MSc Thesis Proposal Announcement of Yash Trivedi:"Lung tumor segmentation using superpixel based Hierarchical clustering and Multilevel thresholding "

Tuesday, June 14, 2022 - 10:00 to 11:00

SCHOOL OF COMPUTER SCIENCE 

The School of Computer Science is pleased to present… 

MSc Thesis Proposal by: Yash Trivedi 

 
Date: Tuesday June 14th June 2022 
Time:  10:00am to 11:00am 
Passcode: If interested in attending this event, contact the Graduate Secretary at csgradinfo@uwindsor.ca with sufficient notice before the event to obtain the passcode.
 

Abstract: 

Lung cancer has become one of the most significant diseases in human history. The World Health Organization estimates the worldwide death toll from lung cancer will be 10,000,000 by 2030. The accuracy of detecting tumor shape and location plays a vital role in successfully diagnosing and treating tumors. Computed tomography (CT) is one of the most common imaging modalities for examining and screening lung cancer. Segmentation of pulmonary nodules remains a challenging task due to intrinsic noise, low contrast, intensity-profile inhomogeneity, and variable sizes and shapes. A common approach to delineating tumors from CT scans involves radiologists manually drawing the tumor boundary. In most cases, manual segmentation is time-consuming and prone to intra- and inter-observer variability, thus making the results unreliable. Thus, an automatic and accurate lung tumor segmentation algorithm is required to display clear boundaries of lung nodules and aid radiologists in deciding on the malignancy of these nodules. Therefore, this research proposes a novel unsupervised algorithm using superpixel-based hierarchical clustering with multilevel thresholding for segmenting lung nodules from lung CT scan images. Preliminary results indicate that the proposed model can segment lung nodules without supervision.  
 
Keywords: Unsupervised learning, Segmentation, Lung cancer, Spectral Clustering, Superpixels, Graphs, Hierarchical Clustering, Thresholding 
 

MSc Thesis Committee:  

Internal Reader: Dr.Boubakeur Boufama              
External Reader: Dr.Esam Abdel-Raheem             
Advisor: Dr. Luis Rueda 
 

MSc Thesis Proposal Announcement  Vector Institute in Artificial Intelligence, artificial intelligence approved topic

 

5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca