CoRLD: Contrastive Representation Learning Of Deformable Shapes In Images

2025-03-21

AI Summary

Existing medical image deformation analysis methods rely on pre-specified templates during inference, suffering from poor generalizability and limited ability to discriminate fine-grained anatomical differences—e.g., among healthy controls, mild cognitive impairment, and dementia patients. To address this, we propose a class-aware implicit deformation space contrastive representation learning framework. Our approach is the first to introduce contrastive learning into the deformation representation space; it decouples the role of templates—using them solely as supervision signals during training while eliminating any dependency on reference images at test time. We integrate differentiable deformation modeling, class-weighted contrastive loss, and unsupervised embedding optimization. Evaluated on real-world brain MRI and adrenal CT datasets, our method significantly improves classification accuracy. The learned deformation representations are plug-and-play, effectively enhancing downstream classifiers. Code is publicly available.

Technology Category

• Machine Learning: Representation Learning
• Computer Vision: Representation Learning for Vision
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Deformable shape representations, parameterized by deformations relative to a given template, have proven effective for improved image analysis tasks. However, their broader applicability is hindered by two major challenges. First, existing methods mainly rely on a known template during testing, which is impractical and limits flexibility. Second, they often struggle to capture fine-grained, voxel-level distinctions between similar shapes (e.g., anatomical variations among healthy individuals, those with mild cognitive impairment, and diseased states). To address these limitations, we propose a novel framework - Contrastive Representation Learning of Deformable shapes (CoRLD) in learned deformation spaces and demonstrate its effectiveness in the context of image classification. Our CoRLD leverages a class-aware contrastive supervised learning objective in latent deformation spaces, promoting proximity among representations of similar classes while ensuring separation of dissimilar groups. In contrast to previous deep learning networks that require a reference image as input to predict deformation changes, our approach eliminates this dependency. Instead, template images are utilized solely as ground truth in the loss function during the training process, making our model more flexible and generalizable to a wide range of medical applications. We validate CoRLD on diverse datasets, including real brain magnetic resonance imaging (MRIs) and adrenal shapes derived from computed tomography (CT) scans. Experimental results show that our model effectively extracts deformable shape features, which can be easily integrated with existing classifiers to substantially boost the classification accuracy. Our code is available at GitHub.

Problem

• Eliminates dependency on known templates during testing
• Captures fine-grained voxel-level shape distinctions
• Enhances classification accuracy via deformable shape features

Innovation

• Contrastive learning in latent deformation spaces
• Eliminates need for reference image input
• Enhances classification with deformable shape features