Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR Images
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 c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/9/1612 |
| _version_ | 1797519679435046912 |
|---|---|
| author | Uju Jeon Hyeonjin Kim Helen Hong Joonho Wang |
| author_facet | Uju Jeon Hyeonjin Kim Helen Hong Joonho Wang |
| author_sort | Uju Jeon |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T07:46:13Z |
| format | Article |
| id | doaj.art-2ca93950115a4879acbdd0dd0d088f94 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T07:46:13Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-2ca93950115a4879acbdd0dd0d088f942023-11-22T12:39:40ZengMDPI AGDiagnostics2075-44182021-09-01119161210.3390/diagnostics11091612Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR ImagesUju Jeon0Hyeonjin Kim1Helen Hong2Joonho Wang3Department of Software Convergence, Seoul Women’s University, Seoul 01797, KoreaDepartment of Software Convergence, Seoul Women’s University, Seoul 01797, KoreaDepartment of Software Convergence, Seoul Women’s University, Seoul 01797, KoreaDepartment of Orthopedic Surgery, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 06351, KoreaMeniscus 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.https://www.mdpi.com/2075-4418/11/9/1612knee MR imagesmeniscus segmentationdeep convolutional neural networkadversarial learningconditional generative adversarial network |
| spellingShingle | Uju Jeon Hyeonjin Kim Helen Hong Joonho Wang Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR Images Diagnostics knee MR images meniscus segmentation deep convolutional neural network adversarial learning conditional generative adversarial network |
| title | Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR Images |
| title_full | Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR Images |
| title_fullStr | Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR Images |
| title_full_unstemmed | Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR Images |
| title_short | Automatic Meniscus Segmentation Using Adversarial Learning-Based Segmentation Network with Object-Aware Map in Knee MR Images |
| title_sort | automatic meniscus segmentation using adversarial learning based segmentation network with object aware map in knee mr images |
| topic | knee MR images meniscus segmentation deep convolutional neural network adversarial learning conditional generative adversarial network |
| url | https://www.mdpi.com/2075-4418/11/9/1612 |
| work_keys_str_mv | AT ujujeon automaticmeniscussegmentationusingadversariallearningbasedsegmentationnetworkwithobjectawaremapinkneemrimages AT hyeonjinkim automaticmeniscussegmentationusingadversariallearningbasedsegmentationnetworkwithobjectawaremapinkneemrimages AT helenhong automaticmeniscussegmentationusingadversariallearningbasedsegmentationnetworkwithobjectawaremapinkneemrimages AT joonhowang automaticmeniscussegmentationusingadversariallearningbasedsegmentationnetworkwithobjectawaremapinkneemrimages |