Medical information processing device, program and method

Abstract

To improve the accuracy of estimating gene mutations in tumor tissue. [Solution] The medical information processing device according to the embodiment comprises an acquisition unit, an identification unit, and a calculation unit. The acquisition unit acquires data relating to the subject's ctDNA (circulating tumor deoxyribonucleic acid). The identification unit identifies genes based on false negative information regarding the estimated gene mutations in the subject's tumor tissue, which are based on the ctDNA data. The calculation unit calculates the estimated gene mutations in the tumor tissue based on medical images of the subject's tumor tissue, for the genes identified based on the false negative information.

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing device, a program, and a method.

Background Art

[0002] As one of the methods for determining the therapeutic effect of cancer, a method of monitoring gene mutations in tumors is known. For example, by periodically checking how gene mutations in tumor tissues are, it is possible to determine whether the current treatment has an effect. Here, among cell-free deoxyribonucleic acid (cfDNA), circulating tumor DNA (ctDNA) derived from tumors is a sample that can be obtained non-invasively and easily, and thus is expected to be applied to the monitoring of gene mutations. However, since ctDNA has a small sample amount and a short half-life, in the analysis using ctDNA, the false negative rate is high, and gene mutations in tumors cannot be accurately captured, and accurate monitoring of gene mutations may not be possible.

Prior Art Documents

Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] One of the problems that the embodiments disclosed herein and in the drawings aim to solve is to improve the accuracy of gene mutation estimation in tumor tissue. However, the problems that the embodiments disclosed herein and in the drawings aim to solve are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems. [Means for solving the problem]

[0005] The medical information processing device according to the embodiment comprises an acquisition unit, an identification unit, and a calculation unit. The acquisition unit acquires data relating to the subject's ctDNA (circulating tumor deoxyribonucleic acid). The identification unit identifies genes based on false negative information regarding the estimated gene mutations in the subject's tumor tissue, which are based on the ctDNA data. The calculation unit calculates estimated gene mutations in the tumor tissue based on medical images of the subject's tumor tissue, for the genes identified based on the false negative information. [Brief explanation of the drawing]

[0006] [Figure 1] Figure 1 shows an example of the configuration of a medical information processing device according to the first embodiment. [Figure 2] Figure 2 illustrates the degree of agreement between tumor tissue samples and gene mutations. [Figure 3] Figure 3 is a diagram illustrating the overview of processing by the medical information processing device according to the first embodiment. [Figure 4] Figure 4 is a flowchart showing the processing procedure performed by each processing function of the processing circuit of the medical information processing device according to the first embodiment. [Figure 5] Figure 5 is a diagram illustrating an example of processing by the medical information processing device according to the first embodiment. [Figure 6] Figure 6 is a diagram illustrating an example of correspondence information according to the first embodiment. [Figure 7]Figure 7 shows an example of display information according to the first embodiment. [Figure 8] Figure 8 is a diagram illustrating an example of processing by the determination function according to the first embodiment. [Modes for carrying out the invention]

[0007] The embodiments of the medical information processing device, program, and method will be described in detail below with reference to the drawings. However, the medical information processing device, program, and method relating to this application are not limited to the embodiments shown below.

[0008] (First Embodiment) Figure 1 shows an example configuration of a medical information processing device according to the first embodiment. For example, as shown in Figure 1, the medical information processing device 3 according to this embodiment is connected to the ctDNA data storage device 1 and the medical image storage device 2 via a network. Note that various other devices and systems may also be connected to the network shown in Figure 1.

[0009] The ctDNA data storage device 1 stores data (ctDNA data) related to the subject's ctDNA (circulating tumor deoxyribonucleic acid). Specifically, the ctDNA data storage device 1 stores information on gene mutations in the ctDNA of cancer patients (subjects) who have undergone liquid biopsy testing. For example, the ctDNA data storage device 1 stores information on gene mutations in the ctDNA contained in cell-free DNA (cfDNA) released into plasma isolated from the blood of cancer patients.

[0010] For example, by analyzing cfDNA contained in the plasma of cancer patients using next-generation sequencing (NGS) and digital polymerase chain reaction (dPCR), gene mutations in ctDNA can be identified, and the MAF (mutant allele frequency) of each gene can be calculated. MAF is calculated by dividing the number of gene mutations after PCR amplification by the total number of that gene amplified by PCR, and it is a value that changes depending on the number of gene mutations that are confirmed (a numerical representation of the degree to which gene mutations were detected). If there are no gene mutations, the MAF will be 0.

[0011] Cancer patients have their blood drawn before and after treatment, and during follow-up, to obtain information about gene mutations in the ctDNA described above. The ctDNA data storage device 1 stores information about gene mutations in the ctDNA for each cancer patient. For example, the ctDNA data storage device 1 can be implemented using computer equipment such as a server or workstation.

