Evaluation of breast cancer with a computer-aided detection system by mammographic appearance and histopathology.

BACKGROUND: The objective of this study was to evaluate the performance of a computer-aided detection (CAD) system for the detection of breast cancer, based on mammographic appearance and histopathology. METHODS: From 1000 consecutive screening mammograms from women with biopsy-proven breast carcinoma, 273 mammograms were selected randomly for retrospective evaluation by CAD. The sensitivity of the CAD system for breast cancer was assessed from the proportion of masses and microcalcifications detected. The corresponding tumor histopathologies also were evaluated. Normal mammograms (n = 155 patients) were used to determine the false-positive rate of the system. RESULTS: Of the 273 breast carcinomas, 149 appeared mammographically as masses, and 88 appeared as microcalcifications, including 36 carcinomas that presented as mixed lesions. The CAD system marked 125 of 149 masses correctly (84%), marked 86 of 88 microcalcifications correctly (98%), and marked 32 of 36 of mixed lesions correctly (89%.). The system showed a high sensitivity for the detection of ductal carcinoma in situ (95%; 73 of 77 lesions), invasive lobular carcinoma (95%; 18 of 19 lesions), invasive ductal carcinoma (85%; 125 of 147 lesions), and invasive mammary carcinoma (90%; 27 of 30 lesions). The highest CAD system sensitivity was for all invasive carcinomas that presented as microcalcifications (100%). On normal mammograms, there was an average of 1.3 false-positive CAD marks per image. CONCLUSIONS: The CAD system correctly marked a large majority of biopsy-proven breast cancers, with a greater sensitivity for lesions with microcalcifications and without significant impact of performance based on tumor histopathology. CAD was highly effective in detecting invasive lobular carcinoma (sensitivity, 95%) and ductal carcinoma in situ (sensitivity, 95%). CAD represents a useful tool for the detection of breast cancer.

A computer-aided detection system for the evaluation of breast cancer by mammographic appearance and lesion size.

OBJECTIVE: The purpose of our study was to evaluate the performance of a computer-aided detection (CAD) system in the detection of breast cancer based on mammographic appearance and lesion size. CONCLUSION: The CAD system correctly marked most biopsy-proven breast cancers, with a greater sensitivity for microcalcification than for mass lesions but with no significant difference in performance based on cancer size. CAD was highly effective in detecting even the smallest lesions, with a sensitivity of 92% for lesions of 5 mm or less. CAD is a useful tool for the detection of breast cancer.

Determining efficacy of mammographic CAD systems.

Computer-aided detection (CAD) system sensitivity estimates without a radiologist in the loop are straightforward to measure but are extremely data dependent. The only relevant performance metric is improvement in CAD-assisted radiologist sensitivity. Unfortunately, this is difficult to accurately assess. Without a large study measuring the improvement in CAD-assisted radiologist sensitivity over the same cases, it is not possible to make valid comparisons between systems. As multiple CAD systems become commercially available, comparison issues need to be explored and resolved. Data from clinical trials of 2 systems are examined. Statistical hypothesis tests are applied to these data. Additionally, sensitivities of 2 systems are compared from an experiment testing over the same 120 cases. Even with large databases, there is not sufficient evidence to conclude performance differences exist between the 2 systems. It is prohibitively expensive to show conclusive sensitivity differences between commercially available mammographic CAD systems.