Hello all,
\nI wish you all the best for the assignment. I have compiled some onboarding materials and hope this helps in getting started.
\nBest of luck for the challenge and warm regards!
", "messages": [ { "id": 2472226, "postDate": "2023-10-07T06:14:10.647Z", "content": "Hello all,
\nI wish you all the best for the assignment. I have compiled some onboarding materials and hope this helps in getting started.
\nBest of luck for the challenge and warm regards!
", "rawMarkdown": "Hello all,\n\nI wish you all the best for the assignment. I have compiled some onboarding materials and hope this helps in getting started.\n\n## Domain references and articles-\n1. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8774015/#:~:text=The%20current%20fifth%20edition%20(2020,clear%20cell%20carcinoma%20(CCC). -- excellent starter article for beginners \n2. https://academic.oup.com/biolreprod/article/101/3/645/5513989 -- excellent simple article explaining the concepts efficiently\n3. https://www.intechopen.com/chapters/75017\n4. https://www.pathologyoutlines.com/topic/ovarytumorwhoclassif.html -- useful beginner friendly resource to start \n5. https://www.cancerresearchuk.org/about-cancer/ovarian-cancer/types -- easy to understand article with less medical terms, suitable for participants from a diverse background\n6. https://www.cancernetwork.com/view/morphologic-immunophenotypic-and-molecular-features-epithelial-ovarian-cancer -- excellent article to understand relevant concepts\n\n## Research papers-\n1. https://paperswithcode.com/paper/classification-of-epithelial-ovarian\n2. https://paperswithcode.com/paper/efficient-subtyping-of-ovarian-cancer\n3. https://paperswithcode.com/paper/digital-pathology-based-study-of-cell-and\n\n## Similar competitions\n### [RSNA Screening Mammography Breast Cancer Detection](https://www.kaggle.com/competitions/rsna-breast-cancer-detection)\n\n#### Kernels\n1. https://www.kaggle.com/code/radek1/eda-training-a-fast-ai-model-submission -- highest voted kernel\n2. https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference -- second highest voted kernel\n3. https://www.kaggle.com/code/andradaolteanu/rsna-breast-cancer-eda-pytorch-baseline -- beginner friendly starter with excellent EDA\n4. https://www.kaggle.com/code/radek1/how-to-process-dicom-images-to-pngs -- highlights image processing elements with aplomb\n5. https://www.kaggle.com/code/allunia/rsna-breast-cancer-eda -- excellent EDA \n6. https://www.kaggle.com/code/darraghdog/4th-place-submission-cdi -- 4th place solution\n7. https://www.kaggle.com/code/dangnh0611/1st-place-submission-code -- winning solution\n\n#### Winning solutions\n1. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/392449 -- rank1\n2. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391676 -- rank2\n3. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391725 -- rank3\n4. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391208 -- rank4\n5. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391979 -- rank5\n\n### [UW-Madison GI Tract Image Segmentation](https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation)\n#### Kernels\n1. https://www.kaggle.com/code/carnozhao/1st-place-winning-solution -- rank1 approach\n2. https://www.kaggle.com/code/hesene/3rd-place-winning-solution -- rank3 approach\n3. https://www.kaggle.com/code/dschettler8845/uwm-gi-tract-image-segmentation-eda -- excellent EDA and starter, most popular kernel\n4. https://www.kaggle.com/code/awsaf49/uwmgi-unet-train-pytorch -- second highest voted kernel\n5. https://www.kaggle.com/code/andradaolteanu/aw-madison-eda-in-depth-mask-exploration -- good starter and EDA elements\n6. https://www.kaggle.com/code/dschettler8845/uwmgit-deeplabv3-end-to-end-pipeline-tf -- very useful pipeline offering an end-to-end architecture\n\n### Winning solutions\n1. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337217 -- rank1\n2. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337400 -- rank2\n3. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337468 -- rank3\n4. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337268 -- rank5\n5. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337359 -- rank8\n\n## [RSNA-MICCAI Brain Tumor Radiogenomic Classification](https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification)\n#### Kernels\n1. https://www.kaggle.com/code/ihelon/brain-tumor-eda-with-animations-and-modeling -- excellent starter with a different EDA process (includes animations)\n2. https://www.kaggle.com/code/rluethy/efficientnet3d-with-one-mri-type -- good starter \n3. https://www.kaggle.com/code/chumajin/brain-tumor-eda-for-starter-english-version -- good EDA and offers 2 versions (English, Japanese)\n4. https://www.kaggle.com/code/ammarnassanalhajali/brain-tumor-3d-training -- could be useful to edit and train a model\n\n### Winning solutions\n1. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/281347 -- rank1\n2. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/280033 -- rank2\n3. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/287713 -- rank3\n4. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/280029 -- rank4\n5. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/281911 -- rank5\n\nBest of luck for the challenge and warm regards! ", "votes": 37 }, { "id": 2474346, "postDate": "2023-10-09T06:25:14.627Z", "content": "Very comprehensive collection of materials. Well done and thank you!