[0012] Medical image storage device 2 stores various medical images related to the subject. Specifically, medical image storage device 2 stores medical images including tumor tissue of cancer patients (subjects). For example, medical image storage device 2 stores medical images collected at the time a liquid biopsy examination is performed for each cancer patient. The medical images stored by medical image storage device 2 are collected by, for example, X-ray diagnostic equipment, X-ray CT (Computed Tomography) equipment, MRI (Magnetic Resonance Imaging) equipment, ultrasound diagnostic equipment, SPECT (Single Photon Emission Computed Tomography) equipment, PET (Positron Emission Computed Tomography) equipment, etc.

[0013] For example, medical image storage device 2 can be implemented using computer equipment such as servers or workstations. Alternatively, medical image storage device 2 can be implemented using PACS (Picture Archiving and Communication System) or the like, and can store medical images in a format compliant with DICOM (Digital Imaging and Communications in Medicine).

[0014] The medical information processing device 3 performs various processes using the medical information of the subject. Specifically, the medical information processing device 3 receives medical information from the ctDNA data storage device 1 and the medical image storage device 2 via a network and performs various processes using this medical information. For example, the medical information processing device 3 is implemented using computer equipment such as a server or workstation.

[0015] For example, the medical information processing device 3 includes a communication interface 31, an input interface 32, a display 33, a storage circuit 34, and a processing circuit 35.

[0016] The communication interface 31 controls the transmission and communication of various data sent and received between the medical information processing device 3 and other devices connected via the network. Specifically, the communication interface 31 is connected to the processing circuit 35 and transmits data received from other devices to the processing circuit 35, or transmits data received from the processing circuit 35 to other devices. For example, the communication interface 31 can be implemented by a network card, network adapter, NIC (Network Interface Controller), etc.

[0017] The input interface 32 receives input operations of various instructions and various information from the user. Specifically, the input interface 32 is connected to the processing circuit 35, converts the input operation received from the user into an electrical signal, and transmits it to the processing circuit 35. For example, the input interface 32 is realized by a trackball, a switch button, a mouse, a keyboard, a touch pad that performs an input operation by touching an operation surface, a touch screen in which a display screen and a touch pad are integrated, a non-contact input interface using an optical sensor, and a voice input interface, etc. Note that in this specification, the input interface 32 is not limited to only those equipped with physical operation components such as a mouse and a keyboard. For example, a processing circuit for electrical signals that receives an electrical signal corresponding to an input operation from an external input device provided separately from the apparatus and transmits this electrical signal to the control circuit is also included in the examples of the input interface 32.

[0018] The display 33 displays various information and various data. Specifically, the display 33 is connected to the processing circuit 35 and displays various information and various data received from the processing circuit 35. For example, the display 33 is realized by a liquid crystal display, a CRT (Cathode Ray Tube) display, a touch panel, an LED (Light Emitting Diode) display, etc.

[0019] The memory circuit 34 stores various data and various programs. Specifically, the memory circuit 34 is connected to the processing circuit 35, stores the data received from the processing circuit 35, or reads out the stored data and transmits it to the processing circuit 35. Also, the memory circuit 34 stores corresponding information, a prediction model, etc. used by the processing circuit 35. Note that the corresponding information and the prediction model will be described in detail later. For example, the memory circuit 34 is realized by a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, etc.

[0020] The processing circuit 35 controls the entire medical information processing device 3. For example, the processing circuit 35 performs various processes according to an input operation received from a user via the input interface 32. For example, the processing circuit 35 receives data transmitted by another device via the communication interface 31 and stores the received data in the storage circuit 34. Also, for example, the processing circuit 35 transmits the data received from the storage circuit 34 to the communication interface 31 to transmit the data to another device. Also, for example, the processing circuit 35 displays the data received from the storage circuit 34 on the display 33.

[0021] The configuration example of the medical information processing device 3 according to the present embodiment has been described above. The medical information processing device 3 according to the present embodiment is installed in a medical facility such as a hospital or a clinic and supports various diagnoses and formulation of treatment plans performed by users such as doctors. Specifically, the medical information processing device 3 improves the estimation accuracy of gene mutations in tumor tissue by combining the ctDNA data of a subject (cancer patient) and the image feature amount of the tumor tissue of the subject. <(

[0022] As described above, since ctDNA is a specimen that can be obtained non-invasively and simply, it is expected to be applied to monitoring gene mutations in tumor tissue. However, because the amount of the specimen is small and the half-life is short, ctDNA may not be detected depending on the timing of performing the liquid biopsy test, resulting in false negatives. On the other hand, there is a certain correlation between the image feature amount of tumor tissue in a medical image and the gene mutation in the tumor tissue, and it is possible to estimate the gene mutation in the tumor tissue from the image feature amount.

