Mammography Screening

Five experienced screeners independently and blindly reviewed mammograms from the first screening round of 46 healthy women, and of 74 women who had histologically proven breast cancers in the first screening round or later. The films were reviewed first as one-view screening and later as two-view screening. Fifty-one breast cancers were detected by at least one of the screeners on either one-view or two-view screening. The mean increase in sensitivity by using two views, instead of one, was 2%. The median of the proportional increase in detected cancers as the result of independent double reading was 14.5% with one-view screening and 12% with two-view screening. Two screeners using one-view screening detected about 10% more cancers than one screener using two-view screening.

Screening mammography benefit controversies: sorting the evidence

Numerous clinical studies have confirmed that screening women age 40 years and older reduces breast cancer mortality by 30% to 50%. Several factors including faster breast cancer growth rates and lower breast cancer incidence among younger women, as well as shorter life expectancy and more comorbid conditions among older women, should also be considered in screening guidelines. Annual screening beginning at age 40 years and continuing with no upper age limit, as long as a woman has a life expectancy of at least 5 years and no significant comorbid conditions, is currently recommended.

Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM

The roles of physicists in medical imaging have expanded over the years, from the study of imaging systems (sources and detectors) and dose to the assessment of image quality and perception, the development of image processing techniques, and the development of image analysis methods to assist in detection and diagnosis. The latter is a natural extension of medical physicists' goals in developing imaging techniques to help physicians acquire diagnostic information and improve clinical decisions. Studies indicate that radiologists do not detect all abnormalities on images that are visible on retrospective review, and they do not always correctly characterize abnormalities that are found. Since the 1950s, the potential use of computers had been considered for analysis of radiographic abnormalities. In the mid-1980s, however, medical physicists and radiologists began major research efforts for computer-aided detection or computer-aided diagnosis (CAD), that is, using the computer output as an aid to radiologists-as opposed to a completely automatic computer interpretation-focusing initially on methods for the detection of lesions on chest radiographs and mammograms. Since then, extensive investigations of computerized image analysis for detection or diagnosis of abnormalities in a variety of 2D and 3D medical images have been conducted. The growth of CAD over the past 20 years has been tremendous-from the early days of time-consuming film digitization and CPU-intensive computations on a limited number of cases to its current status in which developed CAD approaches are evaluated rigorously on large clinically relevant databases. CAD research by medical physicists includes many aspects-collecting relevant normal and pathological cases; developing computer algorithms appropriate for the medical interpretation task including those for segmentation, feature extraction, and classifier design; developing methodology for assessing CAD performance; validating the algorithms using appropriate cases to measure performance and robustness; conducting observer studies with which to evaluate radiologists in the diagnostic task without and with the use of the computer aid; and ultimately assessing performance with a clinical trial. Medical physicists also have an important role in quantitative imaging, by validating the quantitative integrity of scanners and developing imaging techniques, and image analysis tools that extract quantitative data in a more accurate and automated fashion. As imaging systems become more complex and the need for better quantitative information from images grows, the future includes the combined research efforts from physicists working in CAD with those working on quantitative imaging systems to readily yield information on morphology, function, molecular structure, and more-from animal imaging research to clinical patient care. A historical review of CAD and a discussion of challenges for the future are presented here, along with the extension to quantitative image analysis.

An ellipse-fitting based method for efficient registration of breast masses on two mammographic views

