A novel collaborative self-supervised learning method for radiomic data

• Published in: NeuroImage (Orlando, Fla.) Vol. 277; p. 120229
• Main Authors: Li, Zhiyuan, Li, Hailong, Ralescu, Anca L., Dillman, Jonathan R., Parikh, Nehal A., He, Lili
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.08.2023; Elsevier Limited; Elsevier
• Subjects: Alzheimer's disease; Between-subjects design; Collaboration; Collaborative learning; Computer Simulation; Data analysis; Diagnosis; Diagnosis, Computer-Assisted; Disease diagnosis; Humans; Learning; Magnetic resonance imaging; Medical prognosis; Morphology; MRI; Performance evaluation; Radiomic data; Radiomics; Self-supervised learning; Supervised Machine Learning; Tomography; Disease diagnosis; MRI; Collaborative learning; Self-supervised learning; Radiomic data
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2023.120229

•Deep learning and radiomics to predict cognitive deficits in very preterm infants.•Self-supervised learning to address the lack of labeled radiomic data.•Collaborative self-supervised learning to learn latent radiomic representations.•Integrate pretext tasks of radiomics reconstruction and subject discrimination. The computer-aided disease diagnosis from radiomic data is important in many medical applications. However, developing such a technique relies on labeling 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 of 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 will have the potential advantage in automatic disease diagnosis with large-scale unlabeled data available.