Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB) · 2025
U2-Attention-Net: a deep learning automatic delineation model for parotid glands in head and neck cancer organs at risk on radiotherapy localization computed tomography images.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wen Xiaobo, Wang Yanhong, Zhang Daijun, Xiu Yutao, Sun Li, Zhao Biao, Liu Ting, Zhang Xinyi, Fan Jinfei, Xu Junlin, An Tianen, Li Weimin, Yang Yi, Xing Dongming
Аннотация
OBJECTIVE: This study aimed to develop a novel deep learning model, U2-Attention-Net (U2A-Net), for precise segmentation of parotid glands on radiotherapy localization CT images.
METHODS: CT images from 79 patients with head and neck cancer were selected, on which the label maps were delineated by relevant practitioners to construct a dataset. The dataset was divided into the training set (n = 60), validation set (n = 6), and test set (n = 13), with the training set augmented. U2A-Net, divided into U2A-Net V1 (sSE) and U2A-Net V2 (cSE) based on different attention mechanisms, was evaluated for parotid gland segmentation based on the DL loss function with U-Net, Attention U-Net, DeepLabV3+, and TransUNet as comparision models. Segmentation was also performed using GDL and GD-BCEL loss functions. Model performance was evaluated using DSC, JSC, PPV, SE, HD, RVD, and VOE metrics.
RESULTS: The quantitative results revealed that U2A-Net based on DL outperformed the comparative models. While U2A-Net V1 had the highest PPV, U2A-Net V2 demonstrated the best quantitative results in other metrics. Qualitative results showed that U2A-Net's segmentation closely matched expert delineations, reducing oversegmentation and undersegmentation, with U2A-Net V2 being more effective. In comparing loss functions, U2A-Net V1 using GD-BCEL and U2A-Net V2 using DL performed best.
CONCLUSION: The U2A-Net model significantly improved parotid gland segmentation on radiotherapy localization CT images. The cSE attention mechanism showed advantages with DL, while sSE performed better with GD-BCEL.
METHODS: CT images from 79 patients with head and neck cancer were selected, on which the label maps were delineated by relevant practitioners to construct a dataset. The dataset was divided into the training set (n = 60), validation set (n = 6), and test set (n = 13), with the training set augmented. U2A-Net, divided into U2A-Net V1 (sSE) and U2A-Net V2 (cSE) based on different attention mechanisms, was evaluated for parotid gland segmentation based on the DL loss function with U-Net, Attention U-Net, DeepLabV3+, and TransUNet as comparision models. Segmentation was also performed using GDL and GD-BCEL loss functions. Model performance was evaluated using DSC, JSC, PPV, SE, HD, RVD, and VOE metrics.
RESULTS: The quantitative results revealed that U2A-Net based on DL outperformed the comparative models. While U2A-Net V1 had the highest PPV, U2A-Net V2 demonstrated the best quantitative results in other metrics. Qualitative results showed that U2A-Net's segmentation closely matched expert delineations, reducing oversegmentation and undersegmentation, with U2A-Net V2 being more effective. In comparing loss functions, U2A-Net V1 using GD-BCEL and U2A-Net V2 using DL performed best.
CONCLUSION: The U2A-Net model significantly improved parotid gland segmentation on radiotherapy localization CT images. The cSE attention mechanism showed advantages with DL, while sSE performed better with GD-BCEL.