{"id":15600593,"url":"https://github.com/borda/kaggle_vol-3d-classify","last_synced_at":"2025-09-11T20:33:13.550Z","repository":{"id":45163571,"uuid":"395378667","full_name":"Borda/kaggle_vol-3D-classify","owner":"Borda","description":"Predict the status of a genetic biomarker important for brain cancer treatment","archived":false,"fork":false,"pushed_at":"2024-12-01T15:04:47.000Z","size":1162,"stargazers_count":38,"open_issues_count":2,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-03T05:48:10.127Z","etag":null,"topics":["3d","brain","image-classification","radiology"],"latest_commit_sha":null,"homepage":"https://borda.github.io/kaggle_vol-3D-classify","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Borda.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-08-12T16:20:34.000Z","updated_at":"2024-12-01T15:04:49.000Z","dependencies_parsed_at":"2024-12-20T07:07:34.775Z","dependency_job_id":"43c3f1f2-a62b-4558-b441-df09081005cc","html_url":"https://github.com/Borda/kaggle_vol-3D-classify","commit_stats":{"total_commits":47,"total_committers":5,"mean_commits":9.4,"dds":0.276595744680851,"last_synced_commit":"4e3e0683740943fdb1b0eb71c7c0f9007f9733e3"},"previous_names":[],"tags_count":6,"template":false,"template_full_name":"Borda/kaggle_SandBox","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Borda%2Fkaggle_vol-3D-classify","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Borda%2Fkaggle_vol-3D-classify/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Borda%2Fkaggle_vol-3D-classify/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Borda%2Fkaggle_vol-3D-classify/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Borda","download_url":"https://codeload.github.com/Borda/kaggle_vol-3D-classify/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":232666169,"owners_count":18557991,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["3d","brain","image-classification","radiology"],"created_at":"2024-10-03T02:04:47.182Z","updated_at":"2025-09-11T20:33:13.494Z","avatar_url":"https://github.com/Borda.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Kaggle competitions on 3D volumes\n\n[![CI complete testing](https://github.com/Borda/kaggle_vol-3D-classify/actions/workflows/ci_testing.yml/badge.svg?branch=main\u0026event=push)](https://github.com/Borda/kaggle_vol-3D-classify/actions/workflows/ci_testing.yml)\n[![codecov](https://codecov.io/gh/Borda/kaggle_vol-3D-classify/branch/main/graph/badge.svg?token=bxqTQDXHvU)](https://codecov.io/gh/Borda/kaggle_vol-3D-classify)\n[![pre-commit.ci status](https://results.pre-commit.ci/badge/github/Borda/kaggle_vol-3D-classify/main.svg)](https://results.pre-commit.ci/latest/github/Borda/kaggle_vol-3D-classify/main)\n\n## Kaggle: [Cervical Spine Fracture Detection](https://www.kaggle.com/competitions/rsna-2022-cervical-spine-fracture-detection)\n\nThe goal is prediction fracture in whole neck 3D scans. The organizers provide 2k cases with partially annotated fractures as bounding boxes or/and pixel-wise segmentations.\n\n![Sample brain visual](./assets/neck3D_spl.png)\n\n## Kaggle: [Brain Tumor Radiogenomic Classification](https://www.kaggle.com/c/rsna-miccai-brain-tumor-radiogenomic-classification)\n\nThe goal of this challenge is to Predict the status of a genetic biomarker important for brain cancer treatment.\n\n![Sample brain visual](./assets/brain3D_spl1.png)\n\n\u003cdetails\u003e\n  \u003csummary\u003eWith interpolation in Z dimension as it happens it is quite sparse\u003c/summary\u003e\n\n![Sample brain visual](./assets/brain3D_spl2.png)\n\n\u003c/details\u003e\n\nEach independent case has a dedicated folder identified by a five-digit number.\nWithin each of these “case” folders, there are four sub-folders, each of them corresponding to each of the structural multi-parametric MRI (mpMRI) scans, in DICOM format.\nThe exact mpMRI scans included are:\n\n- **FLAIR**: Fluid Attenuated Inversion Recovery\n- **T1w**: T1-weighted pre-contrast\n- **T1Gd**: T1-weighted post-contrast\n- **T2**: T2-weighted\n\nThe labels/targets are `MGMT_value`:\n\n![Label distribution](./assets/labels.png)\n\n## Experimentation\n\n### install this tooling\n\nA simple way how to use this basic functions:\n\n```bash\n! pip install https://github.com/Borda/kaggle_vol-3D-classify/archive/refs/heads/main.zip\n```\n\n### run notebooks in Kaggle\n\n- [🧠 Brain Tumor Classif. ~ Lightning⚡EfficientNet3D](https://www.kaggle.com/jirkaborovec/brain-tumor-classif-lightning-efficientnet3d)\n- [🧠 Brain Tumor Classif. ~ Lightning⚡MONAI-ResNet3D](https://www.kaggle.com/jirkaborovec/brain-tumor-classif-lightning-monai-resnet3d)\n\n### local notebooks\n\n- [Brain tumor classification meets PT-Lightning and MONAI EfficientNet3D](notebooks/Brain-tumor-classif_PT-Lightning_EfficientNet3D.ipynb)\n- [Brain tumor classification meets PT-Lightning and pre-trained ResNet3D](notebooks/Brain-tumor-classif_PT-Lightning_ResNet3D.ipynb)\n\n### some results\n\nTraining progress with EfficientNet3D with training for 10 epochs \u003e over 96% validation accuracy:\n\n![Training process](./assets/metrics.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborda%2Fkaggle_vol-3d-classify","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fborda%2Fkaggle_vol-3d-classify","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborda%2Fkaggle_vol-3d-classify/lists"}