WATUNet: a deep neural network for segmentation of volumetric sweep imaging ultrasound.

Limited access to breast cancer diagnosis globally leads to delayed treatment. Ultrasound, an effective yet underutilized method, requires specialized training for sonographers, which hinders its widespread use. Volume sweep imaging (VSI) is an innovative approach that enables untrained operators to capture high-quality ultrasound images. Combined with deep learning, like convolutional neural networks, it can potentially transform breast cancer diagnosis, enhancing accuracy, saving time and costs, and improving patient outcomes. The widely used UNet architecture, known for medical image segmentation, has limitations, such as vanishing gradients and a lack of multi-scale feature extraction and selective region attention. In this study, we present a novel segmentation model known as Wavelet_Attention_UNet (WATUNet). In this model, we incorporate wavelet gates and attention gates between the encoder and decoder instead of a simple connection to overcome the limitations mentioned, thereby improving model performance. Two datasets are utilized for the analysis: the public 'Breast Ultrasound Images' dataset of 780 images and a private VSI dataset of 3818 images, captured at the University of Rochester by the authors. Both datasets contained segmented lesions categorized into three types: no mass, benign mass, and malignant mass. Our segmentation results show superior performance compared to other deep networks. The proposed algorithm attained a Dice coefficient of 0.94 and an F1 score of 0.94 on the VSI dataset and scored 0.93 and 0.94 on the public dataset, respectively. Moreover, our model significantly outperformed other models in McNemar's test with false discovery rate correction on a 381-image VSI set. The experimental findings demonstrate that the proposed WATUNet model achieves precise segmentation of breast lesions in both standard-of-care and VSI images, surpassing state-of-the-art models. Hence, the model holds considerable promise for assisting in lesion identification, an essential step in the clinical diagnosis of breast lesions.

Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet.

Segmentation of breast ultrasound images is a crucial and challenging task in computer-aided diagnosis systems. Accurately segmenting masses in benign and malignant cases and identifying regions with no mass is a primary objective in breast ultrasound image segmentation. Deep learning (DL) has emerged as a powerful tool in medical image segmentation, revolutionizing how medical professionals analyze and interpret complex imaging data. The UNet architecture is a highly regarded and widely used DL model in medical image segmentation. Its distinctive architectural design and exceptional performance have made it popular among researchers. With the increase in data and model complexity, optimization and fine-tuning models play a vital and more challenging role than before. This paper presents a comparative study evaluating the effect of image preprocessing and different optimization techniques and the importance of fine-tuning different UNet segmentation models for breast ultrasound images. Optimization and fine-tuning techniques have been applied to enhance the performance of UNet, Sharp UNet, and Attention UNet. Building upon this progress, we designed a novel approach by combining Sharp UNet and Attention UNet, known as Sharp Attention UNet. Our analysis yielded the following quantitative evaluation metrics for the Sharp Attention UNet: the Dice coefficient, specificity, sensitivity, and F1 score values obtained were 0.93, 0.99, 0.94, and 0.94, respectively. In addition, McNemar's statistical test was applied to assess significant differences between the approaches. Across a number of measures, our proposed model outperformed all other models, resulting in improved breast lesion segmentation.

A Systematic Review of Breast Implant-Associated Squamous Cell Carcinoma.

Breast augmentation is considered safe, but rare cases of breast implant-associated squamous cell carcinoma (BIA-SCC) have been reported. This study aimed to systematically review published cases of BIA-SCC, providing valuable clinical data. The review included 14 articles and 18 cases of BIA-SCC. An increasing trend in reported BIA-SCC cases was observed, with four cases in the 1990s and 14 cases since 2010. The mean age of affected patients was 56 years, and symptoms typically appeared around 21 years after breast augmentation. Silicone implants used in cosmetic procedures were most commonly associated with BIA-SCC. Implant removal was necessary in all cases, and some patients required a mastectomy. Treatment approaches varied, with the selective use of chemotherapy and/or radiotherapy. The estimated 6-month mortality rate was 11.1%, while the 12-month mortality rate was 23.8%. The estimated 6-month mortality rate should be cautiously interpreted due to the limited sample size. It appears lower than the rate reported by the American Society of Plastic Surgeons, without clear reasons for this discrepancy. This study highlights the importance of enhanced monitoring and information sharing to improve detection and management of BIA-SCC. Healthcare providers should maintain vigilance during the long-term follow-up of breast augmentation patients.

