Characterization Of Breast Lesions Research Articles

Improved Breast 2D SWE Algorithm to Eliminate False-Negative Cases.

Two-dimensional shear wave elastography (SWE) has been limited in breast lesion characterization due to false-negative results from artifacts. The aim of this study was to evaluate an updated Food and Drug Administration-approved breast 2D-SWE algorithm and compare with the standard algorithm (SA). This prospective, single-center study was approved by our local institutional review board and Health Insurance Portability and Accountability Act compliant. From April 25, 2019 to May 2, 2022, raw shear wave data were saved on patients having screening or diagnostic breast ultrasound on a Siemens Sequoia US. After removing duplicate images and those without biopsy diagnosis or stability over 2 years, there were 298 patients with 394 lesions with biopsy-proven pathology or >2-year follow-up. Raw data were processed using the SA and a new algorithm (NA). Five-millimeter regions of interest were placed in the highest stiffness in the lesion or adjacent 3 mm on the SA. Stiffness values (shear wave speed, max) in this location from both algorithms were recorded. Statistics were calculated for comparing the 2 algorithms. The mean patient age was 56.3 ± 16.1 years (range, 21-93 years). The mean benign lesion size was 10.7 ± 8.0 mm (range, 2-46 mm), whereas the mean malignant lesion size was 14.9 ± 7.8 mm (range, 4-36 mm). There were 201 benign (>2-year follow-up) and 193 biopsied lesions (65 benign; 128 malignant). The mean maximum stiffness for benign lesions was 2.37 m/s (SD 1.26 m/s) for SA and 3.51 m/s (SD 2.05 m/s) for NA. For malignant lesions, the mean maximum stiffness was 4.73 m/s (SD, 1.71 m/s) for SA and 8.45 m/s (SD, 1.42 m/s) for NA. The area under the receiver operating characteristic curve was 0.87 SA and 0.95 NA when using the optimal cutoff value. Using a threshold value of 5.0 m/s for NA and comparing to SA, the sensitivity increased from 0.45 to 1.00 and the specificity decreased from 0.94 to 0.81; the positive predictive value was 0.72, the negative predictive value was 1.00, and the negative likelihood ratio was 0.00. Using a new breast SWE algorithm significantly improves the sensitivity of the technique with a small decrease in specificity, virtually eliminating the "soft" cancer artifact. The new 2D-SWE algorithm significantly increases the sensitivity and negative predictive value in characterizing breast lesions as benign or malignant and allows for downgrading all BI-RADS 4 lesions.

Clinical utility of abbreviated breast MRI based on diffusion tensor imaging in patients underwent breast conservative therapy.

To evaluate the added value of the diffusion tensor imaging (DTI) parameters to abbreviated breast MRI protocol in differentiating recurrent breast cancer from post-operative changes in cases of breast conservative surgery (BCS). This prospective study was approved by our institutional review board. Written informed consent was obtained in all patients. 47 female patients (mean age, 49years; range, 32-66years) that previously underwent breast conservative surgery with a palpable mass were included in this study (62 breast lesions). Two abbreviated MRI protocols were compared using 1.5 Tesla MRI, AB-MRI 1 (axial T1, T2, pre-contrast T1, 1st post-contrast and subtracted images) and AB-MRI 2 (same sequences plus adding DTI). In both protocols, the wash-in rate was calculated. Histopathology was used as the standard of reference. Appropriate statistical tests were used to assess sensitivity, specificity, and diagnostic accuracy for each protocol. The mean total acquisition time was of 6min for AB-MRI 1 and 10min for AB-MRI 2 protocols while the mean interpretation time was of 57.5 and 75s, respectively. Among analyzed DTI parameters, MD (mean diffusivity) showed the highest sensitivity (96.43%) and specificity (91.18%) (P value = < 0.001). FA (fractional anisotropy), AD (axial diffusivity) and RD (radial diffusivity) showed sensitivity = (78.57%, 82.14% and 85.71%), specificity = (88.24, 85.29% and 79.41%), respectively, P value (< 0.001). DTI may be included in abbreviated MRI protocols without a significant increase in acquisition time and with the advantage of increasing specificity and clinical utility in the characterization of post-conservative breast lesions.

