Logo eprints

Quantitative methods for computer aided decision support systems in confocal laser endomicroscopy imaging of the gastrointestinal tract

Boschetto, Davide (2016) Quantitative methods for computer aided decision support systems in confocal laser endomicroscopy imaging of the gastrointestinal tract. Advisor: Caldarelli, Prof. Guido. Coadvisor: Grisan, Prof. Enrico . pp. 168. [IMT PhD Thesis]

[img] Text
Boschetto_phdthesis.pdf - Published Version
Restricted to IMT staff and National library only until June 2017.

Download (27MB)

Abstract

The mucosa of the gastrointestinal tract represents the main barrier between the inner body and the external world. A layer of cells runs from the esophagus to the rectum, playing a key role in preventing access to environmental hostile factors that could cause inflammation. Alterations in such mucosa are caused or can cause severe problems to patients, among others celiac disease, irritable bowel disease, Crohn’s disease, ulcerative colitis and Barrett’s esophagus. The gold standard for evaluating such diseases requires biopsies to be performed on the patient, often following the random fourquadrant protocol, other than positive serology. Quantitative methods for evaluating in-vivo these diseases, by exploiting distinctive image features that vary according to the grade of the disease, would improve the way clinical examinations are performed. This could in the long run lead to virtual biopsies with a single endoscopy examination. We propose a Computer Aided Decision Support System for endoscopic examinations performed using Confocal Laser Endomicroscopy for celiac disease and irritable bowel syndrome that, exploiting image features extracted in an automatic way, can assist the physician in its diagnosis and help him in selecting and identifying the areas that most require attention during an examination. Exploiting image features that are well-investigated in the literature, our tool outputs valuable information about the mucosa under examination with a friendly user interface. We hope with such solution to increase the attention towards the need of quantitative methods in this medical field.

Item Type: IMT PhD Thesis
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
PhD Course: Computer Decision and System Science
Identification Number: 10.6092/imtlucca/e-theses/201
Date Deposited: 22 Mar 2017 10:26
URI: http://e-theses.imtlucca.it/id/eprint/201

Actions (login required)

View Item View Item