Neuroradiology · 2025
A semantic segmentation model for automatic precise identification of pituitary microadenomas with preoperative MRI.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
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.
Yuan ChenGang, Qu Hang, Dai HuMing, Jiang HaiXiao, Cao DeMao, Shao LiYing, Zhou LiangXue, Peng AiJun
Аннотация
PURPOSE: Magnetic resonance imaging (MRI) is an essential technique for diagnosing pituitary adenomas; however, it is also challenging for neurosurgeons to use it to precisely identify some types of microadenomas. A novel neural network model was developed using preoperative MRI to assist clinicians in diagnosing pituitary microadenomas.
METHOD: Sixty patients with pathologically diagnosed pituitary microadenomas, including hyperprolactinemia (n = 19), growth hormone microadenomas (n = 17), and adrenocorticotropin microadenomas (n = 24), were enrolled. An image edge-supervised same receptive field semantic segmentation network was developed based on T1-weighted, T2-weighted, and contrast-enhanced T1-weighted images.
RESULTS: The mean Intersection over Unions of our neural network model were 0.7013 ± 0.3400, 0.7295 ± 0.321, and 0.8053 ± 0.3052 for the test sets of T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences, respectively, while the Dice Similarity Coefficient values were 0.8075 ± 0.3895, 0.8192 ± 0.3733, and 0.8860 ± 0.3443 for the corresponding sequences. The performance on contrast-enhanced T1-weighted images was better than that of the other two MR sequences.
CONCLUSIONS: The image edge-supervised same receptive field segmentation network can potentially be used to precisely identify pituitary microadenomas automatically with preoperative MRI. The developed model exhibited good performance with contrast-enhanced T1-weighted images and could help neurosurgeons accurately determine the locations of pituitary microadenomas.
METHOD: Sixty patients with pathologically diagnosed pituitary microadenomas, including hyperprolactinemia (n = 19), growth hormone microadenomas (n = 17), and adrenocorticotropin microadenomas (n = 24), were enrolled. An image edge-supervised same receptive field semantic segmentation network was developed based on T1-weighted, T2-weighted, and contrast-enhanced T1-weighted images.
RESULTS: The mean Intersection over Unions of our neural network model were 0.7013 ± 0.3400, 0.7295 ± 0.321, and 0.8053 ± 0.3052 for the test sets of T1-weighted, T2-weighted, and contrast-enhanced T1-weighted sequences, respectively, while the Dice Similarity Coefficient values were 0.8075 ± 0.3895, 0.8192 ± 0.3733, and 0.8860 ± 0.3443 for the corresponding sequences. The performance on contrast-enhanced T1-weighted images was better than that of the other two MR sequences.
CONCLUSIONS: The image edge-supervised same receptive field segmentation network can potentially be used to precisely identify pituitary microadenomas automatically with preoperative MRI. The developed model exhibited good performance with contrast-enhanced T1-weighted images and could help neurosurgeons accurately determine the locations of pituitary microadenomas.