MsGoF: Breast lesion classification on ultrasound images by multi-scale gradational-order fusion framework

Background and Objective: Predicting the malignant potential of breast lesions based on breast ultrasound (BUS) images is a crucial component of computer-aided diagnosis system for breast cancers. However, since breast lesions in BUS images generally have various shapes with relatively low contrast and present complex textures, it still remains challenging to accurately identify the malignant potential of breast lesions. Methods: In this paper, we propose a multi-scale gradational-order fusion framework to make full advantages of multi-scale representations incorporating with gradational-order characteristics of BUS images for breast lesions classification. Specifically, we first construct a spatial context aggregation module to generate multi-scale context representations from the original BUS images. Subsequently, multi-scale representations are efficiently fused in feature fusion block that is armed with special fusion strategies to comprehensively capture morphological characteristics of breast lesions. To better characterize complex textures and enhance non-linear modeling capability, we further propose isotropous gradational-order feature module in the feature fusion block to learn and combine multi-order representations. Finally, these multi-scale gradational-order representations are utilized to perform prediction for the malignant potential of breast lesions. Results: The proposed model was evaluated on three open datasets by using 5-fold cross-validation. The experimental results (Accuracy: 85.32%, Sensitivity: 85.24%, Specificity: 88.57%, AUC: 90.63% on dataset A; Accuracy: 76.48%, Sensitivity: 72.45%, Specificity: 80.42%, AUC: 78.98% on dataset B) demonstrate that the proposed method achieves the promising performance when compared with other deep learning-based methods in BUS classification task. Conclusions: The proposed method has demonstrated a promising potential to predict malignant potential of breast lesion using ultrasound image in an end-to-end manner.

Ktrans Calculation Using Reference Method Corrected Native T10 for Breast Cancer Diagnosis.

The objective of the study is to use multiple tube phantoms to generate correction factor at different spatial locations for each breast coil cuff to correct the native T10 value in the corresponding spatial location of the breast lesion. The corrected T10 value was used to compute Ktrans and analyze its diagnostic accuracy in the classification of target condition, i.e., breast tumors into malignant and benign. Both in vitro phantom study (external reference) and patient's studies were acquired on simultaneous positron emission tomography/magnetic resonance imaging (PET/MRI) Biograph molecular magnetic resonance (mMR) system using 4 channel mMR breast coil. The spatial correction factors derived using multiple tube phantom were used for a retrospective analysis of dynamic contrast-enhanced (DCE) MRI data of 39 patients with a mean age of 50 years (31-77 years) having 51 enhancing breast lesions. Corrected and non-corrected receiver operating characteristic (ROC) curve analysis revealed a mean Ktrans value of 0.64 min-1 and 0.60 min-1, respectively. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and overall accuracy for non-corrected data were 86.21%, 81.82%, 86.20%, 81.81%, and 84.31%, respectively, and for corrected data were 93.10%, 86.36%, 90%, 90.47%, and 90.20% respectively. The area under curve (AUC) of corrected data was improved to 0.959 (95% confidence interval [CI] 0.862-0.994) from 0.824 (95% CI 0.694-0.918) of non-corrected data, and for NPV, it was improved to 90.47% from 81.81%, respectively. T10 values were normalized using multiple tube phantom which was used for computation of Ktrans. We found significant improvement in the diagnostic accuracy of corrected Ktrans values that results in better characterization of breast lesions.

Breast Ultrasound vs Mammography: Is the Former a Better Replacement for the Latter? A Comparative Study

Breast cancer is the most commonly occurring cancer in women. It is also the second leading cause of cancer death in women. Breast Cancer is the most common and most lethal cancer in Nigeria with an estimated 27,304 new cases in 2012 and which is estimated to increase in further years despite the lack of adequate data. Mortality rates are very high in our locality with approximately 13,960 deaths annually. Mammography is the gold standard for breast cancer screening in developed countries with some evidence showing improved survival particularly among women 50–69 years in some randomized controlled trials in developed countries where breast cancer prevalence is high. Studies gives a mammography sensitivity of (83-86%), a specificity of (48-55.5%), and a diagnostic accuracy of 56-68%. However, mammograms still pose the risk of exposing the breasts to radiation, and is also not well suited for women with dense breasts, implants, fibrocystic breasts, or those on hormone replacement therapy. Breast ultrasound has been used for many years in the characterization of breast lesions, and can also be used to help guide a biopsy needle into an area of the breast for testing. Ultrasound is relied upon significantly since mammographic facilities are few and breast magnetic resonance imaging is either too expensive or unavailable and is it also not limited by breast density. Studies show ultrasound has a sensitivity of (72.2% - 86.3%), and a specificity of (79.8-93.6%). Ultrasound is unable to screen for many types of breast cancer. It is also difficult to detect calcification in the ultrasound of the breast, and this is an early sign of breast cancer. Therefore ultrasound is mainly used in LMIC, where late presentation is most common due to lack of funds because it is cheaper and more portable and it also has a higher sensitivity in women greater than 40 years. In conclusion, this study aims to compare ultrasound and mammography if the former is a better replacement for the latter.

