Explore the vast range of titles available.

To develop an artificial intelligence (AI) model able to perform both segmentation of hand joint ultrasound images for osteophytes, bone, and synovium and perform osteophyte severity scoring following the EULAR-OMERACT grading system (EOGS) for hand osteoarthritis (OA). One hundred sixty patients with pain or reduced function of the hands were included. Ultrasound images of the metacarpophalangeal (MCP), proximal interphalangeal (PIP), distal interphalangeal (DIP), and first carpometacarpal (CMC1) joints were then manually segmented for bone, synovium and osteophytes and scored from 0 to 3 according to the EOGS for OA. Data was divided into a training, validation, and test set. The AI model was trained on the training data to perform bone, synovium, and osteophyte identification on the images. Based on the manually performed image segmentation, an AI was trained to classify the severity of osteophytes according to EOGS from 0 to 3. Percent Exact Agreement (PEA) and Percent Close Agreement (PCA) were assessed on individual joints and overall. PCA allows a difference of one EOGS grade between doctor assessment and AI. A total of 4615 ultrasound images were used for AI development and testing. The developed AI model scored on the test set for the MCP joints a PEA of 76% and PCA of 97%; for PIP, a PEA of 70% and PCA of 97%; for DIP, a PEA of 59% and PCA of 94%, and CMC a PEA of 50% and PCA of 82%. Combining all joints, we found a PEA between AI and doctor assessments of 68% and a PCA of 95%. The developed AI model can perform joint ultrasound image segmentation and severity scoring of osteophytes, according to the EOGS. As proof of concept, this first version of the AI model is successful, as the agreement performance is slightly higher than previously found agreements between experts when assessing osteophytes on hand OA ultrasound images. The segmentation of the image makes the AI explainable to the doctor, who can immediately see why the AI applies a given score. Future validation in hand OA cohorts is necessary though.

Purpose Automated three-dimensional (3D) breast ultrasound (US) systems are meant to overcome the shortcomings of hand-held ultrasound (HHUS). The aim of this study is to analyze and compare clinical performance of an automated 3D-US system by comparing it with HHUS, mammography and the clinical gold standard (defined as the combination of HHUS, mammography and—if indicated—histology). Methods Nine hundred and eighty three patients (=1,966 breasts) were enrolled in this monocentric, explorative and prospective cohort study. All examinations were analyzed blinded to the patients´ history and to the results of the routine imaging. The agreement of automated 3D-US with HHUS, mammography and the gold standard was assessed with kappa statistics. Sensitivity, specificity and positive and negative predictive value were calculated to assess the test performance. Results Blinded to the results of the gold standard the agreement between automated 3D-US and HHUS or mammography was fair, given by a Kappa coefficient of 0.31 (95 % CI [0.26;0.36], p  < 0.0001) and 0.25 (95 % CI [0.2;0.3], p  < 0.0001), respectively. Our results showed a high negative predictive value (NPV) of 98 %, a high specificity of 85 % and a sensitivity of 74 % based on the cases with US-guided biopsy. Including the cases where the lesion was seen in a second-look automated 3D-US the sensitivity improved to 84 % (NPV = 99 %, specificity = 85 %). Conclusion The results of this study let us suggest, that automated 3D-US might be a helpful new tool in breast imaging, especially in screening.

This book introduces an exciting new method for breast ultrasound diagnostics - automated whole-breast volume scanning (3D ABVS). Scanning technique is described in detail, with guidance on scanning positions and protocols. Imaging findings are then illustrated and discussed for normal breast variants, the different forms of breast cancer, fibroadenomas, cystic disease, benign and malignant male breast disorders, mastitis, breast implants, and postoperative breast scars. In order to aid appreciation of the benefits of 3D ABVS, comparisons with findings on X-ray mammography and conventional 2D hand-held US are presented. Readers will be especially impressed by the convincing demonstration of the advantages of the new method for diagnosis of breast cancer in women with dense glandular tissue. In enabling readers to learn how to perform and interpret 3D ABVS, this book will be of great value for all who are embarking on its use. It will also serve as a welcome reference for radiologists, oncologists, and ultrasonographers who already have some familiarity with the technique.

Background Left atrial (LA) sizing in patients with atrial fibrillation (AF) is crucial for follow-up and outcome. Recently, the automated quantification of LA using the novel three-beat averaging real-time three dimensional echocardiography (3BA-RT3DE) is introduced. The aim of this study was to assess the feasibility and accuracy of 3BA-RT3DE in patients with atrial fibrillation (AF). Methods Thirty-one patients with AF (62.8 ± 11.7 years, 67.7 % male) were prospectively recruited to have two dimensional echocardiography (2DE) and 3BA-RT3DE (SC 2000, ACUSON, USA). The maximal left atrial (LA) volume was measured by the conventional prolate-ellipse (PE) and area-length (AL) method using three-beat averaging 2D transthoracic echocardiography and automated software analysis (eSie volume analysis, Siemens Medical Solution, Mountain view, USA); measurements were compared with those obtained by computed tomography (CT). Results Maximal LA volume by 3BA-RT3DE was feasible for all patients. LA volume was 68.4 ± 28.2 by PE-2DE, 89.2 ± 33.1 by AL-2DE, 100.6 ± 31.8 by 3BA-RT3DE, and 131.2 ± 42.2 mL by CT. LA volume from PE-2DE (R 2  = 0.48, p  < 0.001, ICC = 0.64, p  < 0.001), AL-2DE (R 2  = 0.47, p  < 0.001, ICC = 0.67, p  < 0.001), and 3BA-RT3DE (R 2  = 0.50, p  = 0.001, ICC = 0.65, p  < 0.001) showed significant correlations with CT. However, 3BA-RT3DE demonstrated a small degree of underestimation (30.5 mL) of LA volume compared to 2DE-based measurements. Good-quality images from 3BA-RT3DE ( n  = 16) showed a significantly tighter correlation with images from CT scanning (R 2  = 0.60, p  = 0.0004, ICC = 0.76, p  < 0.001) compared to those of fair quality. Conclusion Automated quantification of LA volume using 3BA-RT3DE is feasible and accurate in patients with AF. An image of good quality is essential for maximizing the value of this method in clinical practice.