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

Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms

Breast cancer is the most common cancer in women. Ultrasound is one of the most used techniques for diagnosis, but an expert in the field is necessary to interpret the test. Computer-aided diagnosis (CAD) systems aim to help physicians during this process. Experts use the Breast Imaging-Reporting and Data System (BI-RADS) to describe tumors according to several features (shape, margin, orientation...) and estimate their malignancy, with a common language. To aid in tumor diagnosis with BI-RADS explanations, this paper presents a deep neural network for tumor detection, description, and classification. An expert radiologist described with BI-RADS terms 749 nodules taken from public datasets. The YOLO detection algorithm is used to obtain Regions of Interest (ROIs), and then a model, based on a multi-class classification architecture, receives as input each ROI and outputs the BI-RADS descriptors, the BI-RADS classification (with 6 categories), and a Boolean classification of malignancy. Six hundred of the nodules were used for 10-fold cross-validation (CV) and 149 for testing. The accuracy of this model was compared with state-of-the-art CNNs for the same task. This model outperforms plain classifiers in the agreement with the expert (Cohen's kappa), with a mean over the descriptors of 0.58 in CV and 0.64 in testing, while the second best model yielded kappas of 0.55 and 0.59, respectively. Adding YOLO to the model significantly enhances the performance (0.16 in CV and 0.09 in testing). More importantly, training the model with BI-RADS descriptors enables the explainability of the Boolean malignancy classification without reducing accuracy.

Vacuum-assisted biopsy system for breast lesions: a potential therapeutic approach

Purpose

The primary objective is to optimize the population eligible for Mammotome Minimally Invasive Surgery (MIS) by refining selection criteria. This involves maximizing procedure benefits, minimizing malignancy risk, and reducing the rate of malignant outcomes.

Patients and methods

A total of 1158 female patients who came to our hospital from November 2016 to August 2021 for the Mammotome MIS were analyzed retrospectively. Following χ2 tests to screen for risk variables, binary logistic regression analysis was used to determine the independent predictors of malignant lesions. In addition, the correlation between age and lesion diameter was investigated for BI-RADS ultrasound (US) category 4a lesions in order to better understand the relationship between these variables.

Results

The malignancy rates of BI-RADS US category 3, category 4a and category 4b patients who underwent the Mammotome MIS were 0.6% (9/1562), 6.4% (37/578) and 8.3% (2/24) respectively. Malignant lesions were more common in patients over the age of 40, have visible blood supply, and BI-RADS category 4 of mammography. In BI-RADS US category 4a lesions, the diameter of malignant tumor was highly correlated with age, and this correlation was strengthened in patients over the age of 40 and with BI-RADS category 4 of mammography.

Conclusion

The results of this study demonstrate that the clinical data and imaging results, particularly age, blood supply, and mammography classification, offer valuable insights to optimize patients' surgical options and decrease the incidence of malignant outcomes.

A Novel Deep-Learning-Based CADx Architecture for Classification of Thyroid Nodules Using Ultrasound Images

Nodules of thyroid cancer occur in the cells of the thyroid as benign or malign types. Thyroid sonographic images are mostly used for diagnosis of thyroid cancer. The aim of this study is to introduce a computer-aided diagnosis system that can classify the thyroid nodules with high accuracy using the data gathered from ultrasound images. Acquisition and labeling of sub-images were performed by a specialist physician. Then the number of these sub-images were increased using data augmentation methods. Deep features were obtained from the images using a pre-trained deep neural network. The dimensions of the features were reduced and features were improved. The improved features were combined with morphological and texture features. This feature group was rated by a value called similarity coefficient value which was obtained from a similarity coefficient generator module. The nodules were classified as benign or malignant using a multi-layer deep neural network with a pre-weighting layer designed with a novel approach. In this study, a novel multi-layer computer-aided diagnosis system was proposed for thyroid cancer detection. In the first layer of the system, a novel feature extraction method based on the class similarity of images was developed. In the second layer, a novel pre-weighting layer was proposed by modifying the genetic algorithm. The proposed system showed superior performance in different metrics compared to the literature.

