An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image Segmentation
Semi-supervised learning is a technique that utilizes a limited set of labeled data and a large amount of unlabeled data to overcome the challenges of obtaining a perfect dataset in deep learning, especially in medical image segmentation. The accuracy of the predicted labels for the unlabeled data i...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2078-2489/14/3/190 |
_version_ | 1797611141204017152 |
---|---|
author | Guoqin Li Nursuriati Jamil Raseeda Hamzah |
author_facet | Guoqin Li Nursuriati Jamil Raseeda Hamzah |
author_sort | Guoqin Li |
collection | DOAJ |
description | Semi-supervised learning is a technique that utilizes a limited set of labeled data and a large amount of unlabeled data to overcome the challenges of obtaining a perfect dataset in deep learning, especially in medical image segmentation. The accuracy of the predicted labels for the unlabeled data is a critical factor that affects the training performance, thus reducing the accuracy of segmentation. To address this issue, a semi-supervised learning method based on the Diff-CoGAN framework was proposed, which incorporates co-training and generative adversarial network (GAN) strategies. The proposed Diff-CoGAN framework employs two generators and one discriminator. The generators work together by providing mutual information guidance to produce predicted maps that are more accurate and closer to the ground truth. To further improve segmentation accuracy, the predicted maps are subjected to an intersection operation to identify a high-confidence region of interest, which reduces boundary segmentation errors. The predicted maps are then fed into the discriminator, and the iterative process of adversarial training enhances the generators’ ability to generate more precise maps, while also improving the discriminator’s ability to distinguish between the predicted maps and the ground truth. This study conducted experiments on the Hippocampus and Spleen images from the Medical Segmentation Decathlon (MSD) dataset using three semi-supervised methods: co-training, semi-GAN, and Diff-CoGAN. The experimental results demonstrated that the proposed Diff-CoGAN approach significantly enhanced segmentation accuracy compared to the other two methods by benefiting on the mutual guidance of the two generators and the adversarial training between the generators and discriminator. The introduction of the intersection operation prior to the discriminator also further reduced boundary segmentation errors. |
first_indexed | 2024-03-11T06:24:37Z |
format | Article |
id | doaj.art-f77338094de9478dbab1aceec06488fc |
institution | Directory Open Access Journal |
issn | 2078-2489 |
language | English |
last_indexed | 2024-03-11T06:24:37Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Information |
spelling | doaj.art-f77338094de9478dbab1aceec06488fc2023-11-17T11:44:20ZengMDPI AGInformation2078-24892023-03-0114319010.3390/info14030190An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image SegmentationGuoqin Li0Nursuriati Jamil1Raseeda Hamzah2Taiyuan Institute of Technology, Taiyuan 030008, ChinaCollege of Computing, Informatics and Media, Universiti Teknologi MARA, Shah Alam 40450, Selangor, MalaysiaCollege of Computing, Informatics and Media, Universiti Teknologi MARA, Melaka Branch, Merlimau 77300, Melaka, MalaysiaSemi-supervised learning is a technique that utilizes a limited set of labeled data and a large amount of unlabeled data to overcome the challenges of obtaining a perfect dataset in deep learning, especially in medical image segmentation. The accuracy of the predicted labels for the unlabeled data is a critical factor that affects the training performance, thus reducing the accuracy of segmentation. To address this issue, a semi-supervised learning method based on the Diff-CoGAN framework was proposed, which incorporates co-training and generative adversarial network (GAN) strategies. The proposed Diff-CoGAN framework employs two generators and one discriminator. The generators work together by providing mutual information guidance to produce predicted maps that are more accurate and closer to the ground truth. To further improve segmentation accuracy, the predicted maps are subjected to an intersection operation to identify a high-confidence region of interest, which reduces boundary segmentation errors. The predicted maps are then fed into the discriminator, and the iterative process of adversarial training enhances the generators’ ability to generate more precise maps, while also improving the discriminator’s ability to distinguish between the predicted maps and the ground truth. This study conducted experiments on the Hippocampus and Spleen images from the Medical Segmentation Decathlon (MSD) dataset using three semi-supervised methods: co-training, semi-GAN, and Diff-CoGAN. The experimental results demonstrated that the proposed Diff-CoGAN approach significantly enhanced segmentation accuracy compared to the other two methods by benefiting on the mutual guidance of the two generators and the adversarial training between the generators and discriminator. The introduction of the intersection operation prior to the discriminator also further reduced boundary segmentation errors.https://www.mdpi.com/2078-2489/14/3/190semi-supervised learningmedical image segmentationco-trainingGANDiff-CoGAN |
spellingShingle | Guoqin Li Nursuriati Jamil Raseeda Hamzah An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image Segmentation Information semi-supervised learning medical image segmentation co-training GAN Diff-CoGAN |
title | An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image Segmentation |
title_full | An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image Segmentation |
title_fullStr | An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image Segmentation |
title_full_unstemmed | An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image Segmentation |
title_short | An Improved Co-Training and Generative Adversarial Network (Diff-CoGAN) for Semi-Supervised Medical Image Segmentation |
title_sort | improved co training and generative adversarial network diff cogan for semi supervised medical image segmentation |
topic | semi-supervised learning medical image segmentation co-training GAN Diff-CoGAN |
url | https://www.mdpi.com/2078-2489/14/3/190 |
work_keys_str_mv | AT guoqinli animprovedcotrainingandgenerativeadversarialnetworkdiffcoganforsemisupervisedmedicalimagesegmentation AT nursuriatijamil animprovedcotrainingandgenerativeadversarialnetworkdiffcoganforsemisupervisedmedicalimagesegmentation AT raseedahamzah animprovedcotrainingandgenerativeadversarialnetworkdiffcoganforsemisupervisedmedicalimagesegmentation AT guoqinli improvedcotrainingandgenerativeadversarialnetworkdiffcoganforsemisupervisedmedicalimagesegmentation AT nursuriatijamil improvedcotrainingandgenerativeadversarialnetworkdiffcoganforsemisupervisedmedicalimagesegmentation AT raseedahamzah improvedcotrainingandgenerativeadversarialnetworkdiffcoganforsemisupervisedmedicalimagesegmentation |