Enhancing Breast Ultrasound Segmentation through Fine-tuning and Optimization Techniques: Sharp Attention UNet.

Segmentation of breast ultrasound images is a crucial and challenging task in computer-aided diagnosis systems. Accurately segmenting masses in benign and malignant cases and identifying regions with no mass is a primary objective in breast ultrasound image segmentation. Deep learning (DL) has emerged as a powerful tool in medical image segmentation, revolutionizing how medical professionals analyze and interpret complex imaging data. The UNet architecture is a highly regarded and widely used DL model in medical image segmentation. Its distinctive architectural design and exceptional performance have made it a popular choice among researchers in the medical image segmentation field. With the increase in data and model complexity, optimization and fine-tuning models play a vital and more challenging role than before. This paper presents a comparative study evaluating the effect of image preprocessing and different optimization techniques and the importance of fine-tuning different UNet segmentation models for breast ultrasound images. Optimization and fine-tuning techniques have been applied to enhance the performance of UNet, Sharp UNet, and Attention UNet. Building upon this progress, we designed a novel approach by combining Sharp UNet and Attention UNet, known as Sharp Attention UNet. Our analysis yielded the following quantitative evaluation metrics for the Sharp Attention UNet: the dice coefficient, specificity, sensitivity, and F1 score obtained values of 0.9283, 0.9936, 0.9426, and 0.9412, respectively. In addition, McNemar's statistical test was applied to assess significant differences between the approaches. Across a number of measures, our proposed model outperforms the earlier designed models and points towards improved breast lesion segmentation algorithms.

Breast Ultrasound Volume Sweep Imaging: A New Horizon in Expanding Imaging Access for Breast Cancer Detection.

OBJECTIVE: The majority of people in the world lack basic access to breast diagnostic imaging resulting in delay to diagnosis of breast cancer. In this study, we tested a volume sweep imaging (VSI) ultrasound protocol for evaluation of palpable breast lumps that can be performed by operators after minimal training without prior ultrasound experience as a means to increase accessibility to breast ultrasound. METHODS: Medical students without prior ultrasound experience were trained for less than 2 hours on the VSI breast ultrasound protocol. Patients presenting with palpable breast lumps for standard of care ultrasound examination were scanned by a trained medical student with the VSI protocol using a Butterfly iQ handheld ultrasound probe. Video clips of the VSI scan imaging were later interpreted by an attending breast imager. Results of VSI scan interpretation were compared to the same-day standard of care ultrasound examination. RESULTS: Medical students scanned 170 palpable lumps with the VSI protocol. There was 97% sensitivity and 100% specificity for a breast mass on VSI corresponding to 97.6% agreement with standard of care (Cohen's κ = 0.95, P < .0001). There was a detection rate of 100% for all cancer presenting as a sonographic mass. High agreement for mass characteristics between VSI and standard of care was observed, including 87% agreement on Breast Imaging-Reporting and Data System assessments (Cohen's κ = 0.82, P < .0001). CONCLUSIONS: Breast ultrasound VSI for palpable lumps offers a promising means to increase access to diagnostic imaging in underserved areas. This approach could decrease delay to diagnosis for breast cancer, potentially improving morbidity and mortality.

No sonographer, no radiologist: Assessing accuracy of artificial intelligence on breast ultrasound volume sweep imaging scans.

