Access to SPIE eBooks is limited to subscribing institutions. Access is not available as part of an individual subscription. However, books can be purchased on SPIE.Org
Chapter 17:
Computer-Aided Diagnosis for 2D/ˆ•3D Breast Ultrasound
Editor(s): Jasjit Singh Suri; Rangaraj M. Rangayyan
Author(s): Chang, Ruey-Feng; Tsai, Chia-Ling; Kuo, Wen-Jia; Chen, Dar-Ren; Huang, Yu-Len; Huang, Sheng-Fang; Moon, Woo Kyung; Chen, Wei-Ming; Wu, Wen-Jie
Abstract
In the early stages, computer-aided diagnosis (CAD) analysis faced skepticism and numerous criticisms due to the premature facilities and techniques. However, with the rapid advances of CAD technologies in recent years, researchers have made considerable progress by showing potential in multiple clinical areas. Study findings have also shown that the diagnostic performance of radiologists can be enhanced if the CAD system is used as a second opinion. The major trends in radiology are toward the digital technologies and computerized management of images. In particular, the evolution in computer technology and in hardware for real-time signal processing contributes to the development of CAD as an additional step in image manipulation in radiology. Many CAD tools can be easily integrated into the existing hardware to meet certain clinical needs, such as analysis of difficult-to-interesting images, lower dependence on human experts, and the cost-effective utilization of available resources. Breast cancer ranks first in the causes of cancer deaths among women in developed countries. The best way to reduce cancer deaths due to breast cancer is early detection and treatment. However, earlier treatment requires both early diagnosis and a reliable diagnostic procedure that allow physicians to accurately differentiate benign breast tumors from malignant ones. Currently, the common methods for early detection of breast cancers include self-examination, biopsy, contrast-enhanced MR imaging, breast scintigraphy, mammography, and sonography. Among those methods, biopsy is most superior in terms of accuracy, which inevitably comes with high clinical cost. Meanwhile, most biopsies are avoidable for the reason that the rate of positive findings at biopsy for cancer is very low, ranging from 10% to 31%. Thus, how to increase the physician's diagnostic confidence becomes the matter of concern. The introduction of CAD mammography improves the performance and confidence of a radiologist by highlighting potential microcalcifications and tumors in film screening (e.g., ImageChecker M1000 System). It also plays an important role in assisting the radiologist to minimize observational lapses by suggesting areas on the original mammogram that may warrant a second review. However, the application of a CAD system for sonography is still not established. Current procedures for detecting and diagnosing breast cancers, however, encounter the difficulty of maximizing both sensitivity and specificity. The reasons for the challenge include a considerable overlap between benignancy and malignancy in ultrasonographic images, and interobserver variation in interpretation. However, the better diagnostic results are usually achieved by experienced radiologists. To overcome the potential vulnerabilities of sonography and to fully expand its capability, only an efficient computerized model offers objective evidence and avoids interobserver variations.
Online access to SPIE eBooks is limited to subscribing institutions.
CHAPTER 17
44 PAGES


SHARE
Back to Top