Ultrasound Imaging Technologies for Breast Cancer Detection and Management: A Review

Study on the Differentiation of Infiltrating Breast Cancer Molecular Subtypes Based on Ultrasound Radiomics

OBJECTIVE

To establish and validate a 2-dimensional ultrasound (US) radiomics model for the noninvasive preoperative differentiation of various molecular subtypes of infiltrating breast cancer (IBC).

METHODS

A retrospective analysis of 210 female patients diagnosed with IBC through surgical operation or needle biopsy pathology at our hospital between May 2019 and February 2024 was conducted. Relevant data were collected to establish predictive models for different molecular subtypes of IBC.

RESULTS

Based on 5936 US radiomics features, 39, 25 and 19 optimal features were identified for the differentiation of luminal versus nonluminal types, luminal A versus luminal B types and human epidermal growth factor receptor 2 (HER2) overexpression versus triple-negative (TN) IBC subgroups, respectively. The corresponding areas under the curve for the training and validation sets were 0.901 and 0.752 (luminal vs. nonluminal), 0.931 and 0.773 (luminal A vs. luminal B) and 0.962 and 0.842 (HER2 overexpression vs. TN), respectively, indicating robust discriminatory performance of these models for different pathological molecular subtypes of IBC.

CONCLUSION

A radiomics model based on US images is capable of effectively differentiating between various molecular subtypes of IBC prior to surgery, holding promise in assisting medical professionals in crafting tailored diagnostic and therapeutic strategies.

Radiogenomic analysis of clinical and ultrasonic characteristics in correlation to immune-related genes in breast cancer

Breast ultrasound plays a significant role in the non-invasive screening and diagnosis of breast cancer. The application of immunotherapy for breast cancer can significantly prolong the overall survival of advanced patients, which is an important research area of breast cancer treatment. The combination of ultrasound and immunotherapy helps patients diagnose and predict survival and develop a personalized treatment plan. This study analyzed the correlation between the clinical and ultrasonic characteristics of breast cancer and immune-related genes. First, the differential expression of immune-related genes was obtained using the GEO and IMMPORT database. Then, differentially expressed immune-related genes related to the overall survival of breast cancer were obtained using the GEPIA and Kaplan-Meier plotter platforms. Additionally, clinical, ultrasonic characteristics and pathological specimens of breast cancer patients' tumors were collected. Whole transcriptome sequencing and immunohistochemical staining were performed on the tumor specimens to obtain gene expression. CXCL2, MIA, NR3C2, PTX3, S100B, SAA1, SAA2, and CXCL9 genes were correlated with each other and with clinical and ultrasonic characteristics. The high expression of MIA was related to the positive expression of PR in breast cancer. The low expression of NR3C2 was correlated with the clinical characteristics of tumor size ≥ 20 mm, later stage, Her-2 positive, Ki-67 ≥ 20%. NR3C2 was negatively correlated with the value of PKI and AUC in contrast-enhanced ultrasound parameters, and positively correlated with the value of AT and TTP. The expression of the PTX3 gene was also negatively correlated with the value of PKI and Emax of shear wave elastography. SAA2 was related to the presence or absence of edge burrs characterized by ultrasound. The expression of the CXCL9 gene was associated with the age of onset and tumor stage. In this study, 8 differentially expressed immune-related genes related to the overall survival of breast cancer were screened, which had been proved to be associated with some characteristics of cancer in previous studies, and could be further studied in the subsequent immunotherapy of breast cancer. Some clinical and ultrasonic characteristics of breast cancer were significantly correlated with immune-related genes, such as NR3C2, SAA2, and CXCL9. Further analysis of these genes provides new ideas for the diagnosis and treatment of breast cancer.

5-Hydroxymethylcytosine signatures in circulating cell-free DNA as potential diagnostic markers for breast cancer

AIMS

Breast cancer is one of the most prevalent cancers among women, and early diagnosis is crucial in reducing the mortality rate. This study aims to identify novel, reliable, and specific biomarkers for breast cancer diagnosis using 5-Hydroxymethylcytosine (5hmC) signatures in circulating cell-free DNA (cfDNA).

MATERIALS AND METHODS

We utilized the sensitive 5hmC seal method to map 5hmC profiles in cfDNA samples from 203 breast cancer patients and 60 healthy individuals. Machine learning models were applied to identify 5hmC marker signatures with high sensitivity and specificity.

RESULTS

A global loss of 5hmC was observed in the blood samples from cancer patients compared to the control group. Several specific 5hmC marker signatures were identified, providing a basis for distinguishing between tumor and healthy individuals.

CONCLUSIONS

Our study offers a comprehensive understanding of genome-wide 5hmC in cfDNA from breast cancer patients, and identifies valuable epigenetic biomarkers for the minimally invasive diagnosis of breast cancer.

Perspectives on Devices for Integrated Phononic Circuits

The phonon wavelength, being much shorter than that of photons at the same frequency, offers phononic devices a unique niche in radio frequency (RF) applications. However, the current limitations of these devices, particularly their restricted functionality, hinder their broader integration and application. Currently, many functions are achieved using alternative signal forms like electric and photonic signals, requiring bulky converters to transform between phonon signals and other forms. The development of functional phononic devices paves the way for integrated phononic circuits, which aim to minimize the need for signal conversion while accomplishing all necessary functions. In this perspective, a brief overview of several types of functional phononic devices is provided that hold promise for integration, such as phononic modulators, amplifiers, lasers, nonreciprocal devices, and those inspired by topological physics. It is envisioned that through continued developments in materials, fabrication techniques, and designs, it's possible to realize integrated phononic circuits which will be applied in miniaturized communication devices with reduced size, weight, power consumption, and cost (SWaP-C), as well as in other fields including quantum information science, sensing, biomedical engineering, and beyond.

Relationship between breast tissue involution and breast cancer

Breast tissue involution is a process in which the epithelial tissue of the mammary gland gradually disappears with age. The relationship between breast tissue involvement and breast cancer (BC) has received increasing amounts of attention in recent years. Many scholars believe that breast tissue involution is a significant risk factor for BC. Breast imaging parameters, particularly mammographic density (MD), may indirectly reflect the degree of breast tissue involution, which may provide a solid basis for classifying priority screening groups for BC. This review explored the relationship between breast tissue involution and BC by providing an overview of breast tissue involution and elaborating on the association between MD and BC. Consistent with the results of other studies, women with complete breast tissue involution had a lower risk of BC, whereas women with a high MD had a relatively greater risk of BC.

Performance of a Logistic Regression Model Using Paired miRNAs to Stratify Abnormal Mammograms for Benign Breast Lesions

BACKGROUND

Mammography is effective in reducing breast cancer mortality, but it has false positive results that cause subsequent interventions such as biopsy or interval repeat mammography. Thus, there is a clinical unmet need for accurate molecular classifiers that can reduce unnecessary additional imaging and/or invasive diagnostic procedures for low-risk women.

METHOD

We performed miRNA profiling on a prospectively collected serum specimen obtained from each of the 432 subjects who received an abnormal mammogram or imaging result and then selected 265 subjects for further analysis. The miRNA classifier, named EarlyGuard, was generated based on a novel logistic regression model using "paired miRNAs" where the two miRNAs of interest exhibit the same properties.

RESULTS

The classifier developed using the training set of 174 subjects enrolled at seven investigative sites resulted in a negative predictive value (NPV) and a sensitivity of 96.4% and 91.2%, respectively. The classifier was validated using the test set consisting of 91 subjects enrolled at three investigative sites, two of which were not included in the training set. The resulting NPV and sensitivity were estimated similarly to be 96.9% and 95.8%, respectively.

CONCLUSIONS

Our miRNA classifier has produced promising results that could be used in conjunction with mammography or other imaging procedures to reduce unnecessary invasive diagnostic procedures for women who are unlikely to have a suspicious or worse result on a subsequent diagnostic biopsy. Additional studies will be conducted in larger cohorts to determine if the sensitivity of the classifier will be improved.

Three-dimensional complementary breast ultrasound (3D CBUS): Improving 3D spatial resolution uniformity with orthogonal images

BACKGROUND

With increasing evidence supporting three-dimensional (3D) automated breast (AB) ultrasound (US) for supplemental screening of breast cancer in increased-risk populations, including those with dense breasts and in limited-resource settings, there is an interest in developing more robust, cost-effective, and high-resolution 3DUS imaging techniques. Compared with specialized ABUS systems, our previously developed point-of-care 3D ABUS system addresses these needs and is compatible with any conventional US transducer, which offers a cost-effective solution and improved availability in clinical practice. While conventional US transducers have high in-plane resolution (axial and lateral), their out-of-plane resolution is constrained by the poor intrinsic elevational US resolution. Consequently, any oblique view plane in an acquired 3DUS image will contain high in-plane and poor out-of-plane resolution components, diminishing spatial resolution uniformity and overall diagnostic utility.

PURPOSE

To develop and validate a novel 3D complementary breast ultrasound (CBUS) approach to improve 3DUS spatial resolution uniformity using a conventional US transducer by acquiring and generating orthogonal 3DUS images.

