Chung Ming Lo

Computer-aided classification of breast masses using speckle features of automated breast ultrasound images

PURPOSE To develop an ultrasound computer-aided diagnosis (CAD) system using speckle features of automated breast ultrasound (ABUS) images. METHODS The ABUS images of 147 pathologically proven breast masses (76 benign and 71 malignant cases) were used. For each mass, a volume of interest (VOI) was cropped to define the tumor area, and the average number of speckle pixels within a VOI was calculated. In addition, first-order and second-order statistical analyses of the speckle pixels were used to quantify the information of gray-level distributions and the spatial relations among the pixels. Receiver operating characteristic curve analysis was used to evaluate the performance. RESULTS The proposed CAD system based on speckle patterns achieved an accuracy of 84.4% (124∕147), a sensitivity of 83.1% (59∕71), a specificity of 85.5% (65∕76), and an Az of 0.91. The performance indices of the speckle features were comparable to the performance indices of the morphological features, which include shape and ellipse-fitting features (p-value > 0.05). Furthermore, combining speckle and morphological features yielded an Az that was significantly better than the Az of the morphological features alone (0.96 vs 0.91, p-value = 0.0154). CONCLUSIONS The results suggest that the proposed speckle features, while combined with morphological features, are promising for the classification of breast masses detected using ABUS.

Multi-Dimensional Tumor Detection in Automated Whole Breast Ultrasound Using Topographic Watershed

Automated whole breast ultrasound (ABUS) is becoming a popular screening modality for whole breast examination. Compared to conventional handheld ultrasound, ABUS achieves operator-independent and is feasible for mass screening. However, reviewing hundreds of slices in an ABUS image volume is time-consuming. A computer-aided detection (CADe) system based on watershed transform was proposed in this study to accelerate the reviewing. The watershed transform was applied to gather similar tissues around local minima to be homogeneous regions. The likelihoods of being tumors of the regions were estimated using the quantitative morphology, intensity, and texture features in the 2-D/3-D false positive reduction (FPR). The collected database comprised 68 benign and 65 malignant tumors. As a result, the proposed system achieved sensitivities of 100% (133/133), 90% (121/133), and 80% (107/133) with FPs/pass of 9.44, 5.42, and 3.33, respectively. The figure of merit of the combination of three feature sets is 0.46 which is significantly better than that of other feature sets (p-value <; 0.05). In summary, the proposed CADe system based on the multi-dimensional FPR using the integrated feature set is promising in detecting tumors in ABUS images.

COMPUTER-AIDED DIAGNOSIS BASED ON SPECKLE PATTERNS IN ULTRASOUND IMAGES

For breast ultrasound, the scatterer number density from backscattered echo was demonstrated in previous research to be a useful feature for tumor characterization. To take advantage of the scatterer number density in B-mode images, spatial compound imaging was obtained, and the statistical properties of speckle patterns were analyzed in this study for use in distinguishing between benign and malignant lesions. A total of 137 breast masses (95 benign cases and 42 malignant cases) were used in the proposed computer-aided diagnosis (CAD) system. For each mass, the average number of speckle pixels in a region of interest (ROI) was calculated to use the concept of scatterer number density. In addition, the first-order and second-order statistics of the speckle pixels were quantified to obtain the distributions of the pixel values and the spatial relations among the pixels. The performance of the speckle features extracted from each ROI was compared with the performance of the segmentation features extracted from each segmented tumor. As a result, the proposed CAD system using the speckle features achieved an accuracy of 89.1% (122/137); a sensitivity of 81.0% (34/42); and a specificity of 92.6% (88/95). All of the differences between the speckle features and the segmentation features are not statistically significant (p > 0.05). In a receiver operating characteristic (ROC) curve analysis, the Az value, area under ROC curve, of the speckle features was significantly better than the Az value of the segmentation features (0.93 vs. 0.86, p = 0.0359). The performance of this approach supports the notion that the speckle patterns induced by the scatterers in tissues can provide information for classifying tumors. The proposed speckle features, which were extracted readily from drawing an ROI without any preprocessing, also provide a more efficient classification approach than tumor segmentation.

Quantification of breast tumor heterogeneity for ER status, HER2 status, and TN molecular subtype evaluation on DCE-MRI.

