Graduation Semester and Year

Summer 2025

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Electrical Engineering

Department

Electrical Engineering

First Advisor

Dr. Venkat Devarajan

Second Advisor

Dr. Ganesh Sankaranarayanan

Abstract

The rapid growth of surgical video analysis presents a need for efficient deep learning models for surgical training, while reducing the need for excessive image and video image storage. Traditional training approaches typically rely on uniformly compressed video data, instead of selectively preserving the most surgically relevant regions. This dissertation investigates the impact of training deep neural networks (DNNs), both convolutional and transformer-based architectures, on saliency-guided, differentially compressed surgical video sequences. The study systematically evaluates how such compression influences prediction accuracy, computational efficiency and storage requirements. Experimental results demonstrate that models trained on ROI-focused compressed data combined with motion vectors achieve comparable, and in some cases, improved, predictive performance for surgical tool detection relative to those trained on uniformly compressed inputs. Notably, these models may also benefit from reduced training time and lower storage demands, indicating the feasibility of integrating such methods into resource-constrained surgical workflows. This work highlights the practical potential of saliency-aware compression combined with motion vectors for enhanced prediction of surgical tools.

Keywords

Deep Learning in Surgery, Vision Transformers (ViT/DeiT), Frame-level Surgical Tool Detection, Multiclass Multilabel Classification, Compressed Domain Learning, Motion Aware Models, Transfer Learning, Motion Vectors, Multi-head Attention

Disciplines

Other Electrical and Computer Engineering | Signal Processing

License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.