no code implementations • 4 Jan 2023 • Aashis Khanal, Rolando Estrada
This paper is a follow-up paper on vessel topology estimation and extraction, we use the extracted topology to perform A-V state-of-the-art Artery-Vein classification, AV ratio calculation, and vessel tortuosity measurement, all fully automated.
no code implementations • 4 Feb 2022 • Aashis Khanal, Saeid Motevali, Rolando Estrada
We also performed several ablation studies to separately verify the importance of the segmentation and AV labeling steps of our proposed method.
no code implementations • 1 Oct 2021 • Saeid Motevali, Aashis Khanal, Rolando Estrada
The optic disc is a crucial diagnostic feature in the eye since changes to its physiognomy is correlated with the severity of various ocular and cardiovascular diseases.
no code implementations • 18 Feb 2021 • Bradley T. Baker, Aashis Khanal, Vince D. Calhoun, Barak Pearlmutter, Sergey M. Plis
We introduce an innovative, communication-friendly approach for training distributed DNNs, which capitalizes on the outer-product structure of the gradient as revealed by the mechanics of auto-differentiation.
1 code implementation • 13 Jul 2020 • Mehdi Mousavi, Aashis Khanal, Rolando Estrada
With AIP, it is trivial to capture the same image under different conditions (e. g., fidelity, lighting, etc.)
Ranked #1 on Depth Estimation on DIODE
4 code implementations • 19 Mar 2019 • Aashis Khanal, Rolando Estrada
To address this limitation, we propose a novel, stochastic training scheme for deep neural networks that better classifies the faint, ambiguous regions of the image.