Computer aided classification system for breast ultrasound based on Breast Imaging Reporting and Data System (BI-RADS)

Ultrasound-based deep learning in the establishment of a breast lesion risk stratification system: a multicenter study

OBJECTIVES

To establish a breast lesion risk stratification system using ultrasound images to predict breast malignancy and assess Breast Imaging Reporting and Data System (BI-RADS) categories simultaneously.

METHODS

This multicenter study prospectively collected a dataset of ultrasound images for 5012 patients at thirty-two hospitals from December 2018 to December 2020. A deep learning (DL) model was developed to conduct binary categorization (benign and malignant) and BI-RADS categories (2, 3, 4a, 4b, 4c, and 5) simultaneously. The training set of 4212 patients and the internal test set of 416 patients were from thirty hospitals. The remaining two hospitals with 384 patients were used as an external test set. Three experienced radiologists performed a reader study on 324 patients randomly selected from the test sets. We compared the performance of the DL model with that of three radiologists and the consensus of the three radiologists.

RESULTS

In the external test set, the DL model achieved areas under the receiver operating characteristic curve (AUCs) of 0.980 and 0.945 for the binary categorization and six-way categorizations, respectively. In the reader study set, the DL BI-RADS categories achieved a similar AUC (0.901 vs. 0.933, p = 0.0632), sensitivity (90.98% vs. 95.90%, p = 0.1094), and accuracy (83.33% vs. 79.01%, p = 0.0541), but higher specificity (78.71% vs. 68.81%, p = 0.0012) than those of the consensus of the three radiologists.

CONCLUSIONS

The DL model performed well in distinguishing benign from malignant breast lesions and yielded outcomes similar to experienced radiologists. This indicates the potential applicability of the DL model in clinical diagnosis.

KEY POINTS

• The DL model can achieve binary categorization for benign and malignant breast lesions and six-way BI-RADS categorizations for categories 2, 3, 4a, 4b, 4c, and 5, simultaneously. • The DL model showed acceptable agreement with radiologists for the classification of breast lesions. • The DL model performed well in distinguishing benign from malignant breast lesions and had promise in helping reduce unnecessary biopsies of BI-RADS 4a lesions.

Towards precision medicine based on a continuous deep learning optimization and ensemble approach

We developed a continuous learning system (CLS) based on deep learning and optimization and ensemble approach, and conducted a retrospective data simulated prospective study using ultrasound images of breast masses for precise diagnoses. We extracted 629 breast masses and 2235 images from 561 cases in the institution to train the model in six stages to diagnose benign and malignant tumors, pathological types, and diseases. We randomly selected 180 out of 3098 cases from two external institutions. The CLS was tested with seven independent datasets and compared with 21 physicians, and the system's diagnostic ability exceeded 20 physicians by training stage six. The optimal integrated method we developed is expected accurately diagnose breast masses. This method can also be extended to the intelligent diagnosis of masses in other organs. Overall, our findings have potential value in further promoting the application of AI diagnosis in precision medicine.

A bimodal BI-RADS-guided GoogLeNet-based CAD system for solid breast masses discrimination using transfer learning

Numerous solid breast masses require sophisticated analysis to establish a differential diagnosis. Consequently, complementary modalities such as ultrasound imaging are frequently required to evaluate mammographically further detected masses. Radiologists mentally integrate complementary information from images acquired of the same patient to make a more conclusive and effective diagnosis. However, it has always been a challenging task. This paper details a novel bimodal GoogLeNet-based CAD system that addresses the challenges associated with combining information from mammographic and sonographic images for solid breast mass classification. Each modality is initially trained using two distinct monomodal models in the proposed framework. Then, using the high-level feature maps extracted from both modalities, a bimodal model is trained. In order to fully exploit the BI-RADS descriptors, different image content representations of each mass are obtained and used as input images. In addition, using an ImageNet pre-trained GoogLeNet model, two publicly available databases, and our collected dataset, a two-step transfer learning strategy has been proposed. Our bimodal model achieves the best recognition results in terms of sensitivity, specificity, F1-score, Matthews Correlation Coefficient, area under the receiver operating characteristic curve, and accuracy metrics of 90.91%, 89.87%, 90.32%, 80.78%, 95.82%, and 90.38%, respectively. The promising results indicate that the proposed CAD system can facilitate bimodal suspicious mass analysis and thus contribute significantly to improving breast cancer diagnostic performance.

Application of ultrasound artificial intelligence in the differential diagnosis between benign and malignant breast lesions of BI-RADS 4A

Background

The classification of Breast Imaging Reporting and Data System 4A (BI-RADS 4A) lesions is mostly based on the personal experience of doctors and lacks specific and clear classification standards. The development of artificial intelligence (AI) provides a new method for BI-RADS categorisation. We analysed the ultrasonic morphological and texture characteristics of BI-RADS 4A benign and malignant lesions using AI, and these ultrasonic characteristics of BI-RADS 4A benign and malignant lesions were compared to examine the value of AI in the differential diagnosis of BI-RADS 4A benign and malignant lesions.

Methods

A total of 206 lesions of BI-RADS 4A examined using ultrasonography were analysed retrospectively, including 174 benign lesions and 32 malignant lesions. All of the lesions were contoured manually, and the ultrasonic morphological and texture features of the lesions, such as circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, margin lobulation, energy, entropy, grey mean, internal calcification and angle between the long axis of the lesion and skin, were calculated using grey level gradient co-occurrence matrix analysis. Differences between benign and malignant lesions of BI-RADS 4A were analysed.

Results

Significant differences in margin lobulation, entropy, internal calcification and ALS were noted between the benign group and malignant group (P = 0.013, 0.045, 0.045, and 0.002, respectively). The malignant group had more margin lobulations and lower entropy compared with the benign group, and the benign group had more internal calcifications and a greater angle between the long axis of the lesion and skin compared with the malignant group. No significant differences in circularity, height-to-width ratio, margin spicules, margin coarseness, margin indistinctness, energy, and grey mean were noted between benign and malignant lesions.

Conclusions

Compared with the naked eye, AI can reveal more subtle differences between benign and malignant BI-RADS 4A lesions. These results remind us carefully observation of the margin and the internal echo is of great significance. With the help of morphological and texture information provided by AI, doctors can make a more accurate judgment on such atypical benign and malignant lesions.

S-Detect characterization of focal solid breast lesions: a prospective analysis of inter-reader agreement for US BI-RADS descriptors

BACKGROUND

To assess inter-reader agreement for US BI-RADS descriptors using S-Detect: a computer-guided decision-making software assisting in US morphologic analysis.

