An Automatic Nuclei Image Segmentation Based on Multi-Scale Split-Attention U-Net

Xu, Qing and Duan, Wenting (2021) An Automatic Nuclei Image Segmentation Based on Multi-Scale Split-Attention U-Net. In: MICCAI 2021 Computational Pathlogy (COMPAY) Workshop.

Full content URL: https://proceedings.mlr.press/v156/xu21a.html

Documents
An Automatic Nuclei Image Segmentation Based on Multi-Scale Split-Attention U-Net
Published manuscript
[img]
[Download]
[img]
Preview
PDF
an_automatic_nuclei_image_segm.pdf - Whole Document

807kB
Item Type:Conference or Workshop contribution (Poster)
Item Status:Live Archive

Abstract

Nuclei segmentation is an important step in the task of medical image analysis. Nowadays, deep learning techniques based on Convolutional Neural Networks (CNNs) have become prevalent methods in nuclei segmentation. In this paper, we propose a network called Multi-scale Split-Attention U-Net (MSAU-Net) for further improving the performance of
cell segmentation. MSAU-Net is based on U-Net architecture and the original blocks used to down-sampling and up-sampling paths are replaced with Multi-scale Split-Attention blocks for capturing independent semantic information of nuclei images. A public microscopy image dataset from 2018 Data Science Bowl grand challenge is selected to train and evaluate MSAU-Net. By running trained models on the test set, our model reaches average Intersection over Union (IoU) of 0.851, which is better than other prominent models, especially 4.8 percent higher than the original U-Net. For other evaluation metrics including accuracy, precision, recall and F1-score, MSAU-Net shows better performance in the most of indicators. The outstanding result reveals that our proposed model presents a promising nuclei segmentation method for the microscopy image analysis.

Keywords:Nuclei Segmentation, Convolutional Neural Network, Multi-scale Split Attention
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:46707
Deposited On:22 Oct 2021 10:12

Repository Staff Only: item control page