[0023] Figure 2 illustrates the degree of agreement between gene mutations in tumor tissue samples and other factors. In Figure 2, the vertical axis represents the degree of agreement in gene mutations, and the horizontal axis represents the timing (time) of the analysis. In Figure 2, line L1 represents the degree of agreement in ctDNA, and line L2 represents the degree of agreement in image features. Specifically, line L1 shows the degree of agreement between tumor gene mutations identified using ctDNA and tumor gene mutations identified using DNA extracted from tumor tissue. Line L2 shows the degree of agreement between gene mutations identified from image features of tumor tissue and tumor gene mutations identified using DNA extracted from tumor tissue.

[0024] As shown by line L1 in Figure 2, gene mutations identified from ctDNA show a high degree of agreement with gene mutations identified from tumor tissue DNA compared to image features, but depending on the timing of the analysis, there may be cases where there is almost no agreement. In other words, if ctDNA is not present in the plasma, a false negative result may occur, indicating that no gene mutation is present even if a gene mutation has occurred in the tumor tissue.

[0025] On the other hand, as shown by line L2 in Figure 2, gene mutations identified from image features show a lower degree of agreement with gene mutations identified from tumor tissue DNA compared to ctDNA, but still exhibit a more consistent degree of agreement.

[0026] Therefore, the medical information processing device 3 according to this embodiment improves the accuracy of gene mutation estimation in tumor tissue by estimating gene mutations that were not detected by ctDNA using image features. Figure 3 is a diagram illustrating the overview of processing by the medical information processing device 3 according to the first embodiment. As shown in Figure 3, the medical information processing device 3 acquires information on gene mutations identified from ctDNA for, for example, genes 1 to 6. If the acquired information includes genes (genes 2 to 4) suspected of being false negatives, the medical information processing device 3 acquires image features that correlate with the gene mutations of each gene identified from the tissue sample for genes 2 to 4, and uses the acquired image features to calculate a tissue sample mutation score for evaluating gene mutations in tumor tissue. The medical information processing device 3 also calculates the tissue sample mutation score for genes 1, 5, and 6, for which gene mutations have been identified from ctDNA, using information on gene mutations identified from ctDNA.

[0027] In this embodiment, for example, as shown in Figure 1, the processing circuit 35 of the medical information processing device 3 performs various processes, including the process described in Figure 3, by executing a control function 351, an acquisition function 352, a classification function 353, a specific function 354, a calculation function 355, and a determination function 356. Here, the control function 351 is an example of a display control unit. The acquisition function 352 is an example of an acquisition unit. The classification function 353 is an example of a classification unit. The specific function 354 is an example of a specific unit. The calculation function 355 is an example of a calculation unit. The determination function 356 is an example of a determination unit.

[0028] The control function 351 controls the generation of various GUIs (Graphical User Interfaces) and various display information in response to operations via the input interface 32, and displays them on the display 33. For example, the control function 351 displays the results of processing performed by each function on the display 33. The control function 351 can also generate and display various display images based on medical images acquired by the acquisition function 352.

[0029] The acquisition function 352 acquires medical information of the subject from the ctDNA data storage device 1 and the medical image storage device 2 via the communication interface 31 and stores it in the memory circuit 34. Specifically, the acquisition function 352 acquires data related to the subject's ctDNA (ctDNA data) from the ctDNA data storage device 1. The acquisition function 352 also acquires medical images, including tumor tissue of the subject, from the medical image storage device 2.

[0030] Classification function 353 classifies genes into gene groups. The processing performed by classification function 353 will be described in detail later.

[0031] The specific function 354 identifies genes based on information regarding false negatives in the estimated gene mutation results in the subject's tumor tissue, which are based on ctDNA data. Specifically, the specific function 354 identifies the first gene that is likely to be false negative in the estimated gene mutation results based on ctDNA data. For example, the specific function 354 determines the likelihood of a false negative in the estimated gene mutation results based on the MAF value for each gene. To give one example, the specific function 354 identifies genes with an MAF value smaller than a threshold as the first gene that is likely to be false negative. The processing performed by the specific function 354 will be described in detail later.

[0032] The calculation function 355 calculates estimated gene mutations in tumor tissue based on medical images of the tumor tissue of the subject, for genes identified based on false negative information. Specifically, the calculation function 355 calculates a mutation score (tissue sample mutation score) for the first gene to estimate gene mutations based on medical images of the tumor tissue, and calculates a mutation score (tissue sample mutation score) for the second gene other than the first gene to estimate gene mutations based on ctDNA data. For example, the calculation function 355 calculates image features in the medical images of tumor tissue as an estimated result of gene mutations for genes identified based on false negative information. The processing by the calculation function 355 will be described in detail later.

