Evaluating unsupervised contrastive learning framework for MRI sequences classification

2025-01-12

AI Summary

To address the challenge of MRI sequence classification arising from inconsistent acquisition protocols across multi-center scanners, this paper proposes an unsupervised contrastive learning framework—the first such approach applied to automatic identification of nine MRI sequences. The method employs a ResNet-18 backbone operating on 2D slices, enabling label-free representation pretraining and facilitating cross-protocol and cross-dataset transfer. Evaluated on an internal dataset and public benchmarks (BraTS, ADNI), it achieves an average classification accuracy exceeding 0.95, demonstrating strong generalizability. Its lightweight architecture ensures low deployment overhead, supporting efficient clinical triage and diagnosis. Key contributions are: (i) the first unsupervised contrastive learning framework specifically designed for multi-protocol MRI sequence recognition; and (ii) a solution that simultaneously mitigates reliance on manual annotations and robustly handles scanner heterogeneity.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The automatic identification of Magnetic Resonance Imaging (MRI) sequences can streamline clinical workflows by reducing the time radiologists spend manually sorting and identifying sequences, thereby enabling faster diagnosis and treatment planning for patients. However, the lack of standardization in the parameters of MRI scans poses challenges for automated systems and complicates the generation and utilization of datasets for machine learning research. To address this issue, we propose a system for MRI sequence identification using an unsupervised contrastive deep learning framework. By training a convolutional neural network based on the ResNet-18 architecture, our system classifies nine common MRI sequence types as a 9-class classification problem. The network was trained using an in-house internal dataset and validated on several public datasets, including BraTS, ADNI, Fused Radiology-Pathology Prostate Dataset, the Breast Cancer Dataset (ACRIN), among others, encompassing diverse acquisition protocols and requiring only 2D slices for training. Our system achieves a classification accuracy of over 0.95 across the nine most common MRI sequence types.

Problem

• MRI Image Recognition
• Machine Setting Variability
• Medical Efficiency

Innovation

• Contrastive Learning
• MRI Image Recognition
• Automated Identification