METHODS

We previously developed a cost-effective, portable, dedicated 3D ABUS system consisting of a wearable base, a compression assembly, and a mechanically driven scanner for automated 3DUS image acquisition, compatible with any commercial linear US transducer. For this system, we have proposed 3D CBUS approach which involves acquiring and registering orthogonal 3DUS images (V A ${V}_A$ andV B ${V}_B$ ) with an aim of overcoming the poor resolution uniformity in the scanning direction in 3D US images. The voxel intensity values in the 3D CBUS image are computed with a spherical-weighted algorithm from the original orthogonal 3DUS images. Experimental validation was performed with 2DUS frame densities of 2, 4, 6 frames mm-1 using an agar-based phantom with a speed of sound of 1540 ms-1 and an embedded nylon bead. Lateral and axial full-width at half-maximum (FWHMLAT and FWHMAX) values were calculated from cross-sections taken at polar view planes ranging from 0° to 90° for 3DUS and 3D CBUS images of a bead phantom in focal zone and far field regions. Kendall's Tau-b correlation coefficients were calculated between FWHM measurements and cross-section angle for all frame density settings at a significance level ofα = 0.05 $\alpha = 0.05$ . Volumetric 3D segmentations were performed for 3DUS and 3D CBUS images of an inclusion phantom to confirm volumetric reconstruction accuracy. For statistical analysis, a repeated measures ANOVA with the Greenhouse-Geisser correction was performed at a significance level ofα = 0.05 $\alpha = 0.05$ .

RESULTS

Experimental validation of the orthogonal 3DUS images show complementary trends of increasing and decreasing FWHMLAT from in-plane to out-of-plane (0° and 90° and vice versa) views. This is exemplified with the scan taken at 4 frames mm-1 in the focal zone, where FWHMLAT ranges from 3.51 to 1.10 mm forV A ${V}_A$ and 1.02-3.02 mm forV B ${V}_B$ , spanning 0°-90°, respectively. When combined in the 3D CBUS image, the FWHMLAT exhibits greater uniformity across view angles by mitigating poor out-of-plane resolution using its complementary in-plane component, with corresponding FWHMLAT values of 1.27 and 1.46 mm. While visual enhancements were seen in the 3D CBUS image, no statistically significant differences were found in volumetric measurements of the spherical inclusions in the 3DUS and 3D CBUS images.

CONCLUSION

The out-of-plane resolution in the orthogonal 3DUS images is improved upon their combination into a single 3D CBUS image. These results demonstrate that the proposed 3D CBUS generation approach can improve 3D spatial resolution uniformity, while employing a commercial US transducer. The proposed 3D CBUS method shows potential utility for improving image resolution uniformity in 3D ABUS images, with the goal of improving point-of-care breast cancer supplemental screening and diagnostic applications, particularly in women with dense breasts and limited resource settings.

Clinical application value of ultrasound artificial intelligence technology in the diagnosis of breast nodules

ObjectiveTo investigate the application value of ultrasound artificial intelligence S-Detect technology in the differential diagnosis of benign and malignant breast nodules.MethodsSuspicious breast nodules were examined using S-Detect technology, conventional ultrasound (US), and contrast-enhanced ultrasound (CEUS). The differential diagnoses were compared with final pathological results to analyze the diagnostic efficacy of these three techniques in distinguishing benign from malignant breast nodules.ResultsThe accuracy of S-Detect in diagnosing benign and malignant breast nodules was 0.859, with a sensitivity of 0.915, specificity of 0.839, and an area under the ROC curve (AUC) of 0.877. The value of AUC was significantly higher than that of US (0.727, P < 0.01), but lower than US + CEUS (0.908, P < 0.05). According to the final pathological classification, S-Detect demonstrated higher accuracy in distinguishing benign from malignant lesions in complex cysts, hyperplastic nodules, and adenomas compared to US (P < 0.05), with no significant difference when compared to US + CEUS. In differentiating malignant breast tumors, there was no significant difference in accuracy between S-Detect and US.ConclusionUltrasound artificial intelligence S-Detect technology exhibits high diagnostic efficacy in the differential diagnosis of benign and malignant breast nodules.

Exploring the Evolution of Breast Cancer Imaging: A Review of Conventional and Emerging Modalities

Breast cancer (BC) is one of the leading causes of malignancy among women, and its prevalence is exponentially rising globally. Early and accurate imaging is critical for early detection, diagnosis, and treatment planning. This comprehensive review explores the current status of BC imaging, from the conventional methods such as mammography, ultrasound (US) and magnetic resonance imaging (MRI) to more advanced techniques including contrast-enhanced imaging, tomosynthesis, and molecular breast imaging (MBI). Conventional imaging remains the foundation for screening, as mammography is the most widely preferred modality. US and MRI are usually employed in dense breasts in highly suspicious cases that are not detected on a mammogram. However, the limitations posed by these traditional techniques can be curtailed using advanced modalities to enhance diagnostic accuracy. These emerging techniques provide faster and earlier detection of malignancy, particularly in high-risk patients, and substantially reduce the burden of missed cases. Emerging technologies, including photoacoustic imaging (PAI) and contrast-enhanced ultrasound (CEUS), show promising potential in visualizing microvascular structures and enhancing diagnostic accuracy. Additionally, artificial intelligence (AI) is revolutionizing BC imaging across all modalities by optimizing interpretation, enhancing sensitivity, and enabling personalized risk assessment. Although technological innovation continues to improve imaging quality and diagnostic precision, challenges such as cost, accessibility, overdiagnosis, and disparities in care remain a concern. Moving forward, a collaborative multimodal strategy that incorporates personalized imaging protocols and equitable access will be crucial for improving BC screening and management. The future of breast imaging lies not in replacing existing modalities but in developing a system where each technology complements the other, leading to earlier detection, more effective treatment, and enhanced outcomes.

The application of contrast-enhanced ultrasound and MicroFlow Imaging in the diagnosis of breast cancer

PURPOSE

The purpose of this study was to compare the value of contrast-enhanced ultrasound (CEUS) plus MicroFlow Imaging (CEUS-MFI), MicroFlow Imaging (MFI) alone, and color Doppler flow imaging (CDFI) in the differential diagnosis of benign and malignant breast lesions.

METHODS

A total of 116 patients with 116 breast lesions categorized as Breast Imaging Reporting and Data System (BI-RADS) category 4 were enrolled in this prospective study. CEUS-MFI, MFI, and CDFI were used to evaluate the microvascular morphology and distribution types of breast lesions. Pathological results were considered the gold standard.

RESULTS

Compared with conventional CDFI and MFI, the CEUS-MFI technique can reveal microvasculature and distribution types at a higher resolution in breast masses. The sensitivity, specificity, and accuracy of CEUS-MFI were 96.3%, 80.6%, and 91.4%, respectively. The sensitivity, specificity, and accuracy of MFI were 87.5%, 75.0%, and 83.6%, respectively. The sensitivity, specificity, and accuracy of CDFI were 58.8%, 72.2%, and 62.9%, respectively. The accuracy was significantly different between CEUS-MFI and MFI (P = 0.024), and the accuracy was significantly different between CEUS-MFI and CDFI (P = 0.000). US BI-RADS 4A masses were downgraded based on CEUS-MFI features without any malignancy missed, with the biopsy rate decreasing from 100% (29/29) to 31.0% (9/29).

CONCLUSION

CEUS-MFI provides improved diagnostic efficacy for breast lesions. The CEUS-MFI technique can be used as an effective supplement to conventional ultrasound in the diagnosis of breast tumors.

Predictive value of ultrasound assessment of axillary and brachial artery parameters for lymph node metastasis in breast cancer patients

OBJECTIVE

This study aimed to assess the predictive value of ultrasound assessment of axillary and brachial artery parameters for lymph node metastasis (LNM) in breast cancer (BRCA) patients.

METHODS

The clinical data of 172 cancer patients were reviewed, and the patients were stratified into two groups based on the presence or absence of axillary LNM. Ultrasound assessment was employed to evaluate axillary and brachial artery parameters using specific techniques, and arterial characteristics were analyzed.

RESULTS

Significant differences were observed in the ultrasound parameters of both axillary and brachial arteries between the non-LNM and LNM groups. Specifically, axillary and brachial artery diameters and resistive index exhibited significant differences and correlations with axillary LNM. Furthermore, molecular markers such as human epidermal growth factor receptor 2 (HER2) status, estrogen receptor (ER) status, and progesterone receptor (PR) status were found to be significantly correlated with LNM. Additionally, a nomogram was constructed, demonstrating the predictive value of the integrated arterial parameters. The combined model, incorporating axillary and brachial artery parameters, exhibited a higher predictive capability for axillary LNM compared to individual arterial parameters (AUC = 0.984).

CONCLUSION

Ultrasound assessment of axillary and brachial artery parameters, in conjunction with molecular markers, holds promise as a non-invasive tool for predicting LNM in BRCA patients. The observed correlations provide insights into the potential clinical relevance of arterial parameters in risk stratification and treatment planning. Further research in larger, prospective cohorts is warranted to validate the findings and enhance the precision of BRCA management.

Widefield ultra-high-density optical breast tomography system supplementing x-ray mammography

We report a wide-field compressive diffuse optical tomography (DOT) system - optical mammography co-imager (OMCI) - which aims to augment tens of thousands of existing x-ray mammography or tomosynthesis systems worldwide by adding functional assessment of breast tissue and improve cancer diagnosis. The OMCI system utilizes large field-of-view structured light illumination and single-pixel-camera based detection techniques to produce ultra-high spatial sampling density while ensuring that the inverse problem remains compact via the development of a unique target-adaptive pattern optimization technique to achieve compressive-sensing based measurements. The reconstructed images can be further enhanced by applying a compositional-prior-guided DOT reconstruction algorithm with tissue structural priors derived from a separately acquired x-ray mammography scans. In this report, we describe the design details and performance characterization of the imaging hardware as well as DOT image reconstruction pipelines. To validate this multi-modal breast DOT system, we include reconstruction results from both tissue-mimicking optical phantoms as well as clinical measurements from normal breasts obtained from a clinical study. Sample reconstructions from a breast containing a malignant tumor are also included, showing the potential of localizing and characterizing breast lesions using multi-modal measurements combining x-ray and DOT.