[0033] The judgment function 356 determines the therapeutic effect on the tumor tissue based on the estimated gene mutations in the tumor tissue before and after treatment of the tumor tissue of the subject. The processing performed by the judgment function 356 will be described in detail later.

[0034] The processing circuit 35 described above is implemented, for example, by a processor. In this case, each of the processing functions described above is stored in the memory circuit 34 in the form of a program that can be executed by a computer. The processing circuit 35 then reads and executes each program stored in the memory circuit 34, thereby realizing the function corresponding to each program. In other words, the processing circuit 35, with each program read, has the processing functions shown in Figure 1.

[0035] Next, the processing procedure by the medical information processing device 3 will be explained using Figure 4, and then the details of each process will be described. Figure 4 is a flowchart showing the processing procedure performed by each processing function of the processing circuit 35 of the medical information processing device 3 according to the first embodiment. Here, as explained in Figure 3, the medical information processing device 3 according to this embodiment can calculate a tissue sample mutation score for each gene, but it can also classify multiple genes into gene groups and calculate a tissue sample mutation score for each gene group. That is, the identification function 354 identifies gene groups that have a high probability of being false negatives in the estimated gene mutation results estimated for each gene group. The calculation function 355 calculates the estimated gene mutation results in the tumor tissue based on the medical image of the tumor tissue of the subject for the identified gene groups. The following describes the case in which a tissue sample mutation score is calculated for each gene group.

[0036] For example, as shown in Figure 4, in this embodiment, the acquisition function 352 acquires the ctDNA data of a subject (cancer patient) from the ctDNA data storage device 1 (step S101). For example, the acquisition function 352 acquires the ctDNA data of the cancer patient to be analyzed in response to the ctDNA acquisition operation via the input interface 32. This process is realized, for example, by the processing circuit 35 calling and executing a program corresponding to the acquisition function 352 from the storage circuit 34.

[0037] Next, the classification function 353 classifies each gene into a gene group (step S102). This process is achieved, for example, by the processing circuit 35 calling and executing a program corresponding to the classification function 353 from the memory circuit 34.

[0038] Next, the specific function 354 calculates the average MAF (mMAF) of the genes included in the gene group based on the ctDNA data (step S103), and determines whether the calculated mMAF exceeds a threshold (step S104). This process is realized, for example, by the processing circuit 35 calling and executing a program corresponding to the specific function 354 from the storage circuit 34.

[0039] If the mMAF exceeds the threshold (step S104, Yes), the calculation function 355 calculates a tissue sample mutation score based on the MAF (step S105). On the other hand, if the mMAF is below the threshold (step S104, No), the calculation function 355 calculates a tissue sample mutation score based on the medical image (step S106). These processes are implemented, for example, by the processing circuit 35 calling and executing a program corresponding to the calculation function 355 from the storage circuit 34.

[0040] Next, the specific function 354 determines whether or not all gene groups have been processed (step S107). If not all gene groups have been processed (step S107, No), the specific function 354 returns to step S103 and performs the processing. If all gene groups have been processed (step S107, Yes), the control function 351 controls the display of the tissue sample mutation score (step S108). These processes are implemented, for example, by the processing circuit 35 calling and executing programs corresponding to the specific function 354 and the control function 351 from the storage circuit 34.

[0041] Next, the judgment function 356 determines whether or not to determine the treatment effect (step S109). If the treatment effect is to be determined (step S109, Yes), the judgment function 356 determines the treatment effect based on the tissue sample mutation score calculated at different points in time, and the control function 351 controls the system to display the determination result (step S110). On the other hand, if the treatment effect is not to be determined (step S109, No), the medical information processing device 3 terminates processing.

[0042] The following describes the details of each process performed by the medical information processing device 3.

[0043] (Acquisition process of ctDNA data) As explained in step S101 of Figure 4, the acquisition function 352 acquires the ctDNA data of the target subject from the ctDNA data storage device 1 in response to the ctDNA acquisition operation via the input interface 32. For example, the acquisition function 352 acquires the MAF results for each gene obtained from the liquid biopsy test for a specified cancer patient. The acquisition function 352 can also acquire medical images of the specified cancer patient at this time. For example, the acquisition function 352 acquires medical images collected at approximately the same time (or close to the time) as the acquired ctDNA data was obtained (when the liquid biopsy test was performed) from the medical image storage device 2.

[0044] The acquisition process in step S101 may be initiated by user instructions via the input interface 32, as described above, but it may also be initiated automatically. In the latter case, for example, the acquisition function 352 monitors the ctDNA data storage device 1 and automatically acquires ctDNA data each time new ctDNA data is stored.