When reading mammograms, radiologists routinely search for and compare suspicious breast lesions identified on two corresponding craniocaudal (CC) and mediolateral oblique (MLO) views. Automatically identifying and matching the same true-positive breast lesions depicted on two views is an important step for developing successful multiview based computer-aided detection (CAD) schemes. The authors developed a method to automatically register breast areas and detect matching strips of interest used to identify the matched mass regions depicted on CC and MLO views. The method uses an ellipse based model to fit the breast boundary contour (skin line) and set a local Cartesian coordinate system for each view. One intersection point between the major/minor axis and the fitted ellipse perimeter passed through breast boundary is selected as the origin and the majoraxis and the minoraxis of the ellipse are used as the two axis of the Cartesian coordinate system. When a mass is identified on one view, the scheme computes its position in the local coordinate system. Then, the distance is mapped onto the local coordinate of the other view. At the end of the mapped distance a registered centerline of the matching strip is created. The authors established an image database that includes 200 test examinations each depicting one verified mass visible on the two views. They tested whether the registered centerline identified on another view can be used to locate the matched mass region. The experiments show that the average distance between the mass region centers and the registered centerlines was +/- 8.3 mm and in 91% of testing cases the registered centerline actually passes through the matched mass regions. A matching strip width of 47 mm was required to achieve 100% sensitivity for the test database. The results demonstrate the feasibility of the proposed method to automatically identify masses depicted on CC and MLO views, which may improve future development of multiview based CAD schemes.

Joint two-view information for computerized detection of microcalcifications on mammograms

We are developing new techniques to improve the accuracy of computerized microcalcification detection by using the joint two-view information on craniocaudal (CC) and mediolateral-oblique (MLO) views. After cluster candidates were detected using a single-view detection technique, candidates on CC and MLO views were paired using their radial distances from the nipple. Candidate pairs were classified with a similarity classifier that used the joint information from both views. Each cluster candidate was also characterized by its single-view features. The outputs of the similarity classifier and the single-view classifier were fused and the cluster candidate was classified as a true microcalcification cluster or a false-positive (FP) using the fused two-view information. A data set of 116 pairs of mammograms containing microcalcification clusters and 203 pairs of normal images from the University of South Florida (USF) public database was used for training the two-view detection algorithm. The trained method was tested on an independent test set of 167 pairs of mammograms, which contained 71 normal pairs and 96 pairs with microcalcification clusters collected at the University of Michigan (UM). The similarity classifier had a very low FP rate for the test set at low and medium levels of sensitivity. However, the highest mammogram-based sensitivity that could be reached by the similarity classifier was 69%. The single-view classifier had a higher FP rate compared to the similarity classifier, but it could reach a maximum mammogram-based sensitivity of 93%. The fusion method combined the scores of these two classifiers so that the number of FPs was substantially reduced at relatively low and medium sensitivities, and a relatively high maximum sensitivity was maintained. For the malignant microcalcification clusters, at a mammogram-based sensitivity of 80%, the FP rates were 0.18 and 0.35 with the two-view fusion and single-view detection methods, respectively. When the training and test sets were switched, a similar improvement was obtained, except that both the fusion and single-view detection methods had superior test performances on the USF data set than those on the UM data set. Our results indicate that correspondence of cluster candidates on two different views provides valuable additional information for distinguishing FPs from true microcalcification clusters.

Interobserver variations in assessment of antral disease from direct sinoscopic observations compared to video recordings

We tested the reliability of visual clinical sinoscopic observations by using video recordings. An edited video tape was made from the video-recorded bilateral antral sinoscopies of nine patients included in a prospective case series of inflammatory maxillary sinus disease in critically ill patients. An expert panel of four consultant ENT surgeons made individual appraisals of the video using a structured form. They had only been informed in general about the study, but had no further case knowledge in order to avoid all biases. Concordance and interobserver variabilities in the expert panel were compared in pairs. The assessments of the expert panel were compared with the observations of the performer, who was biased through individual case knowledge. Nine patients, either nasotracheally intubated or tracheotomized, had ventilator treatment for more than 7 days. One ENT surgeon performed all sinoscopies and made the direct observations. Satisfactory agreement was found on mucosal alterations. The concordance of recognizing bacterial infection was almost perfect. However, the assessment of redness from a video recording displayed only chance agreement. The differences between kappa statistic values within the expert panel group compared to the comparisons of performer versus expert panel were not significant. The case knowledge of the sinoscopist did not alter the assessments markedly and thus seemed only to have minor influence. Video recording as a method for second opinion was shown to be a useful technique, but will have to be further developed.