Early and noninvasive prediction of response to neoadjuvant therapy for breast cancer via longitudinal ultrasound and MR deep learning: A multicentre study

RATIONALE AND OBJECTIVES

The early prediction of response to neoadjuvant chemotherapy (NAC) will aid in the development of personalized treatments for patients with breast cancer. This study investigated the value of longitudinal multimodal deep learning (DL) based on breast MR and ultrasound (US) in predicting pathological complete response (pCR) after NAC.

MATERIALS AND METHODS

We retrospectively reviewed the pre-NAC and post-2nd-NAC MR and/or US images of 448 patients enrolled from three centers and extracted DL features from the largest section of the breast tumour using ResNet50. T test, Pearson correlation analysis and least absolute shrinkage and selection operator regression were used to select the most significant DL features for the pre-NAC and post-2nd-NAC MR and US DL models. The stacking model integrates different single-modality DL models and meaningful clinical data. The diagnostic performance of the models was evaluated.

RESULTS

In all the patients, the pCR rate was 36.65%. There was no significant difference in diagnostic performance between the different single-modality DL models (DeLong test, p > 0.05). The stacking model integrating the above four DL models with HER2 status yielded areas under the curves of 0.951-0.979, accuracies of 91.55%-92.65%, sensitivities of 90.63%-93.94%, and specificities of 89.47%-94.44% in the cohorts.

CONCLUSION

Longitudinal multimodal DL can be useful in predicting pCR. The stacking model can be used as a new tool for the early noninvasive prediction of the response to NAC, as evidenced by its excellent performance, and therefore aid the development of personalized treatment strategies for patients with breast cancer.

Enhancing Axillary Lymph Node Diagnosis in Breast Cancer with a Novel Photoacoustic Imaging-Based Radiomics Nomogram: A Comparative Study of Peritumoral Regions

RATIONALE AND OBJECTIVES

This study aims to assess the predictive ability of photoacoustic (PA) imaging-based radiomics combined with clinical characteristics for axillary lymph node (ALN) status in early-stage breast cancer patients and to compare performance in different peritumoral regions.

METHODS

This study involved 369 patients from Shenzhen People's Hospital, divided into a training set of 295 and a testing set of 74. PA imaging data were collected from all participants, and radiomics analysis was performed on intratumoral and various peritumoral regions. Features extracted from the training set were analyzed using LASSO regression to construct a model integrating radiomics features with clinical characteristics. Clinical factors were determined through multivariate logistic regression analysis. A radiomics nomogram was developed using logistic regression classifiers, combining radiomics features and clinical factors. The predictive efficacy of the model was evaluated using the areas under curves (AUC), and its clinical utility and accuracy were assessed through decision curve analysis and calibration curves, respectively.

RESULTS

The developed nomogram combines 5 mm peritumoral data with intratumoral and clinical features and shows excellent diagnostic performance, achieving an AUC of 0.972 in the training set and in the testing achieved 0.905. They both showed good calibrations. The model outperformed models based solely on clinical features or other radiomics methods, with the 5 mm surrounding tumor area proving most effective in identifying positive versus negative ALN in breast cancer patients.

CONCLUSION

The established nomogram is a prospective clinical prediction tool for non-invasive assessment of ALN status. It has the ability to enhance the accuracy of early-stage breast cancer treatment.

SUMMARY

This study highlights the effectiveness of combining photoacoustic radiomics with clinical parameters to predict axillary lymph node status in breast cancer, identifying a 5 mm peritumoral model as particularly potent. Future research should aim to enhance this model's robustness by expanding the sample size and advancing imaging technologies for broader clinical application.

Attention-based Fusion Network for Breast Cancer Segmentation and Classification Using Multi-modal Ultrasound Images

OBJECTIVE

Breast cancer is one of the most commonly occurring cancers in women. Thus, early detection and treatment of cancer lead to a better outcome for the patient. Ultrasound (US) imaging plays a crucial role in the early detection of breast cancer, providing a cost-effective, convenient, and safe diagnostic approach. To date, much research has been conducted to facilitate reliable and effective early diagnosis of breast cancer through US image analysis. Recently, with the introduction of machine learning technologies such as deep learning (DL), automated lesion segmentation and classification, the identification of malignant masses in US breasts has progressed, and computer-aided diagnosis (CAD) technology is being applied in clinics effectively. Herein, we propose a novel deep learning-based "segmentation + classification" model based on B- and SE-mode images.

METHODS

For the segmentation task, we propose a Multi-Modal Fusion U-Net (MMF-U-Net), which segments lesions by mixing B- and SE-mode information through fusion blocks. After segmenting, the lesion area from the B- and SE-mode images is cropped using a predicted segmentation mask. The encoder part of the pre-trained MMF-U-Net model is then used on the cropped B- and SE-mode breast US images to classify benign and malignant lesions.

RESULTS

The experimental results using the proposed method showed good segmentation and classification scores. The dice score, intersection over union (IoU), precision, and recall are 78.23%, 68.60%, 82.21%, and 80.58%, respectively, using the proposed MMF-U-Net on real-world clinical data. The classification accuracy is 98.46%.

CONCLUSION

Our results show that the proposed method will effectively segment the breast lesion area and can reliably classify the benign from malignant lesions.

A Low-Cost Optomechatronic Diffuse Optical Mammography System for 3D Image Reconstruction: Proof of Concept

Background: The development and initial testing of an optomechatronic system for the reconstruction of three-dimensional (3D) images to identify abnormalities in breast tissue and assist in the diagnosis of breast cancer is presented. Methods: This system combines 3D reconstruction technology with diffuse optical mammography (DOM) to offer a detecting tool that complements and assists medical diagnosis. DOM analyzes tissue properties with light, detecting density and composition variations. Integrating 3D reconstruction enables detailed visualization for precise tumor localization and sizing, offering more information than traditional methods. This technological combination enables more accurate, earlier diagnoses and helps plan effective treatments by understanding the patient's anatomy and tumor location. Results: Using Chinese ink, it was possible to identify simulated abnormalities of 10, 15, and 20 mm in diameter in breast tissue phantoms from cosmetic surgery. Conclusions: Data can be processed using algorithms to generate three-dimensional images, providing a non-invasive and safe approach for detecting anomalies. Currently, the system is in a pilot testing phase using breast tissue phantoms, enabling the evaluation of its accuracy and functionality before application in clinical studies.

A fiber-shaped ultrasonic transducer by designing a flexible epoxy/nano-zirconia composite as an acoustic matching layer

Acoustic matching layers play an important role in ultrasonic transducers. However, the acoustic matching layer with both intrinsic flexibility and high acoustic impedance remains an unmet need to achieve high-performing flexible ultrasonic transducers. Herein, we present an epoxy/nano-zirconia composite with excellent flexibility and acoustic performance by the chemical coupling method. (3-Aminopropyl)triethoxysilane was used to effectively disperse nano-zirconia particles in epoxy resin, and endow the resultant composite with flexibility. After carefully adjusting the additions of nano-zirconia particles and (3-aminopropyl)triethoxysilane, the modulus of the epoxy/nano-zirconia composite was 4.5 MPa, combined with an elongation at break over 90%. The acoustic impedance of the epoxy/nano-zirconia composite (∼4.5 MRayl) exceeded that of other typical polymer counterparts. The flexible acoustic matching layer based on an epoxy/nano-zirconia composite could significantly improve the sensitivity and bandwidth of ultrasonic transducers. A fiber-shaped ultrasonic transducer with high sensitivity and wide bandwidth was fabricated, displaying promising application potential in wearable medical electronics.

Multi-sequence MRI-based nomogram for prediction of human epidermal growth factor receptor 2 expression in breast cancer

Objective

To develop a nomogram based on multi-sequence MRI (msMRI) radiomics features and imaging characteristics for predicting human epidermal growth factor receptor 2 (HER2) expression in breast cancer (BC).

Methods

206 women diagnosed with invasive BC were retrospectively enrolled and randomly divided into a training set (n = 144) and a validation set (n = 62) at the ratio of 7 : 3. Tumor segmentation and feature extraction were performed on dynamic contrast-enhanced (DCE) MRI, T2-weighted imaging (T2WI), and apparent diffusion coefficient (ADC) map. Radiomics models were constructed using radiomics features and the radiomics score (Rad-score) was calculated. Rad-score and significant imaging characteristics were included in the multivariate analysis to establish the nomogram. The performance was mainly evaluated via the area under the receiver operating characteristic curve (AUC).

Results

Edema types on T2WI (OR = 4.480, P = 0.008), enhancement type (OR = 7.550, P = 0.002), and Rad-score (OR = 5.906, P < 0.001) were independent imaging predictors for HER2 expression. Radiomics model based on msMRI (including DCE-MRI, T2WI, and ADC map) had AUCs of 0.936 and 0.880 in the training and validation sets, respectively, exceeding the AUCs of one sequence or dual sequences. With the combination of edema and enhancement types, the nomogram achieved the highest performance in the training set (AUC: 0.940) and validation set (AUC: 0.893).

Conclusion

The developed multi-sequence MRI-based nomogram presents a promising tool for predicting HER2 expression, and is expected to improve the diagnosis and treatment of BC.

