Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer Network
Aim: This article presents a novel approach to automate the segmentation of organ at risk (OAR) for high-dose-rate brachytherapy patients using three deep learning models combined with ensemble learning techniques. It aims to improve the accuracy and efficiency of segmentation. Materials and Methods...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Medknow Publications
2024-12-01
|
| Series: | Journal of Medical Physics |
| Subjects: | |
| Online Access: | https://journals.lww.com/10.4103/jmp.jmp_160_24 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556613516754944 |
|---|---|
| author | Soniya Pal Raj Pal Singh Anuj Kumar |
| author_facet | Soniya Pal Raj Pal Singh Anuj Kumar |
| author_sort | Soniya Pal |
| collection | DOAJ |
| description | Aim:
This article presents a novel approach to automate the segmentation of organ at risk (OAR) for high-dose-rate brachytherapy patients using three deep learning models combined with ensemble learning techniques. It aims to improve the accuracy and efficiency of segmentation.
Materials and Methods:
The dataset comprised computed tomography (CT) scans of 60 patients obtained from our own institutional image bank and 10 patients from the other institute, all in Digital Imaging and Communications in Medicine format. Experienced radiation oncologists manually segmented four OARs for each scan. Each scan was preprocessed and three models, Double U-Net (DUN), Bi-directional ConvLSTM U-Net (BCUN), and Transformer Networks (TN), were trained on reduced CT scans (240 × 240 × 128) due to memory limitations. Ensemble learning techniques were employed to enhance accuracy and segmentation metrics. Testing and validation were conducted on 12 patients from our institute (OID) and 10 patients from another institute (DID).
Results:
For DID test dataset, using the ensemble learning technique combining Transformer Network (TN) and BCUN, i.e., TN + BCUN, the average Dice similarity coefficient (DSC) ranged from 0.992 to 0.998, and for DUN and BCUN (DUN + BCUN) combination, the average DSC ranged from 0.990 to 0.993, which reflecting high segmentation accuracy. The 95% Hausdorff distance (HD) ranged from 0.9 to 1.2 mm for TN + BCUN and 1.1 to 1.4 mm for DUN + BCUN, demonstrating precise segmentation boundaries.
Conclusion:
The proposed method leverages the strengths of each network architecture. The DUN setup excels in sequential processing, the BCUN captures spatiotemporal dependencies, and transformer networks provide a robust understanding of global context. This combination enables efficient and accurate segmentation, surpassing human expert performance in both time and accuracy. |
| format | Article |
| id | doaj-art-f41176d5dab64f70920b87d7cf8e4599 |
| institution | Kabale University |
| issn | 0971-6203 1998-3913 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wolters Kluwer Medknow Publications |
| record_format | Article |
| series | Journal of Medical Physics |
| spelling | doaj-art-f41176d5dab64f70920b87d7cf8e45992025-01-07T07:19:03ZengWolters Kluwer Medknow PublicationsJournal of Medical Physics0971-62031998-39132024-12-0149457458210.4103/jmp.jmp_160_24Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer NetworkSoniya PalRaj Pal SinghAnuj KumarAim: This article presents a novel approach to automate the segmentation of organ at risk (OAR) for high-dose-rate brachytherapy patients using three deep learning models combined with ensemble learning techniques. It aims to improve the accuracy and efficiency of segmentation. Materials and Methods: The dataset comprised computed tomography (CT) scans of 60 patients obtained from our own institutional image bank and 10 patients from the other institute, all in Digital Imaging and Communications in Medicine format. Experienced radiation oncologists manually segmented four OARs for each scan. Each scan was preprocessed and three models, Double U-Net (DUN), Bi-directional ConvLSTM U-Net (BCUN), and Transformer Networks (TN), were trained on reduced CT scans (240 × 240 × 128) due to memory limitations. Ensemble learning techniques were employed to enhance accuracy and segmentation metrics. Testing and validation were conducted on 12 patients from our institute (OID) and 10 patients from another institute (DID). Results: For DID test dataset, using the ensemble learning technique combining Transformer Network (TN) and BCUN, i.e., TN + BCUN, the average Dice similarity coefficient (DSC) ranged from 0.992 to 0.998, and for DUN and BCUN (DUN + BCUN) combination, the average DSC ranged from 0.990 to 0.993, which reflecting high segmentation accuracy. The 95% Hausdorff distance (HD) ranged from 0.9 to 1.2 mm for TN + BCUN and 1.1 to 1.4 mm for DUN + BCUN, demonstrating precise segmentation boundaries. Conclusion: The proposed method leverages the strengths of each network architecture. The DUN setup excels in sequential processing, the BCUN captures spatiotemporal dependencies, and transformer networks provide a robust understanding of global context. This combination enables efficient and accurate segmentation, surpassing human expert performance in both time and accuracy.https://journals.lww.com/10.4103/jmp.jmp_160_24brachytherapyimage segmentationlstm u-netmedical image segmentationorgan at risktransformeru-net |
| spellingShingle | Soniya Pal Raj Pal Singh Anuj Kumar Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer Network Journal of Medical Physics brachytherapy image segmentation lstm u-net medical image segmentation organ at risk transformer u-net |
| title | Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer Network |
| title_full | Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer Network |
| title_fullStr | Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer Network |
| title_full_unstemmed | Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer Network |
| title_short | Ensemble Learning for Three-dimensional Medical Image Segmentation of Organ at Risk in Brachytherapy Using Double U-Net, Bi-directional ConvLSTM U-Net, and Transformer Network |
| title_sort | ensemble learning for three dimensional medical image segmentation of organ at risk in brachytherapy using double u net bi directional convlstm u net and transformer network |
| topic | brachytherapy image segmentation lstm u-net medical image segmentation organ at risk transformer u-net |
| url | https://journals.lww.com/10.4103/jmp.jmp_160_24 |
| work_keys_str_mv | AT soniyapal ensemblelearningforthreedimensionalmedicalimagesegmentationoforganatriskinbrachytherapyusingdoubleunetbidirectionalconvlstmunetandtransformernetwork AT rajpalsingh ensemblelearningforthreedimensionalmedicalimagesegmentationoforganatriskinbrachytherapyusingdoubleunetbidirectionalconvlstmunetandtransformernetwork AT anujkumar ensemblelearningforthreedimensionalmedicalimagesegmentationoforganatriskinbrachytherapyusingdoubleunetbidirectionalconvlstmunetandtransformernetwork |