John P. Campbell - US grants

PROJECT SUMMARY The long-term goal of this project is to determine whether optical coherence tomography (OCT) and OCT angiography (OCTA) might lead more accurate and objective diagnosis, earlier intervention, and improved outcomes in retinopathy of prematurity (ROP). International consensus and National Institute of Health (NIH) funded clinical trials over the last 30 years have defined the phenotypic classifications, natural history, prognosis, and management of ROP. However, it is well established that due to the subjectivity of the ophthalmoscopic examination, and systematic bias between examiners, there is significant variation in treatment of the most severe forms of ROP in the real world. This leads to both under-treatment (and poor outcomes due to retinal detachment) and over-treatment (exposing neonates to the ocular and systemic risks of treatment). Roughly 20,000 babies per year develop retinal detachments (RD) due to ROP and there is strong evidence that most of these are preventable. In adult retinal vascular diseases, most notably diabetic retinopathy (DR), OCT and OCTA can detect and quantify disease features such as diabetic macular edema (DME) and retinal neovascularization (NV) before they are noted clinically, enabling earlier treatment and reducing the risk of blindness from RD. However, evaluating the use of this technology in neonates requires high speed and portable technology, and the commercially available handheld OCTs are too slow for ultra-widefield (UWF) OCT and OCTA imaging. Several groups (including our own) have published preliminary results using prototype 100 to 200 kHz swept- source (SS) OCT systems, however consistent data acquisition remains challenging due to the lack of fixation and subsequent motion in an awake neonate, which has limited the evaluation of the potential benefits of the technology in this population. Recently, there has been much interest in using artificial intelligence (AI) (specifically deep learning), which relies on high speed graphics processing units (GPUs) to provide real time OCT image processing, segmentation, and tracking. This application addresses 2 fundamental gaps in knowledge: (1) Can we overcome the technical challenges through the development of a faster ultrawide-field view SS-OCT system coupled with a GPU-enabled DL software system to enable consistent data acquisition in neonates? (2) Would quantitative objective metrics of ROP improve objectivity of ROP diagnosis and detect subclinical signs of disease progression which may enable earlier intervention and improved outcomes in the future. By leveraging our institution?s OCT, AI, and ROP expertise, we will address these questions in three specific aims: (1) Develop an ultra-high speed, handheld, panoramic ultra-widefield OCT/OCTA system. (2) Develop real time GPU accelerated intelligent image acquisition software. (3) Evaluate the clinical significance OCT derived biomarkers. Successful translation of this technology to the ROP population could improve the accuracy and objectivity of ROP diagnosis, and lead to earlier intervention and improved outcomes in patients with severe ROP.

Project Summary The long-term goal of this project is to establish a quantitative framework for retinopathy of prematurity (ROP) care based on clinical, imaging, genetic, and informatics principles. In the previous grant period, we have developed artificial intelligence methods for ROP diagnosis, but real-world adoption has been limited by lack of prospective validation and by perception of these systems as ?black boxes? that do not explain their rationale for diagnosis. Furthermore, although biomedical research data are being generated at an enormous pace, much less work has been done to integrate disparate scientific findings across the spectrum from genomics to imaging to clinical medicine. This renewal will address current gaps in knowledge in these areas. Our overall hypotheses are that developing a quantitative framework for ROP care using artificial intelligence and analytics will improve clinical disease management, that building ?explainable? artificial intelligence systems will enhance clinical acceptance and educational opportunities, and that analysis of relationships among clinical, imaging, environmental, and genetic findings, in ROP will improve understanding of disease pathogenesis and risk. These hypotheses will be tested using three Specific Aims: (1) Evaluation performance of an artificial intelligence system for ROP diagnosis and screening prospectively. This will include: (a) recruit a target of over 2000 eye exams including wide-angle retinal images from 375 subjects at 5 centers, (b) optimize an image quality detection algorithm we have recently developed, and (c) analyze system accuracy for ROP diagnosis and screening (using a novel quantitative vascular severity scale). (2) Improve the interpretability of our existing artificial intelligence methods for ROP diagnosis. This will include: (a) increase ?explainability? of systems by combining deep learning with traditional feature extraction methods, (b) develop neural networks to identify changes between serial images, and (c) evaluate these methods through systematic feedback by experts. (3) Develop integrated models for ROP pathogenesis and risk. This will include: (a) build and improve ROP risk prediction models based on clinical, image, and demographic features, and (b) integrate genetic, imaging, clinical, and environmental variables through genetic risk prediction by machine learning, by investigating casual relationships with genetic variants and genetic risk scores, and by incorporating SNP associations with gene expression measurements to identify functional genes of ROP. Ultimately, these studies will significantly reduce barriers to adoption of technologies such as artificial intelligence for clinicians, and will demonstrate a prototype for health information management which combines genotypic and phenotypic data. This project will be performed by a multi-disciplinary team of investigators who have worked successfully together for nearly 10 years, and who have expertise in ophthalmology, biomedical informatics, computer science, computational biology, ophthalmic genetics, genetic analysis, and statistical genetics.