Glioblastoma and radiotherapy: A multicenter AI study for Survival Predictions from MRI (GRASP study).
Обработка статьи · этапы, ошибки и управление
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.
Chelliah Alysha, Wood David A, Canas Liane S, Shuaib Haris, Currie Stuart, Fatania Kavi, Frood Russell, Rowland-Hill Chris, Thust Stefanie, Wastling Stephen J, Tenant Sean, McBain Catherine, Foweraker Karen, Williams Matthew, Wang Qiquan, Roman Andrei, Dragos Carmen, MacDonald Mark, Lau Yue Hui, Linares Christian A, Bassiouny Ahmed, Luis Aysha, Young Thomas, Brock Juliet, Chandy Edward, Beaumont Erica, Lam Tai-Chung, Welsh Liam, Lewis Joanne, Mathew Ryan, Kerfoot Eric, Brown Richard, Beasley Daniel, Glendenning Jennifer, Brazil Lucy, Swampillai Angela, Ashkan Keyoumars, Ourselin Sébastien, Modat Marc, Booth Thomas C
Аннотация
METHODS: Retrospective and prospective data were collected from 206 consecutive glioblastoma, isocitrate dehydrogenase -wildtype patients diagnosed between March 2014 and February 2022 across 11 UK centers. Models were trained on 158 retrospective patients from 3 centers. Holdout test sets were retrospective (n = 19; internal validation), and prospective (n = 29; external validation from 8 distinct centers). Neural network branches for T2-weighted and contrast-enhanced T1-weighted inputs were concatenated to predict survival. A nonimaging branch (demographics/MGMT/treatment data) was also combined with the imaging model. We investigated the influence of individual MR sequences; nonimaging features; and weighted dense blocks pretrained for abnormality detection.
RESULTS: The imaging model outperformed the nonimaging model in all test sets (area under the receiver-operating characteristic curve, AUC P = .038) and performed similarly to a combined imaging/nonimaging model (P > .05). Imaging, nonimaging, and combined models applied to amalgamated test sets gave AUCs of 0.93, 0.79, and 0.91. Initializing the imaging model with pretrained weights from 10 000s of brain MRIs improved performance considerably (amalgamated test sets without pretraining 0.64; P = .003).
CONCLUSIONS: A deep learning model using MRI images after radiotherapy reliably and accurately determined survival of glioblastoma. The model serves as a prognostic biomarker identifying patients who will not survive beyond a typical course of adjuvant temozolomide, thereby stratifying patients into those who might require early second-line or clinical trial treatment.