{ "id": 208035, "title": "🔱 ⚜️ Chest X-ray Datasets Compilation 🔰 ♻️", "url": "/competitions/vinbigdata-chest-xray-abnormalities-detection/discussion/208035", "author_name": "Tensor Girl", "post_date": "2021-01-01T13:53:03.618000", "votes": 10, "comment_count": 1, "views": 0, "content": "

\"\"
\nHere is the compilation of Chest X-rays datasets if you are looking for external datasets in addition to the given competition Dataset .
\nCheXpert :
\nCheXpert is a large dataset of chest X-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard evaluation sets.
\nhttps://www.kaggle.com/mimsadiislam/chexpert
\nPulmonary Chest X-Ray Abnormalities
\nThis dataset contains over 500 x-rays scans with clinical labels collected by radiologists.The two datasets were published together in an analysis here: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4256233/.The datasets come from Shenzhen and Montgomery respectively.
\nhttps://www.kaggle.com/kmader/pulmonary-chest-xray-abnormalities

\n

NIH Chest X-rays
\nThis NIH Chest X-ray Dataset comprises 112,120 X-ray images with disease labels from 30,805 unique patients.
\nhttps://www.kaggle.com/nih-chest-xrays/data
\nCOVIDx-CT
\nCOVIDx-CT, an open access benchmark dataset that we generated from open source datasets, currently comprises 104,009 CT slices from 1,489 patients. We will be adding to COVIDx-CT over time to improve the dataset.
\nResearch Paper : https://arxiv.org/abs/2009.05383
\nhttps://www.kaggle.com/hgunraj/covidxct
\nX-ray Bone Shadow Suppression
\nBone suppression is an autoencoder-like model for eliminating bone shadow from Chest X-ray images. The model requires two types of dataset: normal and bone-suppression X-ray images. The target model can suppress bone shadow from Chest X-ray images, and help Radiologists diagnose better lung related diseases.
\nhttps://www.kaggle.com/hmchuong/xray-bone-shadow-supression
\nCOVID-19 Radiography Database
\n{{ Winner of the COVID-19 Dataset Award by Kaggle Community }}
\nA team of researchers from Qatar University, Doha, Qatar, and the University of Dhaka, Bangladesh along with their collaborators from Pakistan and Malaysia in collaboration with medical doctors have created a database of chest X-ray images for COVID-19 positive cases along with Normal and Viral Pneumonia images.
\nhttps://www.kaggle.com/tawsifurrahman/covid19-radiography-database
\nChest X-Ray Images (Pneumonia)
\nThis dataset contains 5,856 validated Chest X-Ray images. The images are split into a training set and a testing set of independent patients. Images are labeled as (disease:NORMAL/BACTERIA/VIRUS)-(randomized patient ID)-(image number of a patient).
\nResearch Paper : https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5
\nhttps://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
\nHope you found this useful . If you come across any other additional datasets in addition to the above , kindly mention it in the comments and I will update the post

", "messages": [ { "id": 1134698, "postDate": "2021-01-01T13:53:03.617Z", "content": "

\"\"
\nHere is the compilation of Chest X-rays datasets if you are looking for external datasets in addition to the given competition Dataset .
\nCheXpert :
\nCheXpert is a large dataset of chest X-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard evaluation sets.
\nhttps://www.kaggle.com/mimsadiislam/chexpert
\nPulmonary Chest X-Ray Abnormalities
\nThis dataset contains over 500 x-rays scans with clinical labels collected by radiologists.The two datasets were published together in an analysis here: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4256233/.The datasets come from Shenzhen and Montgomery respectively.
\nhttps://www.kaggle.com/kmader/pulmonary-chest-xray-abnormalities