Identification of differentiating sonographic features between fibroadenomas and malignant tumors of the breast mimicking fibroadenomas: 10-year experience in 421 histologically verified cases

Ultrasound is a highly effective imaging tool for assessing abnormalities within the breast. However, especially the identification of malignant tumors of the breast mimicking fibroadenomas (MTMF) by means of breast ultrasound can be challenging. This study aimed to identify reliable imaging characteristics of MTMF.This retrospective study was approved by the local ethics review board. After screening 623 patients, 421 cases with histologically verified fibroadenomas and MTMF between 2011 and 2021 were included. Sonographic features were compared to histopathological results and an algorithm-based quantitative ranking of predictors contributing most to the correct classification of malignant tumors was conducted.A total of 363 benign, 18 intermediate, and 40 malignant lesions were analyzed. Algorithm-based quantitative ranking showed that the most predictive features indicating malignancy were a hyperechoic rim (gain ratio merit 0.135 ± 0.004), an irregular border (0.057 ± 0.002), perilesional stiffening (0.054 ± 0.002), pectoral contact (0.051 ± 0.003), an irregular shape (0.029 ± 0.001), and irregular vasculature (0.027 ± 0.002).Ultrasound findings for fibroadenomas vary, making identification of MTMF challenging. Features such as indistinct margins and increased perilesional echogenicity are predictors for malignancy and should be considered during sonographic evaluation of fibroadenomas and MTMF.

Classifications of triple-negative breast cancer: insights and current therapeutic approaches

Triple-negative breast cancer (TNBC) is an aggressive and challenging type of cancer, characterized by the absence of specific receptors targeted by current therapies, which limits effective targeted treatment options. TNBC has a high risk of recurrence and distant metastasis, resulting in lower survival rates. Additionally, TNBC exhibits significant heterogeneity at histopathological, proteomic, transcriptomic, and genomic levels, further complicating the development of effective treatments. While some TNBC subtypes may initially respond to chemotherapy, resistance frequently develops, increasing the risk of aggressive recurrence. Therefore, precisely classifying and characterizing the distinct features of TNBC subtypes is crucial for identifying the most suitable molecular-based therapies for individual patients. In this review, we provide a comprehensive overview of these subtypes, highlighting their unique profiles as defined by various classification systems. We also address the limitations of conventional therapeutic approaches and explore innovative biological strategies, all aimed at advancing the development of targeted and effective therapeutic strategies for TNBC.

Classifying, recognizing, and troubleshooting errors in magnetic resonance imaging (MRI)-guided breast biopsies

MRI-guided biopsies can generate challenging scenarios. Errors can occur for many reasons, both preprocedural and intraprocedural. Radiology errors have been studied for many years, originally classified by Renfrew in 1992 and revised in 2014 by Kim and Mansfield. While classification systems have focused on diagnostic radiology; many can also apply to procedural errors. This review aims to use the Kim-Mansfield modification of the Renfrew error classification system to provide a discussion and review of common MRI-guided biopsy errors to help radiologists manage them efficiently and appropriately.

Enhancing Early Breast Cancer Diagnosis With Contrast-Enhanced Ultrasound Radiomics: Insights From Intratumoral and Peritumoral Analysis

INTRODUCTION

To develop and validate contrast-enhanced ultrasound (CEUS) radiomics model for the accurate diagnosis of breast cancer by integrating intratumoral and peritumoral regions.

MATERIALS AND METHODS

This study enrolled 333 patients with breast lesions from Shenzhen people's hospital between March 2022 and March 2024. Radiomics features were extracted from both intratumoral and peritumoral (3 mm) regions on CEUS images. Significant features were identified using the Mann-Whitney U test, Spearman's correlation coefficient, and least absolute shrinkage and selection operator logistic regression. These features were used to construct radiomics models. The model's performance was evaluated using the area under the receiver operating characteristic curve, area under curve (AUC), decision curve analysis, and calibration curves.

RESULTS

The radiomics models demonstrated robust diagnostic performance in both the training and testing sets. The model that combined intratumoral and peritumoral features showed superior predictive accuracy, with AUCs of 0.933 (95% CI: 0.891, 0.974) and 0.949 (95% CI: 0.916, 0.983), respectively, compared to the intratumoral model alone. Calibration curves indicated excellent agreement between predicted and observed outcomes, with Hosmer-Lemeshow test P = .97 and P= .62 for the both the training and testing sets, respectively. decision curve analysis revealed that the combined model provided significant clinical benefits across a wide range of threshold probabilities, outperforming the intratumoral model in both sets.

CONCLUSION

The radiomics model integrating intratumoral and peritumoral features shows significant potential for the accurate diagnosis of breast cancer, enhancing clinical decision-making and guiding treatment strategies.

LightweightUNet: Multimodal Deep Learning with GAN-Augmented Imaging Data for Efficient Breast Cancer Detection

Breast cancer ranks as the second most prevalent cancer globally and is the most frequently diagnosed cancer among women; therefore, early, automated, and precise detection is essential. Most AI-based techniques for breast cancer detection are complex and have high computational costs. Hence, to overcome this challenge, we have presented the innovative LightweightUNet hybrid deep learning (DL) classifier for the accurate classification of breast cancer. The proposed model boasts a low computational cost due to its smaller number of layers in its architecture, and its adaptive nature stems from its use of depth-wise separable convolution. We have employed a multimodal approach to validate the model's performance, using 13,000 images from two distinct modalities: mammogram imaging (MGI) and ultrasound imaging (USI). We collected the multimodal imaging datasets from seven different sources, including the benchmark datasets DDSM, MIAS, INbreast, BrEaST, BUSI, Thammasat, and HMSS. Since the datasets are from various sources, we have resized them to the uniform size of 256 × 256 pixels and normalized them using the Box-Cox transformation technique. Since the USI dataset is smaller, we have applied the StyleGAN3 model to generate 10,000 synthetic ultrasound images. In this work, we have performed two separate experiments: the first on a real dataset without augmentation and the second on a real + GAN-augmented dataset using our proposed method. During the experiments, we used a 5-fold cross-validation method, and our proposed model obtained good results on the real dataset (87.16% precision, 86.87% recall, 86.84% F1-score, and 86.87% accuracy) without adding any extra data. Similarly, the second experiment provides better performance on the real + GAN-augmented dataset (96.36% precision, 96.35% recall, 96.35% F1-score, and 96.35% accuracy). This multimodal approach, which utilizes LightweightUNet, enhances the performance by 9.20% in precision, 9.48% in recall, 9.51% in F1-score, and a 9.48% increase in accuracy on the combined dataset. The LightweightUNet model we proposed works very well thanks to a creative network design, adding fake images to the data, and a multimodal training method. These results show that the model has a lot of potential for use in clinical settings.

Computer-assisted diagnosis for axillary lymph node metastasis of early breast cancer based on transformer with dual-modal adaptive mid-term fusion using ultrasound elastography

Accurate preoperative qualitative assessment of axillary lymph node metastasis (ALNM) in early breast cancer patients is crucial for precise clinical staging and selection of axillary treatment strategies. Although previous studies have introduced artificial intelligence (AI) to enhance the assessment performance of ALNM, they all focus on the prediction performances of their AI models and neglect the clinical assistance to the radiologists, which brings some issues to the clinical practice. To this end, we propose a human-AI collaboration strategy for ALNM diagnosis of early breast cancer, in which a novel deep learning framework, termed DAMF-former, is designed to assist radiologists in evaluating ALNM. Specifically, the DAMF-former focuses on the axillary region rather than the primary tumor area in previous studies. To mimic the radiologists' alternative integration of the UE images of the target axillary lymph nodes for comprehensive analysis, adaptive mid-term fusion is proposed to alternatively extract and adaptively fuse the high-level features from the dual-modal UE images (i.e., B-mode ultrasound and Shear Wave Elastography). To further improve the diagnostic outcome of the DAMF-former, an adaptive Youden index scheme is proposed to deal with the fully fused dual-modal UE image features at the end of the framework, which can balance the diagnostic performance in terms of sensitivity and specificity. The clinical experiment indicates that the designed DAMF-former can assist and improve the diagnostic abilities of less-experienced radiologists for ALNM. Especially, the junior radiologists can significantly improve the diagnostic outcome from 0.807 AUC [95% CI: 0.781, 0.830] to 0.883 AUC [95% CI: 0.861, 0.902] (P-value <0.0001). Moreover, there are great agreements among radiologists of different levels when assisted by the DAMF-former (Kappa value ranging from 0.805 to 0.895; P-value <0.0001), suggesting that less-experienced radiologists can potentially achieve a diagnostic level similar to that of experienced radiologists through human-AI collaboration. This study explores a potential solution to human-AI collaboration for ALNM diagnosis based on UE images.

Revolutionizing early breast cancer screening: Advanced multi-spectral transmission imaging classification with improved Otsu's method and K-means clustering

Breast cancer stands as a formidable danger to the health of women worldwide, underscoring the critical need for effective screening methods. Multispectral transmission imaging offers a promising avenue due to its non-invasive potential for early screening. Some researchers already suggested registration to solve the problem of jitters due to respiration and movement and frame accumulation technology to solve the low grayscale problem. However, the classification of blood vessels and breast tissue in breast images often suffers from low signal-to-noise ratio (SNR) and low contrast, hindering accurate classification. This paper proposes a novel improved Otsu's method with K-Means clustering to address this challenge. The proposed method aims to enhance the foundation for classification using multispectral transmission images. The study utilizes multispectral transmission images captured at four wavelengths, representing an innovative avenue for early, affordable breast cancer screening research. Initially, 300 images are registered and accumulated to prove the efficiency of the suggested methodology. Then, median filtering is applied to reduce noise in the images. Improved Otsu's segmentation method is then employed to separate blood vessels from breast tissue. After that, K-means clustering is utilized to accurately classify these components. The results of the proposed method demonstrate significant improvements in classification accuracy and grayscale contrast of multispectral breast images. By effectively distinguishing blood vessels and breast tissue, the proposed methodology addresses the inherent challenges of low contrast in multispectral transmission imaging. This advancement offers a clearer pathway for early breast cancer screening.

