Lung cancer is one of the most prevalent and lethal cancers. To improve health outcomes while reducing health care burden, it becomes crucial to move toward early detection and cost-effective workflows. Currently, there is no method for the on-site rapid histologic feedback on biopsies taken in diagnostic, endoscopic, or surgical procedures. Higher harmonic generation (HHG) microscopy is a laser-based technique that provides images of unprocessed tissue. In this study, we report the feasibility of an HHG portable microscope in the clinical workflow in terms of acquisition time, image quality, and diagnostic accuracy in suspected pulmonary and pleural malignancy. One hundred nine biopsies of 47 patients were imaged and a biopsy overview image was provided within a median acquisition time of 6 minutes after excision. The assessment by pathologists and an artificial intelligence algorithm showed that image quality was sufficient for a malignancy or nonmalignancy diagnosis in 97% of the biopsies, and 87% of the HHG images were correctly scored by the pathologists. HHG is therefore an excellent candidate to provide a rapid pathology outcome on biopsy samples, enabling immediate diagnosis and (local) treatment.
Keywords: deep learning; higher-harmonic generation microscopy; lung biopsy; lung cancer; multiinstance learning; multiphoton excited autofluorescence.
Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.