A deep learning model that leverages interpretable cellular features to improve feature extraction from H&E-stained tissue sections (NEURAL-PC) and represents an extensively validated diagnostic and prognostic model for advanced prostate cancer.
Abstract
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.
The deep learning-based multi-cancer disease-free survival model performed robustly across cancer subtypes, with the nomogram improving risk stratification, particularly for stage I malignancies, complementing existing staging.
Si-Teng Chen, En-Cheng Zhang, Fu-Kang Sun et al.· Cancers· 0 citations
Non-small cell lung cancer (NSCLC) is characterized by profound biological heterogeneity, frequently leading to late-stage diagnosis, recurrence, or metastasis. Conventional clinical pathways heavily depend on subjective visual interpretations, invasive tissue biopsies, and experience-based medical models that constrai...
Shuai-Yu Zheng, Chi Lv, Zhen Yao· Frontiers in Medicine· 0 citations
INTRODUCTION
Breast cancer is a heterogeneous malignancy comprising distinct molecular subtypes, each with varying therapeutic strategies and prognoses. Conventional molecular subtyping relies on immunohistochemistry and in situ hybridization studies, which may not be universally accessible due to financial and technic...
Mehdi Zarei, M. Arabfard, Mehdi Raei et al.· Cancer Treatment and Researc...· 0 citations
This review examines how computational pathology and convolutional neural networks (CNNs) can improve histopathologic diagnosis and risk stratification of melanoma, evaluate current image-based deep learning (DL) approaches, and outline a path toward explainable, multimodal prognostic tools.
Eudora Lee, R. Karagenova, Y. Semenov· International Journal of Der...· 1 citation
It is suggested that deep learning models, particularly Inception V3, can effectively predict TMB status in patients using histopathological images, and the potential for integrating DL techniques in clinical settings to enhance personalized treatment strategies for patients with varying TMB is highlighted.
T. A. Serel, Onur Ertunç, M. Kıran et al.· OBM Genetics· 0 citations
The first validated morpho-molecular classification of Esophageal adenocarcinoma is reported, with the transitional and signet ring signatures associated with worse prognosis compared to tumors with a glandular signature.
G. Wilson, Jin-soo Park, F. Allison et al.· Diseases of the esophagus· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.