\n

NIH Chest X-rays
\nThis NIH Chest X-ray Dataset comprises 112,120 X-ray images with disease labels from 30,805 unique patients.
\nhttps://www.kaggle.com/nih-chest-xrays/data
\nCOVIDx-CT
\nCOVIDx-CT, an open access benchmark dataset that we generated from open source datasets, currently comprises 104,009 CT slices from 1,489 patients. We will be adding to COVIDx-CT over time to improve the dataset.
\nResearch Paper : https://arxiv.org/abs/2009.05383
\nhttps://www.kaggle.com/hgunraj/covidxct
\nX-ray Bone Shadow Suppression
\nBone suppression is an autoencoder-like model for eliminating bone shadow from Chest X-ray images. The model requires two types of dataset: normal and bone-suppression X-ray images. The target model can suppress bone shadow from Chest X-ray images, and help Radiologists diagnose better lung related diseases.
\nhttps://www.kaggle.com/hmchuong/xray-bone-shadow-supression
\nCOVID-19 Radiography Database
\n{{ Winner of the COVID-19 Dataset Award by Kaggle Community }}
\nA team of researchers from Qatar University, Doha, Qatar, and the University of Dhaka, Bangladesh along with their collaborators from Pakistan and Malaysia in collaboration with medical doctors have created a database of chest X-ray images for COVID-19 positive cases along with Normal and Viral Pneumonia images.
\nhttps://www.kaggle.com/tawsifurrahman/covid19-radiography-database
\nChest X-Ray Images (Pneumonia)
\nThis dataset contains 5,856 validated Chest X-Ray images. The images are split into a training set and a testing set of independent patients. Images are labeled as (disease:NORMAL/BACTERIA/VIRUS)-(randomized patient ID)-(image number of a patient).
\nResearch Paper : https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5
\nhttps://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
\nHope you found this useful . If you come across any other additional datasets in addition to the above , kindly mention it in the comments and I will update the post

", "rawMarkdown": "\n![](https://drive.google.com/uc?id=1VkquW4Y5w8GyWAjgf7RcTiJQZjTydThc)\n\nHere is the compilation of Chest X-rays datasets if you are looking for external datasets in addition to the given competition Dataset . \n\n\n**CheXpert :**\nCheXpert is a large dataset of chest X-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard evaluation sets.\n\nhttps://www.kaggle.com/mimsadiislam/chexpert\n\n**Pulmonary Chest X-Ray Abnormalities**\nThis dataset contains over 500 x-rays scans with clinical labels collected by radiologists.The two datasets were published together in an analysis here: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4256233/.The datasets come from Shenzhen and Montgomery respectively.\nhttps://www.kaggle.com/kmader/pulmonary-chest-xray-abnormalities\n \n**NIH Chest X-rays**\nThis NIH Chest X-ray Dataset comprises 112,120 X-ray images with disease labels from 30,805 unique patients. \n\nhttps://www.kaggle.com/nih-chest-xrays/data\n\n**COVIDx-CT**\n\nCOVIDx-CT, an open access benchmark dataset that we generated from open source datasets, currently comprises 104,009 CT slices from 1,489 patients. We will be adding to COVIDx-CT over time to improve the dataset.\n\nResearch Paper : https://arxiv.org/abs/2009.05383\n\nhttps://www.kaggle.com/hgunraj/covidxct\n\n**X-ray Bone Shadow Suppression**\n\nBone suppression is an autoencoder-like model for eliminating bone shadow from Chest X-ray images. The model requires two types of dataset: normal and bone-suppression X-ray images. The target model can suppress bone shadow from Chest X-ray images, and help Radiologists diagnose better lung related diseases. \n\nhttps://www.kaggle.com/hmchuong/xray-bone-shadow-supression\n\n**COVID-19 Radiography Database** \n{{ Winner of the COVID-19 Dataset Award by Kaggle Community }}\n\nA team of researchers from Qatar University, Doha, Qatar, and the University of Dhaka, Bangladesh along with their collaborators from Pakistan and Malaysia in collaboration with medical doctors have created a database of chest X-ray images for COVID-19 positive cases along with Normal and Viral Pneumonia images.\n\nhttps://www.kaggle.com/tawsifurrahman/covid19-radiography-database\n\n**Chest X-Ray Images (Pneumonia)**\n\nThis dataset contains 5,856 validated Chest X-Ray images. The images are split into a training set and a testing set of independent patients. Images are labeled as (disease:NORMAL/BACTERIA/VIRUS)-(randomized patient ID)-(image number of a patient).\n\nResearch Paper : https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5\n\nhttps://www.kaggle.com/paultimothymooney/chest-xray-pneumonia\n\n\n\nHope you found this useful . If you come across any other additional datasets in addition to the above , kindly mention it in the comments and I will update the post\n", "votes": 10 }, { "id": 1139537, "postDate": "2021-01-05T13:20:10.513Z", "content": "

I found yet another useful dataset. Hope it helps you too!

