Although breast ultrasonography is the mainstay modality for differentiating between benign and malignant breast masses, it has intrinsic problems with false positives and substantial interobserver variability. Artificial intelligence (AI), particularly with deep learning models, is expected to improve workflow efficiency and serve as a second opinion. AI is highly useful for performing three main clinical tasks in breast ultrasonography: detection (localization/ segmentation), differential diagnosis (classification), and prognostication (prediction). This article provides a current overview of AI applications in breast ultrasonography, with a discussion of methodological considerations in the development of AI models and an up-to-date literature review of potential clinical applications.

This study was conducted to evaluate the diagnostic performance of machine learning in differentiating follicular adenoma from carcinoma using preoperative ultrasonography (US). In this retrospective study, preoperative US images of 348 nodules from 340 patients were collected from two tertiary referral hospitals. Two experienced radiologists independently reviewed each image and categorized the nodules according to the 2015 American Thyroid Association guideline. Categorization of a nodule as highly suspicious was considered a positive diagnosis for malignancy. The nodules were manually segmented, and 96 radiomic features were extracted from each region of interest. Ten significant features were selected and used as final input variables in our in-house developed classifier models based on an artificial neural network (ANN) and support vector machine (SVM). The diagnostic performance of radiologists and both classifier models was calculated and compared. In total, 252 nodules from 245 patients were confirmed as follicular adenoma and 96 nodules from 95 patients were diagnosed as follicular carcinoma. As measures of diagnostic performance, the average sensitivity, specificity, and accuracy of the two experienced radiologists in discriminating follicular adenoma from carcinoma on preoperative US images were 24.0%, 84.0%, and 64.8%, respectively. The sensitivity, specificity, and accuracy of the ANN and SVM-based models were 32.3%, 90.1%, and 74.1% and 41.7%, 79.4%, and 69.0%, respectively. The kappa value of the two radiologists was 0.076, corresponding to slight agreement. Machine learning-based classifier models may aid in discriminating follicular adenoma from carcinoma using preoperative US.

Recently, the amount of attention paid towards convolutional neural networks (CNN) in medical image analysis has rapidly increased since they can analyze and classify images faster and more accurately than human abilities. As a result, CNNs are becoming more popular and play a role as a supplementary assistant for healthcare professionals. Using the CNN on portable medical devices can enable a handy and accurate disease diagnosis. Unfortunately, however, the CNNs require high-performance computing resources as they involve a significant amount of computation to process big data. Thus, they are limited to being used on portable medical devices with limited computing resources. This paper discusses the network quantization techniques that reduce the size of CNN models and enable fast CNN inference with an energy-efficient CNN accelerator integrated into recent mobile processors. With extensive experiments, we show that the quantization technique reduces inference time by 97% on the mobile system integrating a CNN acceleration engine.

Although the role of axillary imaging has been redirected for predicting high nodal burden rather than predicting nodal metastases since ACOSOG Z1011 trial, it remains unclear whether and how axillary lymph node (ALN) characteristics predicts high nodal burden. Our study was aimed to evaluate the predictive value of imaging characteristics of ALNs at ultrasound and magnetic resonance imaging (MRI) for prediction of high nodal burden (≥3 metastatic ALNs) in clinically node-negative breast cancer patients. Clinicopathological and imaging characteristics were evaluated in patients with ultrasound (n = 312) and MRI (n = 256). Imaging characteristics include number of suspicious ALNs and cortical morphologic changes (grade 1, cortical thickness < 2 mm; grade 2, 2–5 mm; grade 3, ≥5 mm or fatty hilum loss). Odds ratios (ORs) were calculated using multivariate analysis. For ultrasound, higher (≥2) T stage (OR = 5.65, P = .005), higher number of suspicious ALNs (2 suspicious ALNs, OR = 6.52, P = .019; ≥ 3 suspicious ALNs, OR = 21.08, P = .005), and grade 3 of cortical morphologic changes (OR = 9.85, P = .023) independently associated with high nodal burden. For MRI, higher (≥2) T stage (OR = 5.17, P = .011) and higher number of suspicious ALNs (2 suspicious ALNs, OR = 69.00, P = .001; ≥ 3 suspicious ALNs, OR = 93.55, P < .001) were independently associated with high nodal burden. Among patients with 2 suspicious ALNs, those with grade 3 cortical morphologic change at ultrasound had a higher rate of high nodal burden than those with grade 2 (60.0% [3/5] vs. 25.0% [2/8]). A higher number of suspicious ALNs is an independent predictor for high nodal burden. Further stratification can be achieved by incorporating assessment of ultrasound-based cortical morphologic changes.