BCTVNet: a 3D Hybrid segmentation neural network for clinical target volume delineation of cervical cancer brachytherapy
Zapisane w:
| Wydane w: | Machine Learning : Science and Technology vol. 6, no. 4 (Dec 2025), p. 045056 |
|---|---|
| 1. autor: | |
| Kolejni autorzy: | , , , , , , , |
| Wydane: |
IOP Publishing
|
| Hasła przedmiotowe: | |
| Dostęp online: | Citation/Abstract Full Text - PDF |
| Etykiety: |
Nie ma etykietki, Dołącz pierwszą etykiete!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3278275493 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2632-2153 | ||
| 024 | 7 | |a 10.1088/2632-2153/ae2233 |2 doi | |
| 035 | |a 3278275493 | ||
| 045 | 2 | |b d20251201 |b d20251231 | |
| 100 | 1 | |a Gu, Yin | |
| 245 | 1 | |a BCTVNet: a 3D Hybrid segmentation neural network for clinical target volume delineation of cervical cancer brachytherapy | |
| 260 | |b IOP Publishing |c Dec 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Clinical target volume (CTV) delineation is essential in cervical cancer brachytherapy (BT), as accurate and automatic segmentation can improve treatment effect for patients with locally advanced disease while reducing the workload of clinicians. We propose BCTVNet (BT CTV),, a 3D hybrid neural network that integrates convolutional neural network (CNN) and transformer branches to combine strong local feature extraction with global context modeling. The 3D architecture enables the model to capture spatial relationships across slices, which is crucial for accurately identifying CTV boundaries in volumetric computed tomography (CT) data. In addition, a 3D contrast limited adaptive histogram equalization preprocessing step is applied to enhance the local contrast of soft tissues, improving anatomical structure visibility and facilitating boundary recognition. Experiments on a private BT CT dataset of 95 patients show that BCTVNet achieves superior performance compared with popular CNN-based and transformer-based segmentation models, reaching a Dice similarity coefficient (DSC) of 83.23% and a Hausdorff distance 95th percentile of 3.53 mm. Evaluation on the publicly available SegTHOR dataset further confirms its strong generalizability, achieving the highest average score among all compared methods, with a DSC of 87.09%. Multiple ablation experiments verify the effectiveness of both the hybrid architecture and the adaptive preprocessing strategy. These results demonstrate that BCTVNet provides accurate and stable CTV delineation, making it a reliable tool for clinical BT and a valuable approach for wider medical image segmentation tasks. | |
| 653 | |a Delineation | ||
| 653 | |a Datasets | ||
| 653 | |a Preprocessing | ||
| 653 | |a Image segmentation | ||
| 653 | |a Computed tomography | ||
| 653 | |a Artificial neural networks | ||
| 653 | |a Cancer | ||
| 653 | |a Radiation therapy | ||
| 653 | |a Neural networks | ||
| 653 | |a Medical imaging | ||
| 653 | |a Ablation | ||
| 653 | |a Soft tissues | ||
| 653 | |a Cervical cancer | ||
| 653 | |a Metric space | ||
| 700 | 1 | |a Guo, Huimin | |
| 700 | 1 | |a Tu, Qisen | |
| 700 | 1 | |a Gao, Yuhua | |
| 700 | 1 | |a Li, Yuexian | |
| 700 | 1 | |a Cui, Ming | |
| 700 | 1 | |a Qian, Wei | |
| 700 | 1 | |a Zhang, Lin | |
| 700 | 1 | |a Ma, He | |
| 773 | 0 | |t Machine Learning : Science and Technology |g vol. 6, no. 4 (Dec 2025), p. 045056 | |
| 786 | 0 | |d ProQuest |t Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3278275493/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3278275493/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch |