medical-5

Brain Segmentation

3260 papers • 126 benchmarks • 313 datasets

( Image credit: 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in brain-segmentation-11

Trend

Dataset

Best Model

Actions

Brain MRI segmentation

Libraries

i

Use these libraries to find brain-segmentation-11 models and implementations

ai-med/squeeze_and_excitation

3 papers 301

Datasets

CrossMoDA

BRATS 2021

Tc1 Mouse cerebellum atlas

Multi-template MRI mouse brain atlas

Subtasks

No subtasks available.

Most implemented papers

Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks

Abhijit Guha Roy, Nassir Navab, C. Wachinger•Tue Mar 06 2018

This paper introduces three variants of SE modules for image segmentation, and effectively incorporates these SE modules within three different state-of-the-art F-CNNs (DenseNet, SD-Net, U-Net) and observes consistent improvement of performance across all architectures, while minimally effecting model complexity.

954

Content

black0017/MedicalZooPytorch

2 papers 1,602

abhi4ssj/squeeze_and_excitation

2 papers 301

0

Paper Graph

QuickNAT: A fully convolutional network for quick and accurate segmentation of neuroanatomy

Abhijit Guha Roy, Nassir Navab, C. Wachinger, Sailesh Conjeti, Alzheimer's Disease Neuroimaging Initiative•Thu Jan 11 2018

QuickNAT, a fully convolutional, densely connected neural network that segments a MRI brain scan in 20 s, is introduced and achieves superior segmentation accuracy and reliability in comparison to state‐of‐the‐art methods, while being orders of magnitude faster.

244 0

Paper Graph

Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm

M. Mazurowski, Mateusz Buda, Ashirbani Saha•Fri May 31 2019

A fully automatic way to quantify tumor imaging characteristics using deep learning-based segmentation and test whether these characteristics are predictive of tumor genomic subtypes is proposed.

316 0

Paper Graph

VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation

Q. Dou, P. Heng, Hao Chen, Lequan Yu•Sat Aug 20 2016

This work unravels the potential of 3D deep learning to advance the recognition performance on volumetric image segmentation and proposes a deep voxelwise residual network, referred as VoxResNet, which borrows the spirit of deep residual learning in 2D image recognition tasks, and is extended into a 3D variant for handlingvolumetric data.

143 0

Paper Graph

3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study

Christian Desrosiers, Ismail Ben Ayed, J. Dolz•Sun Dec 11 2016

This work is the first to study subcortical structure segmentation on such large‐scale and heterogeneous data and yielded segmentations that are highly consistent with a standard atlas‐based approach, while running in a fraction of the time needed by atlas-based methods and avoiding registration/normalization steps.

378 0

Paper Graph

HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation

Christian Desrosiers, Jing Yuan, J. Dolz, Karthik Gopinath, H. Lombaert, Ismail ben Ayed•Sun Apr 08 2018

HyperDenseNet is proposed, a 3-D fully convolutional neural network that extends the definition of dense connectivity to multi-modal segmentation problems and has total freedom to learn more complex combinations between the modalities, within and in-between all the levels of abstraction, which increases significantly the learning representation.

489 0

Paper Graph

A Learning Strategy for Contrast-agnostic MRI Segmentation

Adrian V. Dalca, B. Fischl, J. E. Iglesias, Benjamin Billot, D. Greve, K. V. Leemput•Tue Mar 03 2020

A deep learning strategy that enables contrast-agnostic semantic segmentation of completely unpreprocessed brain MRI scans, without requiring additional training or fine-tuning for new modalities, and generalizes significantly better across datasets, compared to training using real images.

82 0

Paper Graph

CrossMoDA 2021 challenge: Benchmark of cross-modality domain adaptation techniques for vestibular schwannoma and cochlea segmentation

Nicola Rieke, S. Bakas, S. Ourselin, M. Modat, Tom Kamiel Magda Vercauteren, Sergio Escalera, R. Dorent, A. Kujawa, M. Ivory, Samuel Joutard, Ben Glocker, Jorge Cardoso, K. Batmanghelich, A. Belkov, Maria G. Baldeon Calisto, J. Choi, B. Dawant, Hexin Dong, Yubo Fan, Lasse Hansen, M. Heinrich, Smriti Joshi, V. Kashtanova, Hyeongyu Kim, Satoshi Kondo, C. Kruse, S. Lai-Yuen, Hao Li, Han Liu, B. Ly, I. Oguz, Hyungseob Shin, B. Shirokikh, Zixian Su, Guotai Wang, Jianghao Wu, Yanwu Xu, Kai Yao, Li Zhang, J. Shapey•Fri Jan 07 2022

The Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Ass Intervention (MICCAI 2021) and is the first large and multi-class benchmark for unsupervised cross-modality domain Adaptation.

102 0

Paper Graph

Deep neural networks for anatomical brain segmentation

G. Montana, A. D. Brébisson•Sun Feb 08 2015

To the knowledge, this technique is the first to tackle the anatomical segmentation of the whole brain using deep neural networks and it does not require any non-linear registration of the MR images.

329 0

Paper Graph

Adding a benchmark result helps the community track progress.