Breast ultrasound provides a first-line evaluation for breast masses, but the majority of the world lacks access to any form of diagnostic imaging. In this pilot study, we assessed the combination of artificial intelligence (Samsung S-Detect for Breast) with volume sweep imaging (VSI) ultrasound scans to evaluate the possibility of inexpensive, fully automated breast ultrasound acquisition and preliminary interpretation without an experienced sonographer or radiologist. This study was conducted using examinations from a curated data set from a previously published clinical study of breast VSI. Examinations in this data set were obtained by medical students without prior ultrasound experience who performed VSI using a portable Butterfly iQ ultrasound probe. Standard of care ultrasound exams were performed concurrently by an experienced sonographer using a high-end ultrasound machine. Expert-selected VSI images and standard of care images were input into S-Detect which output mass features and classification as "possibly benign" and "possibly malignant." Subsequent comparison of the S-Detect VSI report was made between 1) the standard of care ultrasound report by an expert radiologist, 2) the standard of care ultrasound S-Detect report, 3) the VSI report by an expert radiologist, and 4) the pathological diagnosis. There were 115 masses analyzed by S-Detect from the curated data set. There was substantial agreement of the S-Detect interpretation of VSI among cancers, cysts, fibroadenomas, and lipomas to the expert standard of care ultrasound report (Cohen's κ = 0.73 (0.57-0.9 95% CI), p<0.0001), the standard of care ultrasound S-Detect interpretation (Cohen's κ = 0.79 (0.65-0.94 95% CI), p<0.0001), the expert VSI ultrasound report (Cohen's κ = 0.73 (0.57-0.9 95% CI), p<0.0001), and the pathological diagnosis (Cohen's κ = 0.80 (0.64-0.95 95% CI), p<0.0001). All pathologically proven cancers (n = 20) were designated as "possibly malignant" by S-Detect with a sensitivity of 100% and specificity of 86%. Integration of artificial intelligence and VSI could allow both acquisition and interpretation of ultrasound images without a sonographer and radiologist. This approach holds potential for increasing access to ultrasound imaging and therefore improving outcomes related to breast cancer in low- and middle- income countries.

Diagnostic Performance of an Artificial Intelligence System in Breast Ultrasound.

OBJECTIVES: We study the performance of an artificial intelligence (AI) program designed to assist radiologists in the diagnosis of breast cancer, relative to measures obtained from conventional readings by radiologists. METHODS: A total of 10 radiologists read a curated, anonymized group of 299 breast ultrasound images that contained at least one suspicious lesion and for which a final diagnosis was independently determined. Separately, the AI program was initialized by a lead radiologist and the computed results compared against those of the radiologists. RESULTS: The AI program's diagnoses of breast lesions had concordance with the 10 radiologists' readings across a number of BI-RADS descriptors. The sensitivity, specificity, and accuracy of the AI program's diagnosis of benign versus malignant was above 0.8, in agreement with the highest performing radiologists and commensurate with recent studies. CONCLUSION: The trained AI program can contribute to accuracy of breast cancer diagnoses with ultrasound.

Dedicated breast CT: state of the art-Part I. Historical evolution and technical aspects.

Dedicated breast CT is an emerging 3D isotropic imaging technology for breast, which overcomes the limitations of 2D compression mammography and limited angle tomosynthesis while providing some of the advantages of magnetic resonance imaging. This first installment in a 2-part review describes the evolution of dedicated breast CT beginning with a historical perspective and progressing to the present day. Moreover, it provides an overview of state-of-the-art technology. Particular emphasis is placed on technical limitations in scan protocol, radiation dose, breast coverage, patient comfort, and image artifact. Proposed methods of how to address these technical challenges are also discussed. KEY POINTS: • Advantages of breast CT include no tissue overlap, improved patient comfort, rapid acquisition, and concurrent assessment of microcalcifications and contrast enhancement. • Current clinical and prototype dedicated breast CT systems differ in acquisition modes, imaging techniques, and detector types. • There are still details to be decided regarding breast CT techniques, such as scan protocol, radiation dose, breast coverage, patient comfort, and image artifact.

Dedicated breast CT: state of the art-Part II. Clinical application and future outlook.

Dedicated breast CT is being increasingly used for breast imaging. This technique provides images with no compression, removal of tissue overlap, rapid acquisition, and available simultaneous assessment of microcalcifications and contrast enhancement. In this second installment in a 2-part review, the current status of clinical applications and ongoing efforts to develop new imaging systems are discussed, with particular emphasis on how to achieve optimized practice including lesion detection and characterization, response to therapy monitoring, density assessment, intervention, and implant evaluation. The potential for future screening with breast CT is also addressed. KEY POINTS: • Dedicated breast CT is an emerging modality with enormous potential in the future of breast imaging by addressing numerous clinical needs from diagnosis to treatment. • Breast CT shows either noninferiority or superiority with mammography and numerical comparability to MRI after contrast administration in diagnostic statistics, demonstrates excellent performance in lesion characterization, density assessment, and intervention, and exhibits promise in implant evaluation, while potential application to breast cancer screening is still controversial. • New imaging modalities such as phase-contrast breast CT, spectral breast CT, and hybrid imaging are in the progress of R & D.

Improving breast cancer diagnosis by incorporating raw ultrasound parameters into machine learning.

The improved diagnostic accuracy of ultrasound breast examinations remains an important goal. In this study, we propose a biophysical feature-based machine learning method for breast cancer detection to improve the performance beyond a benchmark deep learning algorithm and to furthermore provide a color overlay visual map of the probability of malignancy within a lesion. This overall framework is termed disease-specific imaging. Previously, 150 breast lesions were segmented and classified utilizing a modified fully convolutional network and a modified GoogLeNet, respectively. In this study multiparametric analysis was performed within the contoured lesions. Features were extracted from ultrasound radiofrequency, envelope, and log-compressed data based on biophysical and morphological models. The support vector machine with a Gaussian kernel constructed a nonlinear hyperplane, and we calculated the distance between the hyperplane and each feature's data point in multiparametric space. The distance can quantitatively assess a lesion and suggest the probability of malignancy that is color-coded and overlaid onto B-mode images. Training and evaluation were performed on in vivo patient data. The overall accuracy for the most common types and sizes of breast lesions in our study exceeded 98.0% for classification and 0.98 for an area under the receiver operating characteristic curve, which is more precise than the performance of radiologists and a deep learning system. Further, the correlation between the probability and Breast Imaging Reporting and Data System enables a quantitative guideline to predict breast cancer. Therefore, we anticipate that the proposed framework can help radiologists achieve more accurate and convenient breast cancer classification and detection.

Cone-Beam Breast Computed Tomography: Time for a New Paradigm in Breast Imaging.

It is time to reconsider how we image the breast. Although the breast is a 3D structure, we have traditionally used 2D mammography to perform screening and diagnostic imaging. Mammography has been continuously modified and improved, most recently with tomosynthesis and contrast mammography, but it is still using modifications of compression 2D mammography. It is time to consider 3D imaging for this 3D structure. Cone-beam breast computed tomography (CBBCT) is a revolutionary modality that will assist in overcoming the limitations of current imaging for dense breast tissue and overlapping structures. It also allows easy administration of contrast material for functional imaging. With a radiation dose on par with diagnostic mammography, rapid 10 s acquisition, no breast compression, and true high-resolution isotropic imaging, CBBCT has the potential to usher in a new era in breast imaging. These advantages could translate into lower morbidity and mortality from breast cancer.

Contrast-enhanced cone beam breast CT features of breast cancers: correlation with immunohistochemical receptors and molecular subtypes.

OBJECTIVES: To investigate the association of contrast-enhanced cone beam breast CT (CE-CBBCT) features, immunohistochemical (IHC) receptors, and molecular subtypes in breast cancer. METHODS: In this retrospective study, patients who underwent preoperative CE-CBBCT and received complete IHC results were analyzed. CE-CBBCT features were evaluated by two radiologists. Observer reproducibility and feature reliability were assessed. The association between CE-CBBCT features, IHC receptors, and molecular subtypes was analyzed using the chi-square, Mann-Whitney, and Kruskal-Wallis tests. Multivariate logistic regression was performed to assess the ability of combined imaging features to discriminate molecular subtypes. ROC curve was used to evaluate prediction performance. RESULTS: A total of 240 invasive cancers identified in 211 women were enrolled. Molecular subtypes of breast cancer were significantly associated with focality number of lesions, lesion type, tumor size, lesion density, internal enhancement pattern, degree of lesion enhancement (ΔHU), mass shape, spiculation, calcifications, calcification distribution, and increased peripheral vascularity of lesion (all p < 0.005), some of which also helped to differentiate IHC receptor status. A multivariate logistic regression model showed that tumor size (odds ratio, OR = 1.244), mass shape (OR = 0.311), spiculation (OR = 0.159), and internal enhancement pattern (OR = 0.227) were associated with differentiation between luminal and non-luminal subtypes (AUC = 0.809). Combined CE-CBBCT features, including lesion type (OR = 0.118), calcifications (OR = 0.181), and ΔHU (OR = 0.962), could be significant indicators of triple-negative versus HER-2-enriched subtypes (AUC = 0.913). CONCLUSIONS: CE-CBBCT features have the potential to help predict IHC receptor status and distinguish molecular subtypes of breast cancer, which could in turn help to develop individual treatment decisions and prognosis predictions. KEY POINTS: • A total of 11 CE-CBBCT features were associated with molecular subtypes, some of which also helped to differentiate IHC receptor status. • Tumor size, irregular mass shape, spiculation, and internal enhancement pattern could help identify luminal subtype. • Lesion type, calcification, and ΔHU could be significant indicators of HER-2- enriched versus triple-negative breast cancers.

