| Autor: |
Jianhao Geng, Xin Sui, Rongxu Du, Jialin Feng, Ruoxi Wang, Meijiao Wang, Kaining Yao, Qi Chen, Lu Bai, Shaobin Wang, Yongheng Li, Hao Wu, Xiangmin Hu, Yi Du |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Radiation Oncology, Vol 19, Iss 1, Pp 1-11 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
1748-717X |
| DOI: |
10.1186/s13014-024-02463-0 |
| Popis: |
Abstract Background and purpose Various deep learning auto-segmentation (DLAS) models have been proposed, some of which have been commercialized. However, the issue of performance degradation is notable when pretrained models are deployed in the clinic. This study aims to enhance precision of a popular commercial DLAS product in rectal cancer radiotherapy by localized fine-tuning, addressing challenges in practicality and generalizability in real-world clinical settings. Materials and methods A total of 120 Stage II/III mid-low rectal cancer patients were retrospectively enrolled and divided into three datasets: training (n = 60), external validation (ExVal, n = 30), and generalizability evaluation (GenEva, n = 30) datasets respectively. The patients in the training and ExVal dataset were acquired on the same CT simulator, while those in GenEva were on a different CT simulator. The commercial DLAS software was first localized fine-tuned (LFT) for clinical target volume (CTV) and organs-at-risk (OAR) using the training data, and then validated on ExVal and GenEva respectively. Performance evaluation involved comparing the LFT model with the vendor-provided pretrained model (VPM) against ground truth contours, using metrics like Dice similarity coefficient (DSC), 95th Hausdorff distance (95HD), sensitivity and specificity. Results LFT significantly improved CTV delineation accuracy (p |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
