Breast-Lesion Characterization using Textural Features of Quantitative Ultrasound Parametric Maps

Ultrasound wavelet spectra enable direct tissue recognition and full-color visualization

Traditional brightness-mode ultrasound imaging is primarily constrained by the low specificity among tissues and the inconsistency among sonographers. The major cause is the imaging method that represents the amplitude of echoes as brightness and ignores other detailed information, leaving sonographers to interpret based on organ contours that depend highly on specific imaging planes. Other ultrasound imaging modalities, color Doppler imaging or shear wave elastography, overlay motion or stiffness information to brightness-mode images. However, tissue-specific scattering properties and spectral patterns remain unknown in ultrasound imaging. Here we demonstrate that the distribution (size and average distance) of scattering particles leads to characteristic wavelet spectral patterns, which enables tissue recognition and high-contrast ultrasound imaging. Ultrasonic wavelet spectra from similar particle distributions tend to cluster in the eigenspace according to principal component analysis, whereas those with different distributions tend to be distinguishable from one another. For each distribution, a few wavelet spectra are unique and act as a fingerprint to recognize the corresponding tissue. Illumination of specific tissues and organs with designated colors according to the recognition results yields high-contrast ultrasound imaging. The fully-colorized tissue-specific ultrasound imaging potentially simplifies the interpretation and promotes consistency among sonographers, or even enables the applicability for non-professionals.

Evaluating the Role of Breast Ultrasound in Early Detection of Breast Cancer in Low- and Middle-Income Countries: A Comprehensive Narrative Review

Breast cancer, affecting both genders, but mostly females, exhibits shifting demographic patterns, with an increasing incidence in younger age groups. Early identification through mammography, clinical examinations, and breast self-exams enhances treatment efficacy, but challenges persist in low- and medium-income countries due to limited imaging resources. This review assesses the feasibility of employing breast ultrasound as the primary breast cancer screening method, particularly in resource-constrained regions. Following the PRISMA guidelines, this study examines 52 publications from the last five years. Breast ultrasound, distinct from mammography, offers advantages like radiation-free imaging, suitability for repeated screenings, and preference for younger populations. Real-time imaging and dense breast tissue evaluation enhance sensitivity, accessibility, and cost-effectiveness. However, limitations include reduced specificity, operator dependence, and challenges in detecting microcalcifications. Automatic breast ultrasound (ABUS) addresses some issues but faces constraints like potential inaccuracies and limited microcalcification detection. The analysis underscores the need for a comprehensive approach to breast cancer screening, emphasizing international collaboration and addressing limitations, especially in resource-constrained settings. Despite advancements, notably with ABUS, the primary goal is to contribute insights for optimizing breast cancer screening globally, improving outcomes, and mitigating the impact of this debilitating disease.

Quantitative ultrasound parameters from scattering and propagation may reduce the biopsy rate for breast tumor

Breast cancer has become the most common cancer worldwide, and early screening improves the patient's survival rate significantly. Although pathology with needle-based biopsy is the gold standard for breast cancer diagnosis, it is invasive, painful, and expensive. Meanwhile it makes patients suffer from misplacement of the needle, resulting in misdiagnosis and further assessment. Ultrasound imaging is non-invasive and real-time, however, benign and malignant tumors are hard to differentiate in grayscale B-mode images. We hypothesis that breast tumors exhibit characteristic properties, which generates distinctive spectral patterns not only in scattering, but also during propagation. In this paper, we propose a breast tumor classification method that evaluates the spectral pattern of the tissues both inside the tumor and beneath it. First, quantitative ultrasonic parameters of these spectral patterns were calculated as the representation of the corresponding tissues. Second, parameters were classified by the K-Nearest Neighbor machine learning model. This method was verified with an open access dataset as a reference, and applied to our own dataset to evaluate the potential for tumors assessment. With both datasets, the proposed method demonstrates accurate classification of the tumors, which potentially makes it unnecessary for certain patients to take the biopsy, reducing the rate of the painful and expensive procedure.

Artificial Intelligence-Enhanced Quantitative Ultrasound for Breast Cancer: Pilot Study on Quantitative Parameters and Biopsy Outcomes

Traditional B-mode ultrasound has difficulties distinguishing benign from malignant breast lesions. It appears that Quantitative Ultrasound (QUS) may offer advantages. We examined the QUS imaging system's potential, utilizing parameters like Attenuation Coefficient (AC), Speed of Sound (SoS), Effective Scatterer Diameter (ESD), and Effective Scatterer Concentration (ESC) to enhance diagnostic accuracy. B-mode images and radiofrequency signals were gathered from breast lesions. These parameters were processed and analyzed by a QUS system trained on a simulated acoustic dataset and equipped with an encoder-decoder structure. Fifty-seven patients were enrolled over six months. Biopsies served as the diagnostic ground truth. AC, SoS, and ESD showed significant differences between benign and malignant lesions (p < 0.05), but ESC did not. A logistic regression model was developed, demonstrating an area under the receiver operating characteristic curve of 0.90 (95% CI: 0.78, 0.96) for distinguishing between benign and malignant lesions. In conclusion, the QUS system shows promise in enhancing diagnostic accuracy by leveraging AC, SoS, and ESD. Further studies are needed to validate these findings and optimize the system for clinical use.

Noninvasive Evaluation of Breast Tumor Response to Combined Ultrasound-Stimulated Microbubbles and Hyperthermia Therapy Using Quantitative Ultrasound-Based Texture Analysis Method

OBJECTIVES

Quantitative ultrasound (QUS) is a noninvasive imaging technique that can be used for assessing response to anticancer treatment. In the present study, tumor cell death response to the ultrasound-stimulated microbubbles (USMB) and hyperthermia (HT) treatment was monitored in vivo using QUS.

METHODS

Human breast cancer cell lines (MDA-MB-231) were grown in mice and were treated with HT (10, 30, 50, and 60 minutes) alone, or in combination with USMB. Treatment effects were examined using QUS with a center frequency of 25 MHz (bandwidth range: 16 to 32 MHz). Backscattered radiofrequency (RF) data were acquired from tumors subjected to treatment. Ultrasound parameters such as average acoustic concentration (AAC) and average scatterer diameter (ASD), were estimated 24 hours prior and posttreatment. Additionally, texture features: contrast (CON), correlation (COR), energy (ENE), and homogeneity (HOM) were extracted from QUS parametric maps. All estimated parameters were compared with histopathological findings.

RESULTS

The findings of our study demonstrated a significant increase in QUS parameters in both treatment conditions: HT alone (starting from 30 minutes of heat exposure) and combined treatment of HT plus USMB finally reaching a maximum at 50 minutes of heat exposure. Increase in AAC for 50 minutes HT alone and USMB +50 minutes was found to be 5.19 ± 0.417% and 5.91 ± 1.11%, respectively, compared to the control group with AAC value of 1.00 ± 0.44%. Furthermore, between the treatment groups, ΔASD-ENE values for USMB +30 minutes HT significantly reduced, depicting 0.00062 ± 0.00096% compared to 30 minutes HT only group, showing 0.0058 ± 0.0013%. Further, results obtained from the histological analysis indicated greater cell death and reduced nucleus size in both HT alone and HT combined with USMB.

