Computerized evaluation of mammographic lesions: what diagnostic role does the shape of the individual microcalcifications play compared with the geometry of the cluster?

OBJECTIVE: The objective of this study was to compare the diagnostic role of features reflecting the geometry of clusters with features reflecting the shape of the individual microcalcification in a mammographic computer-aided diagnosis system. MATERIALS AND METHODS: Three hundred twenty-four cases of clustered microcalcifications with biopsy-proven results were digitized at 42-microm resolution and analyzed on a computerized system. The shape factor and number of neighbors were computed for each microcalcification, and the eccentricity of the cluster was computed as well. The shape factor is related to the individual microcalcification; the average number of neighbors and the cluster eccentricity reflect the cluster geometry. Stepwise discriminant analysis was used to evaluate the contribution of the extracted features in predicting malignancy. The performance of a classifier based on the features selected by stepwise discriminant analysis was evaluated by receiver operating characteristic (ROC) analysis. RESULTS: To obtain the best discrimination model, we used stepwise discriminant analysis to select the average number of neighbors and the shape of the individual microcalcification, but excluded cluster eccentricity. A classification scheme assigned the average number of neighbors a weighting factor, which was 1.49 times greater than that assigned to the shape factor of the individual microcalcification. A scheme based only on these two features yielded an ROC curve with an area under the curve (A(z)) of 0.87, indicating a positive predictive value of 61% for 98% sensitivity. CONCLUSION: Computerized analysis permitted calculations reflecting the shape of individual microcalcification and the geometry of clusters of microcalcifications. For the computerized classification scheme studied, the cluster geometry was more effective in differentiating benign from malignant clusters than was the shape of individual microcalcification.

Role of US-guided fine-needle aspiration with on-site cytopathologic evaluation in management of nonpalpable breast lesions.

RATIONALE AND OBJECTIVES: The purpose of this study was to evaluate the accuracy of ultrasound (US)-guided fine-needle aspiration (FNA), with radiographic follow-up or surgical excision, in conjunction with on-site cytopathologic support in the management of nonpalpable breast lesions. MATERIALS AND METHODS: The findings of 266 consecutive mammographically or sonographically identified, nonpalpable lesions (228 patients) that underwent US-guided FNA were examined retrospectively. Clustered microcalcifications did not undergo biopsy with this method. Patients who underwent follow-up excisional biopsy or mammography with a duration of at least 24 months were included in the study. RESULTS: In all, 117 lesions met criteria for inclusion, of which 85 (73%) were diagnosed as benign at cytopathologic evaluation and underwent mammographic follow-up of at least 24 months (range, 24-67 months; mean, 36 months). Thirty-two lesions (27%) had either malignant or atypical cytopathologic findings, for which surgery was recommended. Eleven (9%) of the 32 had malignant cytopathologic findings from initial US-guided FNA, which were confirmed at surgical excision. The remaining 21 lesions (18%) were diagnosed as atypical on the basis of US-guided FNA results. Of these, 18 lesions underwent excisional biopsy: Two were diagnosed as carcinoma (not otherwise specified), and 16 were diagnosed with a variety of benign disorders. The remaining three patients with atypical lesions chose mammographic follow-up rather than surgical diagnosis, and their conditions have remained stable for more than 24 months. Of the 85 benign cases, one changed during follow-up (12 months) and underwent repeat biopsy, with malignancy noted. The sensitivity of US-guided FNA in identifying malignant lesions was 93% (13 of 14), and the specificity of a benign finding was 100% (102 of 102). The positive and negative predictive values of US-guided FNA supported by on-site cytopathologic evaluation were 100% (13 of 13) and 99% (102 of 103), respectively. CONCLUSION: Supported by appropriately trained on-site cytopathologists and in conjunction with follow-up mammography, US-guided FNA appears to be efficacious in the management of patients with abnormal radiographic findings. It is quick, relatively inexpensive, and minimally invasive, and, in the presence of competent cytopathologists, should be the modality of choice.

The use of an interactive software program for quantitative characterization of microcalcifications on digitized film-screen mammograms.

RATIONALE AND OBJECTIVES: Mammography is relatively nonspecific for the early detection of breast cancer. This study evaluates the accuracy of mammographic interpretation using quantitative features characterizing microcalcifications, which are extracted by a computerized system. METHODS: A computer-aided diagnosis (CAD) system enabling digitization of film-screen mammograms and automatic feature extraction was developed. A classification scheme (discriminant analysis) based on these features was constructed and trained on 217 cases with known pathology. The diagnostic performance of the classification scheme was tested against the radiologist's conventional interpretation on 45 additional cases of microcalcifications, each analyzed independently by four radiologists. RESULTS: The sensitivity of the CAD system analysis (95.7%) was significantly better than that of conventional interpretation (84.8%). The positive predictive value of interpretation increased significantly, as did the area under the receiver operating characteristic curve. CONCLUSIONS: This classification scheme for microcalcifications, based on quantitative features characterizing the lesion, significantly improved the accuracy of mammographic interpretation.

Analysis of clustered microcalcifications by using a single numeric classifier extracted from mammographic digital images.

RATIONALE AND OBJECTIVES: The authors prospectively tested the performance of a single numeric classifier constructed from a discriminative analysis classification system based on automatic computer-extracted quantitative features of clustered microcalcifications. MATERIALS AND METHODS: Mammographically detected clustered microcalcifications in patients who had been referred for biopsy were digitized at 600 dpi with an 8-bit gray scale. A software program was developed to extract features automatically from digitized images to describe the clustered microcalcifications quantitatively. The significance of these features was evaluated by using the Wilcoxon test, the Welch modified two-sample t test, and the two-sample Kolmogorov-Smirnov test. A discriminant analysis pattern recognition system was constructed to generate a single numeric classifier for each case, based on the extracted features. This system was trained on 137 archival known reference cases and its performance tested on 24 unknown prospective cases. The results were evaluated by using receiver operating characteristic analysis. RESULTS: Thirty-seven extracted parameters demonstrated a statistically significant difference between the values for the benign and for the malignant lesions. Seven independent factors were selected to construct the classifier and to evaluate the unknown prospective cases. The area under the receiver operating characteristic curve for the prospective cases was 0.88. CONCLUSION: A pattern recognition classifier based on quantitative features for clustered microcalcifications at screen-film mammography was found to perform satisfactorily. The software may be of value in the interpretation of mammographically detected microcalcifications.