MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1038/s41467-025-64249-6

Медицинская библиотека · Nature communications · 2025

Uncertainty-aware ensemble of foundation models differentiates glioblastoma from its mimics.

Zhao Junhan, Lin Shih-Yen, Attias Raphaël, Mathews Liza, Engel Christian, Larghero Guillaume, Vremenko Dmytro, Kao Ting-Wan, Lee Tsung-Hua, Wang Yu-Hsuan, Tsai Cheng Che, Marostica Eliana, Lo Ying-Chun, Meredith David, Ligon Keith L, Arnaout Omar, Roetzer-Pejrimovsky Thomas, Lin Shih-Chieh, Shih Natalie Nc, Chaisuriya Nipon, Cook David J, Chiang Jung-Hsien, Liu Chia-Jen, Woehrer Adelheid, Golden Jeffrey A, Nasrallah MacLean P, Yu Kun-Hsing

СтатьяПеревод в очереди

Аннотация

Accurate pathological diagnosis is crucial in guiding personalized treatments for patients with central nervous system cancers. Distinguishing glioblastoma and primary central nervous system lymphoma is particularly challenging due to their overlapping pathology features, despite the distinct treatments required. To address this challenge, we establish the Pathology Image Characterization Tool with Uncertainty-aware Rapid Evaluations (PICTURE) system using 2141 pathology slides collected worldwide. PICTURE employs Bayesian inference, deep ensemble, and normalizing flow to account for the uncertainties in its predictions and training set labels. PICTURE accurately diagnoses glioblastoma and primary central nervous system lymphoma with an area under the receiver operating characteristic curve (AUROC) of 0.989, with the results validated in five independent cohorts (AUROC = 0.924-0.996). In addition, PICTURE identifies samples belonging to 67 types of rare central nervous system cancers that are neither gliomas nor lymphomas. Our approaches provide a generalizable framework for differentiating pathological mimics and enable rapid diagnoses for central nervous system cancer patients.

Для цитирования: Zhao Junhan, Lin Shih-Yen, Attias Raphaël, Mathews Liza, Engel Christian, Larghero Guillaume, Vremenko Dmytro, Kao Ting-Wan, Lee Tsung-Hua, Wang Yu-Hsuan, Tsai Cheng Che, Marostica Eliana, Lo Ying-Chun, Meredith David, Ligon Keith L, Arnaout Omar, Roetzer-Pejrimovsky Thomas, Lin Shih-Chieh, Shih Natalie Nc, Chaisuriya Nipon, Cook David J, Chiang Jung-Hsien, Liu Chia-Jen, Woehrer Adelheid, Golden Jeffrey A, Nasrallah MacLean P, Yu Kun-Hsing. Uncertainty-aware ensemble of foundation models differentiates glioblastoma from its mimics.. Nature communications. 2025. DOI: 10.1038/s41467-025-64249-6.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

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.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.