Ultrasound elastography improves differentiation between benign and malignant breast lumps using B-mode ultrasound and color Doppler

Comparing the Diagnostic Performance of Ultrasound Elastography and Magnetic Resonance Imaging to Differentiate Benign and Malignant Breast Lesions: A Systematic Review and Meta-analysis

OBJECTIVE

The purpose of this systematic review and meta-analysis was comparing diagnostic performance of ultrasound elastography (UE), strain UE and shear wave elastography (SWE), with magnetic resonance imaging (MRI) in differentiating benign and malignant breast lesions.

METHODS

Literature search of MEDLINE, Web of Science, SCOPUS and Google Scholar was performed in June 2023. Included studies used Breast Imaging Reporting and Data System (BI-RADS) and histopathology as reference standard. A bivariate random-effects model was used to calculate sensitivity, specificity, diagnostic odds ratio (DOR), positive and negative likelihood ratios and area under the curve (AUC). Meta-regression subgroup analysis was performed.

RESULTS

Nine studies and 536 lesions were included. Pooled sensitivity was not different between MRI vs UE [MRI: 94% (95% CI: 88.2%-96.9%) vs UE: 90% (95% CI: 84.7%-93.1%); P=0.153] but a difference was found for specificity [UE: 78% (95% CI: 66.3%-86.4%) vs MRI: 71.3% (95% CI: 52.1%-85%); P=0.0065]. Strain UE showed higher specificity and similar sensitivity to SWE [strain UE: 0.85 (95% CI: 0.71-0.93) vs SWE: 0.72 (95% 0.58-0.83); P=0.017 and strain UE: 0.87 (95% CI 0.79-0.93) vs SWE: 0.91 (95% CI 0.85-0.95); P=0.311, respectively]. AUC was similar between MRI vs UE [0.91 (95% CI 0.87-0.95) vs 0.92 (95% CI 0.88-0.95); P=0.452, respectively] as was DOR [MRI: 38.083 (95% CI: 12.401-116.957) vs UE: 30.395 (95% CI: 16.572-55.75); P>0.05]. Meta-regression analysis found no significant differences in the diagnostic accuracy between MRI, strain UE and SWE.

CONCLUSION

Our results show that UE when compared to MRI has adequate performance in differentiating benign and malignant breast lesions.

Diagnostic Accuracy of Spectral Doppler Indices and Sonoelastography in Predicting Malignancy in Breast Imaging Reporting and Database System 3 Breast Lesions With Histopathology as the Reference Standard

Introduction Breast cancer is a significant health concern in India, representing a large portion of all cancers affecting women and ranking as one of the most common cancers overall. Reliable diagnostic tools are essential for accurately predicting malignancy and reducing the need for unnecessary biopsies. A Breast Imaging Reporting and Database System (BI-RADS) 3 designation suggests a low likelihood of cancer, indicating that findings are likely benign. For these cases, short-term follow-up imaging is generally preferred over immediate biopsy as the probability of malignancy is minimal. This study evaluates the effectiveness of strain elastography, specifically the strain ratio, in predicting malignancy in BI-RADS 3 breast lesions in a cohort of 50 patients. Additionally, it examines the role of Doppler indices, including the Pulsatility Index (PI) and Resistance Index (RI). Histopathological analysis was used as the reference standard. Methods A descriptive cross-sectional study was conducted on 50 patients presenting with palpable breast lumps or abnormalities detected via ultrasonography or mammography. Conventional B-mode ultrasound examinations were performed on all the patients, and those with BI-RADS 3 lesions were identified. The Doppler technique was employed to calculate PI and RI values, followed by strain elastography to determine the strain ratio. Histopathological confirmation was performed for all patients. Results Histopathological analysis revealed that 92% (N=46) of the lesions were benign, while 8% (N=4) were malignant. For strain elastography, the sensitivity was 75%, specificity was 97.83%, positive predictive value (PPV) was 75%, negative predictive value (NPV) was 97.83%, and the diagnostic accuracy was 96%. For Doppler PI, the sensitivity was 75%, specificity was 95.65%, PPV was 60%, NPV was 97.78%, and the overall diagnostic accuracy was 94%. Similarly, for Doppler RI, the sensitivity was 75%, specificity was 95.65%, PPV was 60%, NPV was 97.78%, and the overall diagnostic accuracy was 94%. Conclusion B-mode ultrasound remains the first-line imaging investigation for evaluating breast masses. In BI-RADS 3 lesions, where the likelihood of malignancy is minimal, the combined use of strain elastography and Doppler PI and RI indices can serve as a valuable adjunct in predicting malignancy and reducing the need for unnecessary biopsies. Moreover, strain elastography demonstrates higher diagnostic accuracy compared to Doppler PI and RI.