Proteomics comparison between mass-like and non-mass-like breast lesions.

The proteomic differences between mass-like (ML) breast lesions and non-mass-like (NML) breast lesions were compared to explore the formation mechanism of NML ultrasonic morphological characteristics. From January to August 2021, tissue samples were collected from 10 patients with malignant ML (MML), 10 patients with malignant NML (MNML), 10 patients with benign ML (BML), and seven patients with benign NML (BNML). The proteomic differences between the BML and BNML groups and the MML and MNML groups were compared by data-independent acquisition (DIA) quantitative mass spectrometry. The differentially expressed proteins were analyzed by Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and protein-protein interaction (PPI) networks analyses. We identified a total of 623 significantly differentially expressed proteins in the MML/MNML group, and 167 significantly differentially expressed proteins in the BML/BNML group, with relative ratios >1.2 or <-0.83. The up-regulated differential proteins were more abundant in the tumor necrosis factor (TNF) signaling pathway in both the MML/MNML and BML/BNML groups, suggesting that the TNF signaling pathway may be related to the ultrasonic morphological characteristics of breast lesions. Dual specificity mitogen-activated protein kinase 3 (MP2K3), a protein factor in the TNF signaling pathway, exhibited significant upregulation in both the malignant and BML groups. The TNF signaling pathway may be associated with the ultrasonic morphological characteristics of breast lesions. MP2K3 is the up-regulated differential expression protein in the MML/MNML and BML/BNML groups, which may be related to the ultrasonic morphological characteristics of breast lesions.

ROLE OF DIFFUSION WEIGHTED IMAGING AND ADC VALUES IN CHARACTERISING BREAST LESIONS ON MR MAMMOGRAPHY

Background- Dynamic contrast enhanced MRI (DCE MR) is an important imaging modality to detect and evaluate the breast lesions with high sensitivity. Aim of study was to characterize breast lesions detect Objective- ed on MR mammography by diffusion weighted imaging and quantify ADC values to differentiate benign and malignant mass and non mass lesions. Methods- This prospective study was performed in thirty female patients on 1.5T GE Healthcare HDXT MRI machine. Thirty three breast lesions were included in this study. Final diagnosis was correlated with histopathological diagnosis. Out of total thirty three lesions, mean ADC value Results- of malignant lesions was 1.01 ± 0.24 x 10-3mm2/sec and for benign lesions was 1.48 ± 0.29 x 10-3 mm2/sec. The calculated ADC cut off value of 1.22x 10-3 mm2/sec gave a sensitivity of 86.96% and specicity of 90% to differentiate malignant and benign breast lesions. As a Conclusion- conclusion Diffusion weighted imaging and quantitative analysis with ADC values can be used with conventional DCE MR to differentiate benign and malignant breast lesions with high sensitivity and specicity

Histopathological Characteristics of Breast Lesions in a Tertiary Health Institution in Southwest Nigeria; A 9-year Review

