Medical Policy: 06.01.26
Original Effective Date: May 2008
Reviewed: April 2018
Revised: April 2017
Benefit determinations are based on the applicable contract language in effect at the time the services were rendered. Exclusions, limitations or exceptions may apply. Benefits may vary based on contract, and individual member benefits must be verified. Wellmark determines medical necessity only if the benefit exists and no contract exclusions are applicable. This medical policy may not apply to FEP. Benefits are determined by the Federal Employee Program.
This Medical Policy document describes the status of medical technology at the time the document was developed. Since that time, new technology may have emerged or new medical literature may have been published. This Medical Policy will be reviewed regularly and be updated as scientific and medical literature becomes available.
The use of computer-aided detection (CAD)/computer aided evaluation (CAE) is proposed to assist radiologists’ interpretation of contrast-enhanced magnetic resonance imaging (MRI) of the breast and improve the accuracy of diagnosis of malignancy. MRI of the breast is suggested as an alternative or adjunct to mammography or other screening and diagnostic tests because of its high sensitivity in detecting breast lesions. However, it has a high false-positive rate because of the difficulty in distinguishing between benign and malignant lesions. MRI may be used to screen geno typical women at high risk of breast cancer or to look for more extensive disease in geno typical women who are eligible for breast-conserving surgery; it is also being studied to gauge the impact of cancer treatment. The CAD/CAE systems reviewed in this policy are intended to improve the specificity of MRI in detecting or measuring malignant tissue, while maintaining the generally high sensitivity of MRI. The use of CAD/CAE may also shorten the time needed to interpret breast MRI images, which currently takes much longer than reading mammograms.
CAD/CAE systems for MRI essentially provide easier ways of interpreting the patterns of contrast enhancement across a series of images, which in turn may help identify lesions and their likelihood of being malignant. In contrast to CAD systems used with mammography, CAD/CAE for MRI is not primarily intended to identify lesions for consideration by a radiologist. Unlike the subtle appearance of lesions on mammography, most cancers enhance on MRI. The challenge is determining which lesions are benign and which are malignant. A large number of images are produced during MRI of the breast: images are taken at varying “depths” throughout each breast multiplied the number of time the breast is imaged to capture different time points in the enhancement process; this can produce hundreds of images. Radiologists view the images to detect suspicious areas, and then can select a region of interest and look at the enhancement pattern. However, there may be variations across radiologists in the regions of interest selected and in the precise definition of the region of interest. CAD/CAE systems, in contrast, use color-coding and differences in hue to indicate the patterns of enhancement for each pixel in the breast image, thereby allowing the radiologist to analyze the enhancement patterns systematically. Some CAD/CAE programs apparently incorporate morphological characteristics as well to estimate a probability of malignancy.
Computer aided evauluation (CAE) systems for MRI of the breast were initially called CAD systems (computer aided detection), the same terminology used for mammography. However, the focus with MRI of the breast is on improving specificity (distinguishing malignant from benign) rather than increasing sensitivity (i.e. detection), as in mammography. Authors of 2 studies refer to CADstream as a CAE program, and that terminology has been adopted in this policy.
At the present time, it is not clear how CAD/CAE systems are to be used with MRI. In the case of CAD with conventional mammography, the radiologist reads the original films first, makes an interpretation, and then reviews the CAD results. Because CAD is not 100% sensitive, lesions detected both before the use of CAD and after viewing the CAD results may be worked up. In this way, CAD can add to the sensitivity of mammography, but not its specificity. With MRI of the breast, the sensitivity is already high and the focus is primarily on increasing the specificity. In some articles, it appears that CAD/CAE is intended as an adjunct to the initial MRI reading, just as with CAD and mammography. In other articles, it is proposed as a way of speeding up the MRI reading process, and the precise protocol to be followed in reading the MRI images is not clear.
A Technology Evaluation Center (TEC) Assessment published in 2006 summarized published articles and abstracts comparing the sensitivity and specificity of MRI of the breast interpreted with and without the use of CAD/CAE systems and reported on cancer detection based on histological results. Unfortunately, the literature on the use of CAD/CAE with MRI of the breast is sparse overall and few studies address the specific situations in which CAD/CAE with MRI may be used in the clinical setting. Many of the few articles and abstract reviewed by TEC calculated test characteristics on the basis of lesions and not the number of women or breasts. In the screening population, many women would not have any lesions. Including these women might alter the results. Given MRI’s lower sensitivity in detecting ductal carcinoma in situ (DCIS), the mix of DCIS versus masses would affect the calculations of sensitivity and specificity and might affect the impact of the CAD system.