Breast Imaging in Transgender Patients.

In the United States, at least 1.4 million adults identify as transgender. Despite growing national awareness, the transgender population experiences disparities in breast care access and breast health outcomes. One of the challenges of breast care delivery to transgender patients is the lack of evidence-based screening guidelines, which is likely partly due to the infrequency of transgender breast cancer cases. Several gender-affirming hormonal and surgical interventions are available that impact the imaging appearance of the breasts and the risk of breast cancer. Breast imaging radiologists should be familiar with the imaging appearance of expected findings and potential complications following gender-affirming interventions. It has been shown that the incidence of breast cancer in transgender women is higher than in natal males but still lower than in natal females, implying that estrogen supplementation confers an increased breast cancer risk. It is proposed that transgender women follow the screening guidelines for natal females if they have risk factors for breast cancer and received hormone therapy for > 5 years. However, further research is necessary, especially in transgender women who have no risk factors or received hormone therapy for ≤ 5 years. The breast cancer risk of presurgical transgender men is considered equivalent to that of natal females, but the risk markedly decreases following bilateral mastectomy. It is proposed that transgender men follow the screening guidelines for natal females if they have any preserved breast tissue, or that they undergo annual chest wall and axillary physical exam if they are status post bilateral mastectomy.

Newer Technologies in Breast Cancer Imaging: Dedicated Cone-Beam Breast Computed Tomography.

Dedicated breast computed tomography (CT) is the latest in a long history of breast imaging techniques dating back to the 1960s. Breast imaging is performed both for cancer screening as well as for diagnostic evaluation of symptomatic patients. Dedicated breast CT received US Food and Drug Administration approval for diagnostic use in 2015 and is slowly gaining recognition for its value in diagnostic 3-dimensional imaging of the breast, and also for injected contrast-enhanced imaging applications. Conventional mammography has known limitations in sensitivity and specificity, especially in dense breasts. Breast tomosynthesis was US Food and Drug Administration approved in 2011 and is now widely used. Dedicated breast CT is the next technological advance, combining real 3-dimensional imaging with the ease of contrast administration. The lack of painful compression and manipulation of the breasts also makes dedicated breast CT much more acceptable for the patients.

The potential role of dedicated 3D breast CT as a diagnostic tool: review and early clinical examples.

Mammography is the gold standard in routine screening for the detection of breast cancer in the general population. However, limitations in sensitivity, particularly in dense breasts, has motivated the development of alternative imaging techniques such as digital breast tomosynthesis, whole breast ultrasound, breast-specific gamma imaging, and more recently dedicated breast computed tomography or "breast CT". Virtually all diagnostic work-ups of asymptomatic nonpalpable findings arise from screening mammography. In most cases, diagnostic mammography and ultrasound are sufficient for diagnosis, with magnetic resonance imaging (MRI) playing an occasional role. Digital breast tomosynthesis, a limited-angle tomographic technique, is increasingly being used for screening. Dedicated breast CT has full three-dimensional (3D) capability with near-isotropic resolution, which could potentially improve diagnostic accuracy. In current dedicated breast CT clinical prototypes, 300-500 low-dose projections are acquired in a circular trajectory around the breast using a flat panel detector, followed by image reconstruction to provide the 3D breast volume. The average glandular dose to the breast from breast CT can range from as little as a two-view screening mammogram to approximately that of a diagnostic mammography examination. Breast CT displays 3D images of the internal structures of the breast; therefore, evaluation of suspicious features like microcalcifications, masses, and asymmetries can be made in multiple anatomical planes from a single scan. The potential role of breast CT for diagnostic imaging is illustrated here through clinical examples such as imaging soft tissue abnormalities and microcalcifications. The potential for breast CT to serve as an imaging tool for extent of disease evaluation and for monitoring neo-adjuvant chemotherapy response is also illustrated.

