Weakly supervised learning for classification of lung cytological images using attention-based multiple instance learning.

Journal: Scientific reports
Published Date: Oct 13, 2021

Abstract

In cytological examination, suspicious cells are evaluated regarding malignancy and cancer type. To assist this, we previously proposed an automated method based on supervised learning that classifies cells in lung cytological images as benign or malignant. However, it is often difficult to label all cells. In this study, we developed a weakly supervised method for the classification of benign and malignant lung cells in cytological images using attention-based deep multiple instance learning (AD MIL). Images of lung cytological specimens were divided into small patch images and stored in bags. Each bag was then labeled as benign or malignant, and classification was conducted using AD MIL. The distribution of attention weights was also calculated as a color map to confirm the presence of malignant cells in the image. AD MIL using the AlexNet-like convolutional neural network model showed the best classification performance, with an accuracy of 0.916, which was better than that of supervised learning. In addition, an attention map of the entire image based on the attention weight allowed AD MIL to focus on most malignant cells. Our weakly supervised method automatically classifies cytological images with acceptable accuracy based on supervised learning without complex annotations.

Authors

  • Atsushi Teramoto
    Faculty of Radiological Technology, School of Health Sciences, Fujita Health University, 1-98 Dengakugakubo, Kutsukake, Toyoake, Aichi 470-1192, Japan.
  • Yuka Kiriyama
    School of Medicine, Fujita Health University, Toyoake, Japan.
  • Tetsuya Tsukamoto
    School of Medicine, Fujita Health University, 1-98 Dengakugakubo, Kutsukake cho, Toyoake City, Aichi, 470-1192, Japan.
  • Eiko Sakurai
    School of Medicine, Fujita Health University, Aichi, Japan.
  • Ayano Michiba
    Graduate School of Medicine, Fujita Health University, Aichi, Japan.
  • Kazuyoshi Imaizumi
    School of Medicine, Fujita Health University, 1-98 Dengakugakubo, Kutsukake cho, Toyoake City, Aichi, 470-1192, Japan.
  • Kuniaki Saito
    Graduate School of Health Sciences, Fujita Health University, 1-98 Dengakugakubo, Kutsukake cho, Toyoake City, Aichi, 470-1192, Japan.
  • Hiroshi Fujita
    Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University, 1-1 Yanagido, Gifu 501-1194, Japan.

Keywords

External Resources

Popular Topics
Recent Journals