METHODS

73 solid focal breast lesions (FBLs) (mean size: 15.9 mm) in 73 consecutive women (mean age: 51 years) detected at US were randomly and independently assessed according to the BI-RADS US lexicon, without and with S-Detect, by five independent reviewers. US-guided core-biopsy and 24-month follow-up were considered as standard of reference. Kappa statistics were calculated to assess inter-operator agreement, between the baseline and after S-Detect evaluation. Agreement was graded as poor (≤ 0.20), moderate (0.21-0.40), fair (0.41-0.60), good (0.61-0.80), or very good (0.81-1.00).

RESULTS

33/73 (45.2%) FBLs were malignant and 40/73 (54.8%) FBLs were benign. A statistically significant improvement of inter-reader agreement from fair to good with the use of S-Detect was observed for shape (from 0.421 to 0.612) and orientation (from 0.417 to 0.7) (p < 0.0001) and from moderate to fair for margin (from 0.204 to 0.482) and posterior features (from 0.286 to 0.522) (p < 0.0001). At baseline analysis isoechoic (0.0485) and heterogeneous (0.1978) echo pattern, microlobulated (0.1161) angular (0.1204) and spiculated (0.1692) margins and combined pattern (0.1549) for posterior features showed the worst agreement rate (poor). After S-Detect evaluation, all variables but isoechoic pattern showed an agreement class upgrade with a statistically significant improvement of inter-reader agreement (p < 0.0001).

CONCLUSIONS

S-Detect significantly improved inter-reader agreement in the assessment of FBLs according to the BI-RADS US lexicon but evaluation of margin and echo pattern needs to be further improved, particularly isoechoic pattern.

Evaluation of the Quadri-Planes Method in Computer-Aided Diagnosis of Breast Lesions by Ultrasonography: Prospective Single-Center Study

Background

Computer-aided diagnosis (CAD) is a tool that can help radiologists diagnose breast lesions by ultrasonography. Previous studies have demonstrated that CAD can help reduce the incidence of missed diagnoses by radiologists. However, the optimal method to apply CAD to breast lesions using diagnostic planes has not been assessed.

Objective

The aim of this study was to compare the performance of radiologists with different levels of experience when using CAD with the quadri-planes method to detect breast tumors.

Methods

From November 2018 to October 2019, we enrolled patients in the study who had a breast mass as their most prominent symptom. We assigned 2 ultrasound radiologists (with 1 and 5 years of experience, respectively) to read breast ultrasonography images without CAD and then to perform a second reading while applying CAD with the quadri-planes method. We then compared the diagnostic performance of the readers for the 2 readings (without and with CAD). The McNemar test for paired data was used for statistical analysis.

Results

A total of 331 patients were included in this study (mean age 43.88 years, range 17-70, SD 12.10), including 512 lesions (mean diameter 1.85 centimeters, SD 1.19; range 0.26-9.5); 200/512 (39.1%) were malignant, and 312/512 (60.9%) were benign. For CAD, the area under the receiver operating characteristic curve (AUC) improved significantly from 0.76 (95% CI 0.71-0.79) with the cross-planes method to 0.84 (95% CI 0.80-0.88; P<.001) with the quadri-planes method. For the novice reader, the AUC significantly improved from 0.73 (95% CI 0.69-0.78) for the without-CAD mode to 0.83 (95% CI 0.80-0.87; P<.001) for the combined-CAD mode with the quadri-planes method. For the experienced reader, the AUC improved from 0.85 (95% CI 0.81-0.88) to 0.87 (95% CI 0.84-0.91; P=.15). The kappa indicating consistency between the experienced reader and the novice reader for the combined-CAD mode was 0.63. For the novice reader, the sensitivity significantly improved from 60.0% for the without-CAD mode to 79.0% for the combined-CAD mode (P=.004). The specificity, negative predictive value, positive predictive value, and accuracy improved from 84.9% to 87.8% (P=.53), 76.8% to 86.7% (P=.07), 71.9% to 80.6% (P=.13), and 75.2% to 84.4% (P=.12), respectively. For the experienced reader, the sensitivity improved significantly from 76.0% for the without-CAD mode to 87.0% for the combined-CAD mode (P=.045). The NPV and accuracy moderately improved from 85.8% and 86.3% to 91.0% (P=.27) and 87.0% (P=.84), respectively. The specificity and positive predictive value decreased from 87.4% to 81.3% (P=.25) and from 87.2% to 93.0% (P=.16), respectively.

Conclusions

S-Detect is a feasible diagnostic tool that can improve the sensitivity, accuracy, and AUC of the quadri-planes method for both novice and experienced readers while also improving the specificity for the novice reader. It demonstrates important application value in the clinical diagnosis of breast cancer.

Trial Registration

ChiCTR.org.cn 1800019649; http://www.chictr.org.cn/showproj.aspx?proj=33094

S-Detect characterization of focal breast lesions according to the US BI RADS lexicon: a pictorial essay

High-resolution ultrasonography (US) is a valuable tool in breast imaging. Nevertheless, US is an operator-dependent technique: to overcome this issue, the American College of Radiology (ACR) has developed the breast imaging-reporting and data system (BI-RADS) US lexicon. Despite this effort, the variability in the assessment of focal breast lesions (FBLs) with the use of BI-RADS US lexicon is still an issue. Within this framework, evidence shows that computer-aided image analysis may be effective in improving the radiologist's assessment of FBLs. In particular, S-Detect is a newly developed image-analytic computer program that provides assistance in morphologic analysis of FBLs seen on US according to the BI-RADS US lexicon. This pictorial essay describes state-of-the-art of sonographic characterization of FBLs by using S-Detect.

Performance of Computer-Aided Diagnosis in Ultrasonography for Detection of Breast Lesions Less and More Than 2 cm: Prospective Comparative Study

Background

Computer-aided diagnosis (CAD) is used as an aid tool by radiologists on breast lesion diagnosis in ultrasonography. Previous studies demonstrated that CAD can improve the diagnosis performance of radiologists. However, the optimal use of CAD on breast lesions according to size (below or above 2 cm) has not been assessed.

Objective

The aim of this study was to compare the performance of different radiologists using CAD to detect breast tumors less and more than 2 cm in size.

Methods

We prospectively enrolled 261 consecutive patients (mean age 43 years; age range 17-70 years), including 398 lesions (148 lesions>2 cm, 79 malignant and 69 benign; 250 lesions≤2 cm, 71 malignant and 179 benign) with breast mass as the prominent symptom. One novice radiologist with 1 year of ultrasonography experience and one experienced radiologist with 5 years of ultrasonography experience were each assigned to read the ultrasonography images without CAD, and then again at a second reading while applying the CAD S-Detect. We then compared the diagnostic performance of the readers in the two readings (without and combined with CAD) with breast imaging. The McNemar test for paired data was used for statistical analysis.

