PMID- 35220077 OWN - NLM STAT- PubMed-not-MEDLINE LR - 20231020 IS - 1879-0534 (Electronic) IS - 0010-4825 (Linking) VI - 143 DP - 2022 Apr TI - Clinical explainable differential diagnosis of polypoidal choroidal vasculopathy and age-related macular degeneration using deep learning. PG - 105319 LID - S0010-4825(22)00111-1 [pii] LID - 10.1016/j.compbiomed.2022.105319 [doi] AB - BACKGROUND: This study aims to achieve an automatic differential diagnosis between two types of retinal pathologies with similar pathological features - Polypoidal choroidal vasculopathy (PCV) and wet age-related macular degeneration (AMD) from volumetric optical coherence tomography (OCT) images, and identify clinically-relevant pathological features, using an explainable deep-learning-based framework. METHODS: This is a retrospective study with data from a cross-sectional cohort. The OCT volume of 73 eyes from 59 patients was included in this study. Disease differentiation was achieved through single-B-scan-based classification followed by a volumetric probability prediction aggregation step. We compared different labeling strategies with and without identifying pathological B-scans within each OCT volume. Clinical interpretability was achieved through normalized aggregation of B-scan-based saliency maps followed by maximum-intensity-projection onto the en face plane. We derived the PCV score from the proposed differential diagnosis framework with different labeling strategies. The en face projection of saliency map was validated with the pathologies identified in Indocyanine green angiography (ICGA). RESULTS: Model trained with both labeling strategies achieved similar level differentiation power (>90%), with good correspondence between pathological features detected from the projected en face saliency map and ICGA. CONCLUSIONS: This study demonstrated the potential clinical application of non-invasive differential diagnosis using AI-driven OCT-based analysis, with minimal requirement of labeling efforts, along with clinical explainability achieved through automatically detected disease-related pathologies. CI - Copyright (c) 2022 Elsevier Ltd. All rights reserved. FAU - Ma, Da AU - Ma D AD - Wake Forest University School of Medicine, Medical Center Boulevard, Winston-Salem, NC, USA; School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada. Electronic address: dma@wakehealth.edu. FAU - Kumar, Meenakshi AU - Kumar M AD - Shri Bhagwan Mahavir Vitreoretinal Service, Medical Research Foundation, Sankara Nethralaya, Chennai, India. FAU - Khetan, Vikas AU - Khetan V AD - Shri Bhagwan Mahavir Vitreoretinal Service, Medical Research Foundation, Sankara Nethralaya, Chennai, India. FAU - Sen, Parveen AU - Sen P AD - Shri Bhagwan Mahavir Vitreoretinal Service, Medical Research Foundation, Sankara Nethralaya, Chennai, India. FAU - Bhende, Muna AU - Bhende M AD - Shri Bhagwan Mahavir Vitreoretinal Service, Medical Research Foundation, Sankara Nethralaya, Chennai, India. FAU - Chen, Shuo AU - Chen S AD - School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada. FAU - Yu, Timothy T L AU - Yu TTL AD - School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada. FAU - Lee, Sieun AU - Lee S AD - School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada; Mental Health & Clinical Neurosciences, School of Medicine, University of Nottingham, Nottingham, United Kingdom. FAU - Navajas, Eduardo V AU - Navajas EV AD - Department of Ophthalmology & Visual Sciences, The University of British Columbia, Vancouver, BC, Canada; University of British Columbia Vancouver General Hospital, Eye Care Centre, Vancouver, BC, Canada. FAU - Matsubara, Joanne A AU - Matsubara JA AD - Department of Ophthalmology & Visual Sciences, The University of British Columbia, Vancouver, BC, Canada; University of British Columbia Vancouver General Hospital, Eye Care Centre, Vancouver, BC, Canada. FAU - Ju, Myeong Jin AU - Ju MJ AD - Department of Ophthalmology & Visual Sciences, The University of British Columbia, Vancouver, BC, Canada; University of British Columbia Vancouver General Hospital, Eye Care Centre, Vancouver, BC, Canada; School of Biomedical Engineering, University of British Columbia, BC, Canada. FAU - Sarunic, Marinko V AU - Sarunic MV AD - School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada; Institute of Ophthalmology, University College London, London, UK; Department of Medical Physics and Biomedical Engineering, University College London, United Kingdom. FAU - Raman, Rajiv AU - Raman R AD - Shri Bhagwan Mahavir Vitreoretinal Service, Medical Research Foundation, Sankara Nethralaya, Chennai, India. Electronic address: rajivpgraman@gmail.com. FAU - Beg, Mirza Faisal AU - Beg MF AD - School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada. Electronic address: faisal-lab@sfu.ca. LA - eng PT - Journal Article DEP - 20220214 PL - United States TA - Comput Biol Med JT - Computers in biology and medicine JID - 1250250 SB - IM OTO - NOTNLM OT - Age-related macular degeneration OT - Convolutional Neural Network OT - Deep learning OT - Differential diagnosis OT - Explainable AI model OT - Optical coherence tomography OT - Polypoidal choroidal vasculopathy EDAT- 2022/02/28 06:00 MHDA- 2022/02/28 06:01 CRDT- 2022/02/27 20:33 PHST- 2021/11/26 00:00 [received] PHST- 2022/02/11 00:00 [revised] PHST- 2022/02/11 00:00 [accepted] PHST- 2022/02/28 06:01 [medline] PHST- 2022/02/28 06:00 [pubmed] PHST- 2022/02/27 20:33 [entrez] AID - S0010-4825(22)00111-1 [pii] AID - 10.1016/j.compbiomed.2022.105319 [doi] PST - ppublish SO - Comput Biol Med. 2022 Apr;143:105319. doi: 10.1016/j.compbiomed.2022.105319. Epub 2022 Feb 14.