Boundary loss for highly unbalanced segmentation

Published in

International Conference on Medical Imaging wit...(2018)

External Links:

Generate Graph DownloadPDF

TL;DR

Inspired by graph-based optimization techniques for computing active-contour flows, a non-symmetric L2 distance on the space of contours as a regional integral is expressed, which avoids completely local differential computations involving contour points.

Authors

Christian Desrosiers

6 papers

Eric Granger

9 papers

Ismail Ben Ayed

11 papers

J. Dolz

14 papers

H. Kervadec

3 papers

Jihene Bouchtiba

1 papers

References26 items

How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study

Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks

A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation

3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes

AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy

Boundary loss for highly unbalanced segmentation

Published in

International Conference on Medical Imaging wit...(2018)

External Links:

Generate Graph DownloadPDF

TL;DR

Authors

Christian Desrosiers

6 papers

Eric Granger

9 papers

Ismail Ben Ayed

11 papers

J. Dolz

14 papers

H. Kervadec

3 papers

Jihene Bouchtiba

1 papers

References26 items

How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study

Reducing the Hausdorff Distance in Medical Image Segmentation With Convolutional Neural Networks

A Novel Focal Tversky Loss Function With Improved Attention U-Net for Lesion Segmentation

3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes

AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy

Automatic differentiation in PyTorch

Focal Loss for Dense Object Detection

Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations

Deep Learning in Medical Image Analysis.

Tversky Loss Function for Image Segmentation Using 3D Fully Convolutional Deep Networks

A survey on deep learning in medical image analysis

Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach

Volumetric ConvNets with Mixed Residual Connections for Automated Prostate Segmentation from 3D MR Images

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

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation

Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound

Deep Convolutional Encoder Networks for Multiple Sclerosis Lesion Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

Brain tumor segmentation with Deep Neural Networks

Fully convolutional networks for semantic segmentation

Variational and Level Set Methods in Image Segmentation

Graph Cuts and Efficient N-D Image Segmentation

An Integral Solution to Surface Evolution PDEs Via Geo-cuts

Geodesic Active Contours

Deep Learning Applications in Medical Image Analysis

Field of Study

Computer ScienceMedicine

Journal Information

Name

Medical image analysis

Page

60-88

Volume

Venue Information

Name

International Conference on Medical Imaging with Deep Learning

Type

conference

URL

https://www.midl.io/

Alternate Names

MIDL
Int Conf Med Imaging Deep Learn