Probing Intrinsic Medical Task Relationships: A Contrastive Learning Perspective
This work addresses the lack of understanding in task relationships for the medical computer vision community, providing foundational insights into task similarities and interconnectedness, though it is incremental in probing these relationships without direct performance improvements.
The paper tackled the problem of exploring intrinsic relationships between 30 diverse medical vision tasks, such as segmentation and denoising, across 39 datasets from various imaging modalities, and introduced Task-Contrastive Learning (TaCo) to embed tasks into a shared representation space, revealing how tasks relate and blend in this space.
While much of the medical computer vision community has focused on advancing performance for specific tasks, the underlying relationships between tasks, i.e., how they relate, overlap, or differ on a representational level, remain largely unexplored. Our work explores these intrinsic relationships between medical vision tasks, specifically, we investigate 30 tasks, such as semantic tasks (e.g., segmentation and detection), image generative tasks (e.g., denoising, inpainting, or colorization), and image transformation tasks (e.g., geometric transformations). Our goal is to probe whether a data-driven representation space can capture an underlying structure of tasks across a variety of 39 datasets from wildly different medical imaging modalities, including computed tomography, magnetic resonance, electron microscopy, X-ray ultrasound and more. By revealing how tasks relate to one another, we aim to provide insights into their fundamental properties and interconnectedness. To this end, we introduce Task-Contrastive Learning (TaCo), a contrastive learning framework designed to embed tasks into a shared representation space. Through TaCo, we map these heterogeneous tasks from different modalities into a joint space and analyze their properties: identifying which tasks are distinctly represented, which blend together, and how iterative alterations to tasks are reflected in the embedding space. Our work provides a foundation for understanding the intrinsic structure of medical vision tasks, offering a deeper understanding of task similarities and their interconnected properties in embedding spaces.