Home   Projects   Research   Teaching   Links   Affiliations  
Contact
Pattern Recognition, Medical Imaging, Machine Intelligence, Computer Vision Hamid R. Tizhoosh
Faculty of Engineering
University of Waterloo


Pattern Recognition, Computer Vision,
Medical Imaging, Machine Intelligence
Hamid R. Tizhoosh
Teaching
Computer Vision
Machine Intelligence
Data Structures
SD750 - OBL
Research
Pattern Recoginition
Computer Vision
Machine Intelligence
Terahertz Imaging
Health Engineering
Opposition-Based Learning
Students
Current Students
Former Students
Projects
LORNET
Prostate Cancer
Breast Cancer
Radiation Therapy
Other Projects
Publications
Books & Chapters
Journals
Conferences
Reports etc.
University of Waterloo :: Faculty of Engineering :: Systems Design

Projects …
Prostate Cancer

Introduction

Prostate Cancer is the second most diagnosed malignancy in men over the age of '50'[1]. It is the most common cancer type and is found at autopsy in 30% of men at the age of 50, 40% at age '60', and almost 90% at age 90.1 Worldwide, it is the second leading cause of death due to cancer in men, accounting for between 2.1% and 15.2% of all cancer deaths [2]. In Canada, prostate cancer is the third leading cause of cancer death in men; about 10,000 new cases will be diagnosed and about 3,000 men will die from this disease every year [3].


Symptoms due to carcinoma of the prostate are generally absent until extensive local growth or metastases develop, accounting for the fact that only 65% of patients are diagnosed with locally confined disease [2]. Once the tumour has extended beyond the prostate, the risk of metastasis increases dramatically. Tumours smaller than 1 to 1.5 cm3 rarely broach the prostatic capsule [4]. When diagnosed at this early stage, the disease is curable [5]. Even at later stages, treatment can be effective. Nevertheless, treatment options vary depending on the extent of the cancer and prognosis worsens when diagnosis occurs at an advanced stage [4]. Clearly, early diagnosis and accurate staging of prostate cancer, as well as a properly performed therapeutic procedures are critical to the patient's well being.

 

Objectives

In this research, we aim to extend the 3-D ultrasound prostate imaging system capabilities as a vital diagnostic tool. The existing version of this system accomplishes simple visualization of prostate. In this research, we are planning to utilize 3-D image data collected from such system to develop a set of tools with novel functionality, which will enable us to extract, clinically, useful information from 3-D imaging system about prostate anatomic structure. The extraction and the classification of this information are based on the knowledge of the expertise in the field. In our research, we will tackle three major problems, which constitute our short-term objectives. These are image segmentation, feature extraction and pattern analysis and classification.

 

Reference

[1] R.L Waterhouse, M.I Resnick, "The use of transrectal prostatic ultrasonography in the evaluation of patients with prostatic carcinoma." J. Urol. 141, 233-239, 1989.

[2] E.Silverberg, C. C. Boring, T. S. Squires, "Cancer Statistics, 1990 CA; 40, 9-26, 1990.

[3] Canadian Cancer Statistics 1990, National Cancer Institute of Canada, Toronto, 14, 16, 28, 45, 1990.

[4] M. D. Rifkin, "MRI of the Prostate". Critical Reviews in Diagnostic Imaging, 31(2), 223-262, 1990.

[5] M.K.Terris, J.E.McNeal, T.A. Stamey, "Estimation of prostate cancer volume by transrectal ultrasound imaging". J. Urol. 147, 855, 1992.

 

 

 

» Supporters

» Affiliations

» Resume

» Contact

 

Typical Processing

Original Ultrasound

Original Ultrasound

After Pre-Processing

After Pre-Processing

Extracted Boundaries

Extracted Boundaries

After Elimination of Irrelevant Data

After Elimination of Irrelevant Data

Detected Prostate

Detected Prostate


Created by: Log Web Design