Sharif Amit

Sharif Amit
University of Nevada, Reno | UNR · Department of Computer Science and Engineering

PhD Candidate, Computer Science and Engineering

About

34
Publications
5,863
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
120
Citations
Introduction
My research interest lies in the intersection of Computer Vision, Deep Learning, and Medical Image Processing. Most of my research involves Supervised and Unsupervised algorithms for Image Classification, Semantic Segmentation, etc. Quite recently, I have been working on improving robustness, image synthesis, and image denoising using GAN on different modalities of Ophthalmological and Calcium imaging data. Website: https://sharifamit.com/
Additional affiliations
May 2021 - December 2021
Genentech
Position
  • Intern - Personalized Healthcare Imaging
August 2019 - present
University of Nevada, Reno
Position
  • Research Assistant
May 2017 - July 2019
Independent University, Bangladesh
Position
  • Researcher
Education
August 2019 - December 2020
University of Nevada, Reno
Field of study
  • Computer Science & Engineering
August 2019 - May 2023
University of Nevada, Reno
Field of study
  • Computer Science and Engineering
January 2013 - April 2017
BRAC University
Field of study
  • Computer Science & Engineering

Publications

Publications (34)
Preprint
Full-text available
Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and conducting supervised training tends to increase the complexity. With the introduction of Fully Convolutional...
Preprint
Full-text available
Retinal vessel segmentation contributes significantly to the domain of retinal image analysis for the diagnosis of vision-threatening diseases. With existing techniques the generated segmentation result deteriorates when thresholded with higher confidence value. To alleviate from this, we propose RVGAN, a new multi-scale generative architecture for...
Preprint
Full-text available
Recently deep learning has reached human-level performance in classifying arrhythmia from Electrocardiogram (ECG). However, deep neural networks (DNN) are vulnerable to adversarial attacks, which can misclassify ECG signals by decreasing the model's precision. Adversarial attacks are crafted perturbations injected in data that manifest the conventi...
Article
Full-text available
Cellular imaging instrumentation advancements as well as readily available optogenetic and fluorescence sensors have yielded a profound need for fast, accurate, and standardized analysis. Deep-learning architectures have revolutionized the field of biomedical image analysis and have achieved state-of-the-art accuracy. Despite these advancements, de...
Chapter
During long-duration spaceflights, some astronauts exhibit ocular structural and functional changes called SANS. Monitoring for SANS is challenging due to time and payload constraints that limit which tests can be performed and at what frequency. A virtual reality (VR)-based system that monitors relevant aspects of ocular properties through multimo...
Preprint
Full-text available
Ophthalmic images may contain identical-looking pathologies that can cause failure in automated techniques to distinguish different retinal degenerative diseases. Additionally, reliance on large annotated datasets and lack of knowledge distillation can restrict ML-based clinical support systems' deployment in real-world environments. To improve the...
Article
Full-text available
During spaceflight, astronauts can experience significantly higher levels of hemolysis. With future space missions exposing astronauts to longer periods of microgravity, such as missions to Mars, there will be a need to for better understanding this phenomenon. We have proposed that retinal fundus photography and deep learning may be utilized to he...
Article
Spaceflight associated neuro-ocular syndrome (SANS) refers to a unique collection of neuro-ophthalmic clinical and imaging findings observed in astronauts after long duration spaceflight. Current in-flight and post-flight imaging modalities (e.g., optical coherence tomography, orbital ultrasound, and funduscopy) have played an instrumental role in...
Article
Spaceflight Associated Neuro-Ocular Syndrome (SANS) refers to a unique collection of neuro-ophthalmic clinical and imaging findings that are observed in astronauts during long duration spaceflight. These findings include optic disc edema, posterior globe flattening, retinal nerve layer fiber thickening, optic nerve sheath distension, and hyperopic...
Article
Certain ocular imaging procedures such as fluoresceine angiography (FA) are invasive with potential for adverse side effects, while others such as funduscopy are non-invasive and safe for the patient. However, effective diagnosis of ophthalmic conditions requires multiple modalities of data and a potential need for invasive procedures. In this stud...
Chapter
High fidelity segmentation of both macro and microvascular structure of the retina plays a pivotal role in determining degenerative retinal diseases, yet it is a difficult problem. Due to successive resolution loss in the encoding phase combined with the inability to recover this lost information in the decoding phase, autoencoding based segmentati...
Preprint
Full-text available
Spear Phishing is a type of cyber-attack where the attacker sends hyperlinks through email on well-researched targets. The objective is to obtain sensitive information such as name, credentials, credit card numbers, or other crucial data by imitating oneself as a trustworthy website. According to a recent report, phishing incidents nearly doubled i...
Preprint
Full-text available
Electrocardiogram (ECG) acquisition requires an automated system and analysis pipeline for understanding specific rhythm irregularities. Deep neural networks have become a popular technique for tracing ECG signals, outperforming human experts. Despite this, convolutional neural networks are susceptible to adversarial examples that can misclassify E...