CONCLUSION

The texture-based QUS parameters indicated a correlation with microstructural changes obtained from histological data. This work demonstrated the use of QUS to detect HT treatment effects in breast cancer tumors in vivo.

H-Scan Ultrasound Monitoring of Breast Cancer Response to Chemotherapy and Validation With Diffusion-Weighted Magnetic Resonance Imaging

OBJECTIVES

H-scan ultrasound (US) imaging is a novel tissue characterization technique to detect apoptosis-induced changes in cancer cells after the initiation of effective drug treatment. The objective of the proposed research was to assess the sensitivity of 3-dimensional (3D) H-scan US technique for monitoring the response of breast cancer-bearing animals to neoadjuvant chemotherapy and correlate results to diffusion-weighted magnetic resonance imaging (DW-MRI) measurements of programmed cancer cell death.

METHODS

Experimental studies used female mice (N = 18) implanted with human breast cancer cells. Animals underwent H-scan US and DW-MRI imaging on days 0, 1, 3, 7, and 10. After imaging at day 0, breast tumor-bearing nude mice were treated biweekly with an apoptosis-inducing drug. Texture analysis of H-scan US images explored spatial relationships between local US scattering. At day 10, H-scan measurements were compared with DW-MRI-derived apparent diffusion coefficient (ADC) values and histological findings.

RESULTS

H-scan US imaging of low and high dose cisplatin-treated cancer-bearing animals revealed changes in image intensity suggesting a progressive decrease in aggregate US scatterer size that was not observed in control animals. Longitudinal trends discovered in H-scan US result matched with texture analysis and DW-MRI (P < .01). Further, analysis of the H-scan US image intensity and corresponding DW-MRI-derived ADC values revealed a strong linear correlation (R²  = .93, P < .001). These changes were due to cancer cell apoptotic activity and consider as early detectable biomarker during treatment.

CONCLUSIONS

The 3D H-scan technique holds promise for assisting clinicians in monitoring the early response of breast cancer tumor to neoadjuvant chemotherapy and adding value to traditional diagnostic ultrasound examinations.

High-Resolution Ultrasound Characterization of Local Scattering in Cancer Tissue

Ultrasound (US) has afforded an approach to tissue characterization for more than a decade. The challenge is to reveal hidden patterns in the US data that describe tissue function and pathology that cannot be seen in conventional US images. Our group has developed a high-resolution analysis technique for tissue characterization termed H-scan US, an imaging method used to interpret the relative size of acoustic scatterers. In the present study, the objective was to compare local H-scan US image intensity with registered histologic measurements made directly at the cellular level. Human breast cancer cells (MDA-MB 231, American Type Culture Collection, Manassas, VA, USA) were orthotopically implanted into female mice (N = 5). Tumors were allowed to grow for approximately 4 wk before the study started. In vivo imaging of tumor tissue was performed using a US system (Vantage 256, Verasonics Inc., Kirkland, WA, USA) equipped with a broadband capacitive micromachined ultrasonic linear array transducer (Kolo Medical, San Jose, CA, USA). A 15-MHz center frequency was used for plane wave imaging with five angles for spatial compounding. H-scan US image reconstruction involved use of parallel convolution filters to measure the relative strength of backscattered US signals. Color codes were applied to filter outputs to form the final H-scan US image display. For histologic processing, US imaging cross-sections were carefully marked on the tumor surface, and tumors were excised and sliced along the same plane. By use of optical microscopy, whole tumor tissue sections were scanned and digitized after nuclear staining. US images were interpolated to have the same number of pixels as the histology images and then spatially aligned. Each nucleus from the histologic sections was automatically segmented using custom MATLAB software (The MathWorks Inc., Natick, MA, USA). Nuclear size and spacing from the histology images were then compared with local H-scan US image features. Overall, local H-scan US image intensity exhibited a significant correlation with both cancer cell nuclear size (R2 > 0.27, p < 0.001) and the inverse relationship with nuclear spacing (R2 > 0.17, p < 0.001).

Quantitative Ultrasound for Evaluation of Tumour Response to Ultrasound-Microbubbles and Hyperthermia

Objectives: Prior study has demonstrated the implementation of quantitative ultrasound (QUS) for determining the therapy response in breast tumour patients. Several QUS parameters quantified from the tumour region showed a significant correlation with the patient's clinical and pathological response. In this study, we aim to identify if there exists such a link between QUS parameters and changes in tumour morphology due to combined ultrasound-stimulated microbubbles (USMB) and hyperthermia (HT) using the breast xenograft model (MDA-MB-231). Method: Tumours grown in the hind leg of severe combined immuno-deficient mice were treated with permutations of USMB and HT. Ultrasound radiofrequency data were collected using a 25 MHz array transducer, from breast tumour-bearing mice prior and post-24-hour treatment. Result: Our result demonstrated an increase in the QUS parameters the mid-band fit and spectral 0-MHz intercept with an increase in HT duration combined with USMB which was found to be reflective of tissue structural changes and cell death detected using haematoxylin and eosin and terminal deoxynucleotidyl transferase dUTP nick end labelling stain. A significant decrease in QUS spectral parameters was observed at an HT duration of 60 minutes, which is possibly due to loss of nuclei by the majority of cells as confirmed using histology analysis. Morphological alterations within the tumour might have contributed to the decrease in backscatter parameters. Conclusion: The work here uses the QUS technique to assess the efficacy of cancer therapy and demonstrates that the changes in ultrasound backscatters mirrored changes in tissue morphology.

Implementation of Non-Invasive Quantitative Ultrasound in Clinical Cancer Imaging

Quantitative ultrasound (QUS) is a non-invasive novel technique that allows treatment response monitoring. Studies have shown that QUS backscatter variables strongly correlate with changes observed microscopically. Increases in cell death result in significant alterations in ultrasound backscatter parameters. In particular, the parameters related to scatterer size and scatterer concentration tend to increase in relation to cell death. The use of QUS in monitoring tumor response has been discussed in several preclinical and clinical studies. Most of the preclinical studies have utilized QUS for evaluating cell death response by differentiating between viable cells and dead cells. In addition, clinical studies have incorporated QUS mostly for tissue characterization, including classifying benign versus malignant breast lesions, as well as responder versus non-responder patients. In this review, we highlight some of the important findings of previous preclinical and clinical studies and expand the applicability and therapeutic benefits of QUS in clinical settings. We summarized some recent clinical research advances in ultrasound-based radiomics analysis for monitoring and predicting treatment response and characterizing benign and malignant breast lesions. We also discuss current challenges, limitations, and future prospects of QUS-radiomics.