Multi-Task/Single-Task Joint Learning of Ultrasound BI-RADS Features

Breast cancer is one of the most common cancers among women in the world. The breast imaging reporting and data system (BI-RADS) features effectively improve the accuracy and sensitivity of breast tumors. Based on the description of signs in BI-RADS, a quantitative scoring scheme is proposed based on ultrasound (US) data. This scheme includes feature extraction of high-level semantic, that is, an intermediate step interpreting the subsequent diagnosis. However, the scheme requires doctors to score the features of breast data, which is labor-intensive. To reduce the burden of doctors, we design a multi-task learning (MTL) framework, which can directly output the scores of different BI-RADS features from the raw US images. The MTL framework consists of a shared network that learns global features and K soft attention networks for different BI-RADS features. Thus, it enables the network not only to learn the potential correlation among different BI-RADS features, but also learn the unique specificity of each feature, which can assist each other and jointly improve the scoring accuracy. In addition, we group different BI-RADS features according to the correlation among tasks and build a multi-task/single-task joint framework. Experimental results on the US breast tumor dataset collected from 1859 patients with 4458 US images show that the proposed BI-RADS feature scoring framework achieves an average scoring accuracy of 84.91% for 11 BI-RADS features on the test dataset, which is helpful for the subsequent diagnosis of breast tumors.

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.

Differential diagnosis between small breast phyllodes tumors and fibroadenomas using artificial intelligence and ultrasound data

Background

It is challenging to differentiate between phyllodes tumors (PTs) and fibroadenomas (FAs). Artificial intelligence (AI) can provide quantitative information regarding the morphology and textural features of lesions. This study attempted to use AI to evaluate the ultrasonic images of PTs and FAs and to explore the diagnostic performance of AI features in the differential diagnosis of PTs and FAs.

Methods

A total of 40 PTs and 290 FAs <5 cm in maximum diameter found in female patients were retrospectively analyzed. All tumors were segmented by doctors, and the features of the lesions were collated, including circularity, height-to-width ratio, margin spicules, margin coarseness (MC), margin indistinctness, margin lobulation (ML), internal calcification, angle between the long axis of the lesion and skin, energy, grey entropy, and grey mean. The differences between PTs and FAs were analyzed, and the diagnostic performance of AI features in the differential diagnosis of PTs and FAs was evaluated.

Results

Statistically significant differences (P<0.05) were found in the height-to-width ratio, ML, energy, and grey entropy between the PTs and FAs. Receiver operating characteristic (ROC) curve analysis of single features showed that the area under the curve [(AUC) 0.759] of grey entropy was the largest among the four features with statistically significant differences, and the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 0.925, 0.459, 0.978, and 0.190, respectively. When considering the combinations of the features, the combination of height-to-width ratio, margin indistinctness, ML, energy, grey entropy, and internal calcification was the most optimal of the combinations of features with an AUC of 0.868, and a sensitivity, specificity, PPV, and NPV of 0.734, 0.900, 0.982, and 0.316, respectively.

Conclusions

Quantitative analysis of AI can identify subtle differences in the morphology and textural features between small PTs and FAs. Comprehensive consideration of multiple features is important for the differential diagnosis of PTs and FAs.

Automated breast ultrasound: Supplemental screening for average-risk women with dense breasts

OBJECTIVE

We review ultrasound (US) options for supplemental breast cancer screening of average risk women with dense breasts.

CONCLUSION

Performance data of physician-performed handheld US (HHUS), technologist-performed HHUS, and automated breast ultrasound (AUS) indicate that all are appropriate for adjunctive screening. Volumetric 3D acquisitions, reduced operator dependence, protocol standardization, reliable comparison with previous studies, independence of performance and interpretation, and whole breast depiction on coronal view may favor selection of AUS. Important considerations are workflow adjustments for physicians and staff.

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.

