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

Kessler, Dimitri A., Mackay, James W. ORCID:, Crowe, Victoria, Henson, Frances, Graves, Martin J., Gilbert, Fiona J. and Kaggie, Joshua D. (2020) The optimisation of deep neural networks for segmenting multiple knee joint tissues from MRIs. Computerized Medical Imaging and Graphics, 86. ISSN 0895-6111

[thumbnail of Accepted_Manuscript]
PDF (Accepted_Manuscript) - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (5MB) | Preview
[thumbnail of Kessler_etal_2020_CMIaG]
PDF (Kessler_etal_2020_CMIaG) - Published Version
Available under License Creative Commons Attribution.

Download (6MB) | Preview


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.

Item Type: Article
Uncontrolled Keywords: convolutional neural network (cnn),generative adversarial network (gan),image segmentation,magnetic resonance imaging (mri),musculoskeletal,radiological and ultrasound technology,radiology nuclear medicine and imaging,computer vision and pattern recognition,health informatics,computer graphics and computer-aided design ,/dk/atira/pure/subjectarea/asjc/3600/3614
Faculty \ School: Faculty of Medicine and Health Sciences > Norwich Medical School
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 30 Sep 2020 23:58
Last Modified: 22 Oct 2022 07:11
DOI: 10.1016/j.compmedimag.2020.101793


Downloads per month over past year

Actions (login required)

View Item View Item