Ultrasound classification of breast masses using a comprehensive Nakagami imaging and machine learning framework

In this study we investigate the potential of parametric images formed from ultrasound B-mode scans using the Nakagami distribution for non-invasive classification of breast lesions and characterization of breast tissue. Through a sliding window technique, we generated seven types of Nakagami images for each patient scan in our dataset using basic and as well as derived parameters of the Nakagami distribution. To determine the suitable window size for image generation, we conducted an empirical analysis using 4 windows, which includes 3 column windows of lengths 0.1875 mm, 0.45 mm and 0.75 mm and widths of 0.002 mm, along with the standard square window with sides equal to three times the pulse length of incident ultrasound. From the parametric image sets generated using each window, we extracted a total of 72 features that consisted of morphometric, elemental and hybrid features. To our knowledge no other literature has conducted such a comprehensive analysis of Nakagami parametric images for the classification of breast lesions. Feature selection was performed to find the most useful subset of features from each of the parametric image sets for the classification of breast cancer. Analyzing the classification accuracy and Area under the Receiver Operating Characteristic (ROC) Curve (AUC) of the selected feature subsets, we determined that the selected features acquired from Nakagami parametric images generated using a column window of length 0.75 mm provides the best results for characterization of breast lesions. This optimal feature set provided a classification accuracy of 93.08%, an AUC of 0.9712, a False Negative Rate (FNR) of 0%, and a very low False Positive Rate (FPR) of 8.65%. Our results indicate that the high accuracy of such a procedure may assist in the diagnosis of breast cancer by helping to reduce false positive diagnoses.

Machine learning-enabled quantitative ultrasound techniques for tissue differentiation

PURPOSE

Quantitative ultrasound (QUS) infers properties about tissue microstructure from backscattered radio-frequency ultrasound data. This paper describes how to implement the most practical QUS parameters using an ultrasound research system for tissue differentiation.

METHODS

This study first validated chicken liver and gizzard muscle as suitable acoustic phantoms for human brain and brain tumour tissues via measurement of the speed of sound and acoustic attenuation. A total of thirteen QUS parameters were estimated from twelve samples, each using data obtained with a transducer with a frequency of 5-11 MHz. Spectral parameters, i.e., effective scatterer diameter and acoustic concentration, were calculated from the backscattered power spectrum of the tissue, and echo envelope statistics were estimated by modelling the scattering inside the tissue as a homodyned K-distribution, yielding the scatterer clustering parameter α and the structure parameter κ. Standard deviation and higher-order moments were calculated from the echogenicity value assigned in conventional B-mode images.

RESULTS

The k-nearest neighbours algorithm was used to combine those parameters, which achieved 94.5% accuracy and 0.933 F1-score.

CONCLUSION

We were able to generate classification parametric images in near-real-time speed as a potential diagnostic tool in the operating room for the possible use for human brain tissue characterisation.

Breast Tumor Classification Using Intratumoral Quantitative Ultrasound Descriptors

Breast cancer is a global epidemic, responsible for one of the highest mortality rates among women. Ultrasound imaging is becoming a popular tool for breast cancer screening, and quantitative ultrasound (QUS) techniques are being increasingly applied by researchers in an attempt to characterize breast tissue. Several different quantitative descriptors for breast cancer have been explored by researchers. This study proposes a breast tumor classification system using the three major types of intratumoral QUS descriptors which can be extracted from ultrasound radiofrequency (RF) data: spectral features, envelope statistics features, and texture features. A total of 16 features were extracted from ultrasound RF data across two different datasets, of which one is balanced and the other is severely imbalanced. The balanced dataset contains RF data of 100 patients with breast tumors, of which 48 are benign and 52 are malignant. The imbalanced dataset contains RF data of 130 patients with breast tumors, of which 104 are benign and 26 are malignant. Holdout validation was used to split the balanced dataset into 60% training and 40% testing sets. Feature selection was applied on the training set to identify the most relevant subset for the classification of benign and malignant breast tumors, and the performance of the features was evaluated on the test set. A maximum classification accuracy of 95% and an area under the receiver operating characteristic curve (AUC) of 0.968 was obtained on the test set. The performance of the identified relevant features was further validated on the imbalanced dataset, where a hybrid resampling strategy was firstly utilized to create an optimal balance between benign and malignant samples. A maximum classification accuracy of 93.01%, sensitivity of 94.62%, specificity of 91.4%, and AUC of 0.966 were obtained. The results indicate that the identified features are able to distinguish between benign and malignant breast lesions very effectively, and the combination of the features identified in this research has the potential to be a significant tool in the noninvasive rapid and accurate diagnosis of breast cancer.

Deep learning of quantitative ultrasound multi-parametric images at pre-treatment to predict breast cancer response to chemotherapy

In this study, a novel deep learning-based methodology was investigated to predict breast cancer response to neo-adjuvant chemotherapy (NAC) using the quantitative ultrasound (QUS) multi-parametric imaging at pre-treatment. QUS multi-parametric images of breast tumors were generated using the data acquired from 181 patients diagnosed with locally advanced breast cancer and planned for NAC followed by surgery. The ground truth response to NAC was identified for each patient after the surgery using the standard clinical and pathological criteria. Two deep convolutional neural network (DCNN) architectures including the residual network and residual attention network (RAN) were explored for extracting optimal feature maps from the parametric images, with a fully connected network for response prediction. In different experiments, the features maps were derived from the tumor core only, as well as the core and its margin. Evaluation results on an independent test set demonstrate that the developed model with the RAN architecture to extract feature maps from the expanded parametric images of the tumor core and margin had the best performance in response prediction with an accuracy of 88% and an area under the receiver operating characteristic curve of 0.86. Ten-year survival analyses indicate statistically significant differences between the survival of the responders and non-responders identified based on the model prediction at pre-treatment and the standard criteria at post-treatment. The results of this study demonstrate the promising capability of DCNNs with attention mechanisms in predicting breast cancer response to NAC prior to the start of treatment using QUS multi-parametric images.