A Novel Computer-Aided-Diagnosis System for Breast Ultrasound Images Based on BI-RADS Categories

The breast ultrasound is not only one of major devices for breast tissue imaging, but also one of important methods in breast tumor screening. It is non-radiative, non-invasive, harmless, simple, and low cost screening. The American College of Radiology (ACR) proposed the Breast Imaging Reporting and Data System (BI-RADS) to evaluate far more breast lesion severities compared to traditional diagnoses according to five-criterion categories of masses composition described as follows: shape, orientation, margin, echo pattern, and posterior features. However, there exist some problems, such as intensity differences and different resolutions in image acquisition among different types of ultrasound imaging modalities so that clinicians cannot always identify accurately the BI-RADS categories or disease severities. To this end, this article adopted three different brands of ultrasound scanners to fetch breast images for our experimental samples. The breast lesion was detected on the original image using preprocessing, image segmentation, etc. The breast tumor’s severity was evaluated on the features of the breast lesion via our proposed classifiers according to the BI-RADS standard rather than traditional assessment on the severity; i.e., merely using benign or malignant. In this work, we mainly focused on the BI-RADS categories 2–5 after the stage of segmentation as a result of the clinical practice. Moreover, several features related to lesion severities based on the selected BI-RADS categories were introduced into three machine learning classifiers, including a Support Vector Machine (SVM), Random Forest (RF), and Convolution Neural Network (CNN) combined with feature selection to develop a multi-class assessment of breast tumor severity based on BI-RADS. Experimental results show that the proposed CAD system based on BI-RADS can obtain the identification accuracies with SVM, RF, and CNN reaching 80.00%, 77.78%, and 85.42%, respectively. We also validated the performance and adaptability of the classification using different ultrasound scanners. Results also indicate that the evaluations of F-score based on CNN can obtain measures higher than 75% (i.e., prominent adaptability) when samples were tested on various BI-RADS categories.

A combined ultrasonic B-mode and color Doppler system for the classification of breast masses using neural network

OBJECTIVES

To develop a dual-modal neural network model to characterize ultrasound (US) images of breast masses.

MATERIALS AND METHODS

A combined US B-mode and color Doppler neural network model was developed to classify US images of the breast. Three datasets with breast masses were originally detected and interpreted by 20 experienced radiologists according to Breast Imaging-Reporting and Data System (BI-RADS) lexicon ((1) training set, 103212 masses from 45,433 + 12,519 patients. (2) held-out validation set, 2748 masses from 1197 + 395 patients. (3) test set, 605 masses from 337 + 78 patients). The neural network was first trained on training set. Then, the trained model was tested on a held-out validation set to evaluate agreement on BI-RADS category between the model and the radiologists. In addition, the model and a reader study of 10 radiologists were applied to the test set with biopsy-proven results. To evaluate the performance of the model in benign or malignant classifications, the receiver operating characteristic curve, sensitivities, and specificities were compared.

RESULTS

The trained dual-modal model showed favorable agreement with the assessment performed by the radiologists (κ = 0.73; 95% confidence interval, 0.71-0.75) in classifying breast masses into four BI-RADS categories in the validation set. For the binary categorization of benign or malignant breast masses in the test set, the dual-modal model achieved the area under the ROC curve (AUC) of 0.982, while the readers scored an AUC of 0.948 in terms of the ROC convex hull.

CONCLUSION

The dual-modal model can be used to assess breast masses at a level comparable to that of an experienced radiologist.

KEY POINTS

• A neural network model based on ultrasonic imaging can classify breast masses into different Breast Imaging-Reporting and Data System categories according to the probability of malignancy. • A combined ultrasonic B-mode and color Doppler neural network model achieved a high level of agreement with the readings of an experienced radiologist and has the potential to automate the routine characterization of breast masses.

Automatic classification of ultrasound breast lesions using a deep convolutional neural network mimicking human decision-making

OBJECTIVES

To evaluate a deep convolutional neural network (dCNN) for detection, highlighting, and classification of ultrasound (US) breast lesions mimicking human decision-making according to the Breast Imaging Reporting and Data System (BI-RADS).

