Abbas Habibalahi1, Chandra Bala2, Alexandra Allende3, Ayad G Anwer4, Ewa M Goldys5. 1. ARC Centre of Excellence for Nanoscale Biophotonics, Macquarie University, North Ryde, NSW, 2109, Australia; School of Engineering, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, 2109, Australia; Graduate School of Biomedical Engineering, University of New South Wales, Sydney, 2032, NSW, Australia. Electronic address: a.habibalahi@unsw.edu.au. 2. Department of Ophthalmology, Faculty of Medicine and Health Sciences, Macquarie University, Sydney, NSW, 2109, Australia. 3. Douglass Hanly Moir Pathology, Macquarie Park, Sydney, NSW, 2113, Australia; Faculty of Medicine and Health Sciences, Macquarie University, Sydney, NSW, 2109, Australia. 4. ARC Centre of Excellence for Nanoscale Biophotonics, Macquarie University, North Ryde, NSW, 2109, Australia; Graduate School of Biomedical Engineering, University of New South Wales, Sydney, 2032, NSW, Australia. 5. ARC Centre of Excellence for Nanoscale Biophotonics, Macquarie University, North Ryde, NSW, 2109, Australia; Graduate School of Biomedical Engineering, University of New South Wales, Sydney, 2032, NSW, Australia. Electronic address: e.goldys@unsw.edu.au.
Abstract
PURPOSE: Diagnosing Ocular surface squamous neoplasia (OSSN) using newly designed multispectral imaging technique. METHODS: Eighteen patients with histopathological diagnosis of Ocular Surface Squamous Neoplasia (OSSN) were recruited. Their previously collected biopsy specimens of OSSN were reprocessed without staining to obtain auto fluorescence multispectral microscopy images. This technique involved a custom-built spectral imaging system with 38 spectral channels. Inter and intra-patient frameworks were deployed to automatically detect and delineate OSSN using machine learning methods. Different machine learning methods were evaluated, with K nearest neighbor and Support Vector Machine chosen as preferred classifiers for intra- and inter-patient frameworks, respectively. The performance of the technique was evaluated against a pathological assessment. RESULTS: Quantitative analysis of the spectral images provided a strong multispectral signature of a relative difference between neoplastic and normal tissue both within each patient (at p < 0.0005) and between patients (at p < 0.001). Our fully automated diagnostic method based on machine learning produces maps of the relatively well circumscribed neoplastic-non neoplastic interface. Such maps can be rapidly generated in quasi-real time and used for intraoperative assessment. Generally, OSSN could be detected using multispectral analysis in all patients investigated here. The cancer margins detected by multispectral analysis were in close and reasonable agreement with the margins observed in the H&E sections in intra- and inter-patient classification, respectively. CONCLUSIONS: This study shows the feasibility of using multispectral auto-fluorescence imaging to detect and find the boundary of human OSSN. Fully automated analysis of multispectral images based on machine learning methods provides a promising diagnostic tool for OSSN which can be translated to future clinical applications.
PURPOSE: Diagnosing Ocular surface squamous neoplasia (OSSN) using newly designed multispectral imaging technique. METHODS: Eighteen patients with histopathological diagnosis of Ocular Surface Squamous Neoplasia (OSSN) were recruited. Their previously collected biopsy specimens of OSSN were reprocessed without staining to obtain auto fluorescence multispectral microscopy images. This technique involved a custom-built spectral imaging system with 38 spectral channels. Inter and intra-patient frameworks were deployed to automatically detect and delineate OSSN using machine learning methods. Different machine learning methods were evaluated, with K nearest neighbor and Support Vector Machine chosen as preferred classifiers for intra- and inter-patient frameworks, respectively. The performance of the technique was evaluated against a pathological assessment. RESULTS: Quantitative analysis of the spectral images provided a strong multispectral signature of a relative difference between neoplastic and normal tissue both within each patient (at p < 0.0005) and between patients (at p < 0.001). Our fully automated diagnostic method based on machine learning produces maps of the relatively well circumscribed neoplastic-non neoplastic interface. Such maps can be rapidly generated in quasi-real time and used for intraoperative assessment. Generally, OSSN could be detected using multispectral analysis in all patients investigated here. The cancer margins detected by multispectral analysis were in close and reasonable agreement with the margins observed in the H&E sections in intra- and inter-patient classification, respectively. CONCLUSIONS: This study shows the feasibility of using multispectral auto-fluorescence imaging to detect and find the boundary of humanOSSN. Fully automated analysis of multispectral images based on machine learning methods provides a promising diagnostic tool for OSSN which can be translated to future clinical applications.
Authors: Nita G Valikodath; Tala Al-Khaled; Emily Cole; Daniel S W Ting; Elmer Y Tu; J Peter Campbell; Michael F Chiang; Joelle A Hallak; R V Paul Chan Journal: J AAPOS Date: 2021-06-01 Impact factor: 1.325
Authors: Abbas Habibalahi; Mahdieh Dashtbani Moghari; Jared M Campbell; Ayad G Anwer; Saabah B Mahbub; Martin Gosnell; Sonia Saad; Carol Pollock; Ewa M Goldys Journal: Redox Biol Date: 2020-05-12 Impact factor: 11.799
Authors: Michael J Bertoldo; Dave R Listijono; Wing-Hong Jonathan Ho; Angelique H Riepsamen; Dale M Goss; Dulama Richani; Xing L Jin; Saabah Mahbub; Jared M Campbell; Abbas Habibalahi; Wei-Guo Nicholas Loh; Neil A Youngson; Jayanthi Maniam; Ashley S A Wong; Kaisa Selesniemi; Sonia Bustamante; Catherine Li; Yiqing Zhao; Maria B Marinova; Lynn-Jee Kim; Laurin Lau; Rachael M Wu; A Stefanie Mikolaizak; Toshiyuki Araki; David G Le Couteur; Nigel Turner; Margaret J Morris; Kirsty A Walters; Ewa Goldys; Christopher O'Neill; Robert B Gilchrist; David A Sinclair; Hayden A Homer; Lindsay E Wu Journal: Cell Rep Date: 2020-02-11 Impact factor: 9.423
Authors: Jared M Campbell; Abbas Habibalahi; Saabah Mahbub; Martin Gosnell; Ayad G Anwer; Sharon Paton; Stan Gronthos; Ewa Goldys Journal: BMC Cancer Date: 2019-12-21 Impact factor: 4.430
Authors: Abbas Habibalahi; Alexandra Allende; Jesse Michael; Ayad G Anwer; Jared Campbell; Saabah B Mahbub; Chandra Bala; Minas T Coroneo; Ewa M Goldys Journal: Cancers (Basel) Date: 2022-03-21 Impact factor: 6.639