SKID: Self-Supervised Learning for Knee Injury Diagnosis from MRI Data

TL;DR

This paper introduces a self-supervised learning approach for knee injury diagnosis from MRI videos, effectively learning spatial features that improve classification, especially for minority classes, without requiring extensive annotated data.

Contribution

It presents the first application of self-supervised learning for class imbalanced multi-label classification in knee MRI videos, demonstrating improved feature learning and reliability.

Findings

Self-supervised features perform competitively in classification tasks.

The approach effectively learns minority class representations.

No additional imbalance strategies needed for reliable minority class detection.

Abstract

In medical image analysis, the cost of acquiring high-quality data and their annotation by experts is a barrier in many medical applications. Most of the techniques used are based on supervised learning framework and need a large amount of annotated data to achieve satisfactory performance. As an alternative, in this paper, we propose a self-supervised learning (SSL) approach to learn the spatial anatomical representations from the frames of magnetic resonance (MR) video clips for the diagnosis of knee medical conditions. The pretext model learns meaningful spatial context-invariant representations. The downstream task in our paper is a class imbalanced multi-label classification. Different experiments show that the features learnt by the pretext model provide competitive performance in the downstream task. Moreover, the efficiency and reliability of the proposed pretext model in learning representations of minority classes without applying any strategy towards imbalance in the dataset can be seen from the results. To the best of our knowledge, this work is the first work of its kind in showing the effectiveness and reliability of self-supervised learning algorithms in class imbalanced multi-label classification tasks on MR videos. The code for evaluation of the proposed work is available at https://github.com/sadimanna/skid.