computer-vision-5
Tumor Segmentation
3260 papers • 126 benchmarks • 313 datasets
Tumor Segmentation is the task of identifying the spatial location of a tumor. It is a pixel-level prediction where each pixel is classified as a tumor or background. The most popular benchmark for this task is the BraTS dataset. The models are typically evaluated with the Dice Score metric.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in tumor-segmentation-5
Trend
Dataset
Best Model
Actions
BUS 2017 Dataset B
BUS 2017 Dataset B
DigestPath
DigestPath
LiTS17
LiTS17
Libraries
iUse these libraries to find tumor-segmentation-5 models and implementations
3 papers 1,989
Datasets
Subtasks
No subtasks available.
Most implemented papers
Brain tumor segmentation with Deep Neural Networks
H. Larochelle, C. Pal, Yoshua Bengio, Aaron C. Courville, David Warde-Farley, Pierre-Marc Jodoin, Axel Davy, Mohammad Havaei, A. Biard•Tue May 12 2015
A fast and accurate fully automatic method for brain tumor segmentation which is competitive both in terms of accuracy and speed compared to the state of the art, and introduces a novel cascaded architecture that allows the system to more accurately model local label dependencies.
3000