MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1172/jci.insight.201872

Медицинская библиотека · JCI insight · 2026

Deep learning-based histologic classifiers enable molecular subtyping of metastatic prostate cancer.

Chen Zhijun, Sayar Erolcan, Guevara Daniela, Richards Helen, Zhang Haoyue, Patel Radhika A, Gawne Agnes C, Liu Lucas J, Coleman Ilsa, Dumpit Ruth, Morrissey Colm, Schweizer Michael T, Raychaudhuri Ruben, Graham Laura S, Yu Evan Y, Cheng Heather H, Ding Chien-Kuang C, Wang Yuzhuo, Choyke Peter, Turkbey Baris, Chanel-Vos Chantal, Fedorov Christina, Otilano Iii John R, Kane Troy, Manohar Jyothi, Sigouros Michael, Nauseef Jones T, Molina Ana, Nanus David, Tagawa Scott T, Mosquera Juan Miguel, Beltran Himisha P, Etzioni Ruth, Nelson Peter S, Soundararajan Rama, Aparicio Ana M, Sternberg Cora N, Haffner Michael C, Harmon Stephanie A

СтатьяПеревод в очереди

Аннотация

Metastatic prostate cancer is a clinically and molecularly heterogeneous disease. Under the selective pressure of androgen receptor (AR)-directed therapies, resistant phenotypes frequently emerge, posing significant diagnostic and therapeutic challenges. Neuroendocrine prostate cancer (NEPC) is a clinically important phenotype characterized by lineage plasticity, neuroendocrine features, visceral metastases and poor prognosis. Accurately diagnosing NEPC remains difficult due to its histologic and molecular complexity but has high clinical relevance. In this study, we developed a deep learning model that leverages interpretable cellular features to improve feature extraction from H&E-stained tissue sections (NEURAL-PC). By incorporating a multiple instance learning (MIL) framework, NEURAL-PC enables robust NEPC classification solely from H&E tumor images, achieving an area under the receiver operating characteristic curve (AUROC) of 0.921 in independent external validation. In addition to its diagnostic utility, NEURAL-PC provides prognostic information that enables further subclassification of advanced prostate cancer across diverse datasets supporting its strong prognostic value and generalizability. Broadly, our work highlights a hybrid approach that integrates features across different domains, offering a promising strategy for developing reliable deep learning tools in pathology. Built on this framework, NEURAL-PC represents an extensively validated diagnostic and prognostic model for advanced prostate cancer.

Для цитирования: Chen Zhijun, Sayar Erolcan, Guevara Daniela, Richards Helen, Zhang Haoyue, Patel Radhika A, Gawne Agnes C, Liu Lucas J, Coleman Ilsa, Dumpit Ruth, Morrissey Colm, Schweizer Michael T, Raychaudhuri Ruben, Graham Laura S, Yu Evan Y, Cheng Heather H, Ding Chien-Kuang C, Wang Yuzhuo, Choyke Peter, Turkbey Baris, Chanel-Vos Chantal, Fedorov Christina, Otilano Iii John R, Kane Troy, Manohar Jyothi, Sigouros Michael, Nauseef Jones T, Molina Ana, Nanus David, Tagawa Scott T, Mosquera Juan Miguel, Beltran Himisha P, Etzioni Ruth, Nelson Peter S, Soundararajan Rama, Aparicio Ana M, Sternberg Cora N, Haffner Michael C, Harmon Stephanie A. Deep learning-based histologic classifiers enable molecular subtyping of metastatic prostate cancer.. JCI insight. 2026. DOI: 10.1172/jci.insight.201872.
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.