27 datasets found

The BraTS 2017 dataset, used for training and testing the segmentation models.

The 2D brain tumour dataset proposed in [16], created from axial slices extracted from the MRI volumes of the 3D brain tumor segmentation challenge (BraTS) 2017 data.

Automated medical image segmentation can assist doctors to diagnose faster and more accurate. Deep learning based models for medical image segmentation have made great progress...

Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved?

The dataset used for vestibular schwannoma MRI segmentation

The MSD Spleen dataset consists of n = 61 portal-venous phase contrast-enhanced abdominal CT scans, out of which n = 41 (67%) contained annotations for the spleen.

The MSD Liver dataset consists of n = 201 portal-venous phase contrast-enhanced abdominal CT scans, out of which n = 131 (65%) contained annotations for the liver and liver tumors.

The Medical Segmentation Decathlon (MSD) is a collection of 10 benchmark datasets for segmentation spanning different body parts and modalities.

Automatic segmentation of brain tumors is an essential but challenging step for extracting quantitative imaging biomarkers for accurate tumor detection, diagnosis, prognosis,...

Liver Tumor Segmentation dataset contains images of liver tumors from CT scans. The dataset is used for automatic segmentation of liver tumors.

Brain Anatomy Segmentation from US images dataset contains images of brain anatomy from ultrasound scans. The dataset is used for automatic segmentation of brain ventricles and...

Multi-parametric MRI scans from 2000 patients were used for BraTS2021, 1251 of which were provided with segmentation labels to the participants for developing their algorithms,...

Medical image segmentation dataset

Medical image segmentation dataset

The Medical Segmentation Decathlon dataset is a benchmark for medical image segmentation, containing 131 CT volumes.

Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep learning-based...

Three challenging medical applications: whole-brain, whole-body and retinal layer segmentation.

The dataset contains 3D thoracic CT scans for segmentation of thoracic organs.

Skin lesion segmentation dataset

The REFUGE2 dataset is a multi-annotated dataset for optic-cup segmentation. The dataset consists of 1200 fundus images, each annotated by seven radiologists.