Architecture for Automatic GLaucoma Diagnosis and Its Genetic

Architecture for Automatic GLaucoma Diagnosis and Its Genetic Association Study through Medical Image Inform. Atics (AGLAIA) Jimmy Liu Jiang 1, Zhang Zhuo 1, Wong Wing Kee 1, Tan Ngan Meng 1, Yin Feng Shou 1, Lee Benghai 1, Cheng Jun 1, Wong Tien Yin 2 1: Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore 2: Singapore Eye Research Institute 1

AGLAIA Single statement A system for the automated detection of glaucoma from multiple image features of retinal images with possible genetic analysis.

Glaucoma Has No Cure! § Glaucoma § Irreversible loss of optic nerves § Leading to blindness § 5. 7 million glaucoma blind (total 38 million blind in the world) § BUT: glaucoma can be slowed if detected early § Vision loss (functional) § Optic nerve damage (imaging)

Optic Nerve Damage Precedes Vision Loss No Glaucoma Early Late Stage Optic Nerve Damaged Pictures from NIH Severe Vision Loss

Measure Optic Nerve Damage from Retinal Image - CDR § CDR (Cup to Disc Ratio) value is an important indicator for Glaucoma § Automatic CDR measurement § Saving clinician’s time § Results reproducible § Ideal for mass screening Cup Disc

AGLAIA § Step 1: Disc segmentation § Step 2: Boundary smoothing of the detected disc § Step 3: Cup segmentation § Step 4: Boundary smoothing of the detected cup § Step 5: Intelligent Fusion

AGLAIA Framework

13 Image cues used in AGLAIA aims to provide a multi-modality system that captures globally a range of parameter that is indicative of early glaucoma damage. AGLAIA will automatically measure and assess the following features objectively and quantitatively, features which are currently evaluated subjectively by glaucoma specialist in clinical practice: Cup-to-disc ratio (CDR) – further refinement will be made based on initial algorithms developed in ARGALI Disc hemorrhage (DH) Thinning of the NRR (Neuro. Retinal Rim) Notching of the NRR Compliance of NRR width by ‘ISNT Rule’ (inferior≥superior≥nasal≥temporal) Inter-eye asymmetry Parapapillary atrophy (PPA) Blood vessel pattern analysis Blood vessel kink analysis Tilted Disc - quantify the degree of tilting based on the disc contour Disc Size - automatically classify disc size to "large, medium or small" categories based on automatic disc measurement Gradeability – analyze the image and determine gradeability Check the presence of RNFL (Retinal Nerve Fiber Layer) defect.

Image Datasets § Datasets used for testing § Retinal Vessel and Glaucoma Subtype Study (RVGSS) § 65 glaucoma images § Singapore Indian Chinese Cohort (SICC) § 224 non-glaucoma images § Clinical CDR provided

Test Result Summary § Specificity § 0. 88 § Sensitivity § 0. 95 § Average absolute CDR error (wrt clinical CDR) § 0. 14

AGLAIA Market Potential § The Technology can be readily implemented in currently available instruments for ocular screening without extensive modifications. § The Technology could potentially be of interest to ocular instrument makers to incorporate the Technology into their equipment, and to health institutions such as clinics and hospitals for glaucoma screening.

AGLALI CDR Absolute Error Distribution Error Interval

Receiver Operating Characteristic (ROC) Curve AUC Sensitivity Specificity ICC Maximum Std. Deviation 0. 94 0. 954 0. 88 0. 553 0. 65 0. 12