Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean

Abstract

Deep learning models achieve strong performance for radiology image classification, but their practical application is bottlenecked by the need for large labeled training datasets. Semi-supervised learning (SSL) approaches leverage small labeled datasets alongside larger unlabeled datasets and offer potential for reducing labeling cost. In this work, we introduce NoTeacher, a novel consistency-based SSL framework which incorporates probabilistic graphical models. Unlike Mean Teacher which maintains a teacher network updated via a temporal ensemble, NoTeacher employs two independent networks, thereby eliminating the need for a teacher network. We demonstrate how NoTeacher can be customized to handle a range of challenges in radiology image classification. Specifically, we describe adaptations for scenarios with 2D and 3D inputs, uni and multi-label classification, and class distribution mismatch between labeled and unlabeled portions of the training data. In realistic empirical evaluations on three public benchmark datasets spanning the workhorse modalities of radiology (X-Ray, CT, MRI), we show that NoTeacher achieves over 90-95% of the fully supervised AUROC with less than 5-15% labeling budget. Further, NoTeacher outperforms established SSL methods with minimal hyperparameter tuning, and has implications as a principled and practical option for semisupervised learning in radiology applications.

Preprint submitted to Medical Image Analysis. Accepted in June 2021

References in corpus (10)

• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Domain-adversarial neural networks to address the appearance variability of histopathology images
• A Survey on Multi-view Learning
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model
• Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification
• Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
• Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images
• Semi-supervised Medical Image Classification with Global Latent Mixing
• Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training
• Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space