MR-Transformer: Vision Transformer for Total Knee Replacement Prediction Using Magnetic Resonance Imaging

TL;DR

This paper introduces MR-Transformer, a deep learning model that leverages transformer architecture and 3D spatial correlation to predict total knee replacement from MRI scans, outperforming existing models.

Contribution

The paper presents a novel transformer-based model that captures 3D spatial information and uses ImageNet pre-training for improved TKR prediction from MRI.

Findings

Achieved state-of-the-art performance on TKR prediction

Demonstrated effectiveness across multiple MRI tissue contrasts

Outperformed existing deep learning models in accuracy

Abstract

A transformer-based deep learning model, MR-Transformer, was developed for total knee replacement (TKR) prediction using magnetic resonance imaging (MRI). The model incorporates the ImageNet pre-training and captures three-dimensional (3D) spatial correlation from the MR images. The performance of the proposed model was compared to existing state-of-the-art deep learning models for knee injury diagnosis using MRI. Knee MR scans of four different tissue contrasts from the Osteoarthritis Initiative and Multicenter Osteoarthritis Study databases were utilized in the study. Experimental results demonstrated the state-of-the-art performance of the proposed model on TKR prediction using MRI.