Computerized detection of masses in digitized mammograms using single-image segmentation and a multilayer topographic feature analysis.

RATIONALE AND OBJECTIVES We developed and evaluated a computer-aided detection (CAD) scheme for masses in digitized mammograms. METHODS A multistep CAD scheme was developed and tested. The method uses a technique of single-image segmentation with Gaussian bandpass filtering to yield a high sensitivity for mass detection. A rule-based multilayer topographic feature analysis method is then used to classify suspected regions. A set of 260 cases, including 162 verified masses, was divided into two subsets; one set was used to set the rule-based classification and one was used to test the performance of the scheme. RESULTS In a preliminary clinical study, the implemented detection scheme yielded 98% sensitivity with a false-positive detection rate of less than one false-positive region per image. CONCLUSION Single-image segmentation methods seem to have high sensitivity in selecting true-positive mass regions in the first stage of a CAD scheme. A multilayer topographic image feature analysis method in the second stage of a CAD scheme has the potential to significantly reduce the false-positive detection rate.

[1]  A B Miller.  Mammography: reviewing the evidence. Epidemiology aspect. , 1993, Canadian family physician Medecin de famille canadien.

[2]  D M Eddy,et al.  The value of mammography screening in women under age 50 years. , 1988, JAMA.

[3]  Jacob Beutel,et al.  Application of neural networks to computer-aided pathology detection in mammography , 1993, Medical Imaging.

[4]  S. Lai,et al.  On techniques for detecting circumscribed masses in mammograms. , 1989, IEEE transactions on medical imaging.

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

[6]  T. Tong,et al.  Cancer statistics, 1992 , 1992, CA: a cancer journal for clinicians.

[7]  D Brzakovic,et al.  An approach to automated detection of tumors in mammograms. , 1990, IEEE transactions on medical imaging.

[8]  K Doi,et al.  Computerized detection of masses in digital mammograms: automated alignment of breast images and its effect on bilateral-subtraction technique. , 1994, Medical physics.

[9]  W F Bischof,et al.  Automated detection and classification of breast tumors. , 1992, Computers and biomedical research, an international journal.

[10]  E. Pisano,et al.  Issues in mammography , 1990, Cancer.

[11]  E. Patrick,et al.  Expert learning system network for diagnosis of breast calcifications. , 1991, Investigative radiology.

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

[13]  P. Strax,et al.  Detection of breast cancer , 1990, JAMA.

[14]  W. Philip Kegelmeyer.  Computer detection of stellate lesions in mammograms , 1992, Electronic Imaging.

[15]  R J Reitemeier,et al.  Randomized phase II clinical trial of adriamycin, methotrexate, and actinomycin‐d in advanced measurable pancreatic carcinoma. A gastrointestinal tumor study group report , 1978, Cancer.

[16]  L. Kuncheva,et al.  Two-level classification schemes in medical diagnostics. , 1993, International journal of bio-medical computing.

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

[18]  K Doi,et al.  Comparison of bilateral-subtraction and single-image processing techniques in the computerized detection of mammographic masses. , 1993, Investigative radiology.

[19]  R. J. Brenner,et al.  Medicolegal aspects of screening mammography. , 1989, AJR. American journal of roentgenology.

[20]  M L Giger,et al.  Computerized detection of masses in digital mammograms: analysis of bilateral subtraction images. , 1991, Medical physics.

[21]  J. Swets,et al.  Enhanced interpretation of diagnostic images. , 1988, Investigative radiology.

[22]  Kunio Doi,et al.  Investigation of methods for the computerized detection and analysis of mammographic masses , 1990, Medical Imaging: Image Processing.

[23]  D Gur,et al.  The significance of concordance in mammographic interpretations , 1979, Cancer.

[24]  K Doi,et al.  Effect of case selection on the performance of computer-aided detection schemes. , 1994, Medical physics.

[25]  A. I. Cohn,et al.  Expert system-controlled image display. , 1989, Radiology.

[26]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[27]  Y. Wu,et al.  Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. , 1993, Radiology.