[0045] (Classification process of gene groups) As explained in step S102 of Figure 4, the classification function 353 classifies each gene into a gene group. Specifically, the classification function 353 classifies genes into gene groups according to their function. For example, the classification function 353 classifies gene groups related to cell proliferation, gene groups related to DNA repair, and gene groups related to cell nucleation, respectively.

[0046] Furthermore, the rules for classifying genes are not limited to those based on the function of each gene as described above; other arbitrary rules may also be used. For example, multiple genes in which gene mutations are observed in only a small number of patients may be grouped together into a single gene group.

[0047] (Identification of false negative genes) As explained in steps S103 and S104 of Figure 4, the specific function 354 calculates the mMAF of a gene group based on the ctDNA data and determines whether the calculated mMAF exceeds a threshold, thereby identifying gene groups that are likely to have false negative results in the gene mutation estimation.

[0048] As mentioned above, MAF is a numerical representation of the degree to which gene mutations are detected, and a value close to 0 indicates a negative result. However, gene mutations identified from ctDNA may not be detected depending on the timing of the analysis, and the MAF value may be a false negative. Therefore, specific function 354 identifies gene groups in which the mMAF value does not exceed a threshold as gene groups in which the estimated gene mutation result may be a false negative.

[0049] Figure 5 is a diagram illustrating an example of processing by the medical information processing device 3 according to the first embodiment. For example, as shown in the upper table of Figure 5, the specific function 354 calculates the average value of MAF of the genes included in gene group A, "mMAF:0.0001". Similarly, the specific function 354 calculates "mMAF:0.2" for gene group B, "mMAF:0.1" for gene group C, "mMAF:0.00" for gene group D, and "mMAF:0.03" for gene group E.

[0050] The specific function 354 then compares the calculated mMAF with a threshold and identifies gene groups with mMAF values ​​below the threshold. For example, if the threshold is set to "0.05", the specific function 354 identifies gene groups A, D, and E, where "mMAF ≤ 0.05", as gene groups that may produce false negatives. Note that the threshold "0.05" mentioned above is merely an example, and the threshold value can be set as appropriate. For example, thresholds may be set for each type of cancer or for each type of gene (or gene group).

[0051] (Calculation process for tissue sample mutation score) As explained in steps S105 and S106 of Figure 4, the calculation function 355 calculates a tissue sample mutation score based on MAF for gene groups where "mMAF > threshold" (second gene), and calculates a tissue sample mutation score based on medical images for gene groups where "mMAF ≤ threshold" (first gene). In other words, the calculation function 355 calculates a tissue sample mutation score based on the image features of tumor tissue for gene groups where "mMAF ≤ threshold".

[0052] For example, as shown in the table in the middle of Figure 5, calculation function 355 calculates tissue sample mutation scores from image features for gene groups A, D, and E, which have been identified as potentially false negatives based on ctDNA MAF. On the other hand, for gene groups B and C, which have not been identified as potentially false negatives, calculation function 355 calculates tissue sample mutation scores from mMAF.

[0053] Here, the correlation between gene groups and image features is predetermined, and this correspondence information is stored in the memory circuit 34. For example, for each gene group, the image features (e.g., pixel values ​​and shape) when the tumor tissue has a gene mutation are compared with those when it does not, and image features with significant differences are identified. Then, the correspondence information, which associates the identified image features with the target gene group, is stored in the memory circuit 34.

[0054] Figure 6 is a diagram illustrating an example of correspondence information according to the first embodiment. For example, as shown in Figure 6, the memory circuit 34 stores correspondence information for each of the gene groups A to E, associating image features (IFs) that correlate with gene mutations. Here, examples of IFs include morphological features of the tumor (such as size and shape) and features related to pixel values ​​(such as features related to frequency distribution and features related to spatial distribution).

[0055] The calculation function 355 identifies correlated image features for gene groups identified as potentially causing false negatives, based on the correspondence information stored in the memory circuit 34. The calculation function 355 then calculates the identified image features in the patient's medical images acquired by the acquisition function 352. For example, as shown in the lower table of Figure 5, the calculation function 355 identifies the image feature "IF1" which is correlated with the gene mutation of gene group A based on the correspondence information, and calculates the image feature "0.7" related to IF1 from the patient's medical images.

[0056] Similarly, the calculation function 355 identifies the image feature "IF2" that correlates with gene mutations for gene groups D and E, and calculates the image features "0.6" and "0.8" related to IF2 from the patient's medical images, respectively. Note that Figure 5 shows the case where one image feature is identified as correlated with gene mutations, but in reality, multiple image features may be identified as correlated with gene mutations. In such cases, the calculation function 355 can combine the identified multiple image features to calculate the tissue sample mutation score.

