Attentive Transfer Learning via Self-supervised Learning for Cervical Dysplasia Diagnosis

Jinyeong Chae, Roger Zimmermann, Dongho Kim, Jihie Kim

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch selfsupervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

Original languageEnglish
Pages (from-to)453-461
Number of pages9
JournalJournal of Information Processing Systems
Volume17
Issue number3
DOIs
StatePublished - Jun 2021

Keywords

  • Attention Learning
  • Cervical Dysplasia
  • Patch self-supervised Learning
  • Transfer Learning

Fingerprint

Dive into the research topics of 'Attentive Transfer Learning via Self-supervised Learning for Cervical Dysplasia Diagnosis'. Together they form a unique fingerprint.

Cite this