Dedicated Breast CT: Feasibility for Monitoring Neoadjuvant Chemotherapy Treatment.

OBJECTIVES: In this prospective pilot study, the feasibility of non-contrast dedicated breast computed tomography (bCT) to determine primary tumor volume and monitor its changes during neoadjuvant chemotherapy (NAC) treatment was investigated. MATERIALS AND METHODS: Eleven women who underwent NAC were imaged with a clinical prototype dedicated bCT system at three time points - pre-, mid-, and post-treatment. The study radiologist marked the boundary of the primary tumor from which the tumor volume was quantified. An automated algorithm was developed to quantify the primary tumor volume for comparison with radiologist's segmentation. The correlation between pre-treatment tumor volumes from bCT and MRI, and the correlation and concordance in tumor size between post-treatment bCT and pathology were determined. RESULTS: Tumor volumes from automated and radiologist's segmentations were correlated (Pearson's r = 0.935, P < 0.001) and were not different over all time points [P = 0.808, repeated measures analysis of variance (ANOVA)]. Pre-treatment tumor volumes from MRI and bCT were correlated (r = 0.905, P < 0.001). Tumor size from post-treatment bCT was correlated with pathology (r = 0.987, P = 0.002) for invasive ductal carcinoma larger than 5 mm and the maximum difference in tumor size was 0.57 cm. The presence of biopsy clip (3 mm) limited the ability to accurately measure tumors smaller than 5 mm. All study participants were pathologically assessed to be responders, with three subjects experiencing complete pathologic response for invasive cancer and the reminder experiencing partial response. Compared to pre-treatment tumor volume, there was a statistically significant (P = 0.0003, paired t-test) reduction in tumor volume at mid-treatment observed with bCT, with an average tumor volume reduction of 47%. CONCLUSIONS: This pilot study suggests that dedicated non-contrast bCT has the potential to serve as an expedient imaging tool for monitoring tumor volume changes during NAC. Larger studies are needed in future.

Investigating the use of texture features for analysis of breast lesions on contrast-enhanced cone beam CT.

Cone beam computed tomography (CBCT) has found use in mammography for imaging the entire breast with sufficient spatial resolution at a radiation dose within the range of that of conventional mammography. Recently, enhancement of lesion tissue through the use of contrast agents has been proposed for cone beam CT. This study investigates whether the use of such contrast agents improves the ability of texture features to differentiate lesion texture from healthy tissue on CBCT in an automated manner. For this purpose, 9 lesions were annotated by an experienced radiologist on both regular and contrast-enhanced CBCT images using two-dimensional (2D) square ROIs. These lesions were then segmented, and each pixel within the lesion ROI was assigned a label - lesion or non-lesion, based on the segmentation mask. On both sets of CBCT images, four three-dimensional (3D) Minkowski Functionals were used to characterize the local topology at each pixel. The resulting feature vectors were then used in a machine learning task involving support vector regression with a linear kernel (SVRlin) to classify each pixel as belonging to the lesion or non-lesion region of the ROI. Classification performance was assessed using the area under the receiver-operating characteristic (ROC) curve (AUC). Minkowski Functionals derived from contrast-enhanced CBCT images were found to exhibit significantly better performance at distinguishing between lesion and non-lesion areas within the ROI when compared to those extracted from CBCT images without contrast enhancement (p < 0.05). Thus, contrast enhancement in CBCT can improve the ability of texture features to distinguish lesions from surrounding healthy tissue.

Breast metastases to thyroid gland.

Metastases to the thyroid gland are uncommon. We present the sonographic features of metastatic breast adenocarcinoma to the thyroid in a 67-year-old woman. The lesion measured up to 0.9 cm in diameter, contained an echogenic focus with associated ring-down, and was predominantly cystic, thereby resembling a benign nodule. Because of the patient's history of breast adenocarcinoma, the nodule nevertheless underwent fine-needle aspiration. The unusual appearance of the thyroid nodule underscores the importance of considering patient history in deciding whether obtaining tissue diagnosis of thyroid nodules is warranted.