The diagnostic performance of leak-plugging automated segmentation versus manual tracing of breast lesions on ultrasound images.

PURPOSE: To assess the diagnostic performance of a leak-plugging segmentation method that we have developed for delineating breast masses on ultrasound images. MATERIALS AND METHODS: Fifty-two biopsy-proven breast lesion images were analyzed by three observers using the leak-plugging and manual segmentation methods. From each segmentation method, grayscale and morphological features were extracted and classified as malignant or benign by logistic regression analysis. The performance of leak-plugging and manual segmentations was compared by: size of the lesion, overlap area (Oa ) between the margins, and area under the ROC curves (Az ). RESULTS: The lesion size from leak-plugging segmentation correlated closely with that from manual tracing (R2 of 0.91). Oa was higher for leak plugging, 0.92 ± 0.01 and 0.86 ± 0.06 for benign and malignant masses, respectively, compared to 0.80 ± 0.04 and 0.73 ± 0.02 for manual tracings. Overall Oa between leak-plugging and manual segmentations was 0.79 ± 0.14 for benign and 0.73 ± 0.14 for malignant lesions. Az for leak plugging was consistently higher (0.910 ± 0.003) compared to 0.888 ± 0.012 for manual tracings. The coefficient of variation of Az between three observers was 0.29% for leak plugging compared to 1.3% for manual tracings. CONCLUSION: The diagnostic performance, size measurements, and observer variability for automated leak-plugging segmentations were either comparable to or better than those of manual tracings.

Going beyond a First Reader: A Machine Learning Methodology for Optimizing Cost and Performance in Breast Ultrasound Diagnosis.

The goal of this study was to devise a machine learning methodology as a viable low-cost alternative to a second reader to help augment physicians' interpretations of breast ultrasound images in differentiating benign and malignant masses. Two independent feature sets consisting of visual features based on a radiologist's interpretation of images and computer-extracted features when used as first and second readers and combined by adaptive boosting (AdaBoost) and a pruning classifier resulted in a very high level of diagnostic performance (area under the receiver operating characteristic curve = 0.98) at a cost of pruning a fraction (20%) of the cases for further evaluation by independent methods. AdaBoost also improved the diagnostic performance of the individual human observers and increased the agreement between their analyses. Pairing AdaBoost with selective pruning is a principled methodology for achieving high diagnostic performance without the added cost of an additional reader for differentiating solid breast masses by ultrasound.

Observer Variability in BI-RADS Ultrasound Features and Its Influence on Computer-Aided Diagnosis of Breast Masses.

OBJECTIVE: Computer classification of sonographic BI-RADS features can aid differentiation of the malignant and benign masses. However, the variability in the diagnosis due to the differences in the observed features between the observations is not known. The goal of this study is to measure the variation in sonographic features between multiple observations and determine the effect of features variation on computer-aided diagnosis of the breast masses. MATERIALS AND METHODS: Ultrasound images of biopsy proven solid breast masses were analyzed in three independent observations for BI-RADS sonographic features. The BI-RADS features from each observation were used with Bayes classifier to determine probability of malignancy. The observer agreement in the sonographic features was measured by kappa coefficient and the difference in the diagnostic performances between observations was determined by the area under the ROC curve, Az, and interclass correlation coefficient. RESULTS: While some features were repeatedly observed, κ = 0.95, other showed a significant variation, κ = 0.16. For all features, combined intra-observer agreement was substantial, κ = 0.77. The agreement, however, decreased steadily to 0.66 and 0.56 as time between the observations increased from 1 to 2 and 3 months, respectively. Despite the variation in features between observations the probabilities of malignancy estimates from Bayes classifier were robust and consistently yielded same level of diagnostic performance, Az was 0.772 - 0.817 for sonographic features alone and 0.828 - 0.849 for sonographic features and age combined. The difference in the performance, ΔAz, between the observations for the two groups was small (0.003 - 0.044) and was not statistically significant (p < 0.05). Interclass correlation coefficient for the observations was 0.822 (CI: 0.787 - 0.853) for BI-RADS sonographic features alone and for those combined with age was 0.833 (CI: 0.800 - 0.862). CONCLUSION: Despite the differences in the BI- RADS sonographic features between different observations, the diagnostic performance of computer-aided analysis for differentiating breast masses did not change. Through continual retraining, the computer-aided analysis provides consistent diagnostic performance independent of the variations in the observed sonographic features.

Bayesian probability of malignancy with BI-RADS sonographic features.

OBJECTIVES: The purpose of this study was to develop a quantitative approach for combining individual American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) sonographic features of breast masses for assessing the overall probability of malignancy. METHODS: Sonograms of solid breast masses were analyzed by 2 observers blinded to patient age, mammographic features, and lesion pathologic findings. BI-RADS sonographic features were determined by using American College of Radiology criteria. A naïve Bayes model was used to determine the probability of malignancy of all the sonographic features together and with age and BI-RADS mammographic features. The diagnostic performance for various combinations was evaluated by using the area under the receiver operating curve (Az). RESULTS: Sonographic features had high positive and negative predictive values. The Az values for BI-RADS sonographic features for the 2 observers ranged from 0.772 to 0.884, which increased to 0.866 to 0.924 when used with patient age and BI-RADS mammographic features. The benefit of adding age and mammographic information was more marked for the observer with lower initial diagnostic performance. Age-specific analysis showed that diagnostic performance varied with age, with higher performance for patients aged 45 years and younger and patients older than 60 years compared to those aged 46 to 60 years. In 85% of cases, the diagnosis of the observers matched. When the consensus between the observers was used for diagnostic decisions, a high level of diagnostic performance (Az, 0.954) was achieved. CONCLUSIONS: A naïve Bayes model provides a systematic approach for combining sonographic features and other patient characteristics for assessing the probability of malignancy to differentiate malignant and benign breast masses.