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 of breast lesions on imaging by mammogram, ultrasonography, elastography, calculating strain ratio and correlating 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.

Bi-Modal Transfer Learning for Classifying Breast Cancers via Combined B-Mode and Ultrasound Strain Imaging

Although accurate detection of breast cancer still poses significant challenges, deep learning (DL) can support more accurate image interpretation. In this study, we develop a highly robust DL model based on combined B-mode ultrasound (B-mode) and strain elastography ultrasound (SE) images for classifying benign and malignant breast tumors. This study retrospectively included 85 patients, including 42 with benign lesions and 43 with malignancies, all confirmed by biopsy. Two deep neural network models, AlexNet and ResNet, were separately trained on combined 205 B-mode and 205 SE images (80% for training and 20% for validation) from 67 patients with benign and malignant lesions. These two models were then configured to work as an ensemble using both image-wise and layer-wise and tested on a dataset of 56 images from the remaining 18 patients. The ensemble model captures the diverse features present in the B-mode and SE images and also combines semantic features from AlexNet and ResNet models to classify the benign from the malignant tumors. The experimental results demonstrate that the accuracy of the proposed ensemble model is 90%, which is better than the individual models and the model trained using B-mode or SE images alone. Moreover, some patients that were misclassified by the traditional methods were correctly classified by the proposed ensemble method. The proposed ensemble DL model will enable radiologists to achieve superior detection efficiency owing to enhance classification accuracy for breast cancers in ultrasound (US) images.

Effect of Anatomical and Physiological Factors on Ultrasonic Breast Imaging Reporting and Data System Score in Iraqi Women Presenting with Breast Lumps

BACKGROUND: Breast lumps are a common presentation that can be assess non-invasively using the ultrasonic examination. AIM: The study aimed to assess the effect of different anatomical and physiological factors on the outcome of ultrasonic scoring of breast lumps. METHODS: A total of 60 females presented with a breast lump on ultrasound assessment were randomly selected after their consent at the Clinic for Early Detection of Breast Cancer in Baghdad. The results were expressed according to the ultrasound breast imaging reporting and data system (BI-RADS) scoring. RESULTS: There was a statistically significant positive correlation between the BI-RADS score with breast size, age, postmenopausal state, and personal or familial history of breast disease. Most cases (46.7%) scored BI-RADS II, followed by scores of III (21.6%), 4 (16.7%), and V (15%). The upper lateral quadrant of the breast was the most commonly affected sites. Marital status, parity, and breastfeeding didn’t have statistically significant influence on the sores. CONCLUSION: Ultrasonic BI-RADS scoring of breast lumps provides an initial reliable tool for the management of breast disease. Higher scores are associated with increasing breast size, age, postmenopausal state, and personal or familial history of breast disease. Several anatomical, physiological, hereditary, and environmental aspects influence such factors.

A Brief Review on Breast Carcinoma and Deliberation on Current Non Invasive Imaging Techniques for Detection

BACKGROUND

Breast carcinoma is a life threatening disease that accounts for 25.1% of all carcinoma among women worldwide. Early detection of the disease enhances the chance for survival.

DISCUSSION

This paper presents comprehensive report on breast carcinoma disease and its modalities available for detection and diagnosis, as it delves into the screening and detection modalities with special focus placed on the non-invasive techniques and its recent advancement work done, as well as a proposal on a novel method for the application of early breast carcinoma detection.

CONCLUSION

This paper aims to serve as a foundation guidance for the reader to attain bird's eye understanding on breast carcinoma disease and its current non-invasive modalities.

Diagnostic Value of Elastography, Strain Ratio, and Elasticity to B-Mode Ratio and Color Doppler Ultrasonography in Breast Lesions

Purpose

The aim of this study was to investigate the sensitivity, specificity, and diagnostic accuracy of sonoelastography (SE), strain ratio (SR), elasticity to B-mode (E/B) ratio, and color Doppler ultrasonography (US) in suspected breast lesions.

Materials and Methods

This prospective study was conducted on women referred to Alzahra university hospital of Tabriz for annual screening of breast cancer between May 2017 and December 2018. B-mode US, SE, and color Doppler imaging were conducted in females with suspected mammography reports. The lesions in B-mode were classified according to the Breast Imaging Reporting and Data System (B-RADS). The results of SE imaging were graded based on five-grade SE score. SR and E/B ratio of each lesion were also analyzed in SE images. Color Doppler findings were categorized from 0 (no visible vessel) to 2 (> two vessels) based on the vascularity of the tumor. Pathology results were used as the gold standard to measure the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and diagnostic accuracy of each modality.

Results

One-hundred and ten breast lesions of 104 women aged 42.05±10.33 years were included in the study. Seventy-seven of the lesions were benign and 3 were malignant. Sensitivity and specificity of 97.0% and 77.9% for B-mode US, 93.9% and 87.0% for SE score, 81.8% and 66.2% for color Doppler US, 72.7% and 77.6% for E/B ratio (cutoff: 1.05), and 77.3% and 79.6% for SR (cutoff: 1.90) were obtained, respectively. Addition of SE score to B-mode US increased the sensitivity to 93.9%, specificity to 93.5%, and AUC from 0.95 to 0.97. Cumulative color Doppler US with B-mode US did not enhance the diagnostic accuracy of B-mode US.

Conclusion

SE was more effective than color Doppler US for distinguishing malignant from benign breast lesion. Among the three different SE features, five-grade SE score was superior to E/B ratio and SR.

Initialization of active contours for segmentation of breast cancer via fusion of ultrasound, Doppler, and elasticity images

Active contours (snakes) are an efficient method for segmentation of ultrasound (US) images of breast cancer. However, the method produces inaccurate results if the seeds are initialized improperly (far from the true boundaries and close to the false boundaries). Therefore, we propose a novel initialization method based on the fusion of a conventional US image with elasticity and Doppler images. The proposed fusion method (FM) has been tested against four state-of-the-art initialization methods on 90 ultrasound images from a database collected by the Thammasat University Hospital of Thailand. The ground truth was hand-drawn by three leading radiologists of the hospital. The reference methods are: center of divergence (CoD), force field segmentation (FFS), Poisson Inverse Gradient Vector Flow (PIG), and quasi-automated initialization (QAI). A variety of numerical tests proves the advantages of the FM. For the raw US images, the percentage of correctly initialized contours is: FM-94.2%, CoD-0%, FFS-0%, PIG-26.7%, QAI-42.2%. The percentage of correctly segmented tumors is FM-84.4%, CoD-0%, FFS-0%, PIG-16.67%, QAI-22.44%. For reduced field of view US images, the percentage of correctly initialized contours is: FM-94.2%, CoD-0%, FFS-0%, PIG-65.6%, QAI-67.8%. The correctly segmented tumors are FM-88.9%, CoD-0%, FFS-0%, PIG-48.9%, QAI-44.5%. The accuracy, in terms of the average Hausdorff distance, is respectively 2.29 pixels, 33.81, 34.71, 7.7, and 8.4, whereas in terms of the Jaccard index, it is 0.9, 0.18, 0.19, 0.63, and 0.48.