Results

For the novice reader, the area under the receiver operating characteristic curve (AUC) improved from 0.74 (95% CI 0.67-0.82) from the without-CAD mode to 0.88 (95% CI 0.83-0.93; P<.001) at the combined-CAD mode in lesions≤2 cm. For the experienced reader, the AUC improved from 0.84 (95% CI 0.77-0.90) to 0.90 (95% CI 0.86-0.94; P=.002). In lesions>2 cm, the AUC moderately decreased from 0.81 to 0.80 (novice reader) and from 0.90 to 0.82 (experienced reader). The sensitivity of the novice and experienced reader in lesions≤2 cm improved from 61.97% and 73.23% at the without-CAD mode to 90.14% and 97.18% (both P<.001) at the combined-CAD mode, respectively.

Conclusions

S-Detect is a feasible diagnostic tool that can improve the sensitivity for both novice and experienced readers, while also improving the negative predictive value and AUC for lesions≤2 cm, demonstrating important application value in the clinical diagnosis of breast cancer.

Trial Registration

Chinese Clinical Trial Registry ChiCTR1800019649; http://www.chictr.org.cn/showprojen.aspx?proj=33094

Feasibility of computer-assisted diagnosis for breast ultrasound: the results of the diagnostic performance of S-detect from a single center in China

Objective

To investigate the feasibility of a CAD system S-detect on a database from a single Chinese medical center.

Materials and methods

An experienced radiologist performed breast US examinations and made assessments of 266 consecutive breast lesions in 227 patients. S-detect classified the lesions automatically in a dichotomous form. An in-training resident who was blind to both the US diagnostic results and histological results reviewed the images afterward. The final histological results were considered as the diagnostic gold standard. The diagnostic performances and interrater agreements were analyzed.

Results

A total of 266 focal breast lesions (161 benign lesions and 105 malignant lesions) were assessed in this study. S-detect had a lower sensitivity (87.07%) and a higher specificity (72.27%) compared with the experienced radiologist (sensitivity 98.1% and specificity 65.43%). The sensitivity and specificity of S-detect were better than that of the resident (sensitivity 82.86% and specificity 68.94%). The AUC value of S-detect (0.807) showed no significant difference with the experienced radiologist (0.817) and was higher than that of the resident (0.758). S-detect had moderate agreement with the experienced radiologist.

Conclusion

In this single-center study, a high level of diagnostic performance of S-detect on 266 breast lesions of Chinese women was observed. S-detect had almost equal diagnostic capacity with an experienced radiologist and performed better than a novice reader. S-detect was also distinguished for its high specificity. These results supported the feasibility of S-detect in aiding the diagnosis of breast lesions on an independent database.

Computer-aided prediction model for axillary lymph node metastasis in breast cancer using tumor morphological and textural features on ultrasound

BACKGROUND AND OBJECTIVES

Axillary lymph node (ALN) status is a key indicator in assessing and determining the treatment strategy for patients with newly diagnosed breast cancer. Previous studies suggest that sonographic features of a primary tumor have the potential to predict ALN status in the preoperative staging of breast cancer. In this study, a computer-aided prediction (CAP) model as well as the tumor features for ALN metastasis in breast cancers were developed using breast ultrasound (US) images.

METHODS

A total of 249 malignant tumors were acquired from 247 female patients (ages 20-84 years; mean 55 ± 11 years) to test the differences between the non-metastatic (130) and metastatic (119) groups based on various features. After applying semi-automatic tumor segmentation, 69 quantitative features were extracted. The features included morphology and texture of tumors inside a ROI of breast US image. By the backward feature selection and linear logistic regression, the prediction model was constructed and established to estimate the likelihood of ALN metastasis for each sample collected.

RESULTS

In the experiments, the texture features showed higher performance for predicting ALN metastasis compared to morphology (Az, 0.730 vs 0.667). The difference, however, was not statistically significant (p-values > 0.05). Combining the textural and morphological features, the accuracy, sensitivity, specificity, and Az value achieved 75.1% (187/249), 79.0% (94/119), 71.5% (93/130), and 0.757, respectively.

CONCLUSIONS

The proposed CAP model, which combines textural and morphological features of primary tumor, may be a useful method to determine the ALN status in patients with breast cancer.

Automated classification of focal breast lesions according to S-detect: validation and role as a clinical and teaching tool

PURPOSE

To assess the diagnostic performance and the potential as a teaching tool of S-detect in the assessment of focal breast lesions.

METHODS

61 patients (age 21-84 years) with benign breast lesions in follow-up or candidate to pathological sampling or with suspicious lesions candidate to biopsy were enrolled. The study was based on a prospective and on a retrospective phase. In the prospective phase, after completion of baseline US by an experienced breast radiologist and S-detect assessment, 5 operators with different experience and dedication to breast radiology performed elastographic exams. In the retrospective phase, the 5 operators performed a retrospective assessment and categorized lesions with BI-RADS 2013 lexicon. Integration of S-detect to in-training operators evaluations was performed by giving priority to S-detect analysis in case of disagreement. 2 × 2 contingency tables and ROC analysis were used to assess the diagnostic performances; inter-rater agreement was measured with Cohen's k; Bonferroni's test was used to compare performances. A significance threshold of p = 0.05 was adopted.

RESULTS

All operators showed sensitivity > 90% and varying specificity (50-75%); S-detect showed sensitivity > 90 and 70.8% specificity, with inter-rater agreement ranging from moderate to good. Lower specificities were improved by the addition of S-detect. The addition of elastography did not lead to any improvement of the diagnostic performance.

CONCLUSIONS

S-detect is a feasible tool for the characterization of breast lesions; it has a potential as a teaching tool for the less experienced operators.

A computer-aided diagnosis system for breast ultrasound based on weighted BI-RADS classes

BACKGROUND AND OBJECTIVE

Conventional computer-aided diagnosis (CAD) systems for breast ultrasound (BUS) are trained to classify pathological classes, that is, benign and malignant. However, from a clinical perspective, this kind of classification does not agree totally with radiologists' diagnoses. Usually, the tumors are assessed by using a BI-RADS (Breast Imaging-Reporting and Data System) category and, accordingly, a recommendation is emitted: annual study for category 2 (benign), six-month follow-up study for category 3 (probably benign), and biopsy for categories 4 and 5 (suspicious of malignancy). Hence, in this paper, a CAD system based on BI-RADS categories weighted by pathological information is presented. The goal is to increase the classification performance by reducing the common class imbalance found in pathological classes as well as to provide outcomes quite similar to radiologists' recommendations.

