Interaction-Oriented Feature Decomposition for Medical Image Lesion Detection

Shen，Junyong1; Hu，Yan1; Zhang，Xiaoqing1; Qiu，Zhongxi1; Deng，Tingming3; Xu，Yanwu2; Liu，Jiang1,4

10.1007/978-3-031-16437-8_31

2022

25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

0302-9743

1611-3349

978-3-031-16436-1

LECT NOTES ARTIF INT

13433 LNCS

324-333

SEP 18-22, 2022

null,Singapore,SINGAPORE

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

Common lesion detection networks typically use lesion features for classification and localization. However, many lesions are classified only by lesion features without considering the relation with global context features, which raises the misclassification problem. In this paper, we propose an Interaction-Oriented Feature Decomposition (IOFD) network to improve the detection performance on context-dependent lesions. Specifically, we decompose features output from a backbone into global context features and lesion features that are optimized independently. Then, we design two novel modules to improve the lesion classification accuracy. A Global Context Embedding (GCE) module is designed to extract global context features. A Global Context Cross Attention (GCCA) module without additional parameters is designed to model the interaction between global context features and lesion features. Besides, considering the different features required by classification and localization tasks, we further adopt a task decoupling strategy. IOFD is easy to train and end-to-end in terms of training and inference. The experimental results for datasets in two modalities outperform state-of-the-art algorithms, which demonstrates the effectiveness and generality of IOFD. The source code is available at https://github.com/mklz-sjy/IOFD

Context embedding Cross attention Lesion detection Medical image

First ; Corresponding

English

CPCI-S

National Natural Science Foundation of China[8210072776] ; Guangdong Provincial Department of Education[2020ZDZX3043] ; Guangdong Basic and Applied Basic Research Foundation[2021A1515012195] ; Guangdong Provincial Key Laboratory[2020B121201001] ; Shenzhen Natural Science Fund["JCYJ20200109140820699","20200925174052004"]

Neurosciences & Neurology ; Radiology, Nuclear Medicine & Medical Imaging

Neuroimaging ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000867397400031

2-s2.0-85139061318

Scopus

1.Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.Intelligent Healthcare Unit,Baidu,Beijing,100000,China
3.Department of Ophthalmology,Shenzhen People’s Hospital,Shenzhen,Guangdong,518020,China
4.Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation,Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China

Shen，Junyong,Hu，Yan,Zhang，Xiaoqing,et al. Interaction-Oriented Feature Decomposition for Medical Image Lesion Detection[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2022:324-333.