Background: The breast is affected by several diseases, including developmental, inflammatory, and neoplastic. While benign breast neoplasms are usually more common, breast cancer is the most common nonskin cancer and the leading cause of cancer-related deaths in women after lung cancer in the world. Objective: The review aimed to assess the histopathological diagnosis of breast lesions over a period of 9years Methods: This was a retrospective review of eight hundred and fourteen histopathologic cases of breast lesions accessed through laboratory records of all breast lesions cases seen. The demographic data were obtained and the patient’s histology slides were reviewed. The tumors were classified according to the WHO International Classification of breast tumors and Malignant breast tumors were graded according to the Nottingham grading system. Data were analyzed using SPSS version 25. Results: The majority of breast cancer cases were seen in patients below 40 years, malignant cases were predominant in older age groups (40 – 59 years; 57.4%, 60 years and above; 23.3%) and malignancy was significantly associated with age group, p-value &lt; 0.05. The prevailing neoplasm was Benign type (68.3%) while malignant neoplasm accounted for 30.2% and invasive ductal carcinoma (89.1%) was most prevalent. Moreso, the majority were in grade 2; 152 (76.8%) using the Nottigham grading system. However, the commonest benign neoplasm was fibroadenoma (53.7%) followed by fibrocystic change (20.1%). Conclusion: Breast lesions are common in this environment. Benign breast neoplasms are commoner than malignant diseases. One in three of every sub-Saharan woman diagnosed with malignant breast lesion may not survive five years post-diagnosis. The prognosis of breast malignancies in sub-Saharan is poor due to late Presentation, ignorance and poverty.

Histopathological Characteristics of Breast Lesions in a Tertiary Health Institution in Southwest Nigeria: A 9-year Review

Background: The breast is affected by several diseases, including developmental, inflammatory, and neoplastic. While benign breast neoplasms are usually more common, breast cancer is the most common nonskin cancer and the leading cause of cancer-related deaths in women after lung cancer in the world.&#x0D; Objective: The review aimed to assess the histopathological diagnosis of breast lesions over a period of 9years&#x0D; Methods: This was a retrospective review of eight hundred and fourteen histopathologic cases of breast lesions accessed through laboratory records of all breast lesions cases seen. The demographic data were obtained and the patient’s histology slides were reviewed. The tumors were classified according to the WHO International Classification of breast tumors and Malignant breast tumors were graded according to the Nottingham grading system. Data were analyzed using SPSS version 25.&#x0D; Results: The majority of breast cancer cases were seen in patients below 40 years, malignant cases were predominant in older age groups (40 – 59 years; 57.4%, 60 years and above; 23.3%) and malignancy was significantly associated with age group, p-value &lt; 0.05. The prevailing neoplasm was Benign type (68.3%) while malignant neoplasm accounted for 30.2% and invasive ductal carcinoma (89.1%) was most prevalent. Moreso, the majority were in grade 2; 152 (76.8%) using the Nottigham grading system. However, the commonest benign neoplasm was fibroadenoma (53.7%) followed by fibrocystic change (20.1%).&#x0D; Conclusion: Breast lesions are common in this environment. Benign breast neoplasms are more commoner than malignant diseases. One in three of every sub-Saharan woman diagnosed with malignant breast lesion may not survive five years post-diagnosis. The prognosis of breast malignancies in sub-Saharan is poor due to late Presentation, ignorance, and poverty.

Correlation of Mammography, Ultrasound and Sonoelastographic Findings With Histopathological Diagnosis in Breast Lesions.

Introduction Breast masses range from inflammatory and benign to malignant lesions, varying in different age groups and clinical presentations. Breast imaging techniques leading to prompt and specific diagnosis have been a lifesaver for millions around the globe saving them undue mental stress in inflammatory lesions and preventing early death in case of neoplasms. Here, we compare mammography, ultrasonography (US) and ultrasound elastography in the screening and diagnosis of breast lesions and the usefulness of strain ratio as a non-invasive tool in diagnosing breast malignancies. Aims and objectives Determining the characteristics ofbreast lesions on imaging by mammogram, ultrasonography, elastography, calculating strain ratio andcorrelating them with histopathology. To further estimate the advantages and limitations of one modality over the other in the evaluation of breast lesions. Methods The study was done over a duration of 18 months from November 2019 to June 2021 at JSS Medical College and Hospital, Mysuru. In this prospective study, 73 female patients with palpable breast lesions were evaluated using mammography, US and sonoelastography and were co-related with histopathological findings. Results This study has proved that the use of ultrasound elastography has higher sensitivity (91.67% with strain ratio kept at 3) in detecting malignant lesions when compared with x-ray mammography and ultrasonography having a sensitivity of 87.88% and 90.91%, respectively. Our study confirmed that there is a correlation between strain ratio and histopathological findings and that the strain ratio has high sensitivity in diagnosing and differentiating malignant breast lesions. Conclusions Mammography, US and sonoelastography when combined together are helpful in characterization and management of breast lesions. This helps to avoid unnecessary invasive interventions. The specificity of the study in detecting malignant lesions was comparable with that of histopathological analysis.

