Kaveri A. Thakoor

TL;DR: In this paper, convolutional neural network (CNN) models were used for detection of glaucoma based upon optical coherence tomography (OCT) retinal nerve fiber layer (RNFL) probability maps.

TL;DR: This work develops CNN architectures that demonstrate robust detection of glaucoma in optical coherence tomography images and test with concept activation vectors (TCAVs) to infer what image concepts CNNs use to generate predictions, and compares TCAV results to eye fixations of clinicians to identify common decision-making features used by both AI and human experts.

TL;DR: In this article , a simple anatomical artifact model based upon known anatomical variations was introduced to help distinguish these artifacts from actual glaucomatous damage, and the model helps account for the success of an AI deep learning model on the retinal nerve fiber layer (RNFL) p-map.

TL;DR: A new near‐real‐time method for converting earthquake source parameters into ground motion (GM) at locations across the west coast of the United States is presented, expected to improve the overall utility of EEW alerts by providing end users with estimates of predicted local GM hazard.

TL;DR: An automated/objective method that can automatically and objectively evaluate aS-aF agreement with a direct comparison of abnormal regions of function and structure for glaucoma diagnosis can overcome subjectivity in this assessment.