3D knee segmentation based on three MRI sequences from different planes

The optimisation of deep neural networks for segmenting multiple knee joint tissues from MRIs

Automated semantic segmentation of multiple knee joint tissues is desirable to allow faster and more reliable analysis of large datasets and to enable further downstream processing e.g. automated diagnosis. In this work, we evaluate the use of conditional Generative Adversarial Networks (cGANs) as a robust and potentially improved method for semantic segmentation compared to other extensively used convolutional neural network, such as the U-Net. As cGANs have not yet been widely explored for semantic medical image segmentation, we analysed the effect of training with different objective functions and discriminator receptive field sizes on the segmentation performance of the cGAN. Additionally, we evaluated the possibility of using transfer learning to improve the segmentation accuracy. The networks were trained on i) the SKI10 dataset which comes from the MICCAI grand challenge "Segmentation of Knee Images 2010″, ii) the OAI ZIB dataset containing femoral and tibial bone and cartilage segmentations of the Osteoarthritis Initiative cohort and iii) a small locally acquired dataset (Advanced MRI of Osteoarthritis (AMROA) study) consisting of 3D fat-saturated spoiled gradient recalled-echo knee MRIs with manual segmentations of the femoral, tibial and patellar bone and cartilage, as well as the cruciate ligaments and selected peri-articular muscles. The Sørensen-Dice Similarity Coefficient (DSC), volumetric overlap error (VOE) and average surface distance (ASD) were calculated for segmentation performance evaluation. DSC ≥ 0.95 were achieved for all segmented bone structures, DSC ≥ 0.83 for cartilage and muscle tissues and DSC of ≈0.66 were achieved for cruciate ligament segmentations with both cGAN and U-Net on the in-house AMROA dataset. Reducing the receptive field size of the cGAN discriminator network improved the networks segmentation performance and resulted in segmentation accuracies equivalent to those of the U-Net. Pretraining not only increased segmentation accuracy of a few knee joint tissues of the fine-tuned dataset, but also increased the network's capacity to preserve segmentation capabilities for the pretrained dataset. cGAN machine learning can generate automated semantic maps of multiple tissues within the knee joint which could increase the accuracy and efficiency for evaluating joint health.

Slower Walking Speed Is Related to Early Femoral Trochlear Cartilage Degradation After ACL Reconstruction

Post-traumatic patellofemoral osteoarthritis (OA) is prevalent after anterior cruciate ligament reconstruction (ACLR) and early cartilage degradation may be especially common in the femoral trochlear cartilage. Determining the presence of and factors associated with early femoral trochlear cartilage degradation, a precursor to OA, is a critical preliminary step in identifying those at risk for patellofemoral OA development and designing interventions to combat the disease. Early cartilage degradation can be detected using quantitative magnetic resonance imaging measures, such as tissue T₂ relaxation time. The purposes of this study were to (i) compare involved (ACLR) versus uninvolved (contralateral) femoral trochlear cartilage T₂ relaxation times 6 months after ACLR, and (ii) determine the relationship between walking speed and walking mechanics 3 months after ACLR and femoral trochlear cartilage T₂ relaxation times 6 months after ACLR. Twenty-six individuals (age 23 ± 7 years) after primary, unilateral ACLR participated in detailed motion analyses 3.3 ± 0.6 months after ACLR and quantitative magnetic resonance imaging 6.3 ± 0.5 months after ACLR. There were no limb differences in femoral trochlear cartilage T₂ relaxation times. Slower walking speed was related to higher (worse) femoral trochlear cartilage T₂ relaxation times in the involved limb (Pearson's r: -0.583, p = 0.002) and greater interlimb differences in trochlear T₂ relaxation times (Pearson's r: -0.349, p = 0.080). Walking mechanics were weakly related to trochlear T₂ relaxation times. Statement of clinical significance: Slower walking speed was by far the strongest predictor of worse femoral trochlear cartilage health, suggesting slow walking speed may be an early clinical indicator of future patellofemoral OA after ACLR. © 2019 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 38:645-652, 2020.