[0057] As described above, the calculation function 355 switches the information used to calculate the tissue sample mutation score depending on whether or not there is a possibility of false negatives in the estimated gene mutation results. In this way, since the source information is switched depending on the situation, the calculation function 355 performs standardization or normalization on both the image features and the mMAF in order to make these values ​​comparable. For example, the calculation function 355 uses the values ​​of the image features and the mMAF as features, respectively, and performs standardization or normalization of the values ​​using the following formula (1) or (2).

[0058]

number

[0059]

number

[0060] For example, when performing the identification process for false-negative genes, the identification function 354 calculates the values ​​shown in Figure 5 by performing the standardization shown in formula (1) or the normalization shown in formula (2) on the mMAF (or MAF). Alternatively, the calculation function 355 can calculate a tissue sample mutation score based on MAF by performing the standardization shown in formula (1) or the normalization shown in formula (2) on the mMAF (or MAF). Furthermore, the calculation function 355 calculates the values ​​shown in Figure 5 by performing the standardization shown in formula (1) or the normalization shown in formula (2) on the image feature values ​​calculated from medical images.

[0061] The calculation function 355 associates the calculated tissue sample mutation score with patient information and stores it in the memory circuit 34.

[0062] (Processing for displaying tissue sample mutation scores) As explained in step S108 of Figure 4, the control function 351 displays the tissue sample mutation score calculated by the calculation function 355 on the display 33. Here, the control function 351 can be controlled to display the tissue sample mutation score based on medical images and the tissue sample mutation score based on ctDNA data in a distinguishable manner.

[0063] Figure 7 shows an example of display information according to the first embodiment. For example, as shown in Figure 7, when the control function 351 displays the tissue sample mutation scores for gene groups A to E, it can display the values ​​based on medical images (image features) and the values ​​based on ctDNA in different display formats (such as displaying them with different background colors) so that it is possible to distinguish which value is based on which.

[0064] (Process for determining treatment effectiveness) As explained in steps S109 and S110 of Figure 4, the judgment function 356 determines the effectiveness of the treatment for cancer patients when it determines that it is appropriate to determine the effectiveness of the treatment. Specifically, in step S109, the judgment function 356 determines to perform a treatment effectiveness determination when an operation for determining the effectiveness of the treatment is performed via the input interface 32, or when the patient has previously had a tissue sample mutation score calculated.

[0065] The determination function 356 then reads the patient's past tissue sample mutation scores from the memory circuit 34 and uses the read past tissue sample mutation scores and the tissue sample mutation scores calculated in step S108 to determine the treatment effect. Figure 8 is a diagram illustrating an example of processing by the determination function 356 according to the first embodiment. Here, Figure 8 shows an example of determining the effect of preoperative radiotherapy (Neoadjuvant RT) from the tissue sample mutation scores calculated before and after preoperative radiotherapy.

[0066] In such cases, for example, as shown in Figure 8, medical images are collected and a liquid biopsy is performed before preoperative radiotherapy (before RT), and based on these results, tissue sample mutation scores for each gene group (cell proliferation, DNA repair, cell nucleation) before radiotherapy are calculated. Furthermore, medical images are collected and a liquid biopsy is performed after preoperative radiotherapy (after RT), and based on these results, tissue sample mutation scores for each gene group (cell proliferation, DNA repair, cell nucleation) after radiotherapy are calculated.

[0067] The judgment function 356 obtains information indicating the therapeutic effect by inputting the tissue sample mutation scores for each gene group before radiation therapy and the tissue sample mutation scores for each gene group after radiation therapy into a tumor cell necrosis prediction model. For example, the tumor cell necrosis prediction model is pre-created using machine learning with the tissue sample mutation scores before and after treatment and information indicating the therapeutic effect (e.g., numerical values ​​assigned to the actual therapeutic effect) as training data, and is stored in the memory circuit 34.

[0068] When the judgment function 356 obtains information indicating the treatment effect, the control function 351 displays the judgment result (information indicating the treatment effect) on the display 33. A clinical team spanning many academic disciplines, including radiation oncologists, surgeons, and radiologists, makes decisions about subsequent treatment (additional radiation therapy, surgery, etc.) based on the judgment result displayed on the display 33.

[0069] Figure 8 illustrates the case where the therapeutic effect is determined using a necrosis prediction model for tumor cells, but the embodiments are not limited to this, and the therapeutic effect may be determined by other methods. For example, the therapeutic effect may be determined from the increase or decrease in the mutation score of a tissue sample.