A priori prediction of local failure in brain metastasis after hypo-fractionated stereotactic radiotherapy using quantitative MRI and machine learning

This study investigated the effectiveness of pre-treatment quantitative MRI and clinical features along with machine learning techniques to predict local failure in patients with brain metastasis treated with hypo-fractionated stereotactic radiation therapy (SRT). The predictive models were developed using the data from 100 patients (141 lesions) and evaluated on an independent test set with data from 20 patients (30 lesions). Quantitative MRI radiomic features were derived from the treatment-planning contrast-enhanced T1w and T2-FLAIR images. A multi-phase feature reduction and selection procedure was applied to construct an optimal quantitative MRI biomarker for predicting therapy outcome. The performance of standard clinical features in therapy outcome prediction was evaluated using a similar procedure. Survival analyses were conducted to compare the long-term outcome of the two patient cohorts (local control/failure) identified based on prediction at pre-treatment, and standard clinical criteria at last patient follow-up after SRT. The developed quantitative MRI biomarker consists of four features with two features quantifying heterogeneity in the edema region, one feature characterizing intra-tumour heterogeneity, and one feature describing tumour morphology. The predictive models with the radiomic and clinical feature sets yielded an AUC of 0.87 and 0.62, respectively on the independent test set. Incorporating radiomic features into the clinical predictive model improved the AUC of the model by up to 16%, relatively. A statistically significant difference was observed in survival of the two patient cohorts identified at pre-treatment using the radiomics-based predictive model, and at post-treatment using the the RANO-BM criteria. Results of this study revealed a good potential for quantitative MRI radiomic features at pre-treatment in predicting local failure in relatively large brain metastases undergoing SRT, and is a step forward towards a precision oncology paradigm for brain metastasis.

Cystic (including atypical) and solid breast lesion classification using the different features of quantitative ultrasound parametric images

PURPOSE

The amount of ultrasound (US) breast examinations continues to grow rapidly because of the wider endorsement of breast cancer screening programs. Cysts are the most commonly diagnosed breast lesions. Atypical breast cysts can be a serious differentiation problem in the US. Our goal was to develop noninvasive automated US grayscale image analysis for the cystic and solid breast lesion differentiation based on mathematical image post-processing.

MATERIALS AND METHODS

We used a set of 217 ultrasound images of proven 107 cystic (including 53 atypical) and 110 solid lesions. Empirical statistical and morphological models of the lesions were used to obtain features. The AUC indicator and Student's t test were used to assess the quality of the individual features. The Pearson correlation matrix was used to calculate the correlation between various features. The LASSO and stepwise regression methods were used to determine the most significant features. Finally, the lesion classification was carried out by the various methods.

RESULTS

The use of LASSO regression for the feature selection made it possible to select the most significant features for classification. The sensitivity increased from 87.1% to 89.2% and the specificity-from 92.2 to 94.8%. After the correlation matrix construction, it was found that features with a high value of the correlation coefficient (0.72; 0.75) can also be used to improve the quality of the classification.

CONCLUSION

The construction of the empirical model of the lesion pixels brightness behavior can provide parameters that are important for the correct classification of ultrasound images. The optimal set of features with the maximum discriminant characteristics may not be consistent with the correlation of features and the value of the AUC index. Features with a low AUC index (in our case 0.72) can also be important for improving the quality of the classification.

Novel gel bolus to improve impedance-based measurements of esophageal cross-sectional area during primary peristalsis

INTRODUCTION

Intraluminal esophageal impedance (ILEE) has the potential to measure esophageal luminal distension during swallow-induced peristalsis in the esophagus. A potential cause of inaccuracy in the ILEE measurement is the swallow-induced air in the bolus.

AIM

Compare a novel gel bolus to the current alternatives for the measurement of impedance-based luminal distension (cross-sectional area, CSA) during primary peristalsis.

METHODS

12 healthy subjects were studied using high-resolution impedance manometry (HRMZ) and concurrently performed intraluminal ultrasound (US) imaging of the esophagus. Three test bolus materials were used: 1) novel gel, 2) 0.5 N saline, and 3) commercially available Diversatek EFTV viscous. Testing was performed in the supine and Trendelenburg (-15°) positions. US imaging assessed air in the bolus and luminal CSA. The Nadir impedance values were correlated to the US measured CSA. A custom Matlab software was used to assess the bolus travel times and impedance-based luminal CSA.

RESULTS

The novel gel bolus had the least amount of air in the bolus during its passage through the esophagus, as assessed by US image analysis. The novel gel bolus in the supine and Trendelenburg positions had the best linear fit between the US measured CSA and nadir impedance value (R²  = 0.88 & R²  = 0.90). The impedance-based calculation of the CSA correlated best with the US measured CSA with the use of the novel gel bolus.

CONCLUSION

We suggest the use of novel gel to assess distension along with contraction during routine clinical HRM testing.

Quantitative ultrasound characterization of therapy response in prostate cancer in vivo

Quantitative ultrasound (QUS) is a non-invasive imaging modality that permits the detection of tumor response following various cancer therapies. Based on ultrasound signal scattering from the biological system, scatterer size, and concentration of microscopic scatterers, QUS enables the rapid characterization of tumor cell death. In this study, tumor response to ultrasound-stimulated microbubbles (USMB) and hyperthermia (HT) in tumor-bearing mice, with prostate cancer xenografts (PC3), was examined using QUS. Treatment conditions included 1% (v/v) Definity microbubbles stimulated at ultrasound pressures (0, 246, and 570 kPa) and HT treatment (0, 10, 40, and 50 minutes). Three ultrasound backscatter parameters, mid-band fit (MBF), 0-MHz spectral intercept (SI), and spectral slope (SS) were estimated prior to, and 24 hours after treatment. Additionally, histological assessment of tumor cell death and tissue microstructural changes was used to complement the results obtained from ultrasound data. Results demonstrated a significant increase in QUS parameters (MBF and SI) followed combined USMB and HT treatment (P<0.05). In contrast, the backscatter parameters from the control (untreated) group, and USMB only group showed minimal changes (P>0.05). Furthermore, histological data demonstrated increased cell death and prominent changes in cellular and tissue structure, nucleus size, and subcellular constituent orientation followed combined treatments. The findings suggested that QUS parameters derived from the ultrasound backscattered power spectrum may be used to detect HT treatment effects in prostate cancer tumors in vivo.

Analytic Global Regularized Backscatter Quantitative Ultrasound

Although a variety of techniques have been developed to reduce the appearance of B-mode speckle, quantitative ultrasound (QUS) aims at extracting the hidden properties of the tissue. Herein, we propose two novel techniques to accurately and precisely estimate two important QUS parameters, namely, the average attenuation coefficient and the backscatter coefficient. Both the techniques optimize a cost function that incorporates data and continuity constraint terms, which we call AnaLytical Global rEgularized BackscatteR quAntitative ultrasound (ALGEBRA). We propose two versions of ALGEBRA, namely, 1-D- and 2-D-ALGEBRA. In 1-D-ALGEBRA, the regularized cost function is formulated in the axial direction, and the QUS parameters are calculated for one line of radio frequency (RF) echo data. In 2-D-ALGEBRA, the regularized cost function is formulated for the entire image, and the QUS parameters throughout the image are estimated simultaneously. This simultaneous optimization allows 2-D-ALGEBRA to "see" all the data before estimating the QUS parameters. In both the methods, we efficiently optimize the cost functions by casting it as a sparse linear system of equations. As a result of this efficient optimization, 1-D-ALGEBRA and 2-D-ALGEBRA are, respectively, 600 and 300 times faster than optimization using the dynamic programming (DP) method previously proposed by our group. In addition, the proposed technique has fewer input parameters that require manual tuning. Our results demonstrate that the proposed ALGEBRA methods substantially outperform least-square and DP methods in estimating the QUS parameters in phantom experiments.

