PMID- 32053142 OWN - NLM STAT- MEDLINE DCOM- 20201113 LR - 20210213 IS - 2168-6173 (Electronic) IS - 2168-6165 (Print) IS - 2168-6165 (Linking) VI - 138 IP - 4 DP - 2020 Apr 1 TI - Assessment of a Segmentation-Free Deep Learning Algorithm for Diagnosing Glaucoma From Optical Coherence Tomography Scans. PG - 333-339 LID - 10.1001/jamaophthalmol.2019.5983 [doi] AB - IMPORTANCE: Conventional segmentation of the retinal nerve fiber layer (RNFL) is prone to errors that may affect the accuracy of spectral-domain optical coherence tomography (SD-OCT) scans in detecting glaucomatous damage. OBJECTIVE: To develop a segmentation-free deep learning (DL) algorithm for assessment of glaucomatous damage using the entire circle B-scan image from SD-OCT. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study at a single institution used data from SD-OCT images of eyes with glaucoma (perimetric and preperimetric) and normal eyes. The data set was randomly split at the patient level into a training (50%), validation (20%), and test data set (30%). Data were collected from March 2008 to April 2019, and analysis began April 2018. EXPOSURES: A convolutional neural network was trained to discriminate glaucomatous from normal eyes using the SD-OCT circle B-scan without segmentation lines. MAIN OUTCOMES AND MEASURES: The ability to discriminate glaucoma from healthy eyes was evaluated by comparing the area under the receiver operating characteristic curve and sensitivity at 80% or 95% specificity for the DL algorithm's predicted probability of glaucoma vs conventional RNFL thickness parameters given by SD-OCT software. The performance was also assessed in preperimetric glaucoma, as well as by visual field severity using Hodapp-Parrish-Anderson criteria. RESULTS: A total of 20 806 SD-OCT images from 1154 eyes of 635 individuals (612 [53%] with glaucoma and 542 normal eyes [47%]) were included. The mean (SD) age at SD-OCT scan was 70.8 (10.4) years in individuals with glaucoma and 55.8 (14.1) years in controls. There were 187 women (53.3%) in the glaucoma group and 165 (59.8%) in the control group. Of 612 eyes with glaucoma, 432 (70.4%) had perimetric and 180 (29.6%) had preperimetric glaucoma. The DL algorithm had a significantly higher area under the receiver operating characteristic curve than global RNFL thickness (0.96 vs 0.87; difference = 0.08 [95% CI, 0.04-0.12]) and each RNFL thickness sector for discriminating between glaucoma and controls (all P < .001). At 95% specificity, the DL algorithm (81%; 95% CI, 64%-97%) was more sensitive than global RNFL thickness (67%; 95% CI, 58%-76%). The areas under the receiver operating characteristic curve were also significantly greater for the DL algorithm compared with RNFL thickness at each stage of disease, especially preperimetric and mild perimetric glaucoma. CONCLUSIONS AND RELEVANCE: A segmentation-free DL algorithm performed better than conventional RNFL thickness parameters for diagnosing glaucomatous damage on OCT scans, especially in early disease. Future studies should investigate how such an approach contributes to diagnostic decisions when combined with other relevant clinical information, such as risk factors and perimetry results. FAU - Thompson, Atalie C AU - Thompson AC AD - Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center, Duke University, Durham, North Carolina. FAU - Jammal, Alessandro A AU - Jammal AA AD - Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center, Duke University, Durham, North Carolina. FAU - Berchuck, Samuel I AU - Berchuck SI AD - Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center, Duke University, Durham, North Carolina. AD - Department of Statistical Science and Forge, Duke University, Durham, North Carolina. FAU - Mariottoni, Eduardo B AU - Mariottoni EB AD - Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center, Duke University, Durham, North Carolina. FAU - Medeiros, Felipe A AU - Medeiros FA AD - Vision, Imaging and Performance Laboratory (VIP), Duke Eye Center, Duke University, Durham, North Carolina. LA - eng GR - K23 EY030897/EY/NEI NIH HHS/United States GR - R01 EY029885/EY/NEI NIH HHS/United States PT - Journal Article PT - Research Support, N.I.H., Extramural PL - United States TA - JAMA Ophthalmol JT - JAMA ophthalmology JID - 101589539 SB - IM CIN - JAMA Ophthalmol. 2020 Apr 1;138(4):339-340. PMID: 32053135 MH - Adult MH - Aged MH - Aged, 80 and over MH - *Algorithms MH - Cross-Sectional Studies MH - *Deep Learning MH - Female MH - Glaucoma, Open-Angle/*diagnostic imaging MH - Gonioscopy MH - Humans MH - Intraocular Pressure MH - Male MH - Middle Aged MH - Nerve Fibers/pathology MH - ROC Curve MH - Retinal Ganglion Cells/pathology MH - Slit Lamp Microscopy MH - *Tomography, Optical Coherence MH - Visual Field Tests MH - Visual Fields PMC - PMC7042899 COIS- Conflict of Interest Disclosures: Dr Thompson is a recipient of the Heed Ophthalmic Fellowship. Dr Jammal reports other support from Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior outside the submitted work. Dr Medeiros reports grants from National Institutes of Health/National Eye Institute, Carl Zeiss Meditec, and Google during the conduct of the study; nonfinancial support (equipment) from Heidelberg Engineering during the conduct of the study; and personal fees from Bausch + Lomb, Merck, Sensimed, Topcon, Reichert, Novartis, Allergan, Galimedix Therapeutics, Stealth BioTherapeutics, and Biogen outside the submitted work. No other disclosures were reported. EDAT- 2020/02/14 06:00 MHDA- 2020/11/18 06:00 PMCR- 2021/02/13 CRDT- 2020/02/14 06:00 PHST- 2020/02/14 06:00 [pubmed] PHST- 2020/11/18 06:00 [medline] PHST- 2020/02/14 06:00 [entrez] PHST- 2021/02/13 00:00 [pmc-release] AID - 2761537 [pii] AID - eoi190100 [pii] AID - 10.1001/jamaophthalmol.2019.5983 [doi] PST - ppublish SO - JAMA Ophthalmol. 2020 Apr 1;138(4):333-339. doi: 10.1001/jamaophthalmol.2019.5983.