[0070] As described above, according to the first embodiment, the acquisition function 352 acquires data relating to the subject's ctDNA. The identification function 354 identifies genes based on false negative information regarding the estimated gene mutations in the subject's tumor tissue, which are based on the ctDNA data. The calculation function 355 calculates the estimated gene mutations in the tumor tissue based on medical images of the subject's tumor tissue for the genes identified based on the false negative information. Therefore, the medical information processing device 3 according to the first embodiment can estimate gene mutations based on medical images for genes that may have false negatives, thereby improving the accuracy of gene mutation estimation in tumor tissue.

[0071] Furthermore, according to the first embodiment, the identification function 354 identifies a first gene that is highly likely to be false negative in the gene mutation estimation results based on ctDNA data. The calculation function 355 calculates a tissue sample mutation score for the first gene to estimate gene mutations based on medical images of tumor tissue, and calculates a tissue sample mutation score for the second gene other than the first gene to estimate gene mutations based on ctDNA data. Therefore, the medical information processing device 3 according to the first embodiment can estimate gene mutations in tumor tissue by combining ctDNA data and medical images, thereby improving the ability to estimate gene mutations in tumor tissue.

[0072] Furthermore, according to the first embodiment, the identification function 354 determines the possibility of a false negative in the gene mutation estimation result based on the MAF for each gene. The identification function 354 also identifies genes with an MAF value smaller than a threshold as first genes with a high probability of being false negatives. Therefore, the medical information processing device 3 according to the first embodiment makes it possible to easily determine the possibility of a false negative.

[0073] Furthermore, according to the first embodiment, the calculation function 355 calculates image features in the medical image of tumor tissue as an estimated result of gene mutations identified based on information regarding false negatives. Therefore, the medical information processing device 3 according to the first embodiment makes it possible to estimate gene mutations with a certain degree of accuracy.

[0074] Furthermore, according to the first embodiment, the control function 351 controls the display of the tissue sample mutation score based on medical images and the tissue sample mutation score based on ctDNA data in a distinguishable manner. Therefore, the medical information processing device 3 according to the first embodiment makes it possible to provide the user with the information used when calculating the tissue sample mutation score.

[0075] Furthermore, according to the first embodiment, the determination function 356 determines the therapeutic effect on the tumor tissue based on the estimated results of gene mutations in the tumor tissue before and after treatment of the tumor tissue of the subject. Therefore, the medical information processing device 3 according to the first embodiment makes it possible to provide the user with information on the therapeutic effect.

[0076] Furthermore, according to the first embodiment, the classification function 353 classifies genes into gene groups. The identification function 354 identifies gene groups that are likely to be false negatives in the estimated gene mutation results estimated for each gene group. The calculation function 355 calculates the estimated gene mutation results in the tumor tissue based on the medical image of the tumor tissue of the subject for the identified gene groups. Therefore, the medical information processing device 3 according to the first embodiment makes it possible to handle cases where significance testing for image features is difficult. The number of gene mutations is enormous relative to the number of patients, and significance testing for image features may be difficult for gene mutations of a single gene. Therefore, as described above, significance testing for image features is made possible by forming gene groups.

[0077] Furthermore, according to the first embodiment, the classification function 353 classifies genes into gene groups according to their function. Therefore, the medical information processing device 3 according to the first embodiment makes it possible to group together genes that are useful for determining the effectiveness of treatment.

[0078] (Other embodiments)

[0079] The embodiments described above describe a case in which gene groups are formed and a tissue sample mutation score is calculated for each gene group. However, the embodiments are not limited to this, and as explained in Figure 3, a tissue sample mutation score may also be calculated for each single gene.

[0080] Furthermore, the processing circuits described in each of the embodiments above may be composed of a combination of multiple independent processors, with each processor executing a program to realize each processing function. Also, each processing function of the processing circuit may be implemented by appropriately distributing or integrating it across one or more processing circuits. Additionally, each processing function of the processing circuit may be implemented by a mixture of hardware such as circuits and software. While this description has described an example where the programs corresponding to each processing function are stored in a single memory circuit 34, the embodiments are not limited to this. For example, the programs corresponding to each processing function may be stored in a distributed manner across multiple memory circuits, and the processing circuit may read and execute each program from each memory circuit.

[0081] In the embodiments described above, examples were given in which each part of this specification is implemented by the respective functions of the processing circuit, but the embodiments are not limited to these. For example, each part of this specification may be implemented not only by the respective functions described in the embodiments, but also by hardware alone, software alone, or a combination of hardware and software.

[0082] Furthermore, the term "processor" used in the above-described embodiment refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), or a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and a Field Programmable Gate Array (FPGA)). Here, instead of storing the program in a memory circuit, the processor may be configured to directly incorporate the program into its circuitry. In this case, the processor realizes its function by reading and executing the program incorporated into the circuitry. Moreover, each processor in this embodiment is not limited to being configured as a single circuit; multiple independent circuits may be combined to form a single processor, and its function may be realized in this way.

