Immunohistochemical index prediction of breast tumor based on multi-dimension features in contrast-enhanced ultrasound

Intratumoral and peritumoral ultrasound-based radiomics for preoperative prediction of HER2-low breast cancer: a multicenter retrospective study

OBJECTIVES

Recent advances in human epidermal growth factor receptor 2 (HER2)-targeted therapies have opened up new therapeutic options for HER2-low cancers. This study aimed to establish an ultrasound-based radiomics model to identify three different HER2 states noninvasively.

METHODS

Between May 2018 and December 2023, a total of 1257 invasive breast cancer patients were enrolled from three hospitals. The HER2 status was divided into three classes: positive, low, and zero. Four peritumoral regions of interest (ROI) were auto-generated by dilating the manually segmented intratumoral ROI to thicknesses of 5 mm, 10 mm, 15 mm, and 20 mm. After image preprocessing, 4720 radiomics features were extracted from each image of every patient. The least absolute shrinkage and selection operator and LightBoost algorithm were utilized to construct single- and multi-region radiomics signatures (RS). A clinical-radiomics combined model was developed by integrating discriminative clinical-sonographic factors with the optimal RS. A data stitching strategy was used to build patient-level models. The Shapley additive explanations (SHAP) approach was used to explain the contribution of internal prediction.

RESULTS

The optimal RS was constructed by integrating 12 tumor features and 9 peritumoral-15mm features. Age, tumor size, and seven qualitative ultrasound features were retained to construct the clinical-radiomics combined model with the optimal RS. In the training, validation, and test cohorts, the patient-level combined model showed the best discrimination ability with the macro-AUCs of 0.988 (95% CI: 0.983-0.992), 0.915 (95% CI: 0.851-0.965), and 0.862 (95% CI: 0.820-0.899), respectively.

CONCLUSION

This study built a robust and interpretable clinical-radiomics model to evaluate three classes of HER2 status based on ultrasound images.

CRITICAL RELEVANCE STATEMENT

Ultrasound-based radiomics method can noninvasively identify three different states of HER2, which may guide treatment decisions and the implementation of personalized HER2-targeted treatment for invasive breast cancer patients.

KEY POINTS

Determination of HER2 status can affect treatment options for breast cancer. The ultrasound-based clinical-radiomics model can discriminate the three different HER2 statuses. Our developed model can assist in providing personalized recommendations for novel HER2-targeted therapies.

Diagnostic performance of ultrasound-based artificial intelligence for predicting key molecular markers in breast cancer: A systematic review and meta-analysis

BACKGROUND

Breast cancer (BC) diagnosis and treatment rely heavily on molecular markers such as HER2, Ki67, PR, and ER. Currently, these markers are identified by invasive methods.

OBJECTIVE

This meta-analysis investigates the diagnostic accuracy of ultrasound-based radiomics as a novel approach to predicting these markers.

METHODS

A comprehensive search of PubMed, EMBASE, and Web of Science databases was conducted to identify studies evaluating ultrasound-based radiomics in BC. Inclusion criteria encompassed research on HER2, Ki67, PR, and ER as key molecular markers. Quality assessment using Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and Radiomics Quality Score (RQS) was performed. The data extraction step was performed systematically.

RESULTS

Our meta-analysis quantifies the diagnostic accuracy of ultrasound-based radiomics with a sensitivity and specificity of 0.76 and 0.78 for predicting HER2, 0.80, and 0.76 for Ki67 biomarkers. Studies did not provide sufficient data for quantitative PR and ER prediction analysis. The overall quality of studies based on the RQS tool was moderate. The QUADAS-2 evaluation showed that the studies had an unclear risk of bias regarding the flow and timing domain.

CONCLUSION

Our analysis indicated that AI models have a promising accuracy for predicting key molecular biomarkers' status in BC patients. We performed the quantitative analysis for HER2 and Ki67 biomarkers which yielded a moderate to high accuracy. However, studies did not provide adequate data for meta-analysis of ER and PR prediction accuracy of developed models. The overall quality of the studies was acceptable. In future research, studies need to report the results thoroughly. Also, we suggest more prospective studies from different centers.

Deep learning-based immunohistochemical estimation of breast cancer via ultrasound image applications

Background

Breast cancer is the key global menace to women's health, which ranks first by mortality rate. The rate reduction and early diagnostics of breast cancer are the mainstream of medical research. Immunohistochemical examination is the most important link in the process of breast cancer treatment, and its results directly affect physicians' decision-making on follow-up medical treatment.

Purpose

This study aims to develop a computer-aided diagnosis (CAD) method based on deep learning to classify breast ultrasound (BUS) images according to immunohistochemical results.