PURPOSE Recognizing molecular markers is helpful for guiding treatment plans for breast cancer. This study correlated estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), and triple-negative breast cancer (TNBC) statuses to the degree of heterogeneity on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS A total of 102 biopsy-proven cancers from 102 patients between October 2010 and December 2012 were used in this study, including ER (59 positive, 43 negative), HER2 (47 positive, 55 negative), and TNBC (22 TNBC, 80 non-TNBC). At first, the tumor region was segmented by using a region growing method. Then, the region-based features were extracted by the proposed regionalization method to quantify intra-tumoral heterogeneity on breast DCE-MRI. The three-dimensional morphological features (texture features and shape feature) and the pharmacokinetic model were also extracted from the segmented tumor region. After feature extraction, a logistic regression was used to classify ER, HER2, and TNBC statuses respectively. The performances were evaluated by using receiver operating characteristic (ROC) curve analysis. RESULTS The proposed region-based features achieved the accuracy of 73.53%, 82.35%, and 77.45% for ER, HER2, and TNBC classifications. The corresponding area under the ROC curves (Az) achieves 0.7320, 0.8458, and 0.8328 that were better than those of texture features, shape features, and Tofts pharmacokinetic model. CONCLUSION The intra-tumoral heterogeneity quantified by the region-based features can be used to reflect the vasculature complexity of different molecular markers and to provide prediction information of cell surface receptors on clinical examination.

Quantitative breast lesion classification based on multichannel distributions in shear-wave imaging

BACKGROUND AND OBJECTIVES A computer-aided diagnosis (CAD) system based on the quantified color distributions in shear-wave elastography (SWE) was developed to evaluate the malignancies of breast tumors. METHODS For 57 benign and 31 malignant tumors, 18 SWE features were extracted from regions of interest (ROI), including the tumor and peritumoral areas. In the ROI, a histogram in each color channel was described using moments such as the mean, variance, skewness, and kurtosis. Moreover, three color channels were combined as a vector to evaluate tissue elasticity. The SWE features were then combined in a logistic regression classifier for breast tumor classification. RESULTS The performance of the CAD system achieved an accuracy of 81%. Combining the CAD system with a BI-RADS assessment obtained an Az improvement from 0.77 to 0.89 (p-value <0.05). CONCLUSIONS The combination of the proposed CAD system based on SWE features and the BI-RADS assessment would provide a promising diagnostic suggestion.

Computer-aided diagnosis for distinguishing between triple-negative breast cancer and fibroadenomas based on ultrasound texture features

PURPOSE Triple-negative breast cancer (TNBC), an aggressive subtype, is frequently misclassified as fibroadenoma due to benign morphologic features on breast ultrasound (US). This study aims to develop a computer-aided diagnosis (CAD) system based on texture features for distinguishing between TNBC and benign fibroadenomas in US images. METHODS US images of 169 pathology-proven tumors (mean size, 1.65 cm; range, 0.7-3.0 cm) composed of 84 benign fibroadenomas and 85 TNBC tumors are used in this study. After a tumor is segmented out using the level-set method, morphological, conventional texture, and multiresolution gray-scale invariant texture feature sets are computed using a best-fitting ellipse, gray-level co-occurrence matrices, and the ranklet transform, respectively. The linear support vector machine with leave-one-out cross-validation schema is used as a classifier, and the diagnostic performance is assessed with receiver operating characteristic curve analysis. RESULTS The Az values of the morphology, conventional texture, and multiresolution gray-scale invariant texture feature sets are 0.8470 [95% confidence intervals (CIs), 0.7826-0.8973], 0.8542 (95% CI, 0.7911-0.9030), and 0.9695 (95% CI, 0.9376-0.9865), respectively. The Az of the CAD system based on the combined feature sets is 0.9702 (95% CI, 0.9334-0.9882). CONCLUSIONS The CAD system based on texture features extracted via the ranklet transform may be useful for improving the ability to discriminate between TNBC and benign fibroadenomas.

Tumor detection in automated breast ultrasound images using quantitative tissue clustering

PURPOSE A computer-aided detection (CADe) system based on quantitative tissue clustering algorithm was proposed to identify potential tumors in automated breast ultrasound (ABUS) images. METHODS Our three-dimensional (3D) ABUS images database included 148 biopsy-verified lesions (size 0.4-7.9 cm; mean 1.76 cm). An ABUS volume was comprised of 229-282 slices of two-dimensional (2D) images. For tumor detection, the fast 3D mean shift method was used to remove the speckle noise and the segment tissues with similar properties. The hypoechogenic regions, i.e., the tumor candidates, were extracted using fuzzy c-means clustering. Seven features related to echogenicity and morphology were quantified and used to predict the likelihood of identifying a tumor and filtering out the false-positive (FP) regions. RESULTS The sensitivity of the proposed CADe system achieved 89.19% (132/148) with 2.00 FPs per volume. For the volumes without lesion, the FP rate was 1.27. The sensitivity was 92.50% (74/80) for malignant tumors and 85.29% (58/68) for benign tumors. CONCLUSIONS The proposed CADe system provides an automatic and quantitative procedure for tumor detection in ABUS images. Further studies are needed to reduce the FP rate of the CADe algorithm.