\n

TBX11k Dataset (Tuberculosis Classification and detection)
\nThis dataset contains about 11K chest x-ray images with train and valid split. The class labels in TB x-rays are of (TB, Non-TB, Sick but not TB). It also has the TB area detection annotations.
\nResearch paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Rethinking_Computer-Aided_Tuberculosis_Diagnosis_CVPR_2020_paper.html
\nDataset competition: https://competitions.codalab.org/competitions/25848

", "rawMarkdown": "I found yet another useful dataset. Hope it helps you too!\n\n**TBX11k Dataset (Tuberculosis Classification and detection)**\nThis dataset contains about 11K chest x-ray images with train and valid split. The class labels in TB x-rays are of (TB, Non-TB, Sick but not TB). It also has the TB area detection annotations.\nResearch paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Rethinking_Computer-Aided_Tuberculosis_Diagnosis_CVPR_2020_paper.html\nDataset competition: https://competitions.codalab.org/competitions/25848", "votes": 1 } ], "comments": [ { "id": 1139537, "author_name": "HARINI NARASIMHAN", "author_url": "", "post_date": "2021-01-05T13:20:10.513000", "content": "

I found yet another useful dataset. Hope it helps you too!

\n

TBX11k Dataset (Tuberculosis Classification and detection)
\nThis dataset contains about 11K chest x-ray images with train and valid split. The class labels in TB x-rays are of (TB, Non-TB, Sick but not TB). It also has the TB area detection annotations.
\nResearch paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Rethinking_Computer-Aided_Tuberculosis_Diagnosis_CVPR_2020_paper.html
\nDataset competition: https://competitions.codalab.org/competitions/25848

", "votes": 1, "replies": [] } ], "raw_markdown_by_id": { "1134698": "\n![](https://drive.google.com/uc?id=1VkquW4Y5w8GyWAjgf7RcTiJQZjTydThc)\n\nHere is the compilation of Chest X-rays datasets if you are looking for external datasets in addition to the given competition Dataset . \n\n\n**CheXpert :**\nCheXpert is a large dataset of chest X-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard evaluation sets.\n\nhttps://www.kaggle.com/mimsadiislam/chexpert\n\n**Pulmonary Chest X-Ray Abnormalities**\nThis dataset contains over 500 x-rays scans with clinical labels collected by radiologists.The two datasets were published together in an analysis here: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4256233/.The datasets come from Shenzhen and Montgomery respectively.\nhttps://www.kaggle.com/kmader/pulmonary-chest-xray-abnormalities\n \n**NIH Chest X-rays**\nThis NIH Chest X-ray Dataset comprises 112,120 X-ray images with disease labels from 30,805 unique patients. \n\nhttps://www.kaggle.com/nih-chest-xrays/data\n\n**COVIDx-CT**\n\nCOVIDx-CT, an open access benchmark dataset that we generated from open source datasets, currently comprises 104,009 CT slices from 1,489 patients. We will be adding to COVIDx-CT over time to improve the dataset.\n\nResearch Paper : https://arxiv.org/abs/2009.05383\n\nhttps://www.kaggle.com/hgunraj/covidxct\n\n**X-ray Bone Shadow Suppression**\n\nBone suppression is an autoencoder-like model for eliminating bone shadow from Chest X-ray images. The model requires two types of dataset: normal and bone-suppression X-ray images. The target model can suppress bone shadow from Chest X-ray images, and help Radiologists diagnose better lung related diseases. \n\nhttps://www.kaggle.com/hmchuong/xray-bone-shadow-supression\n\n**COVID-19 Radiography Database** \n{{ Winner of the COVID-19 Dataset Award by Kaggle Community }}\n\nA team of researchers from Qatar University, Doha, Qatar, and the University of Dhaka, Bangladesh along with their collaborators from Pakistan and Malaysia in collaboration with medical doctors have created a database of chest X-ray images for COVID-19 positive cases along with Normal and Viral Pneumonia images.\n\nhttps://www.kaggle.com/tawsifurrahman/covid19-radiography-database\n\n**Chest X-Ray Images (Pneumonia)**\n\nThis dataset contains 5,856 validated Chest X-Ray images. The images are split into a training set and a testing set of independent patients. Images are labeled as (disease:NORMAL/BACTERIA/VIRUS)-(randomized patient ID)-(image number of a patient).\n\nResearch Paper : https://www.cell.com/cell/fulltext/S0092-8674(18)30154-5\n\nhttps://www.kaggle.com/paultimothymooney/chest-xray-pneumonia\n\n\n\nHope you found this useful . If you come across any other additional datasets in addition to the above , kindly mention it in the comments and I will update the post\n", "1139537": "I found yet another useful dataset. Hope it helps you too!\n\n**TBX11k Dataset (Tuberculosis Classification and detection)**\nThis dataset contains about 11K chest x-ray images with train and valid split. The class labels in TB x-rays are of (TB, Non-TB, Sick but not TB). It also has the TB area detection annotations.\nResearch paper: https://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Rethinking_Computer-Aided_Tuberculosis_Diagnosis_CVPR_2020_paper.html\nDataset competition: https://competitions.codalab.org/competitions/25848" } }