Abstract
Meniscus segmentation from knee MR images is an essential step when analyzing the length, width, height, cross-sectional area, surface area for meniscus allograft transplantation using a 3D reconstruction model based on the patient’s normal meniscus. In this paper, we propose a two-stage DCNN that combines a 2D U-Net-based meniscus localization network with a conditional generative adversarial network-based segmentation network using an object-aware map. First, the 2D U-Net segments knee MR images into six classes including bone and cartilage with whole MR images at a resolution of 512 × 512 to localize the medial and lateral meniscus. Second, adversarial learning with a generator based on the 2D U-Net and a discriminator based on the 2D DCNN using an object-aware map segments the meniscus into localized regions-of-interest with a resolution of 64 × 64. The average Dice similarity coefficient of the meniscus was 85.18% at the medial meniscus and 84.33% at the lateral meniscus; these values were 10.79%p and 1.14%p, and 7.78%p and 1.12%p higher than the segmentation method without adversarial learning and without the use of an object-aware map with the Dice similarity coefficient at the medial meniscus and lateral meniscus, respectively. The proposed automatic meniscus localization through multi-class can prevent the class imbalance problem by focusing on local regions. The proposed adversarial learning using an object-aware map can prevent under-segmentation by repeatedly judging and improving the segmentation results, and over-segmentation by considering information only from the meniscus regions. Our method can be used to identify and analyze the shape of the meniscus for allograft transplantation using a 3D reconstruction model of the patient’s unruptured meniscus.
Highlights
The menisci is a thin, semi lunar-like tissue pad consisting of the medial meniscus located on the inside of the knee and the lateral meniscus located on the outside of the knee, distributing the load while reducing friction in the knee [1,2]
In deep-learning-based methods, U-Net-based deep learning networks have been applied in most studies. 2D U-Net, and 3D U-Net with various other methods such as auxiliary classifier, residual link, statistical shape model (SSM), 3D conditional random field (CRF), 3D simplex deformable modeling, and attention module have been proposed to segment cartilage and meniscus to assess OA progression [10,11,12,13,14]
We propose an automatic meniscus segmentation method that integrates multi-class segmentation networks to localize the meniscus and adversarial-learningbased segmentation networks with an object-aware map to segment the meniscus
Summary
The menisci is a thin, semi lunar-like tissue pad consisting of the medial meniscus located on the inside of the knee and the lateral meniscus located on the outside of the knee, distributing the load while reducing friction in the knee [1,2]. 2D U-Net, and 3D U-Net with various other methods such as auxiliary classifier, residual link, statistical shape model (SSM), 3D conditional random field (CRF), 3D simplex deformable modeling, and attention module have been proposed to segment cartilage and meniscus to assess OA progression [10,11,12,13,14]. These deeplearning-based methods did not take into account the class imbalance problem between the meniscus and other structures apart from the meniscus
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