METHODS AND MATERIALS

One thousand nineteen breast ultrasound images from 582 patients (age 56.3 ± 11.5 years) were linked to the corresponding radiological report. Lesions were categorized into the following classes: no tissue, normal breast tissue, BI-RADS 2 (cysts, lymph nodes), BI-RADS 3 (non-cystic mass), and BI-RADS 4-5 (suspicious). To test the accuracy of the dCNN, one internal dataset (101 images) and one external test dataset (43 images) were evaluated by the dCNN and two independent readers. Radiological reports, histopathological results, and follow-up examinations served as reference. The performances of the dCNN and the humans were quantified in terms of classification accuracies and receiver operating characteristic (ROC) curves.

RESULTS

In the internal test dataset, the classification accuracy of the dCNN differentiating BI-RADS 2 from BI-RADS 3-5 lesions was 87.1% (external 93.0%) compared with that of human readers with 79.2 ± 1.9% (external 95.3 ± 2.3%). For the classification of BI-RADS 2-3 versus BI-RADS 4-5, the dCNN reached a classification accuracy of 93.1% (external 95.3%), whereas the classification accuracy of humans yielded 91.6 ± 5.4% (external 94.1 ± 1.2%). The AUC on the internal dataset was 83.8 (external 96.7) for the dCNN and 84.6 ± 2.3 (external 90.9 ± 2.9) for the humans.

CONCLUSION

dCNNs may be used to mimic human decision-making in the evaluation of single US images of breast lesion according to the BI-RADS catalog. The technique reaches high accuracies and may serve for standardization of highly observer-dependent US assessment.

KEY POINTS

• Deep convolutional neural networks could be used to classify US breast lesions. • The implemented dCNN with its sliding window approach reaches high accuracies in the classification of US breast lesions. • Deep convolutional neural networks may serve for standardization in US BI-RADS classification.

Classification of breast lesions in ultrasonography using sparse logistic regression and morphology-based texture features

PURPOSE

This work proposes a new reliable computer-aided diagnostic (CAD) system for the diagnosis of breast cancer from breast ultrasound (BUS) images. The system can be useful to reduce the number of biopsies and pathological tests, which are invasive, costly, and often unnecessary.

METHODS

The proposed CAD system classifies breast tumors into benign and malignant classes using morphological and textural features extracted from breast ultrasound (BUS) images. The images are first preprocessed to enhance the edges and filter the speckles. The tumor is then segmented semiautomatically using the watershed method. Having the tumor contour, a set of 855 features including 21 shape-based, 810 contour-based, and 24 textural features are extracted from each tumor. Then, a Bayesian Automatic Relevance Detection (ARD) mechanism is used for computing the discrimination power of different features and dimensionality reduction. Finally, a logistic regression classifier computed the posterior probabilities of malignant vs benign tumors using the reduced set of features.

RESULTS

A dataset of 104 BUS images of breast tumors, including 72 benign and 32 malignant tumors, was used for evaluation using an eightfold cross-validation. The algorithm outperformed six state-of-the-art methods for BUS image classification with large margins by achieving 97.12% accuracy, 93.75% sensitivity, and 98.61% specificity rates.

CONCLUSIONS

Using ARD, the proposed CAD system selects five new features for breast tumor classification and outperforms state-of-the-art, making a reliable and complementary tool to help clinicians diagnose breast cancer.

Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic review

BACKGROUND AND OBJECTIVE

The high incidence of breast cancer in women has increased significantly in the recent years. Physician experience of diagnosing and detecting breast cancer can be assisted by using some computerized features extraction and classification algorithms. This paper presents the conduction and results of a systematic review (SR) that aims to investigate the state of the art regarding the computer aided diagnosis/detection (CAD) systems for breast cancer.

METHODS

The SR was conducted using a comprehensive selection of scientific databases as reference sources, allowing access to diverse publications in the field. The scientific databases used are Springer Link (SL), Science Direct (SD), IEEE Xplore Digital Library, and PubMed. Inclusion and exclusion criteria were defined and applied to each retrieved work to select those of interest. From 320 studies retrieved, 154 studies were included. However, the scope of this research is limited to scientific and academic works and excludes commercial interests.

