Analysis of methods for reducing false positives in the automated detection of clustered microcalcifications in mammograms.

Clustered microcalcifications are often the first sign of breast cancer in a mammogram. Nevertheless, all clustered microcalcifications are not found by an individual radiologist reading a mammogram. The use of a second reader may find those clusters of microcalcifications not found by the first reader, thereby improving the sensitivity of detecting clustered microcalcifications. Our laboratory has developed a computerized scheme for the detection of clustered microcalcifications, which can act like a second reader, that is undergoing clinical evaluation. This paper concerns the feature analysis stage of the computer scheme, which is designed to remove some of the false-computer detections. We have examined three methods of feature analysis, namely, rule based (the method currently used), an artificial neural network (ANN), and a combined method. In an independent database of 50 images, at a sensitivity of 83%, the average number of false positive (FP) detections per image was: 1.9 for rule-based, 1.6 for ANN, and 0.8 for the combined method. We demonstrate that the combined method performs best because each of the two stages eliminates different types of false positives.

[1]  K Doi,et al.  Computer-aided detection of clustered microcalcifications: an improved method for grouping detected signals. , 1993, Medical physics.

[2]  Ping Lu,et al.  Initial experience with a prototype clinical intelligent mammography workstation for computer-aided diagnosis , 1995, Medical Imaging.

[3]  K Doi,et al.  Improvement in radiologists' detection of clustered microcalcifications on mammograms. The potential of computer-aided diagnosis. , 1990, Investigative radiology.

[4]  D R Dance,et al.  The automatic computer detection of subtle calcifications in radiographically dense breasts. , 1992, Physics in medicine and biology.

[5]  K Doi,et al.  Computerized detection of clustered microcalcifications in digital mammograms using a shift-invariant artificial neural network. , 1994, Medical physics.

[6]  P. Wingo,et al.  Cancer statistics, 1995 , 1995, CA: a cancer journal for clinicians.

[7]  R M Nishikawa,et al.  Image feature analysis and computer-aided diagnosis in mammography: reduction of false-positive clustered microcalcifications using local edge-gradient analysis. , 1995, Medical physics.

[8]  K Doi,et al.  Image feature analysis and computer-aided diagnosis in digital radiography. I. Automated detection of microcalcifications in mammography. , 1987, Medical physics.

[9]  W. Willett,et al.  Breast cancer (2). , 1992, The New England journal of medicine.

[10]  R. Bird,et al.  Analysis of cancers missed at screening mammography. , 1992, Radiology.

[11]  Berkman Sahiner,et al.  Computerized detection and classification of microcalcifications on mammograms , 1995, Medical Imaging.

[12]  M Moskowitz,et al.  Occult breast cancer: prevalence and radiographic detectability. , 1987, Radiology.

[13]  I S Simor,et al.  Sensitivity and specificity of first screen mammography in the Canadian National Breast Screening Study: a preliminary report from five centers. , 1986, Radiology.

[14]  K. Doi,et al.  Computer-aided detection of microcalcifications in mammograms. Methodology and preliminary clinical study. , 1988, Investigative radiology.

[15]  E. Thurfjell,et al.  Benefit of independent double reading in a population-based mammography screening program. , 1994, Radiology.

[16]  Robert M. Nishikawa,et al.  Characterization of the mammographic appearance of microcalcifications: applications in computer-aided diagnosis , 1993 .

[17]  Carey E. Priebe,et al.  Comparative evaluation of pattern recognition techniques for detection of microcalcifications , 1993, Electronic Imaging.

[18]  K Doi,et al.  Computerized detection of clustered microcalcifications in digital mammograms: applications of artificial neural networks. , 1992, Medical physics.