Multitask Conditional Generative Adversarial Network Enables Automatic Whole Knee Cartilage and Menisci Segmentation and Reliable T1\r{ho} and T2 Quantification Without High-Resolution Morphological Images

2026-10-05

AI Summary

Early osteoarthritis detection relies on time-consuming and costly high-resolution DESS scans. This work proposes a multi-task conditional generative adversarial network (MT-cGAN) that, for the first time, enables the joint synthesis of DESS-like images and tissue segmentation directly from quantitative MRI echo images acquired via the MAPSS sequence, eliminating the need for additional morphological scans. Experimental results demonstrate that the proposed model achieves an average Dice coefficient of 0.84, significantly outperforming existing state-of-the-art methods. Furthermore, it yields the lowest coefficients of variation for T1ρ and T2 relaxation times, thereby validating its feasibility for precise clinical assessment.

Abstract

Early osteoarthritis detection through quantitative MRI (qMRI) requires accurate cartilage and meniscus segmentation, traditionally necessitating time-consuming, costly 3D high-resolution Double Echo Steady-State (DESS) MRI scans. This study developed a multi-task conditional generative adversarial network (MT-cGAN) to simultaneously synthesize DESS-like images and segment tissues directly from qMRI echo images. This retrospective study evaluated 508 knee MRI volumes from 361 subjects (mean age: $40.4 \pm 12.2$ years; 179 female) across three cohorts. Ground truth segmentation masks were generated from DESS images using a pretrained model with manual correction, and $T_{1\rho}$ and $T_2$ maps were computed from magnetization-prepared angle-modulated partitioned $k$-space spoiled gradient echo snapshots (MAPSS) echo images. MT-cGAN was trained to jointly synthesize DESS-like images and segment cartilage and meniscus directly from echo images. Model performance was evaluated using Dice score for segmentation accuracy and coefficient of variation (CV) for $T_{1\rho}$ and $T_2$ quantification. MT-cGAN achieved the highest segmentation performance, mean Dice score 0.84 (range: 0.80--0.86) across all cartilage and meniscus compartments and significantly outperformed the state-of-the-art conditional GAN model with transfer learning (mean Dice, 0.82; $p<0.001$, Wilcoxon signed-rank test). For relaxometry quantification, MT-cGAN demonstrated the highest consistency with the reference DESS protocol, yielding the lowest CV ($T_{1\rho}$: 1.84%, $T_2$: 1.81%). The proposed MT-cGAN accurately segmented cartilage and menisci while providing reliable $T_{1\rho}$ and $T_2$ quantification directly from echo images. By eliminating the need for separate morphological DESS scans, this workflow reduces required scan times to facilitate the clinical translation of qMRI.

Problem

• Knee cartilage segmentation
• Menisci segmentation
• Quantitative MRI
• T1ρ and T2 quantification
• Early osteoarthritis detection

Innovation

• Multi-task conditional GAN
• Cartilage segmentation
• Quantitative MRI
• Image synthesis
• Relaxometry quantification