METHODS

The BUS dataset considers 781 benign lesions and 347 malignant tumors proven by biopsy. Moreover, every lesion is associated to one BI-RADS category in the set {2, 3, 4, 5}. Thus, the dataset is split into three weighted classes: benign, BI-RADS 2 in benign lesions; probably benign, BI-RADS 3 and 4 in benign lesions; and malignant, BI-RADS 4 and 5 in malignant lesions. Thereafter, a random forest (RF) classifier, denoted by RF_w, is trained to predict the weighted BI-RADS classes. In addition, for comparison purposes, a RF classifier is trained to predict pathological classes, denoted as RF_p.

RESULTS

The ability of the classifiers to predict the pathological classes is measured by the area under the ROC curve (AUC), sensitivity (SEN), and specificity (SPE). The RF_w classifier obtained AUC=0.872,SEN=0.826, and SPE=0.919, whereas the RF_p classifier reached AUC=0.868,SEN=0.808, and SPE=0.929. According to a one-way analysis of variance test, the RF_w classifier statistically outperforms (p < 0.001) the RF_p classifier in terms of the AUC and SEN. Moreover, the classification performance of RF_w to predict weighted BI-RADS classes is given by the Matthews correlation coefficient that obtained 0.614.

CONCLUSIONS

The division of the classification problem into three classes reduces the imbalance between benign and malignant classes; thus, the sensitivity is increased without degrading the specificity. Therefore, the CAD based on weighted BI-RADS classes improves the classification performance of the conventional CAD systems. Additionally, the proposed approach has the advantage of being capable of providing a multiclass outcome related to radiologists' recommendations.

Computer-Aided tumor diagnosis in 3-D breast elastography

BACKGROUND AND OBJECTIVE

Breast cancer is the major cause of cancer-related mortality in women. However, the death rate can be effectively decreased if the breast cancer can be detected early and treated appropriately. In recent years, many studies have indicated that the elastography has the better diagnosis performance than conventional ultrasound (US).

METHOD

In this study, the 3-D tumor contour is obtained by using the proposed segmentation methods and then the features containing texture information, shape information, ellipsoid fitting information are extracted respectively by using the segmented 3-D tumor contour and B-mode images, and the features containing elasticity information are calculated using the same contour and elastographic images.

RESULTS

In this experiment, totally 40 biopsy-proved lesions containing 20 benign tumors and 20 malignant tumors are used to evaluate the proposed computer-aided diagnosis (CAD) system. From the experimental results, the combination of shape, ellipsoid fitting and elastographic features has the best performance with accuracy 90.50% (36/40), sensitivity 85.00% (17/20), specificity 95.00% (19/20), and the area under the ROC curve Az 0.987.

CONCLUSION

The result shows that tumors can be diagnosed more precisely by using the elastography images.

Application of Computer-Aided Diagnosis on Breast Ultrasonography: Evaluation of Diagnostic Performances and Agreement of Radiologists According to Different Levels of Experience

OBJECTIVES

To investigate the feasibility of a computer-aided diagnosis (CAD) system (S-Detect; Samsung Medison, Co, Ltd, Seoul, Korea) for breast ultrasonography (US), according to radiologists with various degrees of experience in breast imaging.

METHODS

From December 2015 to March 2016, 119 breast masses in 116 women were included. Ultrasonographic images of the breast masses were retrospectively reviewed and analyzed by 2 radiologists specializing in breast imaging (7 and 1 years of experience, respectively) and S-Detect, according to the individual ultrasonographic descriptors from the fifth edition of the American College of Radiology Breast Imaging Reporting and Data System and final assessment categories. Diagnostic performance and the interobserver agreement among the radiologists and S-Detect was calculated and compared.

RESULTS

Among the 119 breast masses, 54 (45.4%) were malignant, and 65 (54.6%) were benign. Compared to the radiologists, S-Detect had higher specificity (90.8% compared to 49.2% and 55.4%) and positive predictive value (PPV; 86.7% compared to 60.7% and 63.8%) (all P < .001). Both radiologists had significantly improved specificity, PPV, and accuracy when using S-Detect compared to US alone (all P < .001). The area under the receiving operating characteristic curves of the both radiologists did not show a significant improvement when applying S-Detect compared to US alone (all P > .05). Moderate agreement was seen in final assessments made by each radiologist and S-Detect (κ = 0.40 and 0.45, respectively).

CONCLUSIONS

S-Detect is a clinically feasible diagnostic tool that can be used to improve the specificity, PPV, and accuracy of breast US, with a moderate degree of agreement in final assessments, regardless of the experience of the radiologist.

EMD-DWT based transform domain feature reduction approach for quantitative multi-class classification of breast lesions

Using a large set of ultrasound features does not necessarily ensure improved quantitative classification of breast tumors; rather, it often degrades the performance of a classifier. In this paper, we propose an effective feature reduction approach in the transform domain for improved multi-class classification of breast tumors. Feature transformation methods, such as empirical mode decomposition (EMD) and discrete wavelet transform (DWT), followed by a filter- or wrapper-based subset selection scheme are used to extract a set of non-redundant and more potential transform domain features through decorrelation of an optimally ordered sequence of N ultrasonic bi-modal (i.e., quantitative ultrasound and elastography) features. The proposed transform domain bi-modal reduced feature set with different conventional classifiers will classify 201 breast tumors into benign-malignant as well as BI-RADS⩽3, 4, and 5 categories. For the latter case, an inadmissible error probability is defined for the subset selection using a wrapper/filter. The classifiers use train truth from histopathology/cytology for binary (i.e., benign-malignant) separation of tumors and then bi-modal BI-RADS scores from the radiologists for separating malignant tumors into BI-RADS category 4 and 5. A comparative performance analysis of several widely used conventional classifiers is also presented to assess their efficacy for the proposed transform domain reduced feature set for classification of breast tumors. The results show that our transform domain bimodal reduced feature set achieves improvement of 5.35%, 3.45%, and 3.98%, respectively, in sensitivity, specificity, and accuracy as compared to that of the original domain optimal feature set for benign-malignant classification of breast tumors. In quantitative classification of breast tumors into BI-RADS categories⩽3, 4, and 5, the proposed transform domain reduced feature set attains improvement of 3.49%, 9.07%, and 3.06%, respectively, in likelihood of malignancy and 4.48% in inadmissible error probability compared to that of the original domain optimal subset. In summary, the construction of a transform domain reduced feature set by extracting complementary information from a large set of available bi-modal features and use of qualitative bi-modal BI-RADS can contribute to improved quantitative classification of breast tumors and thereby help reduce the number of unnecessary biopsies, securing a nearly minimum chance of a life-endangering diagnosis.