", "rawMarkdown": "Very comprehensive collection of materials. Well done and thank you!", "votes": 1 }, { "id": 2474221, "postDate": "2023-10-09T04:48:47.920Z", "content": "Thanks for sharing this valuable information.
", "rawMarkdown": "Thanks for sharing this valuable information.", "votes": 1 }, { "id": 2472588, "postDate": "2023-10-07T12:36:59.697Z", "content": "wow. It's a huge materials for the assignment
", "rawMarkdown": "wow. It's a huge materials for the assignment", "votes": 1 }, { "id": 2497988, "postDate": "2023-10-25T04:17:01.283Z", "content": "Hey @ravi20076 Thanks for resource sharing. This comp. WSI image classification challenge. Before in the Kaggle there was another WSI image based comp. happened -> mayo-clinic-strip-ai . You can add to your thread :)
", "rawMarkdown": "Hey @ravi20076 Thanks for resource sharing. This comp. WSI image classification challenge. Before in the Kaggle there was another WSI image based comp. happened -> [mayo-clinic-strip-ai](https://www.kaggle.com/competitions/mayo-clinic-strip-ai/) . You can add to your thread :) " } ], "comments": [ { "id": 2474346, "author_name": "Jared Jordan", "author_url": "", "post_date": "2023-10-09T06:25:14.627000", "content": "Very comprehensive collection of materials. Well done and thank you!
", "votes": 1, "replies": [] }, { "id": 2474221, "author_name": "sunil thite", "author_url": "", "post_date": "2023-10-09T04:48:47.920000", "content": "Thanks for sharing this valuable information.
", "votes": 1, "replies": [] }, { "id": 2472588, "author_name": "Al Sani", "author_url": "", "post_date": "2023-10-07T12:36:59.697000", "content": "wow. It's a huge materials for the assignment
", "votes": 1, "replies": [] }, { "id": 2497988, "author_name": "AIFahim", "author_url": "", "post_date": "2023-10-25T04:17:01.283000", "content": "Hey @ravi20076 Thanks for resource sharing. This comp. WSI image classification challenge. Before in the Kaggle there was another WSI image based comp. happened -> mayo-clinic-strip-ai . You can add to your thread :)
", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "2472226": "Hello all,\n\nI wish you all the best for the assignment. I have compiled some onboarding materials and hope this helps in getting started.\n\n## Domain references and articles-\n1. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8774015/#:~:text=The%20current%20fifth%20edition%20(2020,clear%20cell%20carcinoma%20(CCC). -- excellent starter article for beginners \n2. https://academic.oup.com/biolreprod/article/101/3/645/5513989 -- excellent simple article explaining the concepts efficiently\n3. https://www.intechopen.com/chapters/75017\n4. https://www.pathologyoutlines.com/topic/ovarytumorwhoclassif.html -- useful beginner friendly resource to start \n5. https://www.cancerresearchuk.org/about-cancer/ovarian-cancer/types -- easy to understand article with less medical terms, suitable for participants from a diverse background\n6. https://www.cancernetwork.com/view/morphologic-immunophenotypic-and-molecular-features-epithelial-ovarian-cancer -- excellent article to understand relevant concepts\n\n## Research papers-\n1. https://paperswithcode.com/paper/classification-of-epithelial-ovarian\n2. https://paperswithcode.com/paper/efficient-subtyping-of-ovarian-cancer\n3. https://paperswithcode.com/paper/digital-pathology-based-study-of-cell-and\n\n## Similar competitions\n### [RSNA Screening Mammography Breast Cancer Detection](https://www.kaggle.com/competitions/rsna-breast-cancer-detection)\n\n#### Kernels\n1. https://www.kaggle.com/code/radek1/eda-training-a-fast-ai-model-submission -- highest voted kernel\n2. https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference -- second highest voted kernel\n3. https://www.kaggle.com/code/andradaolteanu/rsna-breast-cancer-eda-pytorch-baseline -- beginner friendly starter with excellent EDA\n4. https://www.kaggle.com/code/radek1/how-to-process-dicom-images-to-pngs -- highlights image processing elements with aplomb\n5. https://www.kaggle.com/code/allunia/rsna-breast-cancer-eda -- excellent EDA \n6. https://www.kaggle.com/code/darraghdog/4th-place-submission-cdi -- 4th place solution\n7. https://www.kaggle.com/code/dangnh0611/1st-place-submission-code -- winning solution\n\n#### Winning solutions\n1. