Evaluating unsupervised contrastive learning framework for MRI sequences classification

TL;DR

This paper presents an unsupervised contrastive learning framework using ResNet-18 for accurate MRI sequence classification, achieving over 95% accuracy across nine common MRI types, aiding clinical workflows.

Contribution

The study introduces a novel unsupervised contrastive deep learning approach for MRI sequence identification, effective across diverse datasets and protocols.

Findings

Achieved over 95% classification accuracy.

Validated on multiple public datasets.

Effective across diverse MRI protocols.

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.