Computer-aided prediction of axillary lymph node status in breast cancer using tumor surrounding tissue features in ultrasound images

BACKGROUND AND OBJECTIVE

The presence or absence of axillary lymph node (ALN) metastasis is the most important prognostic factor for patients with early-stage breast cancer. In this study, a computer-aided prediction (CAP) system using the tumor surrounding tissue features in ultrasound (US) images was proposed to determine the ALN status in breast cancer.

METHODS

The US imaging database used in this study contained 114 cases of invasive breast cancer and 49 of them were ALN metastasis. After the tumor region segmentation by the level set method, image matting method was used to extract surrounding abnormal tissue of tumor from the acquired images. Then, 21 features composed of 2 intensity, 3 morphology, and 16 textural features are extracted from the surrounding tissue and processed by a logistic regression model. Finally, the prediction model is trained and tested from the selected features.

RESULTS

In the experiments, the textural feature set extracted from surrounding tissue showed higher performance than intensity and morphology feature sets (Az, 0.7756 vs 0.7071 and 0.6431). The accuracy, sensitivity, specificity and the area index Az under the receiver operating characteristic (ROC) curve for the CAP system were 81.58% (93/114), 81.63% (40/49), 81.54% (53/65), and 0.8269 for using combined feature set.

CONCLUSIONS

These results indicated that the proposed CAP system can be helpful to determine the ALN status in patients with breast cancer.

Computer-aided tumor diagnosis using shear wave breast elastography

The shear wave elastography (SWE) uses the acoustic radiation force to measure the stiffness of tissues and is less operator dependent in data acquisition compared to strain elastography. However, the reproducibility of the result is still interpreter dependent. The purpose of this study is to develop a computer-aided diagnosis (CAD) method to differentiate benign from malignant breast tumors using SWE images. After applying the level set method to automatically segment the tumor contour and hue-saturation-value color transformation, SWE features including average tissue elasticity, sectional stiffness ratio, and normalized minimum distance for grouped stiffer pixels are calculated. Finally, the performance of CAD based on SWE features are compared with those based on B-mode ultrasound (morphologic and textural) features, and a combination of both feature sets to differentiate benign from malignant tumors. In this study, we use 109 biopsy-proved breast tumors composed of 57 benign and 52 malignant cases. The experimental results show that the sensitivity, specificity, accuracy and the area under the receiver operating characteristic ROC curve (Az value) of CAD are 86.5%, 93.0%, 89.9%, and 0.905 for SWE features whereas they are 86.5%, 80.7%, 83.5% and 0.893 for B-mode features and 90.4%, 94.7%, 92.3% and 0.961 for the combined features. The Az value of combined feature set is significantly higher compared to the B-mode and SWE feature sets (p=0.0296 and p=0.0204, respectively). Our results suggest that the CAD based on SWE features has the potential to improve the performance of classifying breast tumors with US.

Computer-aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system (LI-RADS)

PURPOSE

To develop and evaluate a computer-aided diagnosis (CAD) program for liver lesions on magnetic resonance (MR) images for classification of the risk of hepatocellular carcinoma (HCC) following the liver imaging reporting and data system (LI-RADS).

MATERIALS AND METHODS

Liver MR images from 41 patients with hyperenhancing liver lesions categorized as LR 3, 4, and 5 were evaluated by two radiologists. The major LI-RADS features of each index liver lesion were recorded, including size (maximum transverse diameter), presence of hyperenhancement, washout appearance, and capsule appearance. A CAD program was implemented to register MR images at different contrast-enhancement phases, segment liver lesions, extract lesion features, and classify lesions according to LI-RADS. The LI-RADS features quantified by CAD were compared with those assessed by radiologists using the intraclass correlation coefficient (ICC) and receiver operator curve (ROC) analyses. The LI-RADS categorization between CAD and radiologists was evaluated using the weighted Cohen's kappa coefficient.

RESULTS

The mean and standard deviation of the lesion diameters were 21 ± 11 mm (range, 7-70 mm) by radiologists and 22 ± 11 mm (range, 8-72 mm) by CAD (ICC, 0.96-0.97). The area under the curve (AUC) for the washout assessment by CAD was 0.79-0.93 with sensitivity 0.69-0.82 and specificity 0.79-1. The AUC for the capsule assessment by CAD was 0.79-0.9 with sensitivity 0.75-0.9 and specificity 0.82-0.96. The classifications by the radiologists and CAD coincided in 76-83% lesions (k = 0.57-0.71), while the agreements between radiologists were in 78% lesions (k = 0.59).

CONCLUSION

We developed a CAD program for liver lesions on MR images and showed a substantial agreement in the LI-RADS-based classification of the risk of HCCs between the CAD and radiologists.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:710-722.

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

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 1cm 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 (<1cm and ⩾1cm) 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 1cm, 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.

The Spatial Relationship of Malignant and Benign Breast Lesions with Respect to the Fat-Gland Interface on Magnetic Resonance Imaging

The fat-gland interface in the breast is noteworthy in that major vessels and lymphatic channels supplying the breast are located there; however, the relationship between breast lesion formation and the fat-gland interface is poorly understood. Here we evaluate the location of malignant and benign breast lesions with respect to the fat-gland interface in 881 women 50 years of age and younger, utilizing MR imaging. We find that most breast lesions are located in or near the interface in qualitative (89.7%) and quantitative (90.0%, 1 cm within the interface) analyses. This propensity for the fat-gland interface is not accounted for by breast anatomy, whereby 12.3% and 55.7% of breast volume is within 2 mm and 1 cm of the interface, respectively. Malignant lesions were located in or near the interface in significantly higher proportions than benign lesions in qualitative (94.3% vs. 67.3%, P < 0.001) and quantitative (49.7% vs. 34.5%, P < 0.001, 2 mm within the interface) analyses. This phenomenon may reflect a biological importance of the fat-gland interface in breast cancer development and progression.

