摘要
膀胱癌MRI图像存在肿瘤边界不清晰、肿瘤区域较小、肿瘤分布不连续等问题,现有的分割算法参数量庞大,计算复杂,且分割精度有待提高。因此,设计了一种多尺度特征融合的轻量化膀胱癌分割算法(pyramidal convolution lightweight network,PylNet),该算法在编码阶段设计的多尺度语义特征提取模块可提取不同尺度的肿瘤区域信息,确保对微小肿瘤信息提取的可靠性和全面性;在解码阶段设计的融合模块可以在保证分割精度的同时,极大地减少算法参数量和复杂度。实验结果表明,相较于FCN8s、DeepLabV3+、U-Net等算法,PylNet算法分割精度有一定的提高,Dice系数达88.40%,参数量是FCN8s的1/13,可实现对膀胱MRI的快速分割。
There exists serveral challenges in MRI images of bladder cancer,such as unclear tumor boundaries,small tumor areas,and discontinuous tumor distribution.The existing segmentation algorithms have huge parameters and complex calculations,and the accuracy and efficiency of the existing methods for bladder tumor segmentation need to be improved.In response to the above issues,a lightweight bladder cancer segmentation algorithm based on multi-scale feature fusion(PylNet)was proposed in this paper.The algorithm can extract information of different scales through the multi-scale semantic feature extraction module.This module was designed in the coding stage to ensure the reliability and comprehensiveness of the extraction of information on small tumor regions.At the same time,the fusion module designed in another stage can quickly complete the tumor region segmentation,and the amount of parameters used is much less.Experimental results show that compared with FCN8s,SegNet,U-Net and other algorithms,the segmentation accuracy of this algorithm is improved to a certain extent where DSC reaches 88.40%,and the parameter amount is 1/13 of FCN8s,which a fast bladder MRI segmentation is achieved.
作者
张娜
张永寿
李翔
丛金玉
李徐周
魏本征
ZHANG Na;ZHANG Yongshou;LI Xiang;CONG Jinyu;LI Xuzhou;WEI Benzheng(College of Intelligence and Information Engineering,Shandong University of Traditional Chinese Medicine,Jinan 250355,Shandong,China;Medical Engineering Department,the 960th Hospital of the PLA,Jinan 250031,Shandong,China;Center for Medical Artificial Intelligence,Shandong University of Traditional Chinese Medicine,Qingdao 266112,Shandong,China;First School of Clinical Medicine,Shandong University of Traditional Chinese Medicine,Jinan 250355,Shandong,China;Qingdao Academy of Chinese Medical Sciences,Shandong University of Traditional Chinese Medicine,Qingdao 266112,Shandong,China;School of Information Engineering,Shandong Youth University of Political Science,Jinan 250103,Shandong,China)
出处
《陕西师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2022年第3期89-95,共7页
Journal of Shaanxi Normal University：Natural Science Edition
基金
山东省自然科学基金面上项目(ZR2020KF013)
山东省自然科学基金重大基础研究项目(ZR2019ZD04,ZR2020ZD44)。
关键词
膀胱癌
MRI
轻量化
多尺度
分割
bladder cancer
MRI
lightweight
multi-scale
segmentation
作者简介
通信作者:张永寿,男,主任技师,研究方向为医疗数据管理和质量控制。E-mail:2041831268@qq.com。
