Photon Absorption Remote Sensing Virtual Histopathology: Diagnostic Equivalence to Gold-Standard H&E Staining in Skin Cancer Excisional Biopsies
Benjamin R. Ecclestone, James E. D. Tweel, Marie Abi Daoud, Hager Gaouda, Deepak Dinakaran, Michael P. Wallace, Ally Khan Somani, Gilbert Bigras, John R. Mackey, Parsin Haji Reza
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
Photon Absorption Remote Sensing (PARS) enables label-free imaging of subcellular morphology by observing biomolecule specific absorption interactions. Coupled with deep-learning, PARS produces label-free virtual Hematoxylin and Eosin (H&E) stained images in unprocessed tissues. This study evaluates the diagnostic performance of these PARS-derived virtual H&E images in benign and malignant excisional skin biopsies, including Squamous (SCC), Basal (BCC) Cell Carcinoma, and normal skin. Sixteen unstained formalin-fixed paraffin-embedded skin excisions were PARS imaged, virtually H&E stained, then chemically stained and imaged at 40x. Seven fellowship trained dermatopathologists assessed all 32 images in a masked randomized fashion. Concordance analysis indicates 95.5% agreement between primary diagnoses rendered on PARS versus H&E images (Cohen's k=0.93). Inter-rater reliability was near-perfect for both image types (Fleiss' k=0.89 for PARS, k=0.80 for H&E). For subtype classification, agreement was near-perfect 91% (k=0.73) for SCC and was perfect for BCC. When assessing malignancy confinement (e.g., cancer margins), agreement was 92% between PARS and H&E (k=0.718). During assessment dermatopathologists could not reliably distinguish image origin (PARS vs. H&E), and diagnostic confidence was equivalent between the modalities. Inter-rater reliability for PARS virtual H&E was consistent with reported benchmarks for histologic evaluation. These results indicate that PARS virtual histology may be diagnostically equivalent to traditional H&E staining in dermatopathology diagnostics, while enabling assessment directly from unlabeled, or unprocessed slides. In turn, the label-free PARS virtual H&E imaging workflow may preserve tissue for downstream analysis while producing data well-suited for AI integration potentially accelerating and enhancing the accuracy of skin cancer diagnostics.