Role of contrast-enhanced spectral mammography in the assessment of residual disease following neoadjuvant chemotherapy in patients with breast cancer

BackgroundNeoadjuvant chemotherapy (NAC) is currently one of the most commonly utilized treatment options for patients with breast cancer. Evaluating residual disease following NAC is vital in post-chemotherapy treatment planning. Underestimation or overestimation of the residual disease may result in incomplete surgical resection or unnecessary aggressive surgical treatment which can compromise patient survival or result in unwanted morbidity. Contrast-enhanced spectral mammography (CESM) is a new imaging modality that can provide both morphological and anatomical characterization of neoplastic breast lesions when MRI is unavailable or contraindicated. The aim of this prospective observational study was to evaluate the value of CESM in assessing the extent of residual disease following NAC and predicting complete response (CR) with histopathology as the gold standard.ResultsA total of 142 patients were included in our study with invasive duct carcinoma the most prevalent histopathological type seen in 81.7% of cases. The average tumor reduction in size was 40.8% by CESM and 35.8% by histopathology. Comparison between maximum tumor diameter after NAC by CESM and histopathology revealed a high degree of correlation (R = 0.918, p < 0.01). In 45.1% of cases, CESM underestimated the residual tumor size by an average of 1.1 cm. Comparison between CESM and histopathology in predicting CR yielded CESM sensitivity, specificity, positive predictive value (PPV), and negative predictive values (NPV) of 96.7%, 84.6%, 97.2%, and 100%, respectively.ConclusionsCESM is a new effective imaging modality in assessing residual disease in breast cancer patients receiving NAC. Post-NAC CESM correlated well with residual tumor size by histopathology with a tendency for underestimation. Careful assessment of CESM images should be made to accurately measure the exact tumor size to avoid overestimation or underestimation potentially increasing the extent of the operation. Proper assessment of the true extent of residual disease can help the surgeon to select the optimal surgical technique ensuring radical treatment of the disease improving patient survival and reducing morbidity.

Volumetric imaging and morphometric analysis of breast tumor angiogenesis using a new contrast-free ultrasound technique: a feasibility study

BackgroundThere is a strong correlation between the morphological features of new tumor vessels and malignancy. However, angiogenic heterogeneity necessitates 3D microvascular data of tumor microvessels for more reliable quantification. To provide more accurate information regarding vessel morphological features and improve breast lesion characterization, we introduced a quantitative 3D high-definition microvasculature imaging (q3D-HDMI) as a new easily applicable and robust tool to morphologically characterize microvasculature networks in breast tumors using a contrast-free ultrasound-based imaging approach.MethodsIn this prospective study, from January 2020 through December 2021, a newly developed q3D-HDMI technique was evaluated on participants with ultrasound-identified suspicious breast lesions recommended for core needle biopsy. The morphological features of breast tumor microvessels were extracted from the q3D-HDMI. Leave-one-out cross-validation (LOOCV) was applied to test the combined diagnostic performance of multiple morphological parameters of breast tumor microvessels. Receiver operating characteristic (ROC) curves were used to evaluate the prediction performance of the generated pooled model.ResultsNinety-three participants (mean age 52 ± 17 years, 91 women) with 93 breast lesions were studied. The area under the ROC curve (AUC) generated with q3D-HDMI was 95.8% (95% CI 0.901–1.000), yielding a sensitivity of 91.7% and a specificity of 98.2%, that was significantly higher than the AUC generated with the q2D-HDMI (p = 0.02). When compared to q2D-HDMI, the tumor microvessel morphological parameters obtained from q3D-HDMI provides distinctive information that increases accuracy in differentiating breast tumors.ConclusionsThe proposed quantitative volumetric imaging technique augments conventional breast ultrasound evaluation by increasing specificity in differentiating malignant from benign breast masses.

BRACS: A Dataset for BReAst Carcinoma Subtyping in H&amp;E Histology Images.