Rapid Breast Density Analysis of Partial Volumes of Automated Breast Ultrasound Images

Rapid volume density analysis (RVDA) for automated breast ultrasound (ABUS) has been proposed as a more efficient method for estimating breast density. In the current experiment, ABUS images were obtained for 67 breasts from 40 patients. For each case, three rectangular volumes of interest (VOIs) were extracted, including the VOIs located at the 6 and 12 o’clock positions relative to the nipple in the anterior to posterior pass and the lateral position relative to the nipple in the lateral pass. The centers of these VOIs were defined to align with the center of nipple, and the depths reached the retromammary fat boundary. The fuzzy c-means classifier was applied to differentiate the fibroglandular and fat tissues to estimate the density. The classification results of the three VOIs were averaged to obtain the breast density. The density correlations between the RVDA and the ABUS methods were 0.98 and 0.96 using Pearson’s correlation and linear regression coefficients, respectively. The average computation times for RVDA and ABUS were 4.2 and 17.8 seconds, respectively, using an Intel® Core™2 2.66 GHz computer with 3.25 GB memory. In conclusion, the RVDA method offers a quantitative and efficient breast density estimation for ABUS.

Computer-Aided Strain Evaluation for Acoustic Radiation Force Impulse Imaging of Breast Masses

Acoustic radiation force impulse (ARFI) is a newly developed elastography technique that uses acoustic radiation force to provide additional stiffness information to conventional sonography. A computer-aided diagnosis (CAD) system was proposed to automatically specify the tumor boundaries in ARFI images and quantify the statistical stiffness information to reduce user dependence. The level-set segmentation was used to delineate tumor boundaries in B-mode images, and the segmented boundaries were then mapped to the corresponding area in ARFI images for a gray-scale calculation. A total of 61 benign and 51 malignant tumors were evaluated in the experiment. The CAD system based on the proposed ARFI features achieved an accuracy of 80% (90/112), a sensitivity of 80% (41/51), and a specificity of 80% (49/61), which is significantly better than that of the quantitative B-mode features (p < 0.05). The ARFI features were further combined with the B-mode features, including shape and texture features, to further improve performance (area under the curve [AUC], 0.90 vs. 0.86). In conclusion, the CAD system based on the proposed ARFI features is a promising and efficient diagnostic method.

The adaptive computer-aided diagnosis system based on tumor sizes for the classification of breast tumors detected at screening ultrasound

HighlightsAn adaptive filtering is introduced into a computer‐aided diagnosis (CAD) system to highlight the characteristic of breast tumors detected in screening ultrasound (US).The adaptive filtering enhances the CAD system to emphasize the meaningfulness of tumor size, allows a new regularization technique to be embedded, and increasing the classification accuracy.For the classification between malignant and benign tumors with two kinds of tumor size (Symbol1 cm and Symbol1 cm), especially in the tumors larger or equal to 1 cm, the proposed CAD was more robust than conventional CAD. Symbol. No caption available. Symbol. No caption available.The CAD system using various quantitative US features would provide a promising diagnostic suggestion for classifying the breast tumors detected at screening US images. Abstract Screening ultrasound (US) is increasingly used as a supplement to mammography in women with dense breasts, and more than 80% of cancers detected by US alone are 1 cm or smaller. An adaptive computer‐aided diagnosis (CAD) system based on tumor size was proposed to classify breast tumors detected at screening US images using quantitative morphological and textural features. In the present study, a database containing 156 tumors (78 benign and 78 malignant) was separated into two subsets of different tumor sizes (Symbol1 cm and Symbol1 cm) to explore the improvement in the performance of the CAD system. After adaptation, the accuracies, sensitivities, specificities and Az values of the CAD for the entire database increased from 73.1% (114/156), 73.1% (57/78), 73.1% (57/78), and 0.790 to 81.4% (127/156), 83.3% (65/78), 79.5% (62/78), and 0.852, respectively. In the data subset of tumors larger than 1 cm, the performance improved from 66.2% (51/77), 68.3% (28/41), 63.9% (23/36), and 0.703 to 81.8% (63/77), 85.4% (35/41), 77.8% (28/36), and 0.855, respectively. The proposed CAD system can be helpful to classify breast tumors detected at screening US.