95 datasets found

Liver vessel segmentation based on 3D swin-transformer with inductive biased multi-head self-attention

The proposed network is implemented in PyTorch using a single Tesla V100-DGXS-32GB GPU of an NVIDIA DGX station. For the ResNet-50 part, PyTorch default ImageNet pretrained...

A new Multiorgan Lesion Segmentation (MLS) dataset that contains images of various organs, including brain, liver, and lung, across different imaging modalities—MR and CT.

MosMed is a publicly-available medical image dataset for COVID-19 detection.

Retinal fundus images have been extensively used for clinical analysis of various ocular diseases, but the quality of fundus images is critical to the diagnosis and screening of...

LesionPaste is a one-shot anomaly detection framework for medical images that utilizes true anomalies from a single sample and synthesizes artificial anomalous samples.

Knee OsteoArthritis (KOA) dataset used for early detection of KOA (KL-0 vs KL-2) using Vision Transformer (ViT) model with selective shuffled position embedding and key-patch...

The DRIVE dataset contains the curvilinear-shaped vessel. This dataset consists of 40 565 × 584 color retinal images, which are split into 20 training images and 20 test images.

The head CT scans dataset is used for training and evaluation of the proposed method.

The CQ500 dataset is a head CT scans dataset used for training and evaluation of the proposed method.

HISTO-FED is a medical image dataset, consisting of both public and private hematoxylin & eosin (H&E) stained histological whole-slide images of human colorectal cancer...

The MICCAI 2009 LV Segmentation Challenge (LV-09) dataset contains 45 subjects with expert annotations.

The dataset used in this paper is a collection of T1, T2, and T2-FLAIR images acquired at a 3T SIEMENS scanner from 170 MS patients.

The dataset used in this paper is a collection of T1, T2, and T2-FLAIR images acquired at a 3T GE scanner from 30 MS patients.

The dataset is used for simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network.

The dataset is used for simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network.

The dataset is used for simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network.

The dataset is used for simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network.

The GlaS dataset contains 165 H&E-stained histopathology patches extracted from 16 WSIs.

A neural network with single-hidden layer of 64 hidden units and ReLU activations. A prior precision of ε = 1, a minibatch size of 128 and 16 Monte-Carlo samples are used for...