{"id":20837774,"url":"https://github.com/astrazeneca/oct_publication","last_synced_at":"2026-01-23T05:36:44.997Z","repository":{"id":103037762,"uuid":"508703273","full_name":"AstraZeneca/OCT_publication","owner":"AstraZeneca","description":"This repository contains the source code for the image analysis of optical coherence tomography images, as stated in the publication of Volumetric wound healing by machine learning and optical coherence tomography in type 2 diabetes.","archived":false,"fork":false,"pushed_at":"2022-06-29T13:30:26.000Z","size":1971,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-09T11:50:59.353Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"MATLAB","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AstraZeneca.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":"AUTHORS.md","dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-06-29T13:29:17.000Z","updated_at":"2025-01-18T01:37:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"9b31f841-253c-4d18-84e3-cda012c5e6e4","html_url":"https://github.com/AstraZeneca/OCT_publication","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AstraZeneca/OCT_publication","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FOCT_publication","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FOCT_publication/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FOCT_publication/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FOCT_publication/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AstraZeneca","download_url":"https://codeload.github.com/AstraZeneca/OCT_publication/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AstraZeneca%2FOCT_publication/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28681005,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-23T04:33:33.518Z","status":"ssl_error","status_checked_at":"2026-01-23T04:33:30.433Z","response_time":59,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-18T01:08:32.879Z","updated_at":"2026-01-23T05:36:44.971Z","avatar_url":"https://github.com/AstraZeneca.png","language":"MATLAB","funding_links":[],"categories":[],"sub_categories":[],"readme":"![Maturity level-1](https://img.shields.io/badge/Maturity%20Level-ML--1-yellow)\n\n# U-net model for analysing OCT image.\n\nThis repository contains the source code for the image analysis of optical coherence tomography images, as stated in the publication of **Volumetric wound healing by machine learning and optical coherence tomography in type 2 diabetes**. \n\n\n**AUTHORS**\n\nYinhai Wang\t\u003csup\u003e1\u003c/sup\u003e, Adrian Freeman\u003csup\u003e2\u003c/sup\u003e, Ramzi Ajjan\u003csup\u003e3\u003c/sup\u003e, Francesco Del Galdo\u003csup\u003e*4,5\u003c/sup\u003e, and Ana Tiganescu\u003csup\u003e*3\u003c/sup\u003e\n\n**AFFILIATIONS**\n\n\u003csup\u003e1\u003c/sup\u003eData Sciences \u0026 Quantitative Biology, Discovery Sciences, BioPharmaceuticals R\u0026D, AstraZeneca, Cambridge, UK; \n\n\u003csup\u003e2\u003c/sup\u003eEmerging Innovations Unit, Discovery Sciences, BioPharmaceuticals R\u0026D, AstraZeneca, Cambridge, UK; \n\n\u003csup\u003e3\u003c/sup\u003eLeeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, UK; \n\n\u003csup\u003e4\u003c/sup\u003eNIHR Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds, UK; \n\n\u003csup\u003e5\u003c/sup\u003eLeeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds, UK.\n\n\na copy of the paper (*pending peer review) can be found here: https://www.medrxiv.org/content/10.1101/2021.03.23.21254200v1.full\n\n--------------------------------------------------------------------------------\n**What it contains**\n\n\n1. All source code are in the \\code folder.\n2. Some test images (2D gray scale images) are in the \\testImages folder.\n3. A pretained u-net model is in the root folder, named \"Unet model.mat\".\n\n--------------------------------------------------------------------------------\n**Software requirements**\n\n\nthis package was developed using Matlab 2019b. this code repository should contain all the dependecies it required, no additional packages are required. \n\nFour functions are from \"Oliver Woodford (2022). real2rgb \u0026 colormaps (https://www.mathworks.com/matlabcentral/fileexchange/23342-real2rgb-colormaps)\" package. These files are included in the repository, which are: colormap_helper, summer, rescale and real2rgb.  They are used but not checked nor modified. \n\nAll code are fully checked and passed the checkcode(), the Matlab equivlant of lint. The exception is that there are two occurances of the warning messages that variables \"change size on every loop iteration. Consider preallocating for speed.\". They are not bugs and the loop counter is small, therefore the speed of the code was not impacted in a noticable way. These were not further fixed.\n\n--------------------------------------------------------------------------------\n**How to run**\n\nTo test the image analysis of an OCT image, please follow the steps in **code\\toPredict.m** \n    \n    %-- define a folder on your local computer where you git cloned the repository\n    rootFolder = 'C:\\Matlab_Works\\testOct';\n\n    %-- load class labels, which is stored in the 'gTruth.mat' file\n    A = load(fullfile(rootFolder, 'gTruth.mat'));\n    obj = cOctUnet.setupTrainingData(A.gTruth);\n    \n    %-- load the trained u-net network which is stored in the 'Unet model.mat' file\n    T = load(fullfile(rootFolder, 'Unet model.mat'));\n    obj.loadNet(T.net);\n\n    %-- to test a single image, please run e.g. \n    aFileName = sprintf('%s/testImages/1.tif', rootFolder);\n    obj.testAnImage(aFileName);\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fastrazeneca%2Foct_publication","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fastrazeneca%2Foct_publication","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fastrazeneca%2Foct_publication/lists"}