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/392449 -- rank1\n2. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391676 -- rank2\n3. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391725 -- rank3\n4. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391208 -- rank4\n5. https://www.kaggle.com/competitions/rsna-breast-cancer-detection/discussion/391979 -- rank5\n\n### [UW-Madison GI Tract Image Segmentation](https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation)\n#### Kernels\n1. https://www.kaggle.com/code/carnozhao/1st-place-winning-solution -- rank1 approach\n2. https://www.kaggle.com/code/hesene/3rd-place-winning-solution -- rank3 approach\n3. https://www.kaggle.com/code/dschettler8845/uwm-gi-tract-image-segmentation-eda -- excellent EDA and starter, most popular kernel\n4. https://www.kaggle.com/code/awsaf49/uwmgi-unet-train-pytorch -- second highest voted kernel\n5. https://www.kaggle.com/code/andradaolteanu/aw-madison-eda-in-depth-mask-exploration -- good starter and EDA elements\n6. https://www.kaggle.com/code/dschettler8845/uwmgit-deeplabv3-end-to-end-pipeline-tf -- very useful pipeline offering an end-to-end architecture\n\n### Winning solutions\n1. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337217 -- rank1\n2. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337400 -- rank2\n3. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337468 -- rank3\n4. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337268 -- rank5\n5. https://www.kaggle.com/competitions/uw-madison-gi-tract-image-segmentation/discussion/337359 -- rank8\n\n## [RSNA-MICCAI Brain Tumor Radiogenomic Classification](https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification)\n#### Kernels\n1. https://www.kaggle.com/code/ihelon/brain-tumor-eda-with-animations-and-modeling -- excellent starter with a different EDA process (includes animations)\n2. https://www.kaggle.com/code/rluethy/efficientnet3d-with-one-mri-type -- good starter \n3. https://www.kaggle.com/code/chumajin/brain-tumor-eda-for-starter-english-version -- good EDA and offers 2 versions (English, Japanese)\n4. https://www.kaggle.com/code/ammarnassanalhajali/brain-tumor-3d-training -- could be useful to edit and train a model\n\n### Winning solutions\n1. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/281347 -- rank1\n2. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/280033 -- rank2\n3. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/287713 -- rank3\n4. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/280029 -- rank4\n5. https://www.kaggle.com/competitions/rsna-miccai-brain-tumor-radiogenomic-classification/discussion/281911 -- rank5\n\nBest of luck for the challenge and warm regards! ", "2474346": "Very comprehensive collection of materials. Well done and thank you!", "2474221": "Thanks for sharing this valuable information.", "2472588": "wow. It's a huge materials for the assignment", "2497988": "Hey @ravi20076 Thanks for resource sharing. This comp. WSI image classification challenge. Before in the Kaggle there was another WSI image based comp. happened -> [mayo-clinic-strip-ai](https://www.kaggle.com/competitions/mayo-clinic-strip-ai/) . You can add to your thread :) " } }