portion of the cancer region that is not included in the muscularis propria region (portion of the cancer region that has invaded the mesorectum region) are present, respectively, in a manner of being superimposed on the target image. It should be noted that the specifying unit 14 may specify at least one of the cancer region, the muscularis propria region, or the portion that is not included in the muscularis propria region of the cancer region. In this case, the display control unit 15 performs control of displaying the region or portion specified by the specifying unit 14 in a discriminable manner.

FIG. 7 is a diagram showing an example of a hardware configuration of the information processing apparatus 10. The information processing apparatus 10 comprises a central processing unit (CPU) 41, a memory 42 as a transitory storage area, and a non-volatile storage unit 43. In addition, the information processing apparatus 10 comprises a display unit 44 configured by a display device, such as a liquid crystal display, and an input unit 45 configured by an input device, such as a keyboard and a mouse. The CPU 41, the memory 42, the storage unit 43, the display unit 44, and the input unit 45 are connected to each other via a bus 46.

The storage unit 43 is realized by, for example, a non-volatile storage medium, such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory. The storage unit 43 stores the training data 20, the estimation model 30, a learning program 51, and an image recognition program 52. The CPU 41 loads the learning program 51 and the image recognition program 52 in the memory 42 and then executes the learning program 51 and the image recognition program 52. The CPU 41 executes the learning program 51, so that the CPU 41 functions as the acquisition unit 11 and the learning unit 12. In addition, the CPU 41 executes the image recognition program 52, so that the CPU 41 functions as the acquisition unit 13, the specifying unit 14, and the display control unit 15. The CPU 41 is an example of a processor according to the disclosed technology.

FIG. 8 is a flowchart showing an example of a flow of learning processing executed by the CPU 41 executing the learning program 51. For example, the CPU 41 executes the learning program 51 in a case in which a user inputs an execution instruction of the learning processing via the input unit 45 in the learning phase.

In step S1, the acquisition unit 11 acquires the plurality of training data 20 stored in the storage unit 43.

In step S2, the learning unit 12 calculates, for each pixel of each of the plurality of training images 21, the probability P_athat the pixel is the cancer region 201, the probability P_bthat the pixel is the muscularis propria region 202, and the probability P_x(=P_a×(1−P_b)) that the pixel is the portion of the cancer region 201 that is not included in the muscularis propria region 202 (portion of the cancer region that has invaded the mesorectum region) by using the estimation model 30.

In step S3, the learning unit 12 calculates the probability sum ΣP_xfor each of the plurality of training images 21.

In step S4, the learning unit 12 calculates the loss L including, as one of the elements, the evaluation value E1 represented by Expression (1) based on the probability sum ΣP_xcalculated in step S3. As the loss L, for example, a value represented by Expression (2) can be used, and as the evaluation value E2, for example, a value represented by Expression (3) can be used.

In step S5, the learning unit 12 trains the estimation model 30 such that the loss L calculated in step S4 is minimized. The estimation model 30 is optimized by repeatedly executing the processing of steps S1 to S5 while exchanging the sets of the training data 20 to be used.

FIG. 9 is a flowchart showing an example of a flow of image recognition processing executed by the CPU 41 executing the image recognition program 52. For example, the CPU 41 executes the image recognition program 52 in a case in which the user inputs an execution instruction of the image recognition processing via the input unit 45 in the operation phase.

In step S11, the acquisition unit 13 acquires the target image. In step S