Although using convolutional neural networks(CNNs)for computer-aided diagnosis(CAD)has made tremen-dous progress in the last few years,the small medical datasets remain to be the major bottleneck in this area.To address this problem,researchers start looking for information out of the medical datasets.Previous efforts mainly leverage information from natural images via transfer learning.More recent research work focuses on integrating knowledge from medical practi-tioners,either letting networks resemble how practitioners are trained,how they view images,or using extra annotations.In this paper,we propose a scheme named Domain Guided-CNN(DG-CNN)to incorporate the margin information,a feature described in the consensus for radiologists to diagnose cancer in breast ultrasound(BUS)images.In DG-CNN,attention maps that highlight margin areas of tumors are first generated,and then incorporated via different approaches into the networks.We have tested the performance of DG-CNN on our own dataset(including 1485 ultrasound images)and on a public dataset.The results show that DG-CNN can be applied to different network structures like VGG and ResNet to improve their performance.For example,experimental results on our dataset show that with a certain integrating mode,the improvement of using DG-CNN over a baseline network structure ResNet 18 is 2.17％in accuracy,1.69％in sensitivity,2.64％in specificity and 2.57％in AUC(Area Under Curve).To the best of our knowledge,this is the first time that the margin information is utilized to improve the performance of deep neural networks in diagnosing breast cancer in BUS images.

Xiao-Zheng Xie;Jian-Wei Niu;Xue-Feng Liu;Qing-Feng Li;Yong Wang;Jie Han;Shaojie Tang

State Key Laboratory of Virtual Reality Technology and Systems,School of Computer Science and Engineering Beihang University,Beijing 100191,China;Beijing Advanced Innovation Center for Big Data and Brain Computing,Beihang University,Hangzhou 310051,China;Department of Diagnostic Ultrasound,National Cancer Center,Chinese Academy of Medical Sciences,Peking Union Medical College,Beijing 100021,China;Naveen Jindal School of Management,The University of Texas at Dallas,Richardson,TX 75080-3021,U.S.A.

计算机科学技术学报（英文版）

[1]Xiao-Zheng Xie;Jian-Wei Niu;Xue-Feng Liu;Qing-Feng Li;Yong Wang;Jie Han;Shaojie Tang-.DG-CNN:Introducing Margin Information into Convolutional Neural Networks for Breast Cancer Diagnosis in Ultrasound Images)[J].计算机科学技术学报（英文版）,2022(02):277-294

letting

DG,Introducing,Margin,Information,into,Convolutional,Neural,Networks,Breast,Cancer,Diagnosis,Ultrasound,Images,Although,using,convolutional,neural,networks,CNNs,computer,aided,diagnosis,CAD,has,made,tremen,dous,progress,last,few,years,small,medical,datasets,remain,major,bottleneck,this,To,address,problem,researchers,start,looking,information,out,Previous,efforts,mainly,leverage,from,natural,images,via,transfer,learning,More,recent,focuses,integrating,knowledge,either,resemble,practitioners,trained,they,view,extra,annotations,paper,we,propose,scheme,named,Domain,Guided,margin,feature,described,consensus,radiologists,diagnose,cancer,breast,ultrasound,BUS,attention,maps,that,highlight,areas,tumors,first,generated,then,incorporated,different,approaches,We,have,tested,performance,our,own,including,public,results,show,applied,structures,like,VGG,ResNet,their,For,example,experimental,certain,mode,improvement,over,baseline,accuracy,sensitivity,specificity,Area,Under,Curve,best,utilized,deep,diagnosing

0.574198