There is no direct evidence that evaluates the impact of computer aided detection (CAD) or computer aided evaluation (CAE) on health outcomes when added to MRI of the breast. There are no prospective studies that examine whether management decisions are changed due to results of CAD/CAE. There are also no relevant modeling studies that estimate the impact of CAD/CAE on outcomes. CAD has not been proven to improve mortality rates from breast cancer screening at this time.
Available evidence primarily consists of retrospective studies that compare the accuracy of computer aided magnetic resonance imaging (MRI) of breast malignancy versus conventional imaging. Populations in these studies are not representative of patients seen in clinical care; rather they include samples of geno typical women who are highly selected and usually have far more cases of cancer than would be encountered in a screening population. As a result, a true sensitivity and specificity of computer aided MRI, and the incremental improvement in accuracy over conventional imaging, cannot be determined with certainty. Larger, well designed, prospective studies are needed that include relevant clinical populations in order to determine whether computer aided evaluation results in a clinically significant improvement in diagnostic accuracy. As a result of the deficiencies in the available literature, the use of computer aided evaluation of malignancy with MRI is considered investigational.
CAD increases the detection of ductal carcinoma in situ (DCIS) as CAD software has increased sensitivity to detect calcifications. Since the natural history of DCIS is indolent and uncertain, the benefit of early detection and treatment for this condition is unclear and the potential for over-treatment of preclinical disease is raised. This is of particular concern in older geno typical women, with a more limited life expectancy.
Does not address the use of computer aided detection (CAD)/computer aided evaluation (CAE) for breast MRI testing.
In 2016, the American College of Radiology (ACR) amended the 2014 practice parameter for the use of MRI-Guided Breast Interventional Procedures. The use of computer aided detection (CAD)/computer aided evaluation (CAE) with breast MRI is not specifically recommended or addressed.
The European Society of Breast Cancer Specialists issued a consensus recommendation for MRI of the breast in 2010. This document stated, “We recommend the use of standardized interpretation systems such as the above mentioned BI-RADS (Breast Imaging Reporting and Data System) lexicon 17, or equivalent. There is some evidence that software for breast MR computer-aided diagnosis (CAD) may be of benefit but insufficient to recommend the routine use of such systems.”
Computer-aided detection (CAD) systems highlight suspicious regions, such as clustered microcalcifications and masses, generally increasing sensitivity, decreasing specificity, and increasing detection of ductal carcinoma in situ (DCIS). Several CAD systems are in use. One large population-based study that compared recall rates and breast cancer detection rates before and after the introduction of CAD systems, found no change in either rate. Another large study noted an increase in recall rate and increased DCIS detection but no improvement in invasive cancer detection rate.
The use of computer-aided detection (CAD)/computer aided evaluation (CAE) for interpretation of magnetic resonance imaging (MRI) of the breast is considered investigational.
Based on peer reviewed literature there is insufficient evidence to assess whether the use of computer aided detection (CAD)/computer aided evaluation (CAE) would maintain or increase the sensitivity, specificity, and recall rates of MRI of the breast. Because incremental changes in sensitivity and specificity with CAE are unknown, it is not possible to estimate the number of additional malignancies that would be detected by CAE, nor is it possible to determine the number of additional false-positive biopsies that would be performed. As a result, the clinical utility of CAE when added to standard MRI of the breast has yet to be determined. Prospective, well-designed studies are needed to determine whether or not the use of CAD/CAE provides a positive clinical benefit. Therefore, the use of CAD/CAE for the interpretation of magnetic resonance imaging (MRI) of the breast is considered investigational.
Wellmark medical policies address the complex issue of technology assessment of new and emerging treatments, devices, drugs, etc. They are developed to assist in administering plan benefits and constitute neither offers of coverage nor medical advice. Wellmark medical policies contain only a partial, general description of plan or program benefits and do not constitute a contract. Wellmark does not provide health care services and, therefore, cannot guarantee any results or outcomes. Participating providers are independent contractors in private practice and are neither employees nor agents of Wellmark or its affiliates. Treating providers are solely responsible for medical advice and treatment of members. Our medical policies may be updated and therefore are subject to change without notice.
*CPT® is a registered trademark of the American Medical Association.