Research

I have been working on Master's thesis from August 2023-Present on Automation of Lumbar Puncture. My work is on 3D reconstruction of Lumbar vertebrae from Ultrsound Images, and point cloud registration to a ground truth for obtaining a precise localization for needle entry point. We also aim to develop a automatic needle insertion manipulator with force feedback for accurate insertion at desired locations.

• Created an advanced image processing pipeline to pinpoint precise needle entry sites in lumbar puncture procedures.

• Processed ultrasound images using OpenCV to segment regions in lumbar data.

• Developed a state-of-the-art computer vision algorithm that harnesses ultrasound images and the probe poses to generate a 3D point cloud using PCL libraries in Python.

• Winner of People’s Choice Award at the 2024 Graduate Research Innovation Exchange GRIE for poster presentation on ”Image Guidance and Needle Trajectory Planning for Lumbar Puncture using Ultrasound Images."

• Extending the MRI-US registration process to 3D-3D space using Iterative Closest Point (ICP) algorithm

• Developing needle navigation and insertion algorithm for a manipulator with force feedback

Projects

Implemented advanced Multi-State Constraint Kalman Filter (MSCKF) following a paper for robust sensor fusion

Implemented NeRF pipeline following this NeRF paper.

Reconstructed a 3D scene and simultaneously extracted camera pose from given camera correspondences using Non/Linear triangulation, Non/Linear PnP and Bundle Adjustment for optimization.

Stitched images having overlapping features to create a panorama using feature matching, ANMS, homography estimation, RANSAC.

Implemented algorithm to automate estimation of camera intrinsics using mathematical model proposed by Zhengyou Zhang.