Evaluation of automated breast volume scanner for breast conservation surgery in ductal carcinoma in situ

The present is a retrospective study examining the use of automated breast volume scanner (ABVS) for guiding breast conservation surgery in ductal carcinoma in situ (DCIS). A total of 142 patients with pathologically confirmed DCIS were initially included in the study. The patients underwent preoperative examination by conventional ultrasound and by ABVS. The BI-RADS category system was used to identify benign and malignant lesions, after which breast conservation surgery was performed, and the therapeutic effects were compared. DCIS lesions were found in each quadrant of the breasts. Typical symptoms included: Duct ectasia and filling in 23 cases, mass (mainly solid, occasionally cystic, with or without calcification) in 38 cases, hypoechoic area (with or without calcification) in 33 cases, calcifications (simple) in 23 cases, and architectural distortion in 17 cases. In addition, 110 cases (82.1%) were detected as grade ≥4 according to the BI-RADS category, and 92 cases (68.7%) were considered malignant lesions following conventional ultrasound scanning. The detection rate of ABVS was significantly higher than that of conventional ultrasound (χ²=268.000, P<0.001). The average tumor diameter was 2.5±0.8 cm using ABVS and 2.0±0.9 cm using conventional ultrasound (the former being significantly higher than the latter; t=6.325, P=0.034). Eight patients (5.6%) had recurrences of the cancer, and the tumor diameter in the 8 patients was significantly larger using ABVS as compared to conventional ultrasound. In the diagnosis of DCIS, ABVS was superior to conventional ultrasound scanner in guiding breast conservation surgery and predicting recurrence. However, large-scale studies are required for confirmation of the findings.

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.

Bimodal Multiparameter-Based Approach for Benign-Malignant Classification of Breast Tumors

Proposed here is a breast tumor classification technique using conventional ultrasound B-mode imaging and a new elasticity imaging-based bimodal multiparameter index. A set of conventional ultrasound (US) and ultrasound elastography (UE) parameters are studied, and among those, the effective ones whose independent as well as combined performance is found satisfactory are selected. To improve the combined US performance, two new US parameters are proposed: edge diffusivity, which assesses edge blurriness to differentiate malignant from benign lesions, and the shape asymmetry factor, which quantifies tumor shape irregularity by comparing the tumor boundary with an ellipse fitted to the lesion. Then a new bimodal multiparameter characterization index is defined to discriminate 201 pathologically confirmed breast tumors of which 56 are malignant lesions, 79 are fibroadenomas, 42 are cysts and 24 are inflammatory lesions. The weights of the multiparameter bimodal index are optimally computed using a genetic algorithm (GA). To evaluate the performance variation of the index on different data sets, the tumors are categorized into three classes: malignant lesion versus fibroadenoma, malignant lesion versus fibroadenoma and cyst and malignant lesion versus fibroadenoma, cyst and inflammation. The test results reveal that the proposed bimodal index achieves satisfactory quality metrics (e.g., 94.64%-98.21% sensitivity, 97.24%-100.00% specificity and 96.52%-99.44% accuracy) for classification of the aforementioned three classes of breast tumors. Its performance is also observed to be better in totality of the quality metrics sensitivity, specificity, accuracy, positive predictive value and negative predictive value as compared with that of a conventional bimodal index as well as unimodal multiparameter indices based on US or UE. It is suggested that the proposed simple bimodal linear classifier may assist radiologists in better diagnosis of breast tumors and help reduce the number of unnecessary biopsies.

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, A_z, 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, A_z 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, ΔA_z, 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.

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.

Computerized determination scheme for histological classification of breast mass using objective features corresponding to clinicians' subjective impressions on ultrasonographic images

It is often difficult for clinicians to decide correctly on either biopsy or follow-up for breast lesions with masses on ultrasonographic images. The purpose of this study was to develop a computerized determination scheme for histological classification of breast mass by using objective features corresponding to clinicians' subjective impressions for image features on ultrasonographic images. Our database consisted of 363 breast ultrasonographic images obtained from 363 patients. It included 150 malignant (103 invasive and 47 noninvasive carcinomas) and 213 benign masses (87 cysts and 126 fibroadenomas). We divided our database into 65 images (28 malignant and 37 benign masses) for training set and 298 images (122 malignant and 176 benign masses) for test set. An observer study was first conducted to obtain clinicians' subjective impression for nine image features on mass. In the proposed method, location and area of the mass were determined by an experienced clinician. We defined some feature extraction methods for each of nine image features. For each image feature, we selected the feature extraction method with the highest correlation coefficient between the objective features and the average clinicians' subjective impressions. We employed multiple discriminant analysis with the nine objective features for determining histological classification of mass. The classification accuracies of the proposed method were 88.4 % (76/86) for invasive carcinomas, 80.6 % (29/36) for noninvasive carcinomas, 86.0 % (92/107) for fibroadenomas, and 84.1 % (58/69) for cysts, respectively. The proposed method would be useful in the differential diagnosis of breast masses on ultrasonographic images as diagnosis aid.

Diagnosis of solid breast tumors using vessel analysis in three-dimensional power Doppler ultrasound images

This study aims to evaluate whether the distribution of vessels inside and adjacent to tumor region at three-dimensional (3-D) power Doppler ultrasonography (US) can be used for the differentiation of benign and malignant breast tumors. 3-D power Doppler US images of 113 solid breast masses (60 benign and 53 malignant) were used in this study. Blood vessels within and adjacent to tumor were estimated individually in 3-D power Doppler US images for differential diagnosis. Six features including volume of vessels, vascularity index, volume of tumor, vascularity index in tumor, vascularity index in normal tissue, and vascularity index in surrounding region of tumor within 2 cm were evaluated. Neural network was then used to classify tumors by using these vascular features. The receiver operating characteristic (ROC) curve analysis and Student's t test were used to estimate the performance. All the six proposed vascular features are statistically significant (p < 0.001) for classifying the breast tumors as benign or malignant. The A Z (area under ROC curve) values for the classification result were 0.9138. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis performance based on all six proposed features were 82.30 (93/113), 86.79 (46/53), 78.33 (47/60), 77.97 (46/59), and 87.04 % (47/54), respectively. The p value of A Z values between the proposed method and conventional vascularity index method using z test was 0.04.

Computer-aided multiview tumor detection for automated whole breast ultrasound

Automated whole breast ultrasound (ABUS) has become a popular screening tool in recent years. To reduce the review time and misdetection from ABUS images by physicians, a computer-aided detection (CADe) system for ABUS images based on a multiview method is proposed in this study. A total of 58 pathology-proven lesions from 41 patients were used to evaluate the performance of the system. In the proposed CADe system, the fuzzy c-mean clustering method was applied to detect tumor candidates from these ABUS images. Subsequently, the tumor likelihoods of these candidates could be estimated by a logistic linear regression model based on the intensity, morphology, location, and size features in the transverse, longitudinal, and coronal views. Finally, the multiview tumor likelihoods of the tumor candidates could be obtained from the estimated tumor likelihoods of the three views, and the tumor candidates with high multiview tumor likelihoods were regarded as the detected tumors in the proposed system. The sensitivities of the multiview tumor detection for selecting 5, 10, 20, and 30 tumor candidates with the largest multiview tumor likelihoods were 79.31%, 86.21%, 96.55%, and 98.28%, respectively.