Methods

A new depth learning framework guided by BUS image data analysis was proposed for the classification of breast cancer nodes in BUS images. The proposed CAD classification network mainly comprised three innovation points. First, a multilevel feature distillation network (MFD-Net) based on CNN, which could extract feature layers of different scales, was designed. Then, the image features extracted at different depths were fused to achieve multilevel feature distillation using depth separable convolution and reverse depth separable convolution to increase convolution depths. Finally, a new attention module containing two independent submodules, the channel attention module (CAM) and the spatial attention module (SAM), was introduced to improve the model classification ability in channel and space.

Results

A total of 500 axial BUS images were retrieved from 294 patients who underwent BUS examination, and these images were detected and cropped, resulting in breast cancer node BUS image datasets, which were classified according to immunohistochemical findings, and the datasets were randomly subdivided into a training set (70%) and a test set (30%) in the classification process, with the results of the four immune indices output simultaneously from training and testing, in the model comparison experiment. Taking ER immune indicators as an example, the proposed model achieved a precision of 0.8933, a recall of 0.7563, an F1 score of 0.8191, and an accuracy of 0.8386, significantly outperforming the other models. The results of the designed ablation experiment also showed that the proposed multistage characteristic distillation structure and attention module were key in improving the accuracy rate.

Conclusion

The extensive experiments verify the high efficiency of the proposed method. It is considered the first classification of breast cancer by immunohistochemical results in breast cancer image processing, and it provides an effective aid for postoperative breast cancer treatment, greatly reduces the difficulty of diagnosis for doctors, and improves work efficiency.

Joint Segmentation and Differential Diagnosis of Thyroid Nodule in Contrast-Enhanced Ultrasound Images

OBJECTIVE

Microvascular perfusion can be observed in real time with contrast-enhanced ultrasound (CEUS), which is a novel ultrasound technology for visualizing the dynamic patterns of parenchymal perfusion. Automatic lesion segmentation and differential diagnosis of malignant and benign based on CEUS are crucial but challenging tasks for computer-aided diagnosis of thyroid nodule.

METHODS

To tackle these two formidable challenges concurrently, we provide Trans-CEUS, a spatial-temporal transformer-based CEUS analysis model to finish the joint learning of these two challenging tasks. Specifically, the dynamic swin-transformer encoder and multi-level feature collaborative learning are combined into U-net for achieving accurate segmentation of lesions with ambiguous boundary from CEUS. In addition, variant transformer-based global spatial-temporal fusion is proposed to obtain long-distance enhancement perfusion of dynamic CEUS for promoting differential diagnosis.

RESULTS

Empirical results of clinical data showed that our Trans-CEUS model achieved not only a good lesion segmentation result with a high Dice similarity coefficient of 82.41%, but also superior diagnostic accuracy of 86.59%. Conclusion & significance: This research is novel since it is the first to incorporate the transformer into CEUS analysis, and it shows promising results on dynamic CEUS datasets for both segmentation and diagnosis tasks of the thyroid nodule.

Artificial intelligence to support person-centred care in breast imaging - A scoping review

AIM

To overview Artificial Intelligence (AI) developments and applications in breast imaging (BI) focused on providing person-centred care in diagnosis and treatment for breast pathologies.

METHODS

The scoping review was conducted in accordance with the Joanna Briggs Institute methodology. The search was conducted on MEDLINE, Embase, CINAHL, Web of science, IEEE explore and arxiv during July 2022 and included only studies published after 2016, in French and English. Combination of keywords and Medical Subject Headings terms (MeSH) related to breast imaging and AI were used. No keywords or MeSH terms related to patients, or the person-centred care (PCC) concept were included. Three independent reviewers screened all abstracts and titles, and all eligible full-text publications during a second stage.

RESULTS

3417 results were identified by the search and 106 studies were included for meeting all criteria. Six themes relating to the AI-enabled PCC in BI were identified: individualised risk prediction/growth and prediction/false negative reduction (44.3%), treatment assessment (32.1%), tumour type prediction (11.3%), unnecessary biopsies reduction (5.7%), patients' preferences (2.8%) and other issues (3.8%). The main BI modalities explored in the included studies were magnetic resonance imaging (MRI) (31.1%), mammography (27.4%) and ultrasound (23.6%). The studies were predominantly retrospective, and some variations (age range, data source, race, medical imaging) were present in the datasets used.

CONCLUSIONS

The AI tools for person-centred care are mainly designed for risk and cancer prediction and disease management to identify the most suitable treatment. However, further studies are needed for image acquisition optimisation for different patient groups, improvement and customisation of patient experience and for communicating to patients the options and pathways of disease management.