RESULTS

This survey provides a general analysis of the current status of CAD systems according to the used image modalities and the machine learning based classifiers. Potential research studies have been discussed to create a more objective and efficient CAD systems.

Classification of breast cancer in ultrasound imaging using a generic deep learning analysis software: a pilot study

OBJECTIVE

To train a generic deep learning software (DLS) to classify breast cancer on ultrasound images and to compare its performance to human readers with variable breast imaging experience.

METHODS

In this retrospective study, all breast ultrasound examinations from January 1, 2014 to December 31, 2014 at our institution were reviewed. Patients with post-surgical scars, initially indeterminate, or malignant lesions with histological diagnoses or 2-year follow-up were included. The DLS was trained with 70% of the images, and the remaining 30% were used to validate the performance. Three readers with variable expertise also evaluated the validation set (radiologist, resident, medical student). Diagnostic accuracy was assessed with a receiver operating characteristic analysis.

RESULTS

82 patients with malignant and 550 with benign lesions were included. Time needed for training was 7 min (DLS). Evaluation time for the test data set were 3.7 s (DLS) and 28, 22 and 25 min for human readers (decreasing experience). Receiver operating characteristic analysis revealed non-significant differences (p-values 0.45-0.47) in the area under the curve of 0.84 (DLS), 0.88 (experienced and intermediate readers) and 0.79 (inexperienced reader).

CONCLUSION

DLS may aid diagnosing cancer on breast ultrasound images with an accuracy comparable to radiologists, and learns better and faster than a human reader with no prior experience. Further clinical trials with dedicated algorithms are warranted. Advances in knowledge: DLS can be trained classify cancer on breast ultrasound images high accuracy even with comparably few training cases. The fast evaluation speed makes real-time image analysis feasible.

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 diagnosis of contrast-enhanced spectral mammography: A feasibility study

OBJECTIVE

To evaluate whether the use of a computer-aided diagnosis-contrast-enhanced spectral mammography (CAD-CESM) tool can further increase the diagnostic performance of CESM compared with that of experienced radiologists.

MATERIALS AND METHODS

This IRB-approved retrospective study analyzed 50 lesions described on CESM from August 2014 to December 2015. Histopathologic analyses, used as the criterion standard, revealed 24 benign and 26 malignant lesions. An expert breast radiologist manually outlined lesion boundaries on the different views. A set of morphologic and textural features were then extracted from the low-energy and recombined images. Machine-learning algorithms with feature selection were used along with statistical analysis to reduce, select, and combine features. Selected features were then used to construct a predictive model using a support vector machine (SVM) classification method in a leave-one-out-cross-validation approach. The classification performance was compared against the diagnostic predictions of 2 breast radiologists with access to the same CESM cases.

RESULTS

Based on the SVM classification, CAD-CESM correctly identified 45 of 50 lesions in the cohort, resulting in an overall accuracy of 90%. The detection rate for the malignant group was 88% (3 false-negative cases) and 92% for the benign group (2 false-positive cases). Compared with the model, radiologist 1 had an overall accuracy of 78% and a detection rate of 92% (2 false-negative cases) for the malignant group and 62% (10 false-positive cases) for the benign group. Radiologist 2 had an overall accuracy of 86% and a detection rate of 100% for the malignant group and 71% (8 false-positive cases) for the benign group.

CONCLUSIONS

The results of our feasibility study suggest that a CAD-CESM tool can provide complementary information to radiologists, mainly by reducing the number of false-positive findings.

EEMD Domain AR Spectral Method for Mean Scatterer Spacing Estimation of Breast Tumors From Ultrasound Backscattered RF Data