Breast cancer is the most commonly diagnosed cancer and registers the highest number of deaths for women. Advances in diagnostic activities combined with large-scale screening policies have significantly lowered the mortality rates for breast cancer patients. However, the manual inspection of tissue slides by pathologists is cumbersome, time-consuming and is subject to significant inter- and intra-observer variability. Recently, the advent of whole-slide scanning systems has empowered the rapid digitization of pathology slides and enabled the development of Artificial Intelligence (AI)-assisted digital workflows. However, AI techniques, especially Deep Learning, require a large amount of high-quality annotated data to learn from. Constructing such task-specific datasets poses several challenges, such as data-acquisition level constraints, time-consuming and expensive annotations and anonymization of patient information. In this paper, we introduce the BReAst Carcinoma Subtyping (BRACS) dataset, a large cohort of annotated Hematoxylin and Eosin (H&E)-stained images to advance AI development in the automatic characterization of breast lesions. BRACS contains 547 Whole-Slide Images (WSIs) and 4539 Regions Of Interest (ROIs) extracted from the WSIs. Each WSI and respective ROIs are annotated by the consensus of three board-certified pathologists into different lesion categories. Specifically, BRACS includes three lesion types, i.e., benign, malignant and atypical, which are further subtyped into seven categories. It is, to the best of our knowledge, the largest annotated dataset for breast cancer subtyping both at WSI and ROI levels. Furthermore, by including the understudied atypical lesions, BRACS offers a unique opportunity for leveraging AI to better understand their characteristics. We encourage AI practitioners to develop and evaluate novel algorithms on the BRACS dataset to further breast cancer diagnosis and patient care. Database URL: https://www.bracs.icar.cnr.it/

Ultrasound strain elastography-based characterization of in vivo breast lesions using deep learning

Ultrasound strain elastography showed great promise for breast lesion characterization. With the readily available computational power in the clinical workflow, machine learning-based is gaining acceptance in cancer imaging applications. In this study, we combine the latest developments in motion tracking that enables us to obtain high-quality axial strain and full shear strain images to test the deep-learning-based prediction of breast lesion malignancy. To our knowledge, total shear strain images have not been widely used for breast lesion differentiation. More specifically, a PDE-based regularization method [Guo et al., Ultrasonic Imaging (2015)] developed by our group has been improved to get high-quality two-dimensional displacement data. From those high-quality displacement data, total shear strain images can be constructed. We adopted three variants of convolution neural network (CNN) models with attention modules to predict breast lesion malignancy by combining B-mode, axial strain, and total shear strain images and their radiomic features. From our internal database, 150 cases of pathologically-confirmed breast ultrasound data [Hall et al., UMB (2003)] with data augmentation are used to evaluate our machine learning models. Our initial testing results are encouraging with the accuracy and area under the curve being around 0.75.

Identification of Anomalies in Mammograms through Internet of Medical Things (IoMT) Diagnosis System.

Breast cancer is the primary health issue that women may face at some point in their lifetime. This may lead to death in severe cases. A mammography procedure is used for finding suspicious masses in the breast. Teleradiology is employed for online treatment and diagnostics processes due to the unavailability and shortage of trained radiologists in backward and remote areas. The availability of online radiologists is uncertain due to inadequate network coverage in rural areas. In such circumstances, the Computer-Aided Diagnosis (CAD) framework is useful for identifying breast abnormalities without expert radiologists. This research presents a decision-making system based on IoMT (Internet of Medical Things) to identify breast anomalies. The proposed technique encompasses the region growing algorithm to segment tumor that extracts suspicious part. Then, texture and shape-based features are employed to characterize breast lesions. The extracted features include first and second-order statistics, center-symmetric local binary pattern (CS-LBP), a histogram of oriented gradients (HOG), and shape-based techniques used to obtain various features from the mammograms. Finally, a fusion of machine learning algorithms including K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA are employed to classify breast cancer using composite feature vectors. The experimental results exhibit the proposed framework's efficacy that separates the cancerous lesions from the benign ones using 10-fold cross-validations. The accuracy, sensitivity, and specificity attained are 96.3%, 94.1%, and 98.2%, respectively, through shape-based features from the MIAS database. Finally, this research contributes a model with the ability for earlier and improved accuracy of breast tumor detection.

Diagnostic value of strain elastography and shear wave elastography in differentiating benign and malignant breast lesions.

