A Novel Collaborative Self-Supervised Learning Method for Radiomic Data

TL;DR

This paper introduces a novel collaborative self-supervised learning approach tailored for radiomic data, effectively reducing the need for labeled data and improving disease diagnosis accuracy in medical imaging.

Contribution

The paper presents the first collaborative self-supervised learning method specifically designed for radiomic data, leveraging latent biological relationships to enhance feature learning.

Findings

Outperforms existing self-supervised methods on classification tasks

Demonstrates robustness across multiple datasets

Reduces reliance on manual annotations

Abstract

The computer-aided disease diagnosis from radiomic data is important in many medical applications. However, developing such a technique relies on annotating radiological images, which is a time-consuming, labor-intensive, and expensive process. In this work, we present the first novel collaborative self-supervised learning method to solve the challenge of insufficient labeled radiomic data, whose characteristics are different from text and image data. To achieve this, we present two collaborative pretext tasks that explore the latent pathological or biological relationships between regions of interest and the similarity and dissimilarity information between subjects. Our method collaboratively learns the robust latent feature representations from radiomic data in a self-supervised manner to reduce human annotation efforts, which benefits the disease diagnosis. We compared our proposed method with other state-of-the-art self-supervised learning methods on a simulation study and two independent datasets. Extensive experimental results demonstrated that our method outperforms other self-supervised learning methods on both classification and regression tasks. With further refinement, our method shows the potential advantage in automatic disease diagnosis with large-scale unlabeled data available.