We present a novel method for estimating the mean scatterer spacing (MSS) of breast tumors using ensemble empirical mode decomposition (EEMD) domain analysis of deconvolved backscattered radio frequency (RF) data. The autoregressive (AR) spectrum from which the MSS is estimated is obtained from the intrinsic mode functions (IMFs) due to regular scatterers embedded in RF data corrupted by the diffuse scatterers. The IMFs are chosen by giving priority to the presence of an enhanced fundamental harmonic and the presence of a greater number of higher harmonics in the AR spectrum estimated from the IMFs. The AR model order is chosen by minimizing the mean absolute percentage error (MAPE) criterion. In order to ensure that the backscattered data is indeed from a source of coherent scattering, we begin by performing a non-parametric Kolmogorov-Smirnov (K-S) classification test on the backscattered RF data. Deconvolution of the backscattered RF data, which have been classified by the K-S test as sources of significant coherent scattering, is done to reduce the system effect. EEMD domain analysis is then performed on the deconvolved data. The proposed method is able to recover the harmonics associated with the regular scatterers and overcomes many problems encountered while estimating the MSS from the AR spectrum of raw RF data. Using our technique, a mean absolute percentage error (MAPE) of 5.78% is obtained while estimating the MSS from simulated data, which is lower than that of the existing techniques. Our proposed method is shown to outperform the state of the art techniques, namely, singular spectrum analysis, generalized spectrum (GS), spectral autocorrelation (SAC), and modified SAC for different simulation conditions. The MSS for in vivo normal breast tissue is found to be 0.69 ± 0.04 mm; for benign and malignant tumors it is found to be 0.73 ± 0.03 and 0.79 ± 0.04 mm, respectively. The separation between the MSS values of normal and benign tissues for our proposed method is similar to the separations obtained for the conventional methods, but the separation between the MSS values for benign and malignant tissues for our proposed method is slightly higher than that for the conventional methods. When the MSS is used to classify breast tumors into benign and malignant, for a threshold-based classifier, the increase in specificity, accuracy, and area under curve are 18%, 19%, and 22%, respectively, and that for statistical classifiers are 9%, 13%, and 19%, respectively, from that of the next best existing technique.

A Fusion-Based Approach for Breast Ultrasound Image Classification Using Multiple-ROI Texture and Morphological Analyses

Ultrasound imaging is commonly used for breast cancer diagnosis, but accurate interpretation of breast ultrasound (BUS) images is often challenging and operator-dependent. Computer-aided diagnosis (CAD) systems can be employed to provide the radiologists with a second opinion to improve the diagnosis accuracy. In this study, a new CAD system is developed to enable accurate BUS image classification. In particular, an improved texture analysis is introduced, in which the tumor is divided into a set of nonoverlapping regions of interest (ROIs). Each ROI is analyzed using gray-level cooccurrence matrix features and a support vector machine classifier to estimate its tumor class indicator. The tumor class indicators of all ROIs are combined using a voting mechanism to estimate the tumor class. In addition, morphological analysis is employed to classify the tumor. A probabilistic approach is used to fuse the classification results of the multiple-ROI texture analysis and morphological analysis. The proposed approach is applied to classify 110 BUS images that include 64 benign and 46 malignant tumors. The accuracy, specificity, and sensitivity obtained using the proposed approach are 98.2%, 98.4%, and 97.8%, respectively. These results demonstrate that the proposed approach can effectively be used to differentiate benign and malignant tumors.

Deep learning based classification of breast tumors with shear-wave elastography

This study aims to build a deep learning (DL) architecture for automated extraction of learned-from-data image features from the shear-wave elastography (SWE), and to evaluate the DL architecture in differentiation between benign and malignant breast tumors. We construct a two-layer DL architecture for SWE feature extraction, comprised of the point-wise gated Boltzmann machine (PGBM) and the restricted Boltzmann machine (RBM). The PGBM contains task-relevant and task-irrelevant hidden units, and the task-relevant units are connected to the RBM. Experimental evaluation was performed with five-fold cross validation on a set of 227 SWE images, 135 of benign tumors and 92 of malignant tumors, from 121 patients. The features learned with our DL architecture were compared with the statistical features quantifying image intensity and texture. Results showed that the DL features achieved better classification performance with an accuracy of 93.4%, a sensitivity of 88.6%, a specificity of 97.1%, and an area under the receiver operating characteristic curve of 0.947. The DL-based method integrates feature learning with feature selection on SWE. It may be potentially used in clinical computer-aided diagnosis of breast cancer.

