{ "id": 497790, "title": "Embargo Lifted on Competition Dataset", "url": "/competitions/UBC-OCEAN/discussion/497790", "author_name": "Hossein", "post_date": "2024-04-25T17:59:41.601000", "votes": 4, "comment_count": 1, "views": 0, "content": "

Dear all,

\n

We are pleased to announce that the embargo on the dataset for this competition has been lifted. Should you choose to utilize this dataset in your studies, please ensure to follow the citation guidelines listed in the How to Cite This Challenge in Publications section found in the Overview section of the competition page.

", "messages": [ { "id": 2775620, "postDate": "2024-04-25T17:59:41.600Z", "content": "

Dear all,

\n

We are pleased to announce that the embargo on the dataset for this competition has been lifted. Should you choose to utilize this dataset in your studies, please ensure to follow the citation guidelines listed in the How to Cite This Challenge in Publications section found in the Overview section of the competition page.

", "rawMarkdown": "Dear all,\n\nWe are pleased to announce that the embargo on the dataset for this competition has been lifted. Should you choose to utilize this dataset in your studies, please ensure to follow the citation guidelines listed in the **How to Cite This Challenge in Publications** section found in the **Overview** section of the competition page.\n", "votes": 4 }, { "id": 3029686, "postDate": "2024-10-27T15:56:25.843Z", "content": "

There is an IEEE paper that is academic fraud. The title is \"OCEAN - Ovarian Cancer subtypE clAssification and outlier detectionioN using DenseNet121\". It claims that only convolutional networks were used without mentioning multi-instance learning. Then, 2,000 WSI images from the OECEN-UBC competition that our contestants could not get were used for training to obtain a classification accuracy of 99.7%. However, our first place winner only had a test accuracy of 0.6 and a 5-fold cross-validation accuracy of less than 90%\"\"\"\"\"\"

", "rawMarkdown": "There is an IEEE paper that is academic fraud. The title is \"OCEAN - Ovarian Cancer subtypE clAssification and outlier detectionioN using DenseNet121\". It claims that only convolutional networks were used without mentioning multi-instance learning. Then, 2,000 WSI images from the OECEN-UBC competition that our contestants could not get were used for training to obtain a classification accuracy of 99.7%. However, our first place winner only had a test accuracy of 0.6 and a 5-fold cross-validation accuracy of less than 90%![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16846649%2F8a1a7f3ab209835daf8153d447cecaba%2F_20241027234938.png?generation=1730044558975865&alt=media)![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16846649%2F87ab35df6a33e8d95ab877851a0f09ac%2Ffake_acc.png?generation=1730044568132323&alt=media)![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16846649%2Fe2ad9151aeaae96db01743e9da39545c%2Ftable.png?generation=1730044580956938&alt=media)" } ], "comments": [ { "id": 3029686, "author_name": "Metavers", "author_url": "", "post_date": "2024-10-27T15:56:25.843000", "content": "

There is an IEEE paper that is academic fraud. The title is \"OCEAN - Ovarian Cancer subtypE clAssification and outlier detectionioN using DenseNet121\". It claims that only convolutional networks were used without mentioning multi-instance learning. Then, 2,000 WSI images from the OECEN-UBC competition that our contestants could not get were used for training to obtain a classification accuracy of 99.7%. However, our first place winner only had a test accuracy of 0.6 and a 5-fold cross-validation accuracy of less than 90%\"\"\"\"\"\"

", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "2775620": "Dear all,\n\nWe are pleased to announce that the embargo on the dataset for this competition has been lifted. Should you choose to utilize this dataset in your studies, please ensure to follow the citation guidelines listed in the **How to Cite This Challenge in Publications** section found in the **Overview** section of the competition page.\n", "3029686": "There is an IEEE paper that is academic fraud. The title is \"OCEAN - Ovarian Cancer subtypE clAssification and outlier detectionioN using DenseNet121\". It claims that only convolutional networks were used without mentioning multi-instance learning. Then, 2,000 WSI images from the OECEN-UBC competition that our contestants could not get were used for training to obtain a classification accuracy of 99.7%. However, our first place winner only had a test accuracy of 0.6 and a 5-fold cross-validation accuracy of less than 90%![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16846649%2F8a1a7f3ab209835daf8153d447cecaba%2F_20241027234938.png?generation=1730044558975865&alt=media)![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16846649%2F87ab35df6a33e8d95ab877851a0f09ac%2Ffake_acc.png?generation=1730044568132323&alt=media)![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F16846649%2Fe2ad9151aeaae96db01743e9da39545c%2Ftable.png?generation=1730044580956938&alt=media)" } }