Preprint
Full-text available
In Fluorescein Angiography (FA), an exogenous dye is injected in the bloodstream to image the vascular structure of the retina. The injected dye can cause adverse reactions such as nausea, vomiting, anaphylactic shock, and even death. In contrast, color fundus imaging is a non-invasive technique used for photographing the retina but does not have s...
Chapter
Spectral Domain Optical Coherence Tomography (SD-OCT) is a demanding imaging technique by which diagnosticians detect retinal diseases. Automating the procedure for early detection and diagnosis of retinal diseases has been proposed in many intricate ways through the use of image processing, machine learning, and deep learning algorithms. Unfortuna...
Article
Full-text available
Fluorescein angiography (FA) is a procedure used to image the vascular structure of the retina and requires the insertion of an exogenous dye with potential adverse side effects. Currently, there is only one alternative non-invasive system based on Optical coherence tomography (OCT) technology, called OCT angiography (OCTA), capable of visualizing...
Chapter
Full-text available
Carrying out clinical diagnosis of retinal vascular degeneration using Fluorescein Angiography (FA) is a time consuming process and can pose significant adverse effects on the patient. Angiography requires insertion of a dye that may cause severe adverse effects and can even be fatal. Currently, there are no non-invasive systems capable of generati...
Preprint
Full-text available
Fluorescein Angiography (FA) is a technique that employs the designated camera for Fundus photography incorporating excitation and barrier filters. FA also requires fluorescein dye that is injected intravenously, which might cause adverse effects ranging from nausea, vomiting to even fatal anaphylaxis. Currently, no other fast and non-invasive tech...
Article
Full-text available
High-resolution Ca²⁺ imaging to study cellular Ca²⁺ behaviors has led to the creation of large datasets with a profound need for standardized and accurate analysis. To analyze these datasets, spatio-temporal maps (STMaps) that allow for 2D visualization of Ca²⁺ signals as a function of time and space are often used. Methods of STMap analysis rely o...
Preprint
Full-text available
COPYRIGHT © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrig...
Preprint
Full-text available
Carrying out clinical diagnosis of retinal vascular degeneration using Fluorescein Angiography (FA) is a time consuming process and can pose significant adverse effects on the patient. Angiography requires insertion of a dye that may cause severe adverse effects and can even be fatal. Currently, there are no non-invasive systems capable of generati...
Conference Paper
Diagnosing different retinal diseases from Spectral Domain Optical Coherence Tomography (SD-OCT) images is a challenging task. Different automated approaches such as image processing, machine learning and deep learning algorithms have been used for early detection and diagnosis of retinal diseases.Unfortunately, these are prone to error and computa...
Preprint
Full-text available
Diagnosing different retinal diseases from Spectral Domain Optical Coherence Tomography (SD-OCT) images is a challenging task. Different automated approaches such as image processing, machine learning and deep learning algorithms have been used for early detection and diagnosis of retinal diseases. Unfortunately, these are prone to error and comput...
Preprint
Full-text available
Diagnosing different retinal diseases from Spectral Domain Optical Coherence Tomography (SD-OCT) images is a challenging task. Different automated approaches such as image processing, machine learning and deep learning algorithms have been used for early detection and diagnosis of retinal diseases. Unfortunately, these are prone to error and comput...
Conference Paper
Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and conducting supervised training tends to increase the complexity. With the introduction of Fully Convolutional...
Preprint
Full-text available
Solving problems with Artificial intelligence in a competitive manner has long been absent in Bangladesh and Bengali-speaking community. On the other hand, there has not been a well structured database for Bengali Handwritten digits for mass public use. To bring out the best minds working in machine learning and use their expertise to create a mode...
Preprint
Full-text available
Recognizing Traffic Signs using intelligent systems can drastically reduce the number of accidents happening world-wide. With the arrival of Self-driving cars it has become a staple challenge to solve the automatic recognition of Traffic and Hand-held signs in the major streets. Various machine learning techniques like Random Forest, SVM as well as...
Preprint
Full-text available
Recognizing Traffic Signs using intelligent systems can drastically reduce the number of accidents happening worldwide. With the arrival of Self-driving cars it has become a staple challenge to solve the automatic recognition of Traffic and Hand-held signs in the major streets. Various machine learning techniques like Random Forest, SVM as well as...

Questions

Question (1)
Question
I'm working on a GAN with multiple scaled images that will be used for Generators and Discriminators. Is Lanczos better than Bicubic for downsampling the images for training in this kind of GAN setting ?

Network

Cited By

Projects

Projects (3)
Project
Our aim is to automate the Ophthalmological diagnosis and quantification of different modalities of opthalmological data by using supervised and unsupervised deep learning techniques.
Archived project
Building semantic segmentation models for images in the wild