A review of self‐supervised, generative, and few‐shot deep learning methods for data‐limited magnetic resonance imaging segmentation

Abstract

Magnetic resonance imaging (MRI) is a ubiquitous medical imaging technology with applications in disease diagnostics, intervention, and treatment planning. Accurate MRI segmentation is critical for diagnosing abnormalities, monitoring diseases, and deciding on a course of treatment. With the advent of advanced deep learning frameworks, fully automated and accurate MRI segmentation is advancing. Traditional supervised deep learning techniques have advanced tremendously, reaching clinical‐level accuracy in the field of segmentation. However, these algorithms still require a large amount of annotated data, which is oftentimes unavailable or impractical. One way to circumvent this issue is to utilize algorithms that exploit a limited amount of labeled data. This paper aims to review such state‐of‐the‐art algorithms that use a limited number of annotated samples. We explain the fundamental principles of self‐supervised learning, generative models, few‐shot learning, and semi‐supervised learning and summarize their applications in cardiac, abdomen, and brain MRI segmentation. Throughout this review, we highlight algorithms that can be employed based on the quantity of annotated data available. We also present a comprehensive list of notable publicly available MRI segmentation datasets. To conclude, we discuss possible future directions of the field—including emerging algorithms, such as contrastive language‐image pretraining, and potential combinations across the methods discussed—that can further increase the efficacy of image segmentation with limited labels.

The Role of Artificial Intelligence in the Identification and Evaluation of Bone Fractures

“…An important contribution to the field has been the recent improvement of selfsupervised and unsupervised learning methods, which are able to learn from large amounts of data without the need for manual annotations [124]. Models using these approaches have already achieved similar or even better performances than models trained with traditional supervised learning methods [125][126][127], giving rise to the idea of AI foundation models.…”