A memory based model for cartilage and meniscus segmentation in 3D knee MRI

作者：Danielle L. Ferreira, Bruno A. A. Nunes, Xuzhe Zhang, Laura Carretero Gómez, Maggie Fung, Ravi Soni · 发表于：Scientific Reports · 年份：2025 · DOI：10.1038/s41598-025-31503-2 · 被引用次数：3 · 研究领域：Osteoarthritis Treatment and Mechanisms、Infrared Thermography in Medicine、Medical Imaging and Analysis

Accurate morphometric assessment of cartilage-such as thickness and volume-via MRI is essential for monitoring knee osteoarthritis. However, segmenting cartilage remains challenging and dependent on extensive expert-annotated datasets, which are heavily subjected to inter-reader variability. Recent advancements in Visual Foundational Models (VFM), particularly memory-based approaches, offer opportunities for improving generalizability and robustness. In this study, we introduce SAMRI-2, a transformer-based deep learning method for cartilage and meniscus segmentation from 3D MRIs using interactive, memory-based VFMs. To improve spatial awareness and convergence, we incorporated a Hybrid Shuffling Strategy (HSS) during training and applied a segmentation mask propagation technique to enhance annotation efficiency. We evaluated SAMRI-2 against four AI models: two 3D convolutional architectures, namely the 3D-VNet and 3D nnU-Net, and two automatic transformer-based models, SAMRI2D and SAMRI3D. These models were trained on 575 3D knee MRI volumes from 270 distinct patients, using both public and internal datasets, and tested on 57 external cases with multi-radiologist annotations and diverse acquisition protocols. Model performance was assessed against reference standards using Dice Similarity Coefficient (DSC) and Intersection over Union, with additional morphometric evaluations to further quantify segmentation accuracy. Our SAMRI-2 model, trained with HSS, outperformed all other...