SA-Net: A scale-attention network for medical image segmentation.

Jingfei Hu,Hua Wang,Jicong Zhang,Jie Wang,Yunqi Wang,Fang He,Yuankai Huo

doi:10.1371/journal.pone.0247388

Abstract

Semantic segmentation of medical images provides an important cornerstone for subsequent tasks of image analysis and understanding. With rapid advancements in deep learning methods, conventional U-Net segmentation networks have been applied in many fields. Based on exploratory experiments, features at multiple scales have been found to be of great importance for the segmentation of medical images. In this paper, we propose a scale-attention deep learning network (SA-Net), which extracts features of different scales in a residual module and uses an attention module to enforce the scale-attention capability. SA-Net can better learn the multi-scale features and achieve more accurate segmentation for different medical image. In addition, this work validates the proposed method across multiple datasets. The experiment results show SA-Net achieves excellent performances in the applications of vessel detection in retinal images, lung segmentation, artery/vein(A/V) classification in retinal images and blastocyst segmentation. To facilitate SA-Net utilization by the scientific community, the code implementation will be made publicly available.

Highlights

Since manual and dense labeling of a large number of medical images is time-consuming, tedious and prone to inter- and intra-observers, automatic methods for medical image segmentation have been rapidly emerging
We propose a new scale-attention deep learning network (SA-Net) based on the residual module and attention module, which could segment the different medical images effectively
For the identification of the blood vessels at different scales, the scaleattention deep learning network (SA-Net) shows more continuous results and the detection of small blood vessels are especially close to the true labels. These results clearly indicate that devising the SA-Net architecture with multi-level scale-aware capabilities led to superior retinal vessel segmentation performance

Summary

Introduction

Since manual and dense labeling of a large number of medical images is time-consuming, tedious and prone to inter- and intra-observers, automatic methods for medical image segmentation have been rapidly emerging. Despite the emergence of the afore-mentioned variants, U-Net is still the most common architecture for medical image segmentation, essentially as its encoder-decoder organization (together with its skip connections) does not hinder efficient information flow, and its performance does not deteriorate at low data regime. The natural way for CNNs to extract coarse-to-fine multi-scale features is to utilize a convolutional operator stack Such inherent CNN capability of extracting multi-scale features leads to good representations for handling numerous medical image analysis tasks. The CE-Net [20] architecture employs Dense Atrous Convolution (DAC) blocks to create a multi-scale network for better medical image understanding. We propose a new scale-attention deep learning network (SA-Net) based on the residual module and attention module, which could segment the different medical images effectively.

Methods

Findings

Discussion and conclusions