Application of Texture and Volume Model Analysis to Dedicated Axillary High-resolution 3D T2-weighted MR Imaging: A Novel Method for Diagnosing Lymph Node Metastasis in Patients with Clinically Node-negative Breast Cancer

Prospects of perfusion contrast-enhanced ultrasound (CE-US) in diagnosing axillary lymph node metastases in breast cancer: a comparison with lymphatic CE-US

Accurate diagnosis of lymph node (LN) metastasis is vital for prognosis and treatment in patients with breast cancer. Imaging 1modalities such as ultrasound (US), MRI, CT, and 18F-FDG PET/CT are used for preoperative assessment. While conventional US is commonly recommended due to its resolution and sensitivity, it has limitations such as operator subjectivity and difficulty detecting small metastases. This review shows the microanatomy of axillary LNs to enhance accurate diagnosis and the characteristics of contrast-enhanced US (CE-US), which utilizes intravascular microbubble contrast agents, making it ideal for vascular imaging. A significant focus of this review is on distinguishing between two types of CE-US techniques for axillary LN evaluation: perfusion CE-US and lymphatic CE-US. Perfusion CE-US is used to assess LN metastasis via transvenous contrast agent administration, while lymphatic CE-US is used to identify sentinel LNs and diagnose LN metastasis through percutaneous contrast agent administration. This review also highlights the need for future research to clarify the distinction between studies involving "apparently enlarged LNs" and "clinical node-negative" cases in perfusion CE-US research. Such research standardization is essential to ensure accurate diagnostic performance in various clinical studies. Future studies should aim to standardize CE-US methods for improved LN metastasis diagnosis, not only in breast cancer but also across various malignancies.

Clinical applications of artificial intelligence in liver imaging

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.