Research Projects - Collaberations

Malaria Project at NIH

This project is mentored by Dr. Stefan Jaeger and it is one of the projects that I'm currently working on in my post- doctorate work.

We are developing automated pipelines and smartphone applications for malaria screening.

Contribution:

Developed a novel pipeline, called “RBCNet”, for detecting red blood cells and white blood cells for malaria screening in thin blood smears. This work is recently accepted in the Journal of Biomedical and Health Informatics https://github.com/nlm-malaria/RBCNet.
Propose a new pipeline for detecting and identifying parasites (plasmodium falciparum and plasmodium vivax) in thick blood smear microscopy images, publication is in progress.

Analyzing Brain Dura Mater Microvasculature from Epifluorescence Imagery Using Machine and Deep Learning at the University of Missouri-Columbia

This project is supervised by Prof. Kannappan Palaniappan during my PhD study through collaboration with Physiologists from the Harry S. Truman Memorial Veterans Hospital and the National Center for Gender Physiology, University of Missouri-Columbia

Contribution:

Developed multiple microvasculature segmentation methodologies that are applied to segment blood vessels in epifluorescence images of mice dura mater and retinal imagery.

Understanding brain circuits containing branchiomotor neurons that control jaw movements in vertebrates at the University of Missouri-Columbia

This project is supervised by Prof. Kannappan Palaniappan during my PhD study through collaboration with Dr. Chandrasekhar in Bond life science center.

Contribution:

Developed an automated image analysis system to extract deformable motion features using video microscopy, for rapid and accurate detection of jaw movement termed gape or mouth opening.

Grading Cornea NeoVascularization (CNV) Disease at the University of Missouri-Columbia

This project is supervised by Prof. Kannappan Palaniappan during my PhD study through collaboration with Dr. shyam chaurasia from Department of Veterinary Medicine and Surgery and Dr. Rajiv R. Mohan from the Medical School.

Contribution:

Developed a regression network using random forest classifier and a robust set of vessel specific features to detect and grade the progress of CNV. The objectives of this research is to examine the CNV grade from in-growthed vessels. https://github.com/CIVA-Lab/CNV

Detecting Small Roosting Birds in IR Drone videos at the University of Missouri-Columbia

This project is supervised by Prof. Kannappan Palaniappan during my PhD study through collaboration with Dr. Michael Byrne from the College of Agriculture, Food, and Natural Resources in University of Missouri - Columbia and another group from Texas parks and wildlife.

Contribution:

Developed a robust pipeline to detect wild turkeys in drone-based thermal IR videos. Automating such process provides a fast and reliable way to survey wild turkeys for wildlife management and conservation. See paper 5 in publications.

Segmention, classification, and quantifiquaton of fondoscopy images (Retinal Imagery)

Worked with three open-access datasets: DRIVE, STARE, and CHASE

Contribution:

Developed a segmentation algorithm that outperform most of the state-of-the-artwork results in segmenting retinal blood vessels in two publications. The image attached is my score in the DRIVE challenge, got the 3'rd place in that challenge in Feb 2019.

Automatic classification

and segmentation of Human epithelial

(HEp-2) cell specimens

Contribution:

we consider automatic cell segmentation and classification

using spatial and texture pattern features and random

forest classifiers. In this paper, we summarize our efforts

in classification and segmentation tasks proposed

in ICPR 2016 contest.

Plant and Leaf Segmentation

Participating in the contest of plant phenotyping.

Contribution:

Developed a robust and fast unsupervised approach for plant extraction and leaf detection. K-means-based mask (of the pot) followed by Expectation-Maximization (EM) algorithm is adopted to estimate a mixture model for identifying the foreground area for the plant.

Page updated

Google Sites

Report abuse