The following abstract is drawn from a recently published paper in Nature – npj Prescision Oncology. We invite you to read the full paper and join the conversation, become a member of the Pathology News community to share your thoughts, ask questions, and engage with others around this work.

Authors: Christian Rolfo, Efrat Ofek, Yoash Barak, Jonathan Weidenfeld, Razan Imad Haj, Yosef Molchanov, Alexander Loebel, David R. Braxton, John S. Cupp, Rinat Yacobi, Chen Mayer, Francesco Drago, Camila Avivi, Nurit Paz-Yaacov, Assaf Avinoam, Jonathan Zalach, Addie Dvir, Inbal Gazy, Nir Peled, Damien Urban, Jair Bar, Dov Hershkoviz & Iris Barshack

Abstract

Non-small cell lung cancer (NSCLC) patient management relies on molecular analysis to determine eligibility for targeted therapy. Furthermore, neoadjuvant immunotherapy is primarily suitable in the absence of specific genomic alterations. However, significant challenges remain, including suboptimal molecular testing and patients being assigned to non-optimal treatment strategies. Here, we present AI classifiers for the identification of EGFR, ALK, BRAF and MET alterations directly from hematoxylin and eosin (H&E)-stained tissue using CanvOI 1.1, a digital pathology foundation model. Their performance was evaluated on an independent validation dataset of 968 NSCLC samples. The classifiers achieved AUCs of 0.87 for EGFR, 0.96 for ALK, 0.88 for BRAF and 0.83 for MET. Moreover, they demonstrated high accuracy in identifying cases lacking alterations. Our results highlight the potential of deep-learning tools for the detection of NSCLC biomarkers and specifically the identification of tumors without EGFR or ALK driver alterations, supporting more informed clinical decision-making.

Read the full article: Validation of histopathology-based deep learning algorithms for detection of actionable non-small cell lung cancer biomarkers | npj Precision Oncology

Affiliations

1. Division of Medical Oncology, Department of Internal Medicine, The Arthur G. James Comprehensive Cancer Center, The Ohio State University, Columbus, OH, USA

   Christian Rolfo & Francesco Drago

2. Institute of Pathology, Sheba Medical Center, Tel Aviv, Israel

   Efrat Ofek, Yoash Barak, Jonathan Weidenfeld, Razan Imad Haj, Yosef Molchanov, Alexander Loebel, Rinat Yacobi, Chen Mayer, Camila Avivi & Iris Barshack

3. Faculty of Medicine and Health Sciences, Tel Aviv University, Tel Aviv, Israel

   Yoash Barak, Damien Urban, Jair Bar, Dov Hershkoviz & Iris Barshack

4. Department of Pathology, Hoag Memorial Hospital Presbyterian, Newport Beach, CA, USA

   David R. Braxton & John S. Cupp

5. Hoag Family Cancer Institute, Newport Beach, CA, USA

   David R. Braxton

6. Imagene AI Ltd, Tel Aviv, Israel

   Nurit Paz-Yaacov, Assaf Avinoam, Jonathan Zalach, Addie Dvir & Inbal Gazy

7. Helmsley Cancer Institute, Shaare Zedek Medical Center, Jerusalem, Israel

   Nir Peled

8. Jusidman Cancer Center, Sheba Medical Center, Tel Aviv, Israel

   Damien Urban & Jair Bar

9. Department of Pathology, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel

   Dov Hershkoviz