Computer-Aided Diagnosis for Breast Ultrasound Using Computerized BI-RADS Features and Machine Learning Methods

This work identifies effective computable features from the Breast Imaging Reporting and Data System (BI-RADS), to develop a computer-aided diagnosis (CAD) system for breast ultrasound. Computerized features corresponding to ultrasound BI-RADs categories were designed and tested using a database of 283 pathology-proven benign and malignant lesions. Features were selected based on classification performance using a "bottom-up" approach for different machine learning methods, including decision tree, artificial neural network, random forest and support vector machine. Using 10-fold cross-validation on the database of 283 cases, the highest area under the receiver operating characteristic (ROC) curve (AUC) was 0.84 from a support vector machine with 77.7% overall accuracy; the highest overall accuracy, 78.5%, was from a random forest with the AUC 0.83. Lesion margin and orientation were optimum features common to all of the different machine learning methods. These features can be used in CAD systems to help distinguish benign from worrisome lesions.

Intensity-Invariant Texture Analysis for Classification of BI-RADS Category 3 Breast Masses

Radiologists likely incorrectly classify benign masses as Breast Imaging Reporting and Data System (BI-RADS) category 3. A computer-aided diagnosis (CAD) system was developed in this study as a second viewer to avoid misclassification of carcinomas. Sixty-nine biopsy-proven BI-RADS category 3 masses, including 21 malignant and 48 benign masses, were used to evaluate the CAD system. To improve the texture features, gray-scale variations between images were reduced by transforming pixels into intensity-invariant ranklet coefficients. The textures of the tumor and speckle pixels were extracted from the transformed ranklet images to provide more robust features than in conventional CAD systems. As a result, tumor texture and speckle texture with ranklet transformation achieved significantly better areas under the receiver operating characteristic curve (Az) compared with those without ranklet transformation (Az = 0.83 vs. 0.58 and Az = 0.80 vs. 0.56, p value < 0.05). The improved CAD system can be a second reader to confirm the classification of BI-RADS category 3 masses.

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.

The normal mode analysis shape detection method for automated shape determination of lung nodules

Surface morphology and shape in general are important predictors for the behavior of solid-type lung nodules detected on CT. More broadly, shape analysis is useful in many areas of computer-aided diagnosis and essentially all scientific and engineering disciplines. Automated methods for shape detection have all previously, to the author's knowledge, relied on some sort of geometric measure. I introduce Normal Mode Analysis Shape Detection (NMA-SD), an approach that measures shape indirectly via the motion it would undergo if one imagined the shape to be a pseudomolecule. NMA-SD allows users to visualize internal movements in the imaging object and thereby develop an intuition for which motions are important, and which geometric features give rise to them. This can guide the identification of appropriate classification features to distinguish among classes of interest. I employ normal mode analysis (NMA) to animate pseudomolecules representing simulated lung nodules. Doing so, I am able to assign a testing set of nodules into the classes circular, elliptical, and irregular with roughly 97 % accuracy. This represents a proof-of-principle that one can obtain shape information by treating voxels as pseudoatoms in a pseudomolecule, and analyzing the pseudomolecule's predicted motion.

Incorporating texture features in a computer-aided breast lesion diagnosis system for automated three-dimensional breast ultrasound

We investigated the benefits of incorporating texture features into an existing computer-aided diagnosis (CAD) system for classifying benign and malignant lesions in automated three-dimensional breast ultrasound images. The existing system takes into account 11 different features, describing different lesion properties; however, it does not include texture features. In this work, we expand the system by including texture features based on local binary patterns, gray level co-occurrence matrices, and Gabor filters computed from each lesion to be diagnosed. To deal with the resulting large number of features, we proposed a combination of feature-oriented classifiers combining each group of texture features into a single likelihood, resulting in three additional features used for the final classification. The classification was performed using support vector machine classifiers, and the evaluation was done with 10-fold cross validation on a dataset containing 424 lesions (239 benign and 185 malignant lesions). We compared the classification performance of the CAD system with and without texture features. The area under the receiver operating characteristic curve increased from 0.90 to 0.91 after adding texture features ([Formula: see text]).

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 ( [Formula: see text]). 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.