Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/522060
Title: Study on impact of voice box changes in vocal cord
Researcher: Antony Sophia N
Guide(s): Wiselin Jiji G
Keywords: Computed Tomography
Computer Aided Diagnosis
Computer Science
Computer Science Software Engineering
Engineering and Technology
Moth Search Algorithm
University: Anna University
Completed Date: 2023
Abstract: Medical imaging plays a major role in diagnosing. Literature said that many people including singers, teachers and preachers had facing serious issues because of voice change. The voice could be changed because of the distress caused in vocal cord. Computer aided diagnosis (CAD) is also one of the challenging task. Physicians getting second opinion through CAD before the treatment process starts. Therefore, an automated statistical tool is required to identify voice change detection. This research is carried out in neck Computed Tomography (CT) images to identify and classify the vocal cord pathologies using an advanced multi-resolution algorithm (MRA). The vocal cord regions are determined using genetic k-means clustering. The pathology features are generated using the Local directional pattern (LDP) that fed for pathology classification using Moth search-rider optimization algorithm (MS-ROA). The hybrid optimization technique, integrates the standard Rider Optimization Algorithm (ROA) and Moth Search Algorithm (MS) to train Deep convolutional neural newlinenetwork (DCNN). The analysis using the real databases regarding the performance metrics revealed that the proposed pathology detection module obtained the accuracy, specificity, and sensitivity of 97.020%, 91.698%, and 96.624%. The laryngeal variation caused by Vocal cord Ulcer is determine and analyze using three dimensional Swin Transformation Volumetric Segmentation Network (3DSTVSNet) in CT images. 3D STVSNet reduces the entanglement and improves the segmentation accuracy. Volumetric quantification on Contrast Enhanced computed tomography (CECT), utilize 3D STVSNet for the extraction of shapes feature that used to evaluate the Vocal cord ulcer (VCU) severity. Evaluation results were 96.20% of sensitivity, 97.15% of accuracy and 96.16% of specificity. Thyroid nodule is common in both genders, its categories into hyper and hypo thyroid. Low Thyroxine indicates hypothyroid and High Thyroxine indicates hyperthyroid. Thyroid nodules are lumps of thyrocytes in the thy
Pagination: xx,155
URI: http://hdl.handle.net/10603/522060
Appears in Departments:Faculty of Information and Communication Engineering

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File182.99 kBAdobe PDFView/Open
02_prelim_pages.pdf3.15 MBAdobe PDFView/Open
03_content.pdf183.99 kBAdobe PDFView/Open
04_abstract.pdf282.8 kBAdobe PDFView/Open
05_chapter 1.pdf671.52 kBAdobe PDFView/Open
06_chapter 2.pdf397.02 kBAdobe PDFView/Open
07_chapter 3.pdf1.14 MBAdobe PDFView/Open
08_chapter 4.pdf1.05 MBAdobe PDFView/Open
09_chapter 5.pdf1.08 MBAdobe PDFView/Open
10_annexures.pdf258.38 kBAdobe PDFView/Open
80_recommendation.pdf105.32 kBAdobe PDFView/Open
Show full item record


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: