ABSTRACT
INTRODUCTION: Deep Learning (DL) and Artificial Intelligence (AI) have become widespread due to the advanced technologies and availability of digital data. Supervised learning algorithms have shown human-level performance or even better and are better feature extractor-quantifier than unsupervised learning algorithms. To get huge dataset with good quality control, there is a need of an annotation tool with a customizable feature set. This paper evaluates the viability of having an in house annotation tool which works on a smartphone and can be used in a healthcare setting. METHODS: We developed a smartphone-based grading system to help researchers in grading multiple retinal fundi. The process consisted of designing the flow of user interface (UI) keeping in view feedback from experts. Quantitative and qualitative analysis of change in speed of a grader over time and feature usage statistics was done. The dataset size was approximately 16,000 images with adjudicated labels by a minimum of 2 doctors. Results for an AI model trained on the images graded using this tool and its validation over some public datasets were prepared. RESULTS: We created a DL model and analysed its performance for a binary referrable DR Classification task, whether a retinal image has Referrable DR or not. A total of 32 doctors used the tool for minimum of 20 images each. Data analytics suggested significant portability and flexibility of the tool. Grader variability for images was in favour of agreement on images annotated. Number of images used to assess agreement is 550. Mean of 75.9% was seen in agreement. CONCLUSION: Our aim was to make Annotation of Medical imaging easier and to minimize time taken for annotations without quality degradation. The user feedback and feature usage statistics confirm our hypotheses of incorporation of brightness and contrast variations, green channels and zooming add-ons in correlation to certain disease types. Simulation of multiple review cycles and establishing quality control can boost the accuracy of AI models even further. Although our study aims at developing an annotation tool for diagnosing and classifying diabetic retinopathy fundus images but same concept can be used for fundus images of other ocular diseases as well as other streams of medical science such as radiology where image-based diagnostic applications are utilised.
ABSTRACT
IMPORTANCE: Optic disc pit with associated maculopathy is a known entity. However, controversy exists regarding the source of subretinal fluid in these cases. In our series, we attempted to analyze the morphologic changes seen in the optic disc pit and evaluate the source of subretinal fluid. OBSERVATIONS: In this prospective observational case series of 4 patients with optic pit maculopathy, a complete ophthalmic evaluation, with fundus color photography and enhanced depth imaging spectral-domain optical coherence tomography scanning of the optic disc, was carried out between January 2013 and November 2013. The optical coherence tomographic section was mapped with infrared image and color photography, and the characteristics of the retina and optic nerve head were analyzed. All the cases had outer layer retinal schisis; 2 of them had associated serous macular detachment while inner retinal schisis was present in 3 cases. A hyporeflective tract was observed in our study connecting the retinal schisis cavity and gap in the lamina cribrosa corresponding to the optic pit. CONCLUSIONS AND RELEVANCE: In our study, we demonstrated the connectivity between retinal schisis and the gap in the lamina cribrosa present in the optic disc pit, supporting the hypothesis of cerebrospinal fluid as the source of subretinal fluid.
