Olives dataset: Ophthalmic labels for investigating visual eye semantics
M Prabhushankar, K Kokilepersaud… - Advances in …, 2022 - proceedings.neurips.cc
Clinical diagnosis of the eye is performed over multifarious data modalities including scalar
clinical labels, vectorized biomarkers, two-dimensional fundus images, and three …
clinical labels, vectorized biomarkers, two-dimensional fundus images, and three …
Clinically labeled contrastive learning for oct biomarker classification
K Kokilepersaud, ST Corona… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
This article presents a novel positive and negative set selection strategy for contrastive
learning of medical images based on labels that can be extracted from clinical data. In the …
learning of medical images based on labels that can be extracted from clinical data. In the …
Probing the purview of neural networks via gradient analysis
J Lee, C Lehman, M Prabhushankar, G AlRegib - IEEE Access, 2023 - ieeexplore.ieee.org
We analyze the data-dependent capacity of neural networks and assess anomalies in inputs
from the perspective of networks during inference. The notion of data-dependent capacity …
from the perspective of networks during inference. The notion of data-dependent capacity …
Patient aware active learning for fine-grained oct classification
This paper considers making active learning more sensible from a medical perspective. In
practice, a disease manifests itself in different forms across patient cohorts. Existing …
practice, a disease manifests itself in different forms across patient cohorts. Existing …
Clinical trial active learning
This paper presents a novel approach to active learning that takes into account the non-
independent and identically distributed (non-iid) structure of a clinical trial setting. There …
independent and identically distributed (non-iid) structure of a clinical trial setting. There …
TrajPRed: Trajectory Prediction With Region-Based Relation Learning
C Zhou, G AlRegib, A Parchami… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Forecasting human trajectories in traffic scenes is critical for safety within mixed or fully
autonomous systems. Human future trajectories are driven by two major stimuli, social …
autonomous systems. Human future trajectories are driven by two major stimuli, social …
Generation of a text description of weakly structured optical coherence tomography images
A Zhigalov, A Lositsky, L Grishina… - ITM Web of …, 2024 - itm-conferences.org
Computer vision methods help to automate and improve processes in the field of medicine.
In the field of ophthalmology, computer vision algorithms can be used to analyze images …
In the field of ophthalmology, computer vision algorithms can be used to analyze images …