236 datasets found

Two datasets used to train the SpineNetV2 pipeline: Oxford Whole Spine (OWS) and Genodisc.

The DeepLesion dataset consists of 32,735 images bookmarked and measured via RECIST annotations by multiple radiologists over multiple years from 10,594 studies of 4,459 patients.

The lesion masks dataset is used for prostate cancer segmentation. It contains 299 lesions annotated by two residents and two experienced board-certified radiologists.

The PROSTATEx challenge dataset is used for prostate cancer triage. It contains 204 patients diagnosed with PCa and 330 lesions. Lesions were annotated by experienced...

Brain tumor segmentation dataset used for training and evaluation of the proposed Squeeze Excitation Embedded Attention UNet (SEEA-UNet) model.

The Chest X-Ray8 dataset is used to validate the performance of the proposed framework. The dataset contains 112,120 frontal view X-ray images of 32,717 unique patients.

The Fundus dataset is a public fundus dataset used for evaluating the performance of the GeCA model.

The OCT-ML dataset is a multi-label OCT dataset consisting of 1435 samples from 369 eyes of 203 patients considering multiple diseases.

The Chexpert dataset is a large chest radiograph dataset with uncertainty labels and expert comparison.

The NIH dataset contains 14 different diseases, including pneumonia, and is used for training and testing machine learning models.

The RSNA dataset contains 26,684 frontal-view chest X-ray images, all of which are labeled as either 0 (no pneumonia) or 1 (pneumonia).

The FFDM dataset is a full-field digital mammography dataset used for training and testing the proposed method.

The DDSM dataset is a public mammogram dataset used for training and testing the proposed method.

Kidney segmentation using 3D U-Net localized with Expectation Maximization

A publicly available radiology dataset of chest x-rays and reports that is a subset of the OpenI open source literature and biomedical image collections.

A deep learning approach for breast cancer detection on screening mammography.

Multiple Sclerosis Lesion Segmentation dataset

Liver lesion segmentation dataset

HyperKvasir is a comprehensive multi-class image and video dataset for gastrointestinal endoscopy.

Gastrointestinal (GI) cancer precursors require frequent monitoring for risk stratification of patients. Automated segmentation methods can help to assess risk areas more...