Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system.

In previous research, we have developed a computer-aided detection (CAD) system designed to detect masses in mammograms. The previous version of our system employed a simple but imprecise method to localize the masses. In this research, we present a more robust segmentation routine for use with mammographic masses. Our hypothesis is that by more accurately describing the morphology of the masses, we can improve the CAD system's ability to distinguish masses from other mammographic structures. To test this hypothesis, we incorporated the new segmentation routine into our CAD system and examined the change in performance. The developed iterative, linear segmentation routine is a gray level-based procedure. Using the identified regions from the previous CAD system as the initial seeds, the new segmentation algorithm refines the suspicious mass borders by making estimates of the interior and exterior pixels. These estimates are then passed to a linear discriminant, which determines the optimal threshold between the interior and exterior pixels. After applying the threshold and identifying the object's outline, two constraints on the border are applied to reduce the influence of background noise. After the border is constrained, the process repeats until a stopping criterion is reached. The segmentation routine was tested on a study database of 183 mammographic images extracted from the Digital Database for Screening Mammography. Eighty-three of the images contained 50 malignant and 50 benign masses; 100 images contained no masses. The previously developed CAD system was used to locate a set of suspicious regions of interest (ROIs) within the images. To assess the performance of the segmentation algorithm, a set of 20 features was measured from the suspicious regions before and after the application of the developed segmentation routine. Receiver operating characteristic (ROC) analysis was employed on the ROIs to examine the discriminatory capabilities of each individual feature before and after the segmentation routine. A statistically significant performance increase was found in many of the individual features, particularly those describing the mass borders. To examine how the incorporation of the segmentation routine affected the performance of the overall CAD system, free-response ROC (FROC) analysis was employed. When considering only malignant masses, the FROC performance of the system with the segmentation routine appeared better than the previous system. When detecting 90% of the malignant masses, the previous system achieved 4.9 false positives per image (FPpI) compared to the post-segmentation system's 4.2 FPpI. At 80% sensitivity, the respective FPpI were 3.5 and 1.6.

[1]  C E Metz,et al.  Gains in Accuracy from Replicated Readings of Diagnostic Images , 1992, Medical decision making : an international journal of the Society for Medical Decision Making.

[2]  M. Giger,et al.  Analysis of spiculation in the computerized classification of mammographic masses. , 1995, Medical physics.

[3]  H P Chan,et al.  Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification. , 1996, Medical physics.

[4]  Y H Chang,et al.  Performance gain in computer-assisted detection schemes by averaging scores generated from artificial neural networks with adaptive filtering. , 2001, Medical physics.

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

[6]  K. Doi,et al.  Computer-aided diagnosis in radiology: potential and pitfalls. , 1999, European journal of radiology.

[7]  N. Petrick,et al.  Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: an ROC study. , 1999, Radiology.

[8]  M. J. Carreira,et al.  Computer-aided diagnoses: automatic detection of lung nodules. , 1998, Medical physics.

[9]  Y H Chang,et al.  Computerized detection of masses in digitized mammograms using single-image segmentation and a multilayer topographic feature analysis. , 1995, Academic radiology.

[10]  Martin D. Fox,et al.  Classifying mammographic lesions using computerized image analysis , 1993, IEEE Trans. Medical Imaging.

[11]  Y H Chang,et al.  Adaptive computer-aided diagnosis scheme of digitized mammograms. , 1996, Academic radiology.

[12]  B. Zheng,et al.  Soft-copy mammographic readings with different computer-assisted detection cuing environments: preliminary findings. , 2001, Radiology.

[13]  D. Ikeda,et al.  Mammographic characteristics of 115 missed cancers later detected with screening mammography and the potential utility of computer-aided detection. , 2001, Radiology.

[14]  R E Hendrick,et al.  Proposition: All mammograms should be double-read. , 1999, Medical physics.

[15]  H P Chan,et al.  Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue. , 1996, Medical physics.

[16]  R A Clark,et al.  False-positive reduction in CAD mass detection using a competitive classification strategy. , 2001, Medical physics.

[17]  Nico Karssemeijer,et al.  Single and multiscale detection of masses in digital mammograms , 1999, IEEE Transactions on Medical Imaging.

[18]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[19]  Y H Chang,et al.  Knowledge-based computer-aided detection of masses on digitized mammograms: a preliminary assessment. , 2001, Medical physics.

[20]  M. Giger,et al.  Image feature analysis and computer-aided diagnosis in digital radiography. 3. Automated detection of nodules in peripheral lung fields. , 1988, Medical physics.

[21]  M. Pamilo,et al.  Double reading of mammography screening films--one radiologist or two? , 1993, Clinical radiology.

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

[23]  N. Petrick,et al.  Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature space. , 1995, Physics in medicine and biology.

[24]  N. Karssemeijer,et al.  Segmentation of suspicious densities in digital mammograms. , 2001, Medical physics.

[25]  M L Giger,et al.  Pulmonary nodules: computer-aided detection in digital chest images. , 1990, Radiographics : a review publication of the Radiological Society of North America, Inc.

[26]  M. Giger,et al.  Improving breast cancer diagnosis with computer-aided diagnosis. , 1999, Academic radiology.

[27]  H. R. Keshavan,et al.  An optimal multiple threshold scheme for image segmentation , 1984, IEEE Transactions on Systems, Man, and Cybernetics.

[28]  T. Freer,et al.  Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. , 2001, Radiology.

[29]  Martin P. DeSimio,et al.  Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saliency , 1997, IEEE Transactions on Medical Imaging.