Comparison of methods for texture analysis of QUS parametric images in the characterization of breast lesions

PURPOSE

Accurate and timely diagnosis of breast carcinoma is very crucial because of its high incidence and high morbidity. Screening can improve overall prognosis by detecting the disease early. Biopsy remains as the gold standard for pathological confirmation of malignancy and tumour grading. The development of diagnostic imaging techniques as an alternative for the rapid and accurate characterization of breast masses is necessitated. Quantitative ultrasound (QUS) spectroscopy is a modality well suited for this purpose. This study was carried out to evaluate different texture analysis methods applied on QUS spectral parametric images for the characterization of breast lesions.

METHODS

Parametric images of mid-band-fit (MBF), spectral-slope (SS), spectral-intercept (SI), average scatterer diameter (ASD), and average acoustic concentration (AAC) were determined using QUS spectroscopy from 193 patients with breast lesions. Texture methods were used to quantify heterogeneities of the parametric images. Three statistical-based approaches for texture analysis that include Gray Level Co-occurrence Matrix (GLCM), Gray Level Run-length Matrix (GRLM), and Gray Level Size Zone Matrix (GLSZM) methods were evaluated. QUS and texture-parameters were determined from both tumour core and a 5-mm tumour margin and were used in comparison to histopathological analysis in order to classify breast lesions as either benign or malignant. We developed a diagnostic model using different classification algorithms including linear discriminant analysis (LDA), k-nearest neighbours (KNN), support vector machine with radial basis function kernel (SVM-RBF), and an artificial neural network (ANN). Model performance was evaluated using leave-one-out cross-validation (LOOCV) and hold-out validation.

RESULTS

Classifier performances ranged from 73% to 91% in terms of accuracy dependent on tumour margin inclusion and classifier methodology. Utilizing information from tumour core alone, the ANN achieved the best classification performance of 93% sensitivity, 88% specificity, 91% accuracy, 0.95 AUC using QUS parameters and their GLSZM texture features.

CONCLUSIONS

A QUS-based framework and texture analysis methods enabled classification of breast lesions with >90% accuracy. The results suggest that optimizing method for extracting discriminative textural features from QUS spectral parametric images can improve classification performance. Evaluation of the proposed technique on a larger cohort of patients with proper validation technique demonstrated the robustness and generalization of the approach.

Predicting Local Failure after Stereotactic Radiation Therapy in Brain Metastasis using Quantitative CT and Machine Learning

Despite recent advances in cancer treatment, the prognosis of patients diagnosed with brain metastasis is still poor. The median survival is limited to months even for patients undergoing treatment. Radiation therapy is a main component of treatment for brain metastasis. However, radiotherapy cannot control local progression in up to 20% of the metastatic brain tumours. An early prediction of radiotherapy outcome for individual patients could facilitate therapy adjustments to improve its efficacy. This study investigated the potential of quantitative CT biomarkers in conjunction with machine learning methods to predict local failure after radiotherapy in brain metastasis. Volumetric CT images were acquired for radiation treatment planning from 120 patients undergoing stereotactic radiotherapy. Quantitative features characterizing the morphology and texture were extracted from different regions of each lesion. A feature reduction/selection framework was adapted to define a quantitative CT biomarker of radiotherapy outcome. Different machine learning methods were applied and evaluated to predict the local failure outcome at pre-treatment. The optimum biomarker consisting of two features in conjunction with an AdaBoost with decision tree could predict the local failure outcome with 71% accuracy on an independent test set (20 patients, 31 lesions). This study is a step forward towards prediction of radiotherapy outcome in brain metastasis using quantitative imaging and machine learning.

Breast lesion characterization using Quantitative Ultrasound (QUS) and derivative texture methods

PURPOSE

Accurate and timely diagnosis of breast cancer is extremely important because of its high incidence and high morbidity. Early diagnosis of breast cancer through screening can improve overall prognosis. Currently, biopsy remains as the gold standard for tumor pathological confirmation. Development of diagnostic imaging techniques for rapid and accurate characterization of breast lesions is required. We aim to evaluate the usefulness of texture-derivate features of QUS spectral parametric images for non-invasive characterization of breast lesions.

METHODS

QUS Spectroscopy was used to determine parametric images of mid-band fit (MBF), spectral slope (SS), spectral intercept (SI), average scatterer diameter (ASD), and average acoustic concentration (AAC) in 204 patients with suspicious breast lesions. Subsequently, texture analysis techniques were used to generate texture maps from parametric images to quantify heterogeneities of QUS parametric images. Further, a second-pass texture analysis was applied to obtain texture-derivate features. QUS parameters, texture-parameters and texture-derivate parameters were determined from both tumor core and a 5-mm tumor margin and were used in comparison to histopathological analysis in order to develop a diagnostic model for classifying breast lesions as either benign or malignant. Both leave-one-out and hold-out cross-validations were used to evaluate the performance of the diagnostic model. Three standard classification algorithms including a linear discriminant analysis (LDA), k-nearest neighbors (KNN), and support vector machines-radial basis function (SVM-RBF) were evaluated.

RESULTS

Core and margin information using the SVM-RBF attained the best classification performance of 90% sensitivity, 92% specificity, 91% accuracy, and 0.93 AUC utilizing QUS parameters and their texture derivatives, evaluated using leave-one-out cross-validation. Implementation of hold-out cross-validation using combination of both core and margin information and SVM-RBF achieved average accuracy and AUC of 88% and 0.92, respectively.

CONCLUSIONS

QUS-based framework and derivative texture methods enable accurate classification of breast lesions. Evaluation of the proposed technique on a large cohort using hold-out cross-validation demonstrates its robustness and its generalization.

Quantitative ultrasound delta-radiomics during radiotherapy for monitoring treatment responses in head and neck malignancies

Aim:

We investigated quantitative ultrasound (QUS) in patients with node-positive head and neck malignancies for monitoring responses to radical radiotherapy (RT).

Materials & methods:

QUS spectral and texture parameters were acquired from metastatic lymph nodes 24 h, 1 and 4 weeks after starting RT. K-nearest neighbor and naive-Bayes machine-learning classifiers were used to build prediction models for each time point. Response was detected after 3 months of RT, and patients were classified into complete and partial responders.

Results:

Single-feature naive-Bayes classification performed best with a prediction accuracy of 80, 86 and 85% at 24 h, week 1 and 4, respectively.

Conclusion:

QUS-radiomics can predict RT response at 3 months as early as 24 h with reasonable accuracy, which further improves into 1 week of treatment.

