Medical ultrasonography最新文献

Aim: This study aims to explore the potential of machine learning as a non-invasive automated tool for skin tumor differentiation.

Material and methods: Data were included from 156 lesions, collected retrospectively from September 2021 to February 2024. Univariate and multivariate analyses of traditional clinical features were performed to establish a logistic regression model. Ultrasound-based radiomics features are extracted from grayscale images after delineating regions of interest (ROIs). Independent samples t-tests, Mann-Whitney U tests, and Least Absolute Shrinkage and Selection Operator (LASSO) regression were employed to select ultrasound-based radiomics features. Subsequently, five machine learning methods were used to construct radiomics models based on the selected features. Model performance was evaluated using receiver operating characteristic (ROC) curves and the Delong test.

Results: Age, poorly defined margins, and irregular shape were identified as independent risk factors for malignant skin tumors. The multilayer perception (MLP) model achieved the best performance, with area under the curve (AUC) values of 0.963 and 0.912, respectively. The results of DeLong's test revealed a statistically significant discrepancy in efficacy between the MLP and clinical models (Z=2.611, p=0.009).

Conclusion: Machine learning based skin tumor models may serve as a potential non-invasive method to improve diagnostic efficiency.

Breast lesions diagnosed during pregnancy and lactation are not very different from those detected in non-pregnant women. The diagnosis is often difficult due to the hormone-induced physiological changes of the breast that consequently alter the normal imaging appearance. Even if most of the breast lesions diagnosed during pregnancy and lactation are benign, breast cancer can also appear, and a correct diagnosis may be challenging. The aim of this pictorial essay is to review the imaging appearance of the breast during pregnancy and lactation, the ultrasound features of the most frequent pathologies encountered in this period and to discuss the limitations and the benefits of each imaging method with emphasis on their role in the diagnosis algorithm.

Stump appendicitis (SA) is a very rare complication after appendectomy. Although the clinical features are the same as appendicitis, the rate of missed or delayed diagnosis is high due to a history of previous appendectomy. This condition can potentially lead to serious complications such as perforation or sepsis, and even mortality. It should always be included in the differential diagnosis in patients presenting with acute abdomen with a history of appendectomy. As imaging plays an important role in the diagnosis of this condition, it is vital that radiologists are aware of this rare but serious condition. In this case report, we report two cases who underwent appendectomy and were subsequently diagnosed with stump appendicitis.

Aim: To evaluate the efficacy of ultrasound-guided ilioinguinal and iliohypogastric nerve block (IIHB) in children undergoing surgery for inguinal hernias.

Material and methods: PubMed, Embase, Cochrane Library, and Web of Science databases were searched to January 4, 2024. For continuous data, the effect sizes were presented as weighted mean differences (WMDs), and for categorical data, they were reported as relative ratios (RR), each accompanied by 95% confidence intervals (CIs).

Results: IIHB demonstrated a longer duration before the need for the first analgesic compared to transverse abdominis plane (TAP), caudal epidural block (CEB), and pre-incisional wound infiltration (PWI), but a shorter duration than quadratus lumborum block (QLB). The IIHB group had a higher probability of requiring rescue analgesics compared to other blocks or PWI (RR: 1.69, 95% CI: 1.25 to 2.28, p=0.001). Higher FLACC scores were noted at 12 hours for the IIHB group (WMD:0.50, 95% CI: 0.13 to 0.86, p=0.008). IIHB required more intraoperative fentanyl compared to controls (RR: 2.14, 95% CI:1.17 to 3.92, p=0.014).

Conclusion: While IIHB may have some benefits, it does not appear to be more effective overall in managing postoperative pain in pediatric inguinal hernia surgery patients compared to other blocks or PWI.

The present work describes the process of the sonographic examination, normal findings and measurements in the B-mode ultrasound evaluation. Reference is made to anatomical variants in shape, the pyramidal lobe, tubercle of Zuckerkandl, ectopic thyroid tissue, and their significance. Particular attention is paid to the reference values, the very miscellaneous reference values in different geographic regions of the world and influencing factors.

Aim: This study aimed to develop a deep learning (DL) model for automatic detection and diagnosis of gouty arthritis (GA) in the first metatarsophalangeal joint (MTPJ) using ultrasound (US) images.

Materials and methods: A retrospective study included individuals who underwent first MTPJ ultrasonography between February and July 2023. A five-fold cross-validation method (training set = 4:1) was employed. A deep residual convolutional neural network (CNN) was trained, and Gradient-weighted Class Activation Mapping (Grad-CAM) was used for visualization. Different ResNet18 models with varying residual blocks (2, 3, 4, 6) were compared to select the optimal model for image classification. Diagnostic decisions were based on a threshold proportion of abnormal images, determined from the training set.

Results: A total of 2401 US images from 260 patients (149 gout, 111 control) were analyzed. The model with 3 residual blocks performed best, achieving an AUC of 0.904 (95% CI: 0.887~0.927). Visualization results aligned with radiologist opinions in 2000 images. The diagnostic model attained an accuracy of 91.1% (95% CI: 90.4%~91.8%) on the testing set, with a diagnostic threshold of 0.328.

Conclusion:  The DL model demonstrated excellent performance in automatically detecting and diagnosing GA in the first MTPJ.

The European Federation of Societies for Ultrasound in Medicine and Biology (EFSUMB) has been publishing guidelines, position papers and also technical reviews. In addition, comments have been published for illustration of such papers including the hepatobiliary system, pancreas, lung and other organs. In the current paper, we aim to summarize the typical sonographic findings of the most commonly seen cutaneous neoplasms.