Artificial intelligence for breast cancer detection and its health technology assessment: A scoping review

BACKGROUND

Recent healthcare advancements highlight the potential of Artificial Intelligence (AI) - and especially, among its subfields, Machine Learning (ML) - in enhancing Breast Cancer (BC) clinical care, leading to improved patient outcomes and increased radiologists' efficiency. While medical imaging techniques have significantly contributed to BC detection and diagnosis, their synergy with AI algorithms has consistently demonstrated superior diagnostic accuracy, reduced False Positives (FPs), and enabled personalized treatment strategies. Despite the burgeoning enthusiasm for leveraging AI for early and effective BC clinical care, its widespread integration into clinical practice is yet to be realized, and the evaluation of AI-based health technologies in terms of health and economic outcomes remains an ongoing endeavor.

OBJECTIVES

This scoping review aims to investigate AI (and especially ML) applications that have been implemented and evaluated across diverse clinical tasks or decisions in breast imaging and to explore the current state of evidence concerning the assessment of AI-based technologies for BC clinical care within the context of Health Technology Assessment (HTA).

METHODS

We conducted a systematic literature search following the Preferred Reporting Items for Systematic review and Meta-Analysis Protocols (PRISMA-P) checklist in PubMed and Scopus to identify relevant studies on AI (and particularly ML) applications in BC detection and diagnosis. We limited our search to studies published from January 2015 to October 2023. The Minimum Information about CLinical Artificial Intelligence Modeling (MI-CLAIM) checklist was used to assess the quality of AI algorithms development, evaluation, and reporting quality in the reviewed articles. The HTA Core Model® was also used to analyze the comprehensiveness, robustness, and reliability of the reported results and evidence in AI-systems' evaluations to ensure rigorous assessment of AI systems' utility and cost-effectiveness in clinical practice.

RESULTS

Of the 1652 initially identified articles, 104 were deemed eligible for inclusion in the review. Most studies examined the clinical effectiveness of AI-based systems (78.84%, n= 82), with one study focusing on safety in clinical settings, and 13.46% (n=14) focusing on patients' benefits. Of the studies, 31.73% (n=33) were ethically approved to be carried out in clinical practice, whereas 25% (n=26) evaluated AI systems legally approved for clinical use. Notably, none of the studies addressed the organizational implications of AI systems in clinical practice. Of the 104 studies, only two of them focused on cost-effectiveness analysis, and were analyzed separately. The average percentage scores for the first 102 AI-based studies' quality assessment based on the MI-CLAIM checklist criteria were 84.12%, 83.92%, 83.98%, 74.51%, and 14.7% for study design, data and optimization, model performance, model examination, and reproducibility, respectively. Notably, 20.59% (n=21) of these studies relied on large-scale representative real-world breast screening datasets, with only 10.78% (n =11) studies demonstrating the robustness and generalizability of the evaluated AI systems.

CONCLUSION

In bridging the gap between cutting-edge developments and seamless integration of AI systems into clinical workflows, persistent challenges encompass data quality and availability, ethical and legal considerations, robustness and trustworthiness, scalability, and alignment with existing radiologists' workflow. These hurdles impede the synthesis of comprehensive, robust, and reliable evidence to substantiate these systems' clinical utility, relevance, and cost-effectiveness in real-world clinical workflows. Consequently, evaluating AI-based health technologies through established HTA methodologies becomes complicated. We also highlight potential significant influences on AI systems' effectiveness of various factors, such as operational dynamics, organizational structure, the application context of AI systems, and practices in breast screening or examination reading of AI support tools in radiology. Furthermore, we emphasize substantial reciprocal influences on decision-making processes between AI systems and radiologists. Thus, we advocate for an adapted assessment framework specifically designed to address these potential influences on AI systems' effectiveness, mainly addressing system-level transformative implications for AI systems rather than focusing solely on technical performance and task-level evaluations.

Electrochemical biosensors for early detection of breast cancer

Breast cancer continues to be a significant contributor to global cancer deaths, particularly among women. This highlights the critical role of early detection and treatment in boosting survival rates. While conventional diagnostic methods like mammograms, biopsies, ultrasounds, and MRIs are valuable tools, limitations exist in terms of cost, invasiveness, and the requirement for specialized equipment and trained personnel. Recent shifts towards biosensor technologies offer a promising alternative for monitoring biological processes and providing accurate health diagnostics in a cost-effective, non-invasive manner. These biosensors are particularly advantageous for early detection of primary tumors, metastases, and recurrent diseases, contributing to more effective breast cancer management. The integration of biosensor technology into medical devices has led to the development of low-cost, adaptable, and efficient diagnostic tools. In this framework, electrochemical screening platforms have garnered significant attention due to their selectivity, affordability, and ease of result interpretation. The current review discusses various breast cancer biomarkers and the potential of electrochemical biosensors to revolutionize early cancer detection, making provision for new diagnostic platforms and personalized healthcare solutions.

The Predictive Value of Blood-Derived Exosomal miRNAs as Biomarkers in Breast Cancer: A Systematic Review

Breast cancer (BC) remains a widespread disease worldwide, despite advances in its detection and treatment. microRNAs (miRNAs) play a significant role in cancer, and their presence within exosomes may confer several advantages in terms of tumor initiation, propagation, immune evasion, and drug resistance compared to freely circulating miRNAs in the blood. The objective of this study was to conduct a systematic review to analyze the role of exosomal miRNAs present in serum or plasma as biomarkers in BC. Bibliographic sources were collected from various databases with no starting date limit until March 2023. The search terms used were related to "breast cancer," "microRNAs," and "exosomes." Following the search, inclusion and exclusion criteria were applied, resulting in a total of 46 articles. Data were extracted from the selected studies and summarized to indicate the miRNAs, type of dysregulation, sample source, number of patients and controls, and clinical relevance of the miRNAs. We carried out an enrichment study of the microRNAs that appeared in at least 3 studies, those that were suitable for selection were miR-16, miR-21 and miR-155. Exosomal miRNAs isolated from blood samples of patients diagnosed with BC could be valuable in the clinical setting. They could provide information about early diagnosis, disease progression, recurrence, treatment response, and metastases. It is crucial to reach a consensus on the specific exosomal miRNAs to detect and the most appropriate type of sample for comprehensive utilization of miRNAs as biomarkers for BC.

CBAM-RIUnet: Breast Tumor Segmentation With Enhanced Breast Ultrasound and Test-Time Augmentation

This study addresses the challenge of precise breast tumor segmentation in ultrasound images, crucial for effective Computer-Aided Diagnosis (CAD) in breast cancer. We introduce CBAM-RIUnet, a deep learning (DL) model for automated breast tumor segmentation in breast ultrasound (BUS) images. The model, featuring an efficient convolutional block attention module residual inception Unet, outperforms existing models, particularly excelling in Dice and IoU scores. CBAM-RIUnet follows the Unet structure with a residual inception depth-wise separable convolution, and incorporates a convolutional block attention module (CBAM) to eliminate irrelevant features and focus on the region of interest. Evaluation under three scenarios, including enhanced breast ultrasound (EBUS) and test-time augmentation (TTA), demonstrates impressive results. CBAM-RIUnet achieves Dice and IoU scores of 89.38% and 88.71%, respectively, showcasing significant improvements compared to state-of-the-art DL techniques. In conclusion, CBAM-RIUnet presents a highly effective and simplified DL model for breast tumor segmentation in BUS imaging.

US-based Radiomics Analysis of Different Machine Learning Models for Differentiating Benign and Malignant BI-RADS 4A Breast Lesions

RATIONALE AND OBJECTIVES

To investigate and authenticate the effectiveness of various radiomics models in distinguishing between benign and malignant BI-RADS 4A lesions.

METHODS

A total of 936 patients with pathologically confirmed 4A lesions were included in the study (training cohort: n = 655; test cohort: n = 281). Radiomic features were derived from greyscale US images. Following dimensionality reduction and feature selection, radiomics models were developed using logistic regression (LR), support vector machine (SVM), random forest (RF), eXtreme gradient boosting (XGBoost) and multilayer perceptron (MLP) algorithms. Univariate and multivariable logistic regression analyses were employed to investigate clinical-radiological characteristics and determine variables for creating a clinical model. Five combined models integrating radiomic and clinical parameters were constructed by using each algorithm, and comparison with radiologists' performance was performed. SHapley Additive exPlanations (SHAP) approach was used to elucidate the radiomic model by ranking the significance of features based on their contribution to the evaluation.

RESULTS

A total of 1561 radiomic features were extracted. Thirty-six features were deemed significant by dimensionality reduction and selection. The radiomic models showed good performance with AUCs of 0.829-0.945 in training cohort; and 0.805-0.857 in test cohort. The combined model developed by using LR showed the best performance (AUC, training cohort: 0.909; test cohort: 0.905), which is superior to radiologists' performance. Decision curve analysis (DCA) of this combined model indicated better clinical efficacy than clinical and radiomic models.

CONCLUSIONS

The combined model integrating radiomic and clinical features demonstrated excellent performance in differentiating between benign and malignant 4A lesions. It may offer a non-invasive and efficient approach to aid in clinical decision-making.

Non-invasive early-stage cancer detection: current methods and future perspectives

This review paper explores the realm of non-invasive methods for early cancer detection. Early identification is crucial for effective therapeutic intervention, and non-invasive techniques have emerged as promising tools to enhance diagnostic accuracy and improve patient outcomes. The paper thoroughly examines the advantages, limitations, and prospects of various non-invasive approaches, including blood tests, non-blood-based tests, and diverse imaging modalities. It discusses the biomarkers found in blood for early-stage cancer detection, specifying the types of cancer associated with each biomarker. The non-blood-based tests focus on components in saliva, urine, and breath for cancer detection, alongside current studies and future perspectives on various cancers. Optical imaging methods covered in this review include fluorescence imaging in the near-infrared (NIR) region, bioluminescence imaging, and Raman spectroscopy for early-stage cancer detection. The review also highlights the pros and cons of ultrasound imaging in early-stage cancer detection. Additionally, the clinical implications of using AI for cancer detection, both present and future, are explored. This paper provides valuable insights for researchers and clinicians working in the field of non-invasive early-stage cancer detection.

