13 March 2024Diagnostic evaluation and clinical concordance analysis of label-free photon absorption remote sensing virtual H&E staining in breast core biopsy samples
James Tweel,1 Benjamin R. Ecclestonehttps://orcid.org/0000-0003-1726-8161,1 Hager Gaouda,2 Deepak Dinakaran,3 Michael P. Wallace,1 Gilbert Bigras,4 John R. Mackey,3 Parsin Haji Reza1
1Univ. of Waterloo (Canada) 2Illumisonics Inc. (Canada) 3illumiSonics Inc. (Canada) 4Univ. of Alberta (Canada)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
We compared the diagnostic accuracy of label-free Photon Absorption Remote Sensing (PARS) virtual hematoxylin and eosin (H&E) staining to conventional histology in breast cancer core needle biopsy (CNB) samples. Matching PARS virtual H&E and real H&E images were acquired for seven breast CNB samples representing a spectrum of histologies. Seven board certified pathologists, blinded to the image origin, provided diagnostic evaluations of each sample. A kappa concordance analysis was performed and revealed 'substantial' agreement (kappa > 0.6) between the PARS and H&E pairs in primary diagnosis. Pathologists were unable to distinguish the true origin of the PARS virtual H&E images.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
James Tweel, Benjamin R. Ecclestone, Hager Gaouda, Deepak Dinakaran, Michael P. Wallace, Gilbert Bigras, John R. Mackey, Parsin Haji Reza, "Diagnostic evaluation and clinical concordance analysis of label-free photon absorption remote sensing virtual H&E staining in breast core biopsy samples," Proc. SPIE PC12831, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XXII, PC1283106 (13 March 2024); https://doi.org/10.1117/12.3001158