DeepAI AI Chat
Log In Sign Up

Divided We Stand: A Novel Residual Group Attention Mechanism for Medical Image Segmentation

12/04/2019
by   Chaitanya Kaul, et al.
University of York
18

Given that convolutional neural networks extract features via learning convolution kernels, it makes sense to design better kernels which can in turn lead to better feature extraction. In this paper, we propose a new residual block for convolutional neural networks in the context of medical image segmentation. We combine attention mechanisms with group convolutions to create our group attention mechanism, which forms the fundamental building block of FocusNetAlpha - our convolutional autoencoder. We adapt a hybrid loss based on balanced cross entropy, tversky loss and the adaptive logarithmic loss to create a loss function that converges faster and more accurately to the minimum solution. On comparison with the different residual block variants, we observed a 5.6 block and a 1.3 show that FocusNetAlpha achieves state-of-the-art results across all metrics for the ISIC 2018 melanoma segmentation, cell nuclei segmentation and the DRIVE retinal blood vessel segmentation datasets with fewer parameters and FLOPs. Our code and pre-trained models will be publicly available on GitHub to maximize reproducibility.

READ FULL TEXT

page 13

page 14

page 15

page 16

03/07/2019

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Medical image segmentation is an important step in medical image analysi...
04/07/2020

Channel Attention Residual U-Net for Retinal Vessel Segmentation

Retinal vessel segmentation is a vital step for the diagnosis of many ea...
02/08/2019

FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation

We propose a novel technique to incorporate attention within convolution...
03/10/2020

Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation

Medical image segmentation has been very challenging due to the large va...
11/20/2019

Hierarchical Attention Networks for Medical Image Segmentation

The medical image is characterized by the inter-class indistinction, hig...
11/22/2019

HybridNetSeg: A Compact Hybrid Network for Retinal Vessel Segmentation

A large number of retinal vessel analysis methods based on image segment...