Big Self-Supervised Models Advance Medical Image Classification

by   Shekoofeh Azizi, et al.

Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis. This paper studies the effectiveness of self-supervised learning as a pretraining strategy for medical image classification. We conduct experiments on two distinct tasks: dermatology skin condition classification from digital camera images and multi-label chest X-ray classification, and demonstrate that self-supervised learning on ImageNet, followed by additional self-supervised learning on unlabeled domain-specific medical images significantly improves the accuracy of medical image classifiers. We introduce a novel Multi-Instance Contrastive Learning (MICLe) method that uses multiple images of the underlying pathology per patient case, when available, to construct more informative positive pairs for self-supervised learning. Combining our contributions, we achieve an improvement of 6.7 dermatology and chest X-ray classification respectively, outperforming strong supervised baselines pretrained on ImageNet. In addition, we show that big self-supervised models are robust to distribution shift and can learn efficiently with a small number of labeled medical images.



page 1

page 3

page 12

page 13

page 18


Self-Supervised Learning as a Means To Reduce the Need for Labeled Data in Medical Image Analysis

One of the largest problems in medical image processing is the lack of a...

Self-Supervised Learning for Gastritis Detection with Gastric X-Ray Images

We propose a novel self-supervised learning method for medical image ana...

MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation

Self-supervised contrastive learning between pairs of multiple views of ...

Contrastive Learning of Medical Visual Representations from Paired Images and Text

Learning visual representations of medical images is core to medical ima...

MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning

We propose a selective learning method using meta-learning and deep rein...

Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels

In clinical practice, medical image interpretation often involves multi-...

How Transferable Are Self-supervised Features in Medical Image Classification Tasks?

Transfer learning has become a standard practice to mitigate the lack of...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.