Artificial intelligence in breast ultrasound

Abstract

Artificial intelligence (AI) is gaining extensive attention for its excellent performance in image-recognition tasks and increasingly applied in breast ultrasound. AI can conduct a quantitative assessment by recognizing imaging information automatically and make more accurate and reproductive imaging diagnosis. Breast cancer is the most commonly diagnosed cancer in women, severely threatening women’s health, the early screening of which is closely related to the prognosis of patients. Therefore, utilization of AI in breast cancer screening and detection is of great significance, which can not only save time for radiologists, but also make up for experience and skill deficiency on some beginners. This article illustrates the basic technical knowledge regarding AI in breast ultrasound, including early machine learning algorithms and deep learning algorithms, and their application in the differential diagnosis of benign and malignant masses. At last, we talk about the future perspectives of AI in breast ultrasound.

Role of Ultrasound and Photoacoustic Imaging in Photodynamic Therapy for Cancer

“…Another major drawback is identification of lesion boundaries leading to interoperator variability. Research on various machine learning, artificial intelligence and 3D reconstruction algorithms that can enhance the detection of tumor boundaries and reduce operator variability is currently being pursued which will further the utility of USI in PDT treatment monitoring .…”

Performance of Ultrasound Techniques and the Potential of Artificial Intelligence in the Evaluation of Hepatocellular Carcinoma and Non-Alcoholic Fatty Liver Disease

“…In broad terms, we highlight two AI techniques with applications within the imaging field—machine learning (ML)-based algorithms with its more advanced class of DL. Convolutional neural networks (CNNs) are the most popular DL architecture used in medical imaging, although they require large amounts of training data [ 123 , 124 ]. AI-based algorithms that guide the examiner towards the best image acquiring position have been developed, so that, in the future, the examiner will not necessarily need to have previous US technique knowledge.…”

Cystic and alveolar echinococcosis of the hepatobiliary tract – the role of new imaging techniques for improved diagnosis

“…Inflammatory reactions in the liver can be displayed by perihepatic lymphadenopathy [28][29][30][31][32][33][34][35][36][37], focal changes to vascularity and perfusion in the surrounding liver parenchyma [38][39][40], or by demonstrating increased metabolic turnover using PET technology. The role of artificial intelligence in the imaging of CE is promising but has not been evaluated so far [41,42].…”