Conventional B-mode breast ultrasonography, though the primary modality to determine benign or malignant nature of a solid breast lesion, sometimes encounters overlapping sonographic morphological features in a single lesion. Elastography leads to improvement by evaluating the structural aspects and characterization of the lesion as benign or malignant on the basis of multi-parametric assessment. Determine the role of strain elastography (SE) and shear wave elastography (SWE) in differentiating benign and malignant breast lesions. Cross sectional SETTING: Radiology department of hospital PATIENTS AND METHODS: Patients meeting inclusion criteria referred to our hospital for ultrasonography followed by biopsy or surgical excisions were examined with B-mode ultrasonography and by both strain and shear wave elastography. Mean values of SE and SWE in benign and malignant breast lesions, determination of cutoff using AUC curves and sensitivity and specificity of both techniques. One hundred breast lesions from 95 consecutive patients. The mean (SD) strain elastography ratio in the overall patient population was 4.1 (2.0). Cutoff for benign vs. malignant lesions was 2.86 on the ROC curve. The AUC was 0.911 (95%CI; 0.835-0.988: SE, 0.039) with a sensitivity of 95.8% and a specificity of 89.3%. For the SWE kPa values, the ROC curve showed the AUC was 0.929 (95% CI, 0.870-0.988; SE: 0.030, P<.001). Assigning 45.3 as a cut off value provided a sensitivity of 95.8% with a specificity of 85.7%; the positive predictive value was 94.5% and the negative predictive value was 89.6%. The Breast Imaging Reporting and Data System (BI-RADS) category alone was able to differentiate between benign and malignant lesions with a sensitivity of 91.7% and a specificity 100% keeping the cut off value between 4a and 4b. The area under the ROC curve was 0.979. Combining the three (BI-RADS + SE + SWE) distinguished benign vs. malignant lesions with a sensitivity up to 100% and specificity up to 96.3%. Combining SE and SWE as a complementary tool with conventional B-mode ultrasonography has a significant potential for better characterization of solid breast lesions and decreasing unnecessary biopsies of BI-RADS IVa lesions. Single institution study. None.

Automated breast ultrasound: A comparison study with handheld ultrasound in detection and characterization of lesions in mammographically dense breast

Background: Although mammography is a powerful screening tool in detection of early breast cancer, it is imperfect, particularly for women with dense breast, which have a higher risk to develop cancer and decrease the sensitivity of mammogram, Automated breast ultrasound is a recently introduced ultrasonography technique, developed with the purpose to standardize breast ultrasonography and overcome some limitations of handheld ultrasound, this study aims to evaluate the diagnostic efficacy of Automated breast ultrasound and compare it with handheld ultrasound in the detection and characterization of breast lesions in women with dense breasts. Objectives: To evaluate the diagnostic efficacy of Automated breast ultrasound and compare it with hand held ultrasound in detection and characterization of breast lesions in women with dense breast. Subjects and Methods: A prospective observational study conducted at Oncology Teaching Hospital during the period of ten months from 1st of February till 1st of December 2020. Included 62 women with dense breasts on diagnostic mammograms. All women underwent technician performed automated breast ultrasound and radiologist performed handheld ultrasound for both breasts. All suspicious lesions with selected probably benign lesions underwent biopsy, handheld ultrasound detected 48 masses (67.6%), 15 of them (21.1%) were cystic, automated breast ultrasound detected 54 masses (76.1%); 20 of them (28.2%) were cystic. The sensitivity of handheld ultrasound was=87.5%, Specificity=58.8%, the sensitivity of automated breast ultrasound was=93.8%, Specificity=70.6%. Conclusion: Automated breast ultrasound is an effective modality to detect occult breast lesion in women with dense breasts, automated breast ultrasound and handheld ultrasound have a reliable agreement in detection and characterization of breast lesions with higher accuracy of automated breast ultrasound in the evaluation of malignant lesions.