Patients with head and neck cancer are often treated with radiation, which usually spans over 6–7 weeks. The response is usually measured 3 months after treatment completion. In this study, we had performed ultrasound scans from the patient’s neck node during radiation treatment (after 24 h, 1 and 4 weeks). Artificial intelligence was used to interpret the ultrasound imaging and predict the response to radiation at the end of 3 months. The scans obtained after the first week were able to predict the treatment response with reasonable accuracy (86%).

Optimization of Ultrasound Backscatter Spectroscopy to Assess Neurotoxic Effects of Anesthesia in the Newborn Non-human Primate Brain

Studies in animal models have revealed that long exposures to anesthetics can induce apoptosis in the newborn and young developing brain. These effects have not been confirmed in humans because of the lack of a non-invasive, practical in vivo imaging tool with the ability to detect these changes. Following the successful use of ultrasound backscatter spectroscopy (UBS) to monitor in vivo cell death in breast tumors, we aimed to use UBS to assess the neurotoxicity of the anesthetic sevoflurane (SEVO) in a non-human primate (NHP) model. Sixteen 2- to 7-day-old rhesus macaques were exposed for 5 h to SEVO. Ultrasound scanning was done with a phased array transducer on a clinical ultrasound scanner operated at 10 MHz. Data consisting of 10-15 frames of radiofrequency (RF) echo signals from coronal views of the thalamus were obtained 0.5 and 6.0 h after initiating exposure. The UBS parameter "effective scatterer size" (ESS) was estimated by fitting a scattering form factor (FF) model to the FF measured from RF echo signals. The approach involved analyzing the frequency dependence of the measured FF to characterize scattering sources and selecting the FF model based on a χ² goodness-of-fit criterion. To assess data quality, a rigorous acceptance criterion based on the analysis of prevalence of diffuse scattering (an assumption in the estimation of ESS) was established. ESS changes after exposure to SEVO were compared with changes in a control group of five primates for which ultrasound data were acquired at 0 and 10 min (no apoptosis expected). Over the entire data set, the average measured FF at 0.5 and 6.0 h monotonically decreased with frequency, justifying fitting a single FF over the analysis bandwidth. χ² values of a (inhomogeneous continuum) Gaussian FF model were one-fifth those of the discrete fluid sphere model, suggesting that a continuum scatterer model better represents ultrasound scattering in the young rhesus brain. After application of the data quality criterion, only 5 of 16 subjects from the apoptotic group and 5 of 5 subjects from the control group fulfilled the acceptance criteria. All subjects in the apoptotic group that passed the acceptance criterion exhibited a significant ESS reduction at 6.0 h. These changes (-6.4%, 95% Interquartile Range: -14.3% to -3.3%) were larger than those in the control group (-0.8%, 95% Interquartile Range: -2.0% to 1.5%]). Data with a low prevalence of diffuse scattering corresponded to possibly biased results. Thus, ESS has the potential to detect changes in brain microstructure related to anesthesia-induced apoptosis.

Quantitative ultrasound radiomics for therapy response monitoring in patients with locally advanced breast cancer: Multi-institutional study results

BACKGROUND

Neoadjuvant chemotherapy (NAC) is the standard of care for patients with locally advanced breast cancer (LABC). The study was conducted to investigate the utility of quantitative ultrasound (QUS) carried out during NAC to predict the final tumour response in a multi-institutional setting.

METHODS

Fifty-nine patients with LABC were enrolled from three institutions in North America (Sunnybrook Health Sciences Centre (Toronto, Canada), MD Anderson Cancer Centre (Texas, USA), and Princess Margaret Cancer Centre (Toronto, Canada)). QUS data were collected before starting NAC and subsequently at weeks 1 and 4 during chemotherapy. Spectral tumour parametric maps were generated, and textural features determined using grey-level co-occurrence matrices. Patients were divided into two groups based on their pathological outcomes following surgery: responders and non-responders. Machine learning algorithms using Fisher's linear discriminant (FLD), K-nearest neighbour (K-NN), and support vector machine (SVM-RBF) were used to generate response classification models.

RESULTS

Thirty-six patients were classified as responders and twenty-three as non-responders. Among all the models, SVM-RBF had the highest accuracy of 81% at both weeks 1 and week 4 with area under curve (AUC) values of 0.87 each. The inclusion of week 1 and 4 features led to an improvement of the classifier models, with the accuracy and AUC from baseline features only being 76% and 0.68, respectively.

CONCLUSION

QUS data obtained during NAC reflect the ongoing treatment-related changes during chemotherapy and can lead to better classifier performances in predicting the ultimate pathologic response to treatment compared to baseline features alone.

Breast Cancer Classification in Automated Breast Ultrasound Using Multiview Convolutional Neural Network with Transfer Learning

To assist radiologists in breast cancer classification in automated breast ultrasound (ABUS) imaging, we propose a computer-aided diagnosis based on a convolutional neural network (CNN) that classifies breast lesions as benign and malignant. The proposed CNN adopts a modified Inception-v3 architecture to provide efficient feature extraction in ABUS imaging. Because the ABUS images can be visualized in transverse and coronal views, the proposed CNN provides an efficient way to extract multiview features from both views. The proposed CNN was trained and evaluated on 316 breast lesions (135 malignant and 181 benign). An observer performance test was conducted to compare five human reviewers' diagnostic performance before and after referring to the predicting outcomes of the proposed CNN. Our method achieved an area under the curve (AUC) value of 0.9468 with five-folder cross-validation, for which the sensitivity and specificity were 0.886 and 0.876, respectively. Compared with conventional machine learning-based feature extraction schemes, particularly principal component analysis (PCA) and histogram of oriented gradients (HOG), our method achieved a significant improvement in classification performance. The proposed CNN achieved a >10% increased AUC value compared with PCA and HOG. During the observer performance test, the diagnostic results of all human reviewers had increased AUC values and sensitivities after referring to the classification results of the proposed CNN, and four of the five human reviewers' AUCs were significantly improved. The proposed CNN employing a multiview strategy showed promise for the diagnosis of breast cancer, and could be used as a second reviewer for increasing diagnostic reliability.

Can contrast-enhanced mammography replace dynamic contrast-enhanced MRI in the assessment of sonomammographic indeterminate breast lesions?

Background

Dynamic contrast-enhanced MRI of the breast has been used for several years in the assessment of indeterminate mammographic findings. Contrast-enhanced mammography is a relatively novel imaging technique that has shown comparable sensitivity and specificity to MRI. Contrast-enhanced mammography is a relatively easy feasible study with high sensitivity and low cost. Our aim was to assess the feasibility of replacing dynamic contrast-enhanced (DCE)-MRI by contrast-enhanced mammography in the assessment of sonomammographic indeterminate lesions (BIRADS 3 and 4).

