Development and external multicentric validation of a deep learning-based clinical target volume segmentation model for whole-breast radiotherapy

Physics and Imaging in Radiation Oncology, Год журнала: 2025, Номер unknown, С. 100749 - 100749

Опубликована: Март 1, 2025

Язык: Английский

---

Development and comprehensive evaluation of a national DBCG consensus-based auto-segmentation model for lymph node levels in breast cancer radiotherapy

Radiotherapy and Oncology, Год журнала: 2024, Номер 201, С. 110567 - 110567

Опубликована: Окт. 5, 2024

Язык: Английский

---

Advances in automatic delineation of target volume and cardiac substructure in breast cancer radiotherapy (Review)

Oncology Letters, Год журнала: 2023, Номер 25(3)

Опубликована: Фев. 2, 2023

Postoperative adjuvant radiotherapy plays an important role in the treatment of patients with breast cancer. With continuous development radiotherapeutic technologies, requirements for accuracy are increasingly high. The target volume and organ at risk delineation significantly affects effect radiotherapy. Automatic software has been continuously developed automatic areas organs risk. segmentation based on atlas deep learning is a hot topic current clinical research. can not only reduce workload times, but also establish uniform standard inter-observer intra-observer differences. In cancer, especially who undergo left radiotherapy, protection heart particularly important. Treating whole as cannot meet needs, it necessary to limit dose specific cardiac substructures. present review discusses importance substructure

Язык: Английский

---

Automated contouring and statistical process control for plan quality in a breast clinical trial

Physics and Imaging in Radiation Oncology, Год журнала: 2023, Номер 28, С. 100486 - 100486

Опубликована: Авг. 24, 2023

Automatic review of breast plan quality for clinical trials is time-consuming and has some unique challenges due to the lack target contours planning techniques. We propose using an auto-contouring model statistical process control independently assess consistency in retrospective data from a radiotherapy trial.A deep learning was created tested quantitatively qualitatively on 104 post-lumpectomy patients' computed tomography images (nnUNet; train/test: 80/20). The then applied 127 patients enrolled trial. Statistical used mean dose auto-contours between plans treatment modalities by setting limits within three standard deviations data's mean. Two physicians reviewed outside possible inconsistencies.Mean Dice similarity coefficients comparing manual above 0.7 volume, supraclavicular internal mammary nodes. radiation oncologists scored 95% as clinically acceptable. trial more variable lymph node than breast, with narrower distribution volumetric modulated arc therapy 3D conformal treatment, requiring distinct limits. Five (5%) were flagged physicians: one required editing, two had acceptable variations planning, poor auto-contouring.An automated contouring framework appropriate assessing

Язык: Английский

---

Extensive clinical testing of Deep Learning Segmentation models for thorax and breast cancer radiotherapy planning

Acta Oncologica, Год журнала: 2023, Номер 62(10), С. 1184 - 1193

Опубликована: Окт. 3, 2023

Background The performance of deep learning segmentation (DLS) models for automatic organ extraction from CT images in the thorax and breast regions was investigated. Furthermore, readiness feasibility integrating DLS into clinical practice were addressed by measuring potential time savings dosimetric impact.

Язык: Английский

---