A self-supervised feature-standardization-block for cross-domain lung disease classification

Xuechen Li, Linlin Shen, Zhihui Lai, Zhongliang Li, Juan Yu, Zuhui Pu, Lisha Mou, Min Cao, Heng Kong, Yingqi Li, Weicai Dai

Research output: Journal PublicationArticlepeer-review

Abstract

With the advance of deep learning technology, convolutional neural network (CNN) has been wildly used and achieved the state-of-the-art performances in the area of medical image classification. However, most existing medical image classification methods conduct their experiments on only one public dataset. When applying a well-trained model to a different dataset selected from different sources, the model usually shows large performance degradation and needs to be fine-tuned before it can be applied to the new dataset. The goal of this work is trying to solve the cross-domain image classification problem without using data from target domain. In this work, we designed a self-supervised plug-and-play feature-standardization-block (FSB) which consisting of image normalization (INB), contrast enhancement (CEB) and boundary detection blocks (BDB), to extract cross-domain robust feature maps for deep learning framework, and applied the network for chest x-ray-based lung diseases classification. Three classic deep networks, i.e. VGG, Xception and DenseNet and four chest x-ray lung diseases datasets were employed for evaluating the performance. The experimental result showed that when employing feature-standardization-block, all three networks showed better domain adaption performance. The image normalization, contrast enhancement and boundary detection blocks achieved in average 2%, 2% and 5% accuracy improvement, respectively. By combining all three blocks, feature-standardization-block achieved in average 6% accuracy improvement.

Original languageEnglish
Pages (from-to)70-77
Number of pages8
JournalMethods
Volume202
DOIs
Publication statusPublished - Jun 2022
Externally publishedYes

Keywords

  • Chest x-ray
  • Computer-aided diagnosis
  • Deep learning
  • Domain adaption
  • Lung disease detection

ASJC Scopus subject areas

  • Molecular Biology
  • Biochemistry, Genetics and Molecular Biology (all)

Fingerprint

Dive into the research topics of 'A self-supervised feature-standardization-block for cross-domain lung disease classification'. Together they form a unique fingerprint.

Cite this