Abstract
In this chapter we discuss rationale and methods for computer-aided diagnosis in mammography. Computer-aided diagnosis (CAD) is a diagnosis made by a clinician who uses the output from a computerized analysis of medical images as a "second opinion" in detecting lesions and in making diagnostic decisions. The final diagnosis is rendered by the clinician, e.g., the radiologist. Computer vision and artificial intelligence techniques are developed and customized to accommodate lesions such as cancer and their radiographic presentations on the normal parenchymal background of the breast.
Mammography, x-ray imaging of the breast, is currently the best method for the early detection of breast cancer. Between 10 and 30% of women who have breast cancer and undergo mammography have negative mammograms, however. In approximately two-thirds of these false-negative mammograms, the radiologist failed to detect a cancer that was evident retrospectively. The missed detections may be due to the subtle nature of the radiographic findings (i.e., low conspicuity of the lesion), poor image quality, eye fatigue, or oversight by the radiologists. It has been suggested that double reading (by two radiologists) may increase sensitivity. Thus, one aim of CAD is to increase the efficiency and effectiveness of screening procedures by using a computer system, as a "second reader" (like a "spell checker"), to indicate locations of suspicious abnormalities in mammograms as an aid to the radiologist leaving the final decision regarding the likelihood of the presence of a cancer and patient management to the radiologist. The interpretation of screening mammograms lends itself to CAD since it is a repetitive task involving mostly normal images. Figure 15.1 shows a schematic diagram of a computerized detection method for use in screening mammography.
If a suspicious region is detected, the radiologist then decides if the abnormality is likely to be malignant or benign, and what course of action should be recommended (i.e., return to screening, return for short term follow-up, or return for biopsy). Many patients are referred for surgical biopsy on the basis of a radiographically detected mass lesion or cluster of microcalcifications. Although general rules for the differentiation between benign and malignant breast lesions exist, considerable variability occurs in the interpretation of findings by radiologists with current radiographic techniques. On average, only 10-20% of masses referred for surgical breast biopsy are actually malignant. Thus, another aim of CAD is to extract and analyze the characteristics of benign and malignant lesions seen at mammography in an objective manner in order to aid the radiologist. This has the potential for increasing diagnostic accuracy and reducing the numbers of false-positive diagnoses of malignancies, thereby decreasing patient morbidity by reducing the number of surgical biopsies performed and their associated complications. Figure 15.2 shows a schematic diagram of a computerized diagnosis method for use in the mammographie workup of a suspect lesion.
Online access to SPIE eBooks is limited to subscribing institutions.