Results

The study included 82 patients with 171 breast lesions. They all performed contrast-enhanced mammography and dynamic contrast-enhanced MRI. DCE-MRI sensitivity and NPV were significantly higher than those of contrast-enhanced mammogram (CEM). The overall accuracy of MRI was better than that of CEM; however, no statistically significant difference could be detected.

Conclusion

Contrast-enhanced mammography and dynamic contrast-enhanced MRI improved the characterization of breast lesions. CEM showed slightly lower sensitivity and accuracy compared to MRI; however, because of being relatively easy, available, cheap, and acceptable by women, CEM can replace DC-MRI as a problem-solving tool in the characterization of indeterminate breast lesions.

Classification of Breast Ultrasound Tomography by Using Textural Analysis

Background: Ultrasound imaging has become one of the most widely utilized adjunct tools in breast cancer screening due to its advantages. The computer-aided detection of breast ultrasound is rapid development via significant features extracted from images. Objectives: The main aim was to identify features of breast ultrasound image that can facilitate reasonable classification of ultrasound images between malignant and benign lesions. Patients and Methods: This research was a retrospective study in which 85 cases (35 malignant [positive group] and 50 benign [negative group] with diagnostic reports) with ultrasound images were collected. The B-mode ultrasound images have manually selected regions of interest (ROI) for estimated features of an image. Then, a fractal dimensional (FD) image was generated from the original ROI by using the box-counting method. Both FD and ROI images were extracted features, including mean, standard deviation, skewness, and kurtosis. These extracted features were tested as significant by t-test, receiver operating characteristic (ROC) analysis and Kappa coefficient. Results: The statistical analysis revealed that the mean texture of images performed the best in differentiating benign versus malignant tumors. As determined by the ROC analysis, the appropriate qualitative values for the mean and the LR model were 0.85 and 0.5, respectively. The sensitivity, specificity, accuracy, positive predicted value (PPV), negative predicted value (NPV), and Kappa for the mean was 0.77, 0.84, 0.81, 0.77, 0.84, and 0.61, respectively. Conclusion: The presented method was efficient in classifying malignant and benign tumors using image textures. Future studies on breast ultrasound texture analysis could focus on investigations of edge detection, texture estimation, classification models, and image features.

An MR Radiomics Framework for Predicting the Outcome of Stereotactic Radiation Therapy in Brain Metastasis

Despite recent advances in cancer treatment, patients with brain metastasis still suffer from poor overall survival (OS) after standard treatment. Predicting the treatment outcome before or early after the treatment can potentially assist the physicians in improving the therapy outcome by adjusting a standard treatment on an individual patient basis. In this study, a data-driven computational framework was proposed and investigated to predict the local control/failure (LC/LF) outcome in patients with brain metastasis treated with hypo-fractionated stereotactic radiation therapy (SRT). The framework extracted several geometrical and textural features from the magnetic resonance (MR) images of the tumour and edema regions acquired for 38 patients. Subsequent to a multi-step feature reduction/selection, a quantitative MR biomarker consisting of two features was constructed. A support vector machine classifier was used for outcome prediction using the constructed MR biomarker. The bootstrap .632+ and leave-one-patient-out cross-validation methods were used to assess the model's performance. The results indicated that the outcome of LF after SRT could be predicted with an area under the curve of 0.80 and a cross-validated accuracy of 82%. The results obtained implied a good potential of the proposed framework for local outcome prediction in patients with brain metastasis treated with SRT and encourage further investigations on a larger cohort of patients.

Locations of optimally matched Gabor atoms from ultrasound RF echoes for inter-scatterer spacing estimation

BACKGROUND AND OBJECTIVE

The resolvable scatterer spacing related to biological tissue microstructures is a quantitative signature used for the disease diagnosis and tissue classification. In the present study, a method by locating optimally matched Gabor atoms (LOMGA) from ultrasound RF echo signals is proposed to improve the inter-scatterer spacing (ISS) estimation.

METHOD

A series of Gabor atoms are obtained from the signals with a matching pursuit algorithm. Then, the optimum atoms highly correlated with the coherent components are automatically selected according to the second-order difference of the reconstructed signal-to-residue ratio. The distances between the locations of adjacent atoms are applied to estimate the ISSs. In the simulation experiments, four regular degrees of the scatterer distributions are modeled with the Gamma distribution. One hundred sets of ultrasound RF echo signals are simulated based on the regular and diffuse scatterer distributions, and then combined to generate signals with preset coherent-to-diffuse ratios (CDRs). The accuracy performance of the LOMGA method is compared with that based on wavelet transform (WT) algorithm. In the microwave ablation experiments, the ultrasound RF echo signals of the region of interest (ROI) are collected from the normal and coagulated porcine liver tissues. The means and standard deviations of the LOMGA-based ISSs are compared with the WT-based results.

RESULTS

The results based on simulated signals with CDRs from 10 dB to -10 dB demonstrate that the proposed method improves the estimation accuracies of the mean ISSs by 5.10%, 9.00%, 19.80%, and 23.82%, and reduces the mean standard deviations by 27.20%, 22.50%, 11.50%, and 4.49% more than the WT method for the four regularities, respectively. The performance of the LOMGA method is also verified with the ultrasound RF echo signals from ex vivo porcine liver tissues in microwave ablation experiments.

CONCLUSIONS

It is concluded that the LOMGA method can provide more accurate and stable ISS estimation, which improves the performance of the tissue characterization with ISS-based quantitative ultrasound.

Predictive quantitative ultrasound radiomic markers associated with treatment response in head and neck cancer

Aim:

We aimed to identify quantitative ultrasound (QUS)-radiomic markers to predict radiotherapy response in metastatic lymph nodes of head and neck cancer.

Materials & methods:

Node-positive head and neck cancer patients underwent pretreatment QUS imaging of their metastatic lymph nodes. Imaging features were extracted using the QUS spectral form, and second-order texture parameters. Machine-learning classifiers were used for predictive modeling, which included a logistic regression, naive Bayes, and k-nearest neighbor classifiers.

Results:

There was a statistically significant difference in the pretreatment QUS-radiomic parameters between radiological complete responders versus partial responders (p < 0.05). The univariable model that demonstrated the greatest classification accuracy included: spectral intercept (SI)-contrast (area under the curve = 0.741). Multivariable models were also computed and showed that the SI-contrast + SI-homogeneity demonstrated an area under the curve = 0.870. The three-feature model demonstrated that the spectral slope-correlation + SI-contrast + SI-homogeneity-predicted response with accuracy of 87.5%.

Conclusion:

Multivariable QUS-radiomic features of metastatic lymph nodes can predict treatment response a priori.