Combined use of super-resolution ultrasound imaging and shear-wave elastography for differential diagnosis of breast masses

Objectives

Shear-wave elastography (SWE) provides valuable stiffness within breast masses, making it a useful supplement to conventional ultrasound imaging. Super-resolution ultrasound (SRUS) imaging enhances microvascular visualization, aiding in the differential diagnosis of breast masses. Current clinical ultrasound diagnosis of breast cancer primarily relies on gray-scale ultrasound. The combined diagnostic potential of tissue stiffness and microvascular characteristics, two critical tumor biomarkers, remains insufficiently explored. This study aims to evaluate the correlation between the elastic modulus, assessed using SWE, and microvascular characteristics captured through SRUS, in order to evaluate the effectiveness of combining these techniques in distinguishing between benign and malignant breast masses.

Materials and methods

In this single-center prospective study, 97 patients underwent SWE to obtain parameters including maximum elasticity (Emax), minimum elasticity (Emin), mean elasticity (Emean), standard deviation of elasticity (Esd), and elasticity ratio. SRUS was used to calculate the microvascular flow rate and microvessel density (MVD) within the breast masses. Spearman correlation analysis was used to explore correlations between Emax and MVD. Receiver operating characteristic curves and nomogram were employed to assess the diagnostic efficacy of combining SRUS with SWE, using pathological results as the gold standard.

Results

Emax, Emean, Esd, and MVD were significantly higher in malignant breast masses compared to benign ones (p < 0.001), while Emin was significantly lower in malignant masses (p < 0.05). In Spearman correlation analysis, Emax was significantly positively correlated with MVD (p < 0.01). The area under the curve for SRUS combined with SWE (0.924) was significantly higher than that for SWE (0.883) or SRUS (0.830) alone (p < 0.001), thus indicating improved diagnostic accuracy. The decision curve analysis of the nomogram indicated that SWE combined with SRUS model had a higher net benefit in predicting breast cancer.

Conclusions

The MVD of the breast mass shows a significant positive correlation with Emax. By integrating SRUS with SWE, this study proposes a novel diagnostic approach designed to improve specificity and accuracy in breast cancer detection, surpassing the limitations of current ultrasound-based methods. This approach shows promise for early breast cancer detection, with the potential to reduce the need for unnecessary biopsies and improve patient outcomes.

Machine learning radiomics based on intra and peri tumor PA/US images distinguish between luminal and non-luminal tumors in breast cancers

PURPOSE

This study aimed to evaluate a radiomics model using Photoacoustic/ultrasound (PA/US) imaging at intra and peri-tumoral area to differentiate Luminal and non-Luminal breast cancer (BC) and to determine the optimal peritumoral area for accurate classification.

MATERIALS AND METHODS

From February 2022 to April 2024, this study continuously collected 322 patients at Shenzhen People's Hospital, using standardized conditions for PA/US imaging of BC. Regions of interest were delineated using ITK-SNAP, with peritumoral regions of 2 mm, 4 mm, and 6 mm automatically expanded using code from the Pyradiomic package. Feature extraction was subsequently performed using Pyradiomics. The study employed Z-score normalization, Spearman correlation for feature correlation, and LASSO regression for feature selection, validated through 10-fold cross-validation. The radiomics model integrated intra and peri-tumoral area, evaluated by receiver operating characteristic curve(ROC), Calibration and Decision Curve Analysis(DCA).

RESULTS

We extracted and selected features from intratumoral and peritumoral PA/US images regions at 2 mm, 4 mm, and 6 mm. The comprehensive radiomics model, integrating these regions, demonstrated enhanced diagnostic performance, especially the 4 mm model which showed the highest area under the curve(AUC):0.898(0.78-1.00) and comparably high accuracy (0.900) and sensitivity (0.937). This model outperformed the standalone clinical model and combined clinical-radiomics model in distinguishing between Luminal and non-Luminal BC, as evidenced in the test set results.

CONCLUSION

This study developed a radiomics model integrating intratumoral and peritumoral at 4 mm region PA/US model, enhancing the differentiation of Luminal from non-Luminal BC. It demonstrated the diagnostic utility of peritumoral characteristics, reducing the need for invasive biopsies and aiding chemotherapy planning, while emphasizing the importance of optimizing tumor surrounding size for improved model accuracy.

On efficient expanding training datasets of breast tumor ultrasound segmentation model

Automatic segmentation of breast tumor ultrasound images can provide doctors with objective and efficient references for lesions and regions of interest. Both dataset optimization and model structure optimization are crucial for achieving optimal image segmentation performance, and it can be challenging to satisfy the clinical needs solely through model structure enhancements in the context of insufficient breast tumor ultrasound datasets for model training. While significant research has focused on enhancing the architecture of deep learning models to improve tumor segmentation performance, there is a relative paucity of work dedicated to dataset augmentation. Current data augmentation techniques, such as rotation and transformation, often yield insufficient improvements in model accuracy. The deep learning methods used for generating synthetic images, such as GANs is primarily applied to produce visually natural-looking images. Nevertheless, the accuracy of the labels for these generated images still requires manual verification, and the images exhibit a lack of diversity. Therefore, they are not suitable for the training datasets augmentation of image segmentation models. This study introduces a novel dataset augmentation approach that generates synthetic images by embedding tumor regions into normal images. We explore two synthetic methods: one using identical backgrounds and another with varying backgrounds. Through experimental validation, we demonstrate the efficiency of the synthetic datasets in enhancing the performance of image segmentation models. Notably, the synthetic method utilizing different backgrounds exhibits superior improvement compared to the identical background approach. Our findings contribute to medical image analysis, particularly in tumor segmentation, by providing a practical and effective dataset augmentation strategy that can significantly improve the accuracy and reliability of segmentation models.

Anatomy, Imaging, and Surgical Treatment of Thoracic Lymphadenopathies in Advanced Epithelial Ovarian Cancer

Ovarian cancer typically presents at advanced stages, with prognosis heavily influenced by the presence of residual disease following cytoreductive surgery. The role of resecting enlarged extra-abdominal lymph nodes during cytoreductive procedures remains contentious. These enlarged lymph nodes are commonly identified through high-resolution imaging techniques such as ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography-computed tomography (PET-CT). A comprehensive understanding of the relevant anatomy, imaging modalities, and surgical techniques for addressing lymphadenopathy in regions such as the supraclavicular fossa, axillae, mediastinum, and pericardiophrenic fat is crucial in determining the feasibility of surgical intervention. An appropriate evaluation of these factors is essential to optimize debulking, which is recognized as the most significant prognostic determinant in patients with ovarian cancer. This review underscores the importance of multidisciplinary approaches in managing advanced ovarian cancer with extra-abdominal lymph node involvement to enhance patient outcomes.

Development of ultrasound-based clinical, radiomics and deep learning fusion models for the diagnosis of benign and malignant soft tissue tumors

Objectives

The aim of this study is to develop an ultrasound-based fusion model of clinical, radiomics and deep learning (CRDL) for accurate diagnosis of benign and malignant soft tissue tumors (STTs).

Methods

In this retrospective study, ultrasound images and clinical data of patients with STTs from two hospitals were collected between January 2021 and December 2023. Radiomics features and deep learning features were extracted from the ultrasound images, and the optimal features were selected to construct fusion models using support vector machines. The predictive performance of the model was evaluated based on three aspects: discrimination, calibration and clinical usefulness. The DeLong test was used to compare whether there was a significant difference in AUC between the models. Finally, two radiologists who were unaware of the clinical information performed an independent diagnosis and a model-assisted diagnosis of the tumor to compare the performance of the two diagnoses.

Results

A training cohort of 516 patients from Hospital-1 and an external validation cohort of 78 patients from Hospital-2 were included in the study. The Pre-FM CRDL showed the best performance in predicting STTs, with area under the curve (AUC) of 0.911 (95%CI: 0.894-0.928) and 0.948 (95%CI: 0.906-0.990) for training cohort and external validation cohort, respectively. The DeLong test showed that the Pre-FM CRDL significantly outperformed the clinical models (P< 0.05). In addition, the Pre-FM CRDL can improve the diagnostic accuracy of radiologists.

Conclusion

This study demonstrates the high clinical applicability of the fusion model in the differential diagnosis of STTs.

Serum Direct Bilirubin as a Biomarker for Breast Cancer

Background

The role of serum total bilirubin (TB) in cancer has been a subject of controversy, as has the role of its subtypes, particularly serum direct bilirubin (DB). The aim of the present study was to investigate the association between serum DB levels and breast cancer, as well as to assess the diagnostic utility of serum DB in breast cancer.

Methods

A total of 5299 patients diagnosed with breast cancer for the first time at Taizhou Hospital of Zhejiang Province were included in the study, and 10028 healthy physical examination subjects were included as healthy controls. Logistics regression was used to investigate the relationship between serum DB and breast cancer, and the value of serum DB in the diagnosis of breast cancer was assessed by means of receiver operator characteristic (ROC) curve analysis.

