Improving ductal carcinoma in situ classification by convolutional neural network with exponential linear unit and rank-based weighted pooling

Yu Dong Zhang, Suresh Chandra Satapathy, Di Wu, David S. Guttery*, Juan Manuel Górriz*, Shui Hua Wang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

27 Citations (Scopus)

Abstract

Ductal carcinoma in situ (DCIS) is a pre-cancerous lesion in the ducts of the breast, and early diagnosis is crucial for optimal therapeutic intervention. Thermography imaging is a non-invasive imaging tool that can be utilized for detection of DCIS and although it has high accuracy (~ 88%), it is sensitivity can still be improved. Hence, we aimed to develop an automated artificial intelligence-based system for improved detection of DCIS in thermographs. This study proposed a novel artificial intelligence based system based on convolutional neural network (CNN) termed CNN-BDER on a multisource dataset containing 240 DCIS images and 240 healthy breast images. Based on CNN, batch normalization, dropout, exponential linear unit and rank-based weighted pooling were integrated, along with L-way data augmentation. Ten runs of tenfold cross validation were chosen to report the unbiased performances. Our proposed method achieved a sensitivity of 94.08 ± 1.22%, a specificity of 93.58 ± 1.49 and an accuracy of 93.83 ± 0.96. The proposed method gives superior performance than eight state-of-the-art approaches and manual diagnosis. The trained model could serve as a visual question answering system and improve diagnostic accuracy.

Original languageEnglish
Pages (from-to)1295-1310
Number of pages16
JournalComplex and Intelligent Systems
Volume7
Issue number3
DOIs
Publication statusPublished - Jun 2021
Externally publishedYes

Keywords

  • Breast thermography
  • Color jittering
  • Convolutional neural network
  • Data augmentation
  • Deep learning
  • Ductal carcinoma in situ
  • Exponential linear unit
  • Rank-based weighted pooling
  • Thermal images
  • Visual question answering

Fingerprint

Dive into the research topics of 'Improving ductal carcinoma in situ classification by convolutional neural network with exponential linear unit and rank-based weighted pooling'. Together they form a unique fingerprint.

Cite this