Automatic generation of fetal ultrasound report

Date of Publication

2007

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Computer Science

Subject Categories

Computer Sciences

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Jose Ronello T. Bartolome

Defense Panel Chair

Nelson Marcos

Defense Panel Member

Rigan P. Ap-Apid

Abstract/Summary

This presents a program simulation of automatic detection and measurement of fetal characteristics present in an ultrasound image. The program aims to aid medical radiologists in dealing with the measurement of fetal ultrasound images by determining and automating the process of measuring the fetal characteristics present from an input ultrasound scan. Performing different image processing methods such as image enhancement, noise reduction and feature extraction does this process. Different algorithms are tested to come up with the automated scheme. Some of the algorithms that were experimented on includes: thresholding, template matching, blobs and active contours. The input image goes through successive process such as auto-leveling to enhance the brightness and contrast of the colors, grayscale image format conversion to quantize the colors and noise reduction to reduce unwanted parts in an image. After which, the program extracts the specified fetal characteristic from the cleaned image and proceeds into the measurement phase. The program is able to measure the major fetal characteristics necessary in monitoring the fetal growth, which are the crown rump length, biparietal diameter, head circumference, abdominal circumference and femur length. The simulation outputs a report, which contains the measurements obtained by the program generated from the set of input ultrasound, scans.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU14618

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

This document is currently not available here.

Share

COinS