# US 12,112,852 B2 · CAD device and method for analysing medical images > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,112,852 B2 - Document ID: US12112852B2 - Status: Granted - Kind: B2 - Application number: 17/094,934 - Filed: 2020-11-11 - Published: 2022-05-12 - Granted: 2024-10-08 - Earliest claimed: 2020-11-11 - Assignees: Optellum Limited - Applicants: Optellum Limited - Inventors: Carlos Federico Arteta Montilva; Nicholas Dowson; Timor Kadir; Jerome Declerck - Web page: https://patentgrep.com/patent/US12112852B2 ## CPC - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06T 7/0012: {Biomedical image inspection} - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 30/40: for processing medical images, e.g. editing - G16H 50/30: for calculating health indices; for individual health risk assessment - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30061: Lung - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A method for providing a lung disease risk measure in a Computer Aided Diagnosis system is described. The method comprises the steps of: receiving an input comprising at least one input image showing all or part of the lungs of a patient; analysing the input to identify a feature descriptor comprised of at least one feature group, where each feature group comprises at least one feature computed from the input image; calculating a score explanation factor for each feature group, and an overall disease risk score for the patient's risk of lung disease from the feature descriptor; outputting the overall disease score risk score and a corresponding score explanation factor for each feature group. A computer aided diagnosis system is also described, along with a method for training a computer aided diagnosis system. ## Claims ### Claim 1 A method for providing a lung disease risk measure in a Computer Aided Diagnosis (CADx) system comprising: receiving an input comprising at least one input image showing all or part of the lungs of a patient; analysing the input to identify a feature descriptor comprised of at least one feature group comprised of at least one feature computed from the input image, wherein the at least one feature group describes a characteristic of the image that is not provided as a separate input and correlates to a known clinical predictor of the lung disease; calculating a score explanation factor for each feature group, and an overall disease risk score for the patient's risk of lung disease from the feature descriptor; and outputting a graphical or textual representation of the overall disease risk score and a corresponding score explanation factor for each feature group, wherein the collection of score explanation factors indicate the proportion to which each characteristic associated with each feature group contributed to the disease risk score; wherein the representation shows which explanation factors have a negative effect on the lung disease risk score, and which explanation factors have a positive effect on the lung disease risk score. ### Claim 2 (depends on 1) A method as claimed in claim 1, wherein the input further comprises one of more of: biomarkers for the patient or clinical parameters for the patient. ### Claim 3 (depends on 2) A method according to claim 2, wherein the biomarkers or clinical parameters comprise: patient age, patient sex, family and clinical history, results of blood tests, and results of lung function tests. ### Claim 4 (depends on 1) A method according to claim 1, wherein the risk score explanation factor is related one or more of tumour size, location and appearance. ### Claim 5 (depends on 1) A method according to claim 1, wherein each at least one feature group comprises a plurality of features for that feature group. ### Claim 6 (depends on 1) A method according to claim 1, wherein the CADx system uses a neural network. ### Claim 7 (depends on 6) A method according to claim 6, wherein the neural network is a convolutional neural network. ### Claim 8 (depends on 1) A method according to claim 1, wherein the overall disease risk score is calculated using a mapping function on the feature descriptor. ### Claim 9 A computer aided diagnosis lung disease risk measure system comprising: an input circuit configured to receive at least one input image showing all or part of the lungs of a patient; an analysis and score circuit configured to: analyse the at least one input image to identify a feature descriptor comprised of at least one feature group, comprised of at least one feature derived from the input image, wherein the at least one feature group describes a characteristic of the image that is not provided as a separate input and correlates to a known clinical predictor of the lung disease; calculate a score explanation factor for each feature group and an overall disease risk score for the patient's risk of lung disease from the feature descriptor; an output circuit to output a graphical or textual representation of the overall disease risk score and a corresponding score explanation factor for each feature group, wherein the collection of score explanation factors indicate the proportion to which each characteristic associated with each feature group contributed to the disease risk score; wherein the representation shows which explanation factors have a negative effect on the lung disease risk score, and which explanation factors have a positive effect on the lung disease risk score. ### Claim 10 (depends on 9) A computer aided diagnosis system according to claim 9, wherein the analysis and score circuit further comprises a feature encoder to receive the input image and identify the feature descriptor. ### Claim 11 (depends on 9) A computer aided diagnosis system according to claim 9, wherein the score explanation factor is calculated by applying a mapping function to the feature descriptor.