From Volumes to Slices: Computationally Efficient Contrastive Learning for Sequential Abdominal CT Analysis

2026-01-21

AI Summary

This work addresses the challenge of limited expert annotations in medical image analysis and the high computational and memory demands of existing 3D self-supervised methods. To this end, we propose 2D-VoCo, a novel approach that reformulates volumetric contrastive learning as a 2D slice-level self-supervised pretraining framework. By leveraging contrastive learning on unlabeled CT slices, 2D-VoCo effectively captures spatial semantic features and integrates them into a CNN-LSTM architecture for multi-organ injury classification. The method achieves competitive performance while substantially reducing computational and memory overhead. Evaluated on the RSNA 2023 abdominal trauma dataset, 2D-VoCo significantly outperforms training from scratch in terms of mAP, precision, recall, and the official RSNA score, thereby alleviating reliance on labeled data and enhancing clinical applicability.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Unsupervised & Self-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The requirement for expert annotations limits the effectiveness of deep learning for medical image analysis. Although 3D self-supervised methods like volume contrast learning (VoCo) are powerful and partially address the labeling scarcity issue, their high computational cost and memory consumption are barriers. We propose 2D-VoCo, an efficient adaptation of the VoCo framework for slice-level self-supervised pre-training that learns spatial-semantic features from unlabeled 2D CT slices via contrastive learning. The pre-trained CNN backbone is then integrated into a CNN-LSTM architecture to classify multi-organ injuries. In the RSNA 2023 Abdominal Trauma dataset, 2D-VoCo pre-training significantly improves mAP, precision, recall, and RSNA score over training from scratch. Our framework provides a practical method to reduce the dependency on labeled data and enhance model performance in clinical CT analysis. We release the code for reproducibility. https://github.com/tkz05/2D-VoCo-CT-Classifier

Problem

• self-supervised learning
• medical image analysis
• abdominal CT
• label scarcity
• computational efficiency

Innovation

• 2D-VoCo
• contrastive learning
• self-supervised pre-training
• abdominal CT
• CNN-LSTM