Results

The serum DB concentration in the breast cancer group was significantly higher than the healthy controls (P < 0.001). Multivariate logistic regression results show that serum DB was an independent risk factor for breast cancer (odds ratio [OR]=4.504, 95% confidence interval [CI]: 4.200-4.831). Subjects with a serum DB concentration in the fourth quartile had a higher risk of breast cancer occurrence compared to those in the first quartile after adjusting for age (OR = 7.155, 95%CI: 6.474-7.907). The optimal cut-off value of serum DB for diagnosing breast cancer was determined to be 2.75 μmol/L, with an area under the curve (AUC) of 0.712 (95% CI: 0.703-0.722). This value exhibited good specificity (77.0%) and negative predictive value (77.8%).

Conclusion

Serum DB was identified as a risk factor for breast cancer, demonstrating good diagnostic potential for the disease. These findings suggest that serum DB could serve as a promising serum molecular marker for breast cancer.

Ultrasonic Imaging of Deeper Bone Defect Using Virtual Source Synthetic Aperture with Phased Shift Migration: A Phantom Study

Ultrasound imaging for bone is a difficult task in the field of medical ultrasound. Compared with other phase array techniques, the synthetic aperture (SA) has a better lateral resolution but a limited imaging depth due to the limited ultrasonic energy emitted by the single emitter in each transmission. In contrast, the virtual source (VS) synthetic aperture allows a simultaneous multi-element emission and could provide a higher ultrasonic incident energy in each transmission. Therefore, the VS might achieve a high imaging quality at a deeper depth for bone imaging than the traditional SA. In this study, we proposed the virtual source phase shift migration (VS-PSM) method to achieve ultrasonic imaging of the deeper bone defect featured in the multilayer structure. The proposed VS-PSM method was validated using standard soft tissue phantom and printed bone phantom with artificial defects. The image quality was evaluated in terms of contrast-to-noise ratios (CNR) and amplitudes of scatters and defects at different imaging depths. The results showed that the VS-PSM method could achieve a high imaging quality of the soft tissues with a significant improvement in the scattering amplitude and without a significant sacrifice of the lateral and axial resolution. The PSM was superior to the DAS in suppressing the background noise in the images. Compared with the traditional SA-PSM, the VS-PSM method could image deeper bone defects at different ultrasonic frequencies, with an average improvement of 50% in CNR. In conclusion, this study demonstrated that the proposed VS-PSM method could image deeper bone defects and might help the diagnosis of bone disease using ultrasonic imaging.

Diffusion-Weighted MRI-Based Virtual Elastography and Shear-Wave Elastography for the Assessment of Breast Lesions

BACKGROUND

Diffusion-weighted imaging (DWI)-based virtual MR elastography (DWI-vMRE) in the assessment of breast lesions is still in the research stage.

PURPOSE

To investigate the usefulness of elasticity values on DWI-vMRE in the evaluation of breast lesions, and the correlation with the values calculated from shear-wave elastography (SWE).

STUDY TYPE

Prospective.

POPULATION/SUBJECTS

153 patients (mean age ± standard deviation: 55 ± 12 years) with 153 pathological confirmed breast lesions (24 benign and 129 malignant lesions).

FIELD STRENGTH/SEQUENCE

1.5-T MRI, multi-b readout segmented echo planar imaging (b-values of 0, 200, 800, and 1000 sec/mm2).

ASSESSMENT

For DWI-vMRE assessment, lesions were manually segmented using apparent diffusion coefficient (ADC0-1000) map, then the region of interests were copied to the map of shifted-ADC (sADC200-800, sADC 200-1500). For SWE assessment, the shear modulus of the lesions was measured by US elastic modulus (μUSE). Intraclass/interclass kappa coefficients were calculated to measure the consistency.

STATISTICAL TESTS

Pearson's correlation was used to assess the relationship between sADC and μUSE. A receiver operating characteristic analysis with the area under the curve (AUC) was performed to compare the diagnostic accuracy between benign and malignant breast lesions of sADC and μUSE. A P value <0.05 was considered statistically significant.

RESULTS

There were significant differences between benign and malignant breast lesions of μUSE (24.17 ± 10.64 vs. 37.20 ± 12.61), sADC200-800 (1.38 ± 0.31 vs. 0.97 ± 0.18 × 10-3 mm2/sec), and sADC200-1500 (1.14 ± 0.30 vs. 0.78 ± 0.13 × 10-3 mm2/sec). In all breast lesions, a moderate but significant correlation was observed between μUSE and sADC200-800/sADC200-1500 (r = -0.49/-0.44). AUC values to differentiate benign from malignant lesions were as follows: μUSE, 0.78; sADC200-800, 0.89; sADC200-1500, 0.89.

DATA CONCLUSIONS

Both SWE and DWI-vMRE could be used for the differentiation of benign versus malignant breast lesions. Furthermore, DWI-vMRE with the use of sADC show relatively higher AUC values than SWE.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 2.

Multimodal ultrasound plus tumor markers demonstrates a high value in enhanced diagnosis of breast cancer

OBJECTIVE

To determine the diagnostic value of multimodal ultrasound combined with tumor markers in breast cancer (BC).

METHODS

A retrospective analysis was conducted on 198 patients with breast lesions treated at the Affiliated Wuxi People's Hospital of Nanjing Medical University between May 2020 and May 2023. All patients underwent multimodal ultrasound and tumor marker testing. Among the 198 patients, 88 patients were pathologically diagnosed with benign disease (benign group) and 110 patients were pathologically diagnosed with malignant disease (malignant group). With the pathological results as the gold standard, the benign and malignant results from different diagnostic methods were compared, focusing on specificity, sensitivity and accuracy.

RESULTS

The areas under the curves (AUCs) of carbohydrate antigen 153 (CA153), CA125, and carcinoembryonic antigen (CEA) for diagnosing BC were 0.810, 0.812, and 0.790, respectively. When these tumor markers were used in combination for diagnosing BC, the AUC increased to 0.928. The AUC of multimodal ultrasound alone in diagnosing BC was 0.845. Additionally, the AUC of multimodal ultrasound combined with tumor markers in diagnosing BC reached 0.971, with the corresponding specificity, sensitivity and accuracy of 90.00%, 94.43% and 91.92%, respectively.

CONCLUSION

In patients with early BC, the combination of multimodal ultrasound and tumor marker detection significantly improves the accuracy of diagnosing benign and malignant breast lesions compared to using either modality alone.

Fusion Imaging Objectively Demonstrates Improved Pancreas Visualization through Manipulation Techniques: A Prospective Interventional Study

Objective Abdominal ultrasonography (AUS) is used to screen for abdominal diseases owing to its low cost, safety, and accessibility. However, the detection rate of pancreatic disease using AUS is unsatisfactory. We evaluated the visualization area of the pancreas and the efficacy of manipulation techniques for AUS with fusion imaging. Methods Magnetic resonance imaging (MRI) volume data were obtained from 20 healthy volunteers in supine and right lateral positions. The MRI volume data were transferred to an ultrasound machine equipped with a fusion imaging software program. We evaluated the visualization area of the pancreas before and after postural changes using AUS with fusion imaging and assessed the liquid-filled stomach method using 500 ml of de-aerated water in 10 randomly selected volunteers. Patients This study included 20 healthy volunteers (19 men and 1 woman) with a mean age of 33.0 (21-37.5) years old. Results Fusion imaging revealed that the visualization area of the entire pancreas using AUS was 55%, which significantly improved to 75% with a postural change and 90% when using the liquid-filled stomach method (p=0.043). Gastrointestinal gas is the main obstacle for visualization of the pancreas. Conclusion Fusion imaging objectively demonstrated that manipulation techniques can improve pancreatic visualization.

Assessing Breast Cancer through Tumor Microenvironment Mapping of Collagen and Other Biomolecule Spectral Fingerprints─A Review

Breast cancer is a major challenge in the field of oncology, with around 2.3 million cases and around 670,000 deaths globally based on the GLOBOCAN 2022 data. Despite having advanced technologies, breast cancer remains the major type of cancer among women. This review highlights various collagen signatures and the role of different collagen types in breast tumor development, progression, and metastasis, along with the use of photoacoustic spectroscopy to offer insights into future cancer diagnostic applications without the need for surgery or other invasive techniques. Through mapping of the tumor microenvironment and spotlighting key components and their absorption wavelengths, we emphasize the need for extensive preclinical and clinical investigations.

Diagnostic Value of Artificial Intelligence in Minimal Breast Lesions Based on Real-Time Dynamic Ultrasound Imaging

Purpose

: To explore the diagnostic value of artificial intelligence (AI)-based on real-time dynamic ultrasound imaging system for minimal breast lesions.

Patients and Methods

Minimal breast lesions with a maximum diameter of ≤10mm were selected in this prospective study. The ultrasound equipment and AI system were activated Simultaneously. The ultrasound imaging video is connected to the server of AI system to achieve simultaneous output of AI and ultrasound scanning. Dynamic observation of breast lesions was conducted via ultrasound. And these lesions were evaluated and graded according to the Breast Imaging Reporting and Data System (BI-RADS) classification system through deep learning (DL) algorithms in AI. Surgical pathology was taken as the gold standard, and ROC curves were drawn to determine the area under the curve (AUC) and the optimal threshold values of BI-RADS. The diagnostic efficacy was compared with the use of a BI-RADS category >3 as the threshold for clinically intervening in diagnosing minimal breast cancers.

Results

291 minimal breast lesions were enrolled in the study, of which 228 were benign (78.35%) and 63 were malignant (21.65%). The AUC of the ROC curve was 0.833, with the best threshold value >4A. When using >BI-RADS 3 and >BI-RADS 4A as threshold values, the sensitivity and negative predictive value for minimal breast cancers were higher for >BI-RADS 3 than >BI-RADS 4A (100% vs 65.08%, 100% vs 89.91%, P values <0.001). However, the corresponding specificity, positive predictive value, and accuracy were lower than those for >BI-RADS 4A (42.11% vs 85.96%, 32.31% vs 56.16%, and 54.64% vs 81.44%, P values <0.001).