[0083] Here, the medical information processing program executed by the processor is provided pre-installed in ROM (Read Only Memory) or memory circuits. Alternatively, this medical information processing program may be provided as a file in an installable or executable format on computer-readable non-transient storage media such as CD (Compact Disk)-ROM, FD (Flexible Disk), CD-R (Recordable), or DVD (Digital Versatile Disk). Furthermore, this medical information processing program may be stored on a computer connected to a network such as the Internet and provided or distributed by downloading it via the network. For example, this medical information processing program consists of modules containing the processing functions described above. In actual hardware, the CPU reads the medical information processing program from a storage medium such as ROM and executes it, loading each module onto main memory and generating it in main memory.

[0084] Furthermore, in the embodiments and modifications described above, each component of each illustrated device is a functional concept and does not necessarily have to be physically configured as shown. In other words, the specific form of distribution or integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed or integrated in any unit according to various loads and usage conditions. Moreover, each processing function performed by each device can be realized in whole or in any part by a CPU and a program that is analyzed and executed by the CPU, or by hardware using wired logic.

[0085] Furthermore, among the processes described in the embodiments and modifications described above, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified.

[0086] According to at least one embodiment described above, the accuracy of estimating gene mutations in tumor tissue can be improved.

[0087] While several embodiments have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0088] 3. Medical Information Processing Device 351 Control Functions 352 Acquisition function 353 Classification function 354 Specific Functions 355 Calculation function 356 Judgment Function

Claims

1. An acquisition unit that acquires data regarding the subject's ctDNA (circulating tumor deoxyribonucleic acid), A gene identification unit that identifies a gene based on false negative information regarding the estimated gene mutation in the tumor tissue of the subject, based on the data relating to the ctDNA, A calculation unit that calculates the estimated gene mutation in the tumor tissue based on medical images of the tumor tissue of the subject, with respect to the genes identified based on the information regarding the false negatives, A medical information processing device equipped with [a specific feature].

2. The specified unit identifies a first gene that has a high probability of being false negative in the estimated gene mutation result based on the data relating to the ctDNA, The medical information processing apparatus according to claim 1, wherein the calculation unit calculates a mutation score for the first gene based on a medical image of the tumor tissue to estimate the gene mutation, and calculates a mutation score for the second gene other than the first gene based on data relating to the ctDNA to estimate the gene mutation.

3. The medical information processing device according to claim 2, wherein the specified unit determines the possibility of a false negative in the estimated result of the gene mutation based on the MAF (mutant allele frequency) for each gene.

4. The medical information processing apparatus according to claim 3, wherein the identifying unit identifies genes whose MAF value is smaller than a threshold as first genes with a high probability of being false negatives.

5. The medical information processing apparatus according to claim 1, wherein the calculation unit calculates image feature quantities in the medical image of the tumor tissue as an estimation result of gene mutations identified based on the information regarding the false negative.

6. The medical information processing apparatus according to claim 2, further comprising a display control unit that controls the display of a mutation score based on the medical image and a mutation score based on data relating to ctDNA in an identifiable manner.

7. The medical information processing apparatus according to claim 1, further comprising a determination unit that determines the therapeutic effect on the tumor tissue based on the estimated results of gene mutations in the tumor tissue before and after treatment of the tumor tissue of the subject.

8. It further includes a classification unit that classifies genes into gene groups, The specified unit identifies gene groups that are highly likely to be false negatives in the estimated gene mutation results for each gene group, The calculation unit calculates the estimated result of gene mutations in the tumor tissue based on a medical image of the tumor tissue of the subject, for the identified gene group, according to any one of claims 1 to 7.

9. The medical information processing apparatus according to claim 8, wherein the classification unit classifies the genes into gene groups according to the function of the genes.

10. We obtained data regarding the subject's ctDNA (circulating tumor deoxyribonucleic acid), Based on the false negative information regarding the estimated gene mutation in the tumor tissue of the subject, which is based on the data relating to the ctDNA, the gene is identified. Based on the information regarding the false negatives, the estimated gene mutations in the tumor tissue are calculated based on medical images of the tumor tissue of the subject. A program that instructs a computer to perform various processes.

11. We obtained data regarding the subject's ctDNA (circulating tumor deoxyribonucleic acid), Based on the false negative information regarding the estimated gene mutation in the tumor tissue of the subject, which is based on the data relating to the ctDNA, the gene is identified. Based on the information regarding the false negatives, the estimated gene mutations in the tumor tissue are calculated based on medical images of the tumor tissue of the subject. A method that includes doing so.

Images