Quantitative ultrasound analysis for classification of BI-RADS category 3 breast masses

The accuracy of an ultrasound (US) computer-aided diagnosis (CAD) system was evaluated for the classification of BI-RADS category 3, probably benign masses. The US database used in this study contained 69 breast masses (21 malignant and 48 benign masses) that at blinded retrospective interpretation were assigned to BI-RADS category 3 by at least one of five radiologists. For computer-aided analysis, multiple morphology (shape, orientation, margin, lesions boundary, and posterior acoustic features) and texture (echo patterns) features based on BI-RADS lexicon were implemented, and the binary logistic regression model was used for classification. The receiver operating characteristic curve analysis was used for statistical analysis. The area under the curve (Az) of morphology, texture, and combined features were 0.90, 0.75, and 0.95, respectively. The combined features achieved the best performance and were significantly better than using texture features only (0.95 vs. 0.75, p value = 0.0163). The cut-off point at the sensitivity of 86 % (18/21), 95 % (20/21), and 100 % (21/21) achieved the specificity of 90 % (43/48), 73 % (35/48), and 33 % (16/48), respectively. In conclusion, the proposed CAD system has the potential to be used in upgrading malignant masses misclassified as BI-RADS category 3 on US by the radiologists.

Computer-aided diagnosis of mass-like lesion in breast MRI: differential analysis of the 3-D morphology between benign and malignant tumors

This study aimed to evaluate the value of using 3-D breast MRI morphologic features to differentiate benign and malignant breast lesions. The 3-D morphological features extracted from breast MRI were used to analyze the malignant likelihood of tumor from ninety-five solid breast masses (44 benign and 51 malignant) of 82 patients. Each mass-like lesion was examined with regards to three categories of morphologic features, including texture-based gray-level co-occurrence matrix (GLCM) feature, shape, and ellipsoid fitting features. For obtaining a robust combination of features from different categories, the biserial correlation coefficient (|r(pb)|)≧0.4 was used as the feature selection criterion. Receiver operating characteristic (ROC) curve was used to evaluate performance and Student's t-test to verify the classification accuracy. The combination of the selected 3-D morphological features, including conventional compactness, radius, spiculation, surface ratio, volume covering ratio, number of inside angular regions, sum of number of inside and outside angular regions, showed an accuracy of 88.42% (84/95), sensitivity of 88.24% (45/51), and specificity of 88.64% (39/44), respectively. The AZ value was 0.8926 for these seven combined morphological features. In conclusion, 3-D MR morphological features specified by GLCM, tumor shape and ellipsoid fitting were useful for differentiating benign and malignant breast masses.

Classification of breast tumors using elastographic and B-mode features: comparison of automatic selection of representative slice and physician-selected slice of images

Inter-observer variability and image quality are two key factors that can affect the diagnostic performance of elastography and B-mode ultrasound for breast tumor characterization. The purpose of this study is to use an image quantification method that automatically chooses a representative slice and then segments the tumor contour to evaluate the diagnostic features for tumor characterization. First, the representative slice is selected based on either the stiffness inside the tumor (the signal-to-noise ratio on the elastogram [SNRe]) or the contrast between the tumor and the surrounding normal tissue (the contrast-to-noise ratio on the elastogram [CNRe]). Next, the level set method is used to segment the tumor contour. Finally, the B-mode and elastographic features related to the segmented tumor are extracted for tumor characterization. The performance of the representative slice selected using the proposed methods is compared to that of the physician-selected slice in 151 biopsy-proven lesions (89 benign and 62 malignant). The diagnostic accuracies using elastographic features are 82.1% (124/151) for the slice with the maximum CNRe value, 82.1% (124/151) for the slice with the maximum SNRe value and 82.8% (125/151) for the physician-selected slice, whereas the diagnostic accuracies using B-mode features are 80.8% (122/151) for the slice with the maximum CNRe value, 87.4% (132/151) for the slice with the maximum SNRe value and 84.1% (127/151) for the physician-selected slice. When using both the B-mode and elastographic features to characterize the tumor, the accuracy of diagnosis is 86.1% (130/151) for the slice with the maximum CNRe value, 90.1% (136/151) for the slice with the maximum SNRe value and 89.4% (135/151) for the physician-selected slice. Our results show that the representative slice selected by SNRe and CNRe could be used to reduce the observer variability and to increase the diagnostic performance by the B-mode and elastographic features.

Computer-aided diagnosis of breast masses using quantified BI-RADS findings

The information from radiologists was utilized in the proposed computer-aided diagnosis (CAD) for breast tumor classification. The ultrasound (US) database used in this study contained 166 benign and 78 malignant masses. For each mass, six quantitative feature sets were used to describe the radiologists' grading of six Breast Imaging Reporting and Data System (BI-RADS) categories including shape, orientation, margins, lesion boundary, echo pattern, and posterior acoustic features on breast US. The descriptive abilities were between 76% and 82% and the predicted descriptors were then used for tumor classification. Using receiver operating characteristic curve for evaluation, the area under curve (AUC) of the proposed CAD was slightly better than that of a conventional CAD based on the combination of all quantitative features (0.96 vs. 0.93, p=0.18). The partial AUC over 90% sensitivity of the proposed CAD was significantly better than that of the conventional CAD (0.90 vs. 0.76, p<0.05). In conclusion, the computer-aided analysis with qualitative information from radiologists showed a promising result for breast tumor classification.

Computer-aided diagnosis for 3-d power Doppler breast ultrasound

In recent studies, both tumor morphology and vascularity played an important role in differentiating breast tumors. In this article, a computer-aided diagnosis (CAD) system was proposed to quantify the tumor morphology of vascularity on three-dimensional (3-D) power Doppler breast ultrasound (PDUS) images. We segmented the tumor margin by the level set method and skeletonized vessels by the 3-D thinning algorithm from 3-D PDUS data to capture the B-mode and vascularity features. The B-mode features including texture, shape and ellipsoid fitting and the vascularity features containing volume, complexity, length, radius and tortuosity were used to differentiate breast tumors. In the experiment, 82 biopsy-verified lesions including 41 benign and 41 malignant lesions were used to test the performance of the proposed system. The proposed method performed well, achieving accuracy, sensitivity, specificity and Az values of 85.37% (70/82), 85.37% (35/41), 85.37% (35/41) and 0.9104, respectively.

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.