Conclusion

The AI-based real-time dynamic ultrasound imaging system shows good capacity in diagnosing minimal breast lesions, which is helpful for early diagnosis and treatment of breast cancer, and improves the prognosis of patients. However, it still results in some missed diagnoses and misdiagnoses of minimal breast cancers.

Employing Raman Spectroscopy and Machine Learning for the Identification of Breast Cancer

BACKGROUND

Breast cancer poses a significant health risk to women worldwide, with approximately 30% being diagnosed annually in the United States. The identification of cancerous mammary tissues from non-cancerous ones during surgery is crucial for the complete removal of tumors.

RESULTS

Our study innovatively utilized machine learning techniques (Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN)) alongside Raman spectroscopy to streamline and hasten the differentiation of normal and late-stage cancerous mammary tissues in mice. The classification accuracy rates achieved by these models were 94.47% for RF, 96.76% for SVM, and 97.58% for CNN, respectively. To our best knowledge, this study was the first effort in comparing the effectiveness of these three machine-learning techniques in classifying breast cancer tissues based on their Raman spectra. Moreover, we innovatively identified specific spectral peaks that contribute to the molecular characteristics of the murine cancerous and non-cancerous tissues.

CONCLUSIONS

Consequently, our integrated approach of machine learning and Raman spectroscopy presents a non-invasive, swift diagnostic tool for breast cancer, offering promising applications in intraoperative settings.

Breast Cancer Detection on Dual-View Sonography via Data-Centric Deep Learning

Goal: This study aims to enhance AI-assisted breast cancer diagnosis through dual-view sonography using a data-centric approach. Methods: We customize a DenseNet-based model on our exclusive dual-view breast ultrasound dataset to enhance the model's ability to differentiate between malignant and benign masses. Various assembly strategies are designed to integrate the dual views into the model input, contrasting with the use of single views alone, with a goal to maximize performance. Subsequently, we compare the model against the radiologist and quantify the improvement in key performance metrics. We further assess how the radiologist's diagnostic accuracy is enhanced with the assistance of the model. Results: Our experiments consistently found that optimal outcomes were achieved by using a channel-wise stacking approach incorporating both views, with one duplicated as the third channel. This configuration resulted in remarkable model performance with an area underthe receiver operating characteristic curve (AUC) of 0.9754, specificity of 0.96, and sensitivity of 0.9263, outperforming the radiologist by 50% in specificity. With the model's guidance, the radiologist's performance improved across key metrics: accuracy by 17%, precision by 26%, and specificity by 29%. Conclusions: Our customized model, withan optimal configuration for dual-view image input, surpassed both radiologists and existing model results in the literature. Integrating the model as a standalone tool or assistive aid for radiologists can greatly enhance specificity, reduce false positives, thereby minimizing unnecessary biopsies and alleviating radiologists' workload.

A Nomogram Based on Conventional Ultrasound Radiomics for Differentiating Between Radial Scar and Invasive Ductal Carcinoma of the Breast

ABSTRACT

We aimed to develop and validate a nomogram based on conventional ultrasound (CUS) radiomics model to differentiate radial scar (RS) from invasive ductal carcinoma (IDC) of the breast. In total, 208 patients with histopathologically diagnosed RS or IDC of the breast were enrolled. They were randomly divided in a 7:3 ratio into a training cohort (n = 145) and a validation cohort (n = 63). Overall, 1316 radiomics features were extracted from CUS images. Then a radiomics score was constructed by filtering unstable features and using the maximum relevance minimum redundancy algorithm and the least absolute shrinkage and selection operator logistic regression algorithm. Two models were developed using data from the training cohort: one using clinical and CUS characteristics (Clin + CUS model) and one using clinical information, CUS characteristics, and the radiomics score (radiomics model). The usefulness of nomogram was assessed based on their differentiating ability and clinical utility. Nine features from CUS images were used to build the radiomics score. The radiomics nomogram showed a favorable predictive value for differentiating RS from IDC, with areas under the curve of 0.953 and 0.922 for the training and validation cohorts, respectively. Decision curve analysis indicated that this model outperformed the Clin + CUS model and the radiomics score in terms of clinical usefulness. The results of this study may provide a novel method for noninvasively distinguish RS from IDC.

Mid-Infrared Photoacoustic Stimulation of Neurons through Vibrational Excitation in Polydimethylsiloxane

Photoacoustic (PA) emitters are emerging ultrasound sources offering high spatial resolution and ease of miniaturization. Thus far, PA emitters rely on electronic transitions of absorbers embedded in an expansion matrix such as polydimethylsiloxane (PDMS). Here, it is shown that mid-infrared vibrational excitation of C─H bonds in a transparent PDMS film can lead to efficient mid-infrared photoacoustic conversion (MIPA). MIPA shows 37.5 times more efficient than the commonly used PA emitters based on carbon nanotubes embedded in PDMS. Successful neural stimulation through MIPA both in a wide field with a size up to a 100 µm radius and in single-cell precision is achieved. Owing to the low heat conductivity of PDMS, less than a 0.5 °C temperature increase is found on the surface of a PDMS film during successful neural stimulation, suggesting a non-thermal mechanism. MIPA emitters allow repetitive wide-field neural stimulation, opening up opportunities for high-throughput screening of mechano-sensitive ion channels and regulators.

Applicability of Quantum Dots in Breast Cancer Diagnostic and Therapeutic Modalities-A State-of-the-Art Review

The increasing incidence of breast cancers (BCs) in the world population and their complexity and high metastatic ability are serious concerns for healthcare systems. Despite the significant progress in medicine made in recent decades, the efficient treatment of invasive cancers still remains challenging. Chemotherapy, a fundamental systemic treatment method, is burdened with severe adverse effects, with efficacy limited by resistance development and risk of disease recurrence. Also, current diagnostic methods have certain drawbacks, attracting attention to the idea of developing novel, more sensitive detection and therapeutic modalities. It seems the solution for these issues can be provided by nanotechnology. Particularly, quantum dots (QDs) have been extensively evaluated as potential targeted drug delivery vehicles and, simultaneously, sensing and bioimaging probes. These fluorescent nanoparticles offer unlimited possibilities of surface modifications, allowing for the attachment of biomolecules, such as antibodies or proteins, and drug molecules, among others. In this work, we discuss the potential applicability of QDs in breast cancer diagnostics and treatment in light of the current knowledge. We begin with introducing the molecular and histopathological features of BCs, standard therapeutic regimens, and current diagnostic methods. Further, the features of QDs, along with their uptake, biodistribution patterns, and cytotoxicity, are described. Based on the reports published in recent years, we present the progress in research on possible QD use in improving BC diagnostics and treatment efficacy as chemotherapeutic delivery vehicles and photosensitizing agents, along with the stages of their development. We also address limitations and open questions regarding this topic.

Artificial Intelligence (AI) and Nuclear Features from the Fine Needle Aspirated (FNA) Tissue Samples to Recognize Breast Cancer

Breast cancer is one of the paramount causes of new cancer cases worldwide annually. It is a malignant neoplasm that develops in the breast cells. The early screening of this disease is essential to prevent its metastasis. A mammogram X-ray image is the most common screening tool practiced currently when this disease is suspected; all the breast lesions identified are not malignant. The invasive fine needle aspiration (FNA) of a breast mass sample is the secondary screening tool to clinically examine cancerous lesions. The visual image analysis of the stained aspirated sample imposes a challenge for the cytologist to identify the malignant cells accurately. The formulation of an artificial intelligence-based objective technique on top of the introspective assessment is essential to avoid misdiagnosis. This paper addresses several artificial intelligence (AI)-based techniques to diagnose breast cancer from the nuclear features of FNA samples. The Wisconsin Breast Cancer dataset (WBCD) from the UCI machine learning repository is applied for this investigation. Significant statistical parameters are measured to evaluate the performance of the proposed techniques. The best detection accuracy of 98.10% is achieved with a two-layer feed-forward neural network (FFNN). Finally, the developed algorithm's performance is compared with some state-of-the-art works in the literature.

A bibliometric analysis of contrast-enhanced ultrasound over the past twenty years

Background

Contrast-enhanced ultrasound (CEUS) technology has been developed for decades, and its application is becoming increasingly more extensive. In this study, bibliometrics was used to characterize the development status of CEUS over the past 20 years and to identify future research hotspots.

Methods

We collected data from the Web of Science and analyzed the literature related to CEUS published from 2002 to 2022. We examined 6,382 publications and analyzed the publication year, country of origin, affiliated institutions, authors, journal, categories, keywords, and research frontiers within the relevant literature. Using bibliometric analysis, we aimed to determine the general research direction and current publication trends. This allowed us to identify the most prolific and outstanding authors, institutions, countries, and keywords in CEUS research. For data collection, analysis, and visualization, we employed VOSviewer (Leiden University, Leiden, the Netherlands), Excel (Microsoft Corp., Redmond, WA, USA), CiteSpace, and biblioshiny. These tools helped us gather, analyze, and visualize the data effectively.

Results

The analyzed publications indicated a consistent upward trend in the number of works published between 2002 and 2022. Notably, China and Sun Yat-sen University emerged as the most prolific countries and institutions, respectively. China published 391 articles with 5,817 citations and was the leader in terms of international cooperation. Moreover, pediatrics-related keywords have surged in frequency in recent years.

Conclusions

The amount of research on CEUS has increased rapidly and continues to grow, with China being at the forefront of this research field. The application of CEUS in some pediatric diseases is a recent research hotspot and perhaps warrants close attention.