In this study, quantitative ultrasound (QUS) and machine-learning classification was used to predict treatment outcomes in head and neck cancer patients. Metastatic lymph nodes in the neck were scanned using conventional frequency ultrasound (US). Quantitative data were collected from the US-radiofrequency signal a priori. Machine-learning classification models were computed using QUS features; these included the linear fit parameters of the power spectrum, and second-order texture parameters of the QUS parametric images. Treatment outcomes were measured based on radiological response. Patients were classified into binary groups: radiologic complete response (CR) or radiological partial response (PR), which was assessed 3 months following treatment. Initial results demonstrate high accuracy (%Acc = 87.5%) for predicting radiological response. The results of this study suggest that QUS can be used to predict head and neck cancer response to radiotherapy a priori.

Quantitative Ultrasound Image Analysis of Axillary Lymph Nodes to Diagnose Metastatic Involvement in Breast Cancer

This study aimed to assess the potential of state-of-the-art ultrasound analysis techniques to non-invasively diagnose axillary lymph nodes involvement in breast cancer. After exclusion criteria, 105 patients were selected from two different hospitals. The 118 lymph node ultrasound images taken from these patients were divided into 53 cases and 65 controls, which made up the study series. The clinical outcome of each node was verified by ultrasound-guided fine needle aspiration, core needle biopsy or surgical biopsy. The achieved accuracy of the proposed method was 86.4%, with 84.9% sensitivity and 87.7% specificity. When tested on breast cancer patients only, the proposed method improved the accuracy of the sonographic assessment of axillary lymph nodes performed by expert radiologists by 9% (87.0% vs 77.9%). In conclusion, the results demonstrate the potential of ultrasound image analysis to detect the microstructural and compositional changes that occur in lymph nodes because of metastatic involvement.

Quantitative Ultrasound and B-Mode Image Texture Features Correlate with Collagen and Myelin Content in Human Ulnar Nerve Fascicles

We investigate the usefulness of quantitative ultrasound and B-mode texture features for characterization of ulnar nerve fascicles. Ultrasound data were acquired from cadaveric specimens using a nominal 30-MHz probe. Next, the nerves were extracted to prepare histology sections. Eighty-five fascicles were matched between the B-mode images and the histology sections. For each fascicle image, we selected an intra-fascicular region of interest. We used histology sections to determine features related to the concentration of collagen and myelin and ultrasound data to calculate the backscatter coefficient (-24.89 ± 8.31 dB), attenuation coefficient (0.92 ± 0.04 db/cm-MHz), Nakagami parameter (1.01 ± 0.18) and entropy (6.92 ± 0.83), as well as B-mode texture features obtained via the gray-level co-occurrence matrix algorithm. Significant Spearman rank correlations between the combined collagen and myelin concentrations were obtained for the backscatter coefficient (R = -0.68), entropy (R = -0.51) and several texture features. Our study indicates that quantitative ultrasound may potentially provide information on structural components of nerve fascicles.

A priori prediction of breast tumour response to chemotherapy using quantitative ultrasound imaging and artificial neural networks

We demonstrate the clinical utility of combining quantitative ultrasound (QUS) imaging of the breast with an artificial neural network (ANN) classifier to predict the response of breast cancer patients to neoadjuvant chemotherapy (NAC) administration prior to the start of treatment.

Using a 6 MHz ultrasound system, radiofrequency (RF) ultrasound data were acquired from 100 patients with biopsy-confirmed locally advanced breast cancer prior to the start of NAC. Quantitative ultrasound mean parameter intensity and texture features were computed from the tumour core and margin, and were compared to the clinical/pathological response and 5-year recurrence-free survival (RFS) of patients. A multi-parametric QUS model in conjunction with an ANN classifier predicted patient response with 96 ± 6% accuracy, and a 0.96 ± 0.08 area under the receiver operating characteristic curve (AUC), compared to 65 ± 10 % accuracy and 0.67 ± 0.14 AUC achieved using a K-Nearest Neighbour (KNN) algorithm. A separate ANN model predicted patient RFS with 85 ± 7% accuracy, and a 0.89 ± 0.11 AUC, whereas the KNN methodology achieved a 58 ± 6 % accuracy and a 0.64 ± 0.09 AUC.

The application of ANN for classifying patient response based on tumour QUS features performs well in terms of predicting response to chemotherapy. The findings here provide a framework for developing personalized a priori chemotherapy selection for patients that are candidates for NAC, potentially resulting in improved patient treatment outcomes and prognosis.

Breast-lesions characterization using Quantitative Ultrasound features of peritumoral tissue

The presented studies evaluate for the first time the efficiency of tumour classification based on the quantitative analysis of ultrasound data originating from the tissue surrounding the tumour. 116 patients took part in the study after qualifying for biopsy due to suspicious breast changes. The RF signals collected from the tumour and tumour-surroundings were processed to determine quantitative measures consisting of Nakagami distribution shape parameter, entropy, and texture parameters. The utility of parameters for the classification of benign and malignant lesions was assessed in relation to the results of histopathology. The best multi-parametric classifier reached an AUC of 0.92 and of 0.83 for outer and intra-tumour data, respectively. A classifier composed of two types of parameters, parameters based on signals scattered in the tumour and in the surrounding tissue, allowed the classification of breast changes with sensitivity of 93%, specificity of 88%, and AUC of 0.94. Among the 4095 multi-parameter classifiers tested, only in eight cases the result of classification based on data from the surrounding tumour tissue was worse than when using tumour data. The presented results indicate the high usefulness of QUS analysis of echoes from the tissue surrounding the tumour in the classification of breast lesions.

Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images

PURPOSE

The nonalcoholic fatty liver disease is the most common liver abnormality. Up to date, liver biopsy is the reference standard for direct liver steatosis quantification in hepatic tissue samples. In this paper we propose a neural network-based approach for nonalcoholic fatty liver disease assessment in ultrasound.

METHODS

We used the Inception-ResNet-v2 deep convolutional neural network pre-trained on the ImageNet dataset to extract high-level features in liver B-mode ultrasound image sequences. The steatosis level of each liver was graded by wedge biopsy. The proposed approach was compared with the hepatorenal index technique and the gray-level co-occurrence matrix algorithm. After the feature extraction, we applied the support vector machine algorithm to classify images containing fatty liver. Based on liver biopsy, the fatty liver was defined to have more than 5% of hepatocytes with steatosis. Next, we used the features and the Lasso regression method to assess the steatosis level.

RESULTS

The area under the receiver operating characteristics curve obtained using the proposed approach was equal to 0.977, being higher than the one obtained with the hepatorenal index method, 0.959, and much higher than in the case of the gray-level co-occurrence matrix algorithm, 0.893. For regression the Spearman correlation coefficients between the steatosis level and the proposed approach, the hepatorenal index and the gray-level co-occurrence matrix algorithm were equal to 0.78, 0.80 and 0.39, respectively.

CONCLUSIONS

The proposed approach may help the sonographers automatically diagnose the amount of fat in the liver. The presented approach is efficient and in comparison with other methods does not require the sonographers to select the region of interest.