Evaluating different combination methods to analyse ultrasound and shear wave elastography images automatically through discriminative convolutional neural network in breast cancer imaging

PurposeUltrasound (US) and Shear Wave Elastography (SWE) imaging are non-invasive methods used for breast lesion characterization. While US and SWE images provide both morphological information, SWE visualizes in addition the elasticity of tissue. In this study a Discriminative Convolutional Neural Network (DCNN) model is applied to US and SWE images and their combination to classify the breast lesions into malignant or benign cases. Furthermore, it is identified whether analysing only the region of the elastogram or including the surrounding B-mode image gives a superior performance.MethodsThe dataset used in this study consists of 746 images obtained from 207 patients comprising 486 malignant and 260 benign breast lesions. From each image the US and SWE image was extracted, once including only the region of the elastogram and once including also the surrounding B-mode image. These four datasets were applied individually to a DCNN to determine their predictive capability. Each the best US and SWE dataset were used to examine different combination methods with DCNN. The results were compared to the manual assessment by an expert radiologist.ResultsThe combination of US and SWE images with the surrounding B-mode image using two ensembled DCNN models achieved best results with an accuracy of 93.53 %, sensitivity of 94.42 %, specificity of 90.75 % and area under the curve (AUC) of 96.55 %.ConclusionThis study showed that using the whole US and SWE images through DCNN was superior to methods, in which only the region of elastogram was used. Combining breast cancer US and SWE images with two ensembled DCNN models in parallel improved the results. The accuracy, sensitivity and AUC of the best combination method were significantly superior to the results of using a single dataset through DCNN and to the results of the expert radiologist.

Development and validation of a deep learning model for breast lesion segmentation and characterization in multiparametric MRI.

ImportanceThe utilization of artificial intelligence for the differentiation of benign and malignant breast lesions in multiparametric MRI (mpMRI) assists radiologists to improve diagnostic performance.ObjectivesTo develop an automated deep learning model for breast lesion segmentation and characterization and to evaluate the characterization performance of AI models and radiologists.Materials and methodsFor lesion segmentation, 2,823 patients were used for the training, validation, and testing of the VNet-based segmentation models, and the average Dice similarity coefficient (DSC) between the manual segmentation by radiologists and the mask generated by VNet was calculated. For lesion characterization, 3,303 female patients with 3,607 pathologically confirmed lesions (2,213 malignant and 1,394 benign lesions) were used for the three ResNet-based characterization models (two single-input and one multi-input models). Histopathology was used as the diagnostic criterion standard to assess the characterization performance of the AI models and the BI-RADS categorized by the radiologists, in terms of sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). An additional 123 patients with 136 lesions (81 malignant and 55 benign lesions) from another institution were available for external testing.ResultsOf the 5,811 patients included in the study, the mean age was 46.14 (range 11–89) years. In the segmentation task, a DSC of 0.860 was obtained between the VNet-generated mask and manual segmentation by radiologists. In the characterization task, the AUCs of the multi-input and the other two single-input models were 0.927, 0.821, and 0.795, respectively. Compared to the single-input DWI or DCE model, the multi-input DCE and DWI model obtained a significant increase in sensitivity, specificity, and accuracy (0.831 vs. 0.772/0.776, 0.874 vs. 0.630/0.709, 0.846 vs. 0.721/0.752). Furthermore, the specificity of the multi-input model was higher than that of the radiologists, whether using BI-RADS category 3 or 4 as a cutoff point (0.874 vs. 0.404/0.841), and the accuracy was intermediate between the two assessment methods (0.846 vs. 0.773/0.882). For the external testing, the performance of the three models remained robust with AUCs of 0.812, 0.831, and 0.885, respectively.ConclusionsCombining DCE with DWI was superior to applying a single sequence for breast lesion characterization. The deep learning computer-aided diagnosis (CADx) model we developed significantly improved specificity and achieved comparable accuracy to the radiologists with promise for clinical application to provide preliminary diagnoses.

Predictive Value of Preoperative Dynamic Contrast-Enhanced MRI Imaging Features in Breast Cancer Patients with Postoperative Recurrence Time.

Although the implementation of surgery has reduced the mortality of breast cancer, postoperative recurrence is still an important problem bothering patients. DCE-GMRI can not only clearly display the morphological characteristics of breast lesions but also dynamically observe the blood perfusion of the lesions. On account of this, we explored the predictive value of preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) imaging features in breast cancer patients on postoperative recurrence time of breast cancer. The results showed that DCE-MRI images can clearly show the hemodynamic characteristics and morphological characteristics of tumor lesions, and have important value in predicting the recurrence time of breast cancer after surgery. The prognosis of early recurrence of breast cancer is worse. DCE-MRI can predict the time of postoperative recurrence and provide important clinical references.