Evaluation of the accuracy of a computer-aided diagnosis (CAD) system in breast ultrasound according to the radiologist's experience

RATIONALE AND OBJECTIVES

The aim of this study was to evaluate the performance of a computer-aided diagnosis (CAD) system for breast ultrasound to improve the characterization of breast lesions detected on ultrasound by junior and senior radiologists.

MATERIALS AND METHODS

One hundred sixty ultrasound breast lesions were randomly reviewed blindly by four radiologists with different levels of expertise (from 20 years [radiologist A] to 4 months [radiologist D]), with and without the help of an ultrasound CAD system (B-CAD version 2). All lesions had been biopsied. Sensitivity and specificity with and without CAD were calculated for each radiologist for the following evaluation criteria: Breast Imaging Reporting and Data System category and the final diagnosis (benign or malignant). Intrinsic sensitivity, specificity, and predictive values of CAD alone were also calculated.

RESULTS

CAD detected all cancers, and its use increased radiologists' sensitivity scores when this was possible (with vs without CAD: radiologist A, 99% vs 99%; radiologist B, 96% vs 87%; radiologist C, 95% vs 88%; radiologist D, 91% vs 88%). Seven additional cancers were diagnosed. However, the low specificity of CAD (48%) decreased the specificity of radiologists, especially of the more experienced among them (with vs without CAD: radiologist A, 46% vs 70%; radiologist B, 58% vs 80%; radiologist C, 57% vs 69%; radiologist D, 71% vs 71%).

CONCLUSIONS

CAD for breast ultrasound appears to be a useful tool for improving the diagnosis of malignant lesions for junior radiologists. Nevertheless, its low specificity must be taken into account to limit biopsies of benign lesions.

Computer-aided diagnosis for the classification of breast masses in automated whole breast ultrasound images

New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student's t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0% (125/147), sensitivity of 84.5% (60/71), specificity of 85.5% (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors.

Computer-aided diagnosis for contrast-enhanced ultrasound in the liver

Computer-aided diagnosis (CAD) has become one of the major research subjects in medical imaging and diagnostic radiology. The basic concept of CAD is to provide computer output as a second opinion to assist radiologists’ image interpretations by improving the accuracy and consistency of radiologic diagnosis and also by reducing the image-reading time. To date, research on CAD in ultrasound (US)-based diagnosis has been carried out mostly for breast lesions and has been limited in the fields of gastroenterology and hepatology, with most studies being conducted using B-mode US images. Two CAD schemes with contrast-enhanced US (CEUS) that are used in classifying focal liver lesions (FLLs) as liver metastasis, hemangioma, or three histologically differentiated types of hepatocellular carcinoma (HCC) are introduced in this article: one is based on physicians’ subjective pattern classifications (subjective analysis) and the other is a computerized scheme for classification of FLLs (quantitative analysis). Classification accuracies for FLLs for each CAD scheme were 84.8% and 88.5% for metastasis, 93.3% and 93.8% for hemangioma, and 98.6% and 86.9% for all HCCs, respectively. In addition, the classification accuracies for histologic differentiation of HCCs were 65.2% and 79.2% for well-differentiated HCCs, 41.7% and 50.0% for moderately differentiated HCCs, and 80.0% and 77.8% for poorly differentiated HCCs, respectively. There are a number of issues concerning the clinical application of CAD for CEUS, however, it is likely that CAD for CEUS of the liver will make great progress in the future.

Classification of benign and malignant breast tumors by 2-d analysis based on contour description and scatterer characterization

Ultrasound B-mode scanning based on the echo intensity has become an important clinical tool for routine breast screening. The efficacy of the Nakagami parametric image based on the distribution of the backscattered signals for quantifying properties of breast tissue was recently evaluated. The B-mode and Nakagami images reflect different physical characteristic of breast tumors: the former describes the contour features, and the latter reflects the scatterer arrangement inside a tumor. The functional complementation of these two images encouraged us to propose a novel method of 2-D analysis based on describing the contour using the B-mode image and the scatterer properties using the Nakagami image, which may provide useful clues for classifying benign and malignant tumors. To validate this concept, raw data were acquired from 60 clinical cases, and five contour feature parameters (tumor circularity, standard deviation of the normalized radial length, area ratio, roughness index, and standard deviation of the shortest distance) and the Nakagami parameters of benign and malignant tumors were calculated. The receiver operating characteristic curve and fuzzy c-means clustering were used to evaluate the performances of combining the parameters in classifying tumors. The clinical results demonstrated the presence of a tradeoff between the sensitivity and specificity when either using a single parameter or combining two contour parameters to discriminate between benign and malignant cases. However, combining the contour parameters and the Nakagami parameter produces sensitivity and specificity that simultaneously exceed 80%, which means that the functional complementation from the B-scan and the Nakagami image indeed enhances the performance in diagnosing breast tumors.

Analysis of elastographic and B-mode features at sonoelastography for breast tumor classification

The purpose of this study was to evaluate the accuracy of neural network analysis of elastographic features at sonoelastography for the classification of biopsy-proved benign and malignant breast tumors. Sonoelastography of 181 solid breast masses (113 benign and 68 malignant tumors) was performed for 181 patients (mean age, 47 years; range, 24-75 years). After the manual segmentation of the tumors, five elastographic features (strain difference, strain ratio, mean, median and mode) and six B-mode features (orientation, undulation, angularity, average gradient, gradient variance and intensity variance) were computed. A neural network was used to classify tumors by the use of these features. The Student's t test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. Area under ROC curve (Az) values of the three elastographic features- mean (0.87), median (0.86) and mode (0.83)-were significantly higher than the Az values for the six B-mode features (0.54-0.69) (p < 0.01). Accuracy, sensitivity, specificity and Az of the neural network for the classification of solid breast tumors were 86.2% (156/181), 83.8% (57/68), 87.6% (99/113) and 0.84 for the elastographic features, respectively, and 82.3% (149/181), 70.6% (48/68), 89.4% (101/113) and 0.78 for the B-mode features, respectively, and 90.6% (164/181), 95.6% (65/68), 87.6% (99/113) and 0.92 for the combination of the elastographic and B-mode features, respectively. We conclude that sonoelastographic images and neural network analysis of features has the potential to increase the accuracy of the use of ultrasound for the classification of benign and malignant breast tumors.

Current improvements in breast ultrasound, with a special focus on elastography

Current improvements in the area of breast ultrasound are described. Digital beam formers contributed to improving both contrast and special resolution of B-mode images and enabled other techniques. Four-dimensional images and CAD are still in progress. Elastography may reduce false-positives and unnecessary interventional procedures, especially in nonsymptomatic patients.