To investigate the relationship between echocardiography segmentation accuracy and clinical examination indicators by comparing segmentation evaluation metrics (S-EM) with cardiac clinical examination indicators evaluation metrics (CCEI-EM). Initially, four UNet-based segmentation models for 2D echocardiography were trained using the CAMUS dataset. Subsequently, 13 clinical examination indicators relevant to cardiac assessment were automatically extracted. Pixel accuracy (PA), dice similarity coefficient (DSC), intersection over union (IOU), and Hausdorff distance (HD) were utilized as S-EM to assess the segmentation outcomes. The deformation ratio between these clinical examination indicators and the ground truth was defined as CCEI-EM. Finally, statistical analyses were conducted to examine the correlations between S-EM and CCEI-EM. Statistically significant differences were detected between S-EM and cardiac structural indicator evaluation metrics (p < 0.05). However, weak correlations were identified for the left ventricular transverse diameter and the left ventricular long diameter with PA, DSC, and IOU (p < 0.05; r < 0.2). No statistically significant differences were found between cardiac functional evaluation metrics with PA, DSC, and IOU (p > 0.05); moreover, end-systolic volume demonstrated weak correlations with PA and DSC (p < 0.05; r < 0.2). S-EM does not directly reflect the quality of cardiac clinical examination indicators derived from segmentation results. It is crucial to evaluate segmentation performance through downstream task-related clinical indicators.

This study presents a case of a giant aneurysm of the ascending aorta that evolved to rupture in a pediatric patient. The diagnosis was made possible through echocardiogram, which was subsequently confirmed by an aortic computed tomography (CT) angiography. The patient was referred for surgical intervention and demonstrated favorable outcomes. The authors describe the differential aspects of the clinical manifestations and immune response in Kawasaki disease. While the coronary arteries represent the main site of aneurysm formation in KD, they are not the sole location, and it is important to keep in mind that aortic aneurysms may occur. Despite the rarity of aortic aneurysms in KD, a take-home message to be learned from this case study is to consider KD in the context of acute onset ascending aortic aneurysm.

Danon disease is an X-chromosome dominant disorder caused by variants in lysosomal-associated membrane protein-2 (LAMP-2). Patients often present with cardiac lesions as their initial symptom, including hypertrophic cardiomyopathy, arrhythmia, and heart failure. We found a case of a 13-year-old male patient with multimodal imaging suggestive of left ventricular hypertrophy, decreased left ventricular myocardial perfusion, electrocardiographic abnormalities, and abnormal serologic parameters. Genetic testing revealed a variant located in the LAMP2 gene, leading to the diagnosis of Danon disease. Danon disease is a multisystem disorder with a predominance of cardiac lesions, and it should be considered when imaging suggests myocardial hypertrophy or dilatation.

Pericardial effusion (PCE) secondary to penetrating traumas is a critical condition requiring prompt diagnosis and intervention. This meta-analysis evaluated the diagnostic performance of point-of-care ultrasound (POCUS) in detecting PCE and its impact on patient outcomes. Data from 10 studies involving 3785 patients demonstrated that POCUS has a pooled sensitivity of 87% and specificity of 99%, with an area under the receiver operating characteristic curve of 0.96. Survival rates among true positive cases were 93%, with a mean time to intervention of 7-13 min. Overall, POCUS has a high specificity and sensitivity for detecting PCE among patients with penetrating injuries. However, a negative POCUS exam should be accompanied by diagnostic modalities, such as computed tomography or formal echocardiography to confirm the absence of PCE.

Portal hypertension (PH) is a major complication of chronic liver disease (CLD) and often leads to life-threatening gastrointestinal bleeding. Splenic stiffness measurement (SSM) has recently emerged as a non-invasive marker for assessment of PH. However, baseline values of splenic stiffness in a healthy population remain relatively unexplored. To determine the splenic stiffness in a cohort of the healthy population from North India and to establish reference values for future clinical applications. This descriptive study was conducted in the Department of Radio-diagnosis in a tertiary care institute in North India. Patients with known chronic liver disease, splenomegaly, focal lesions in the liver or spleen, congestive heart failure, chronic kidney disease, or portal vein thrombosis, pregnant women, and pediatric patients (< 18 years of age) were excluded. Splenic stiffness was assessed using 2-D shear wave elastography (SWE). A total of 10 elastography readings were taken per patient, and the mean value was recorded. The study population comprised 52 males and 48 females with a M:F ratio of 1.08. In our study, mean splenic stiffness was 13.44 kPa (±1.96 SD) with a median of 13.5 kPa. The majority of participants had SSM between 10 and 16 kPa (91%). A significant difference was observed in mean SSM between men and women in our study. This study provides splenic stiffness values in a cohort of healthy population in North India and can serve as a reference for non-invasive assessment of PH. Future studies should be performed focusing on multicenter trials with inter-observer variability assessment and comparison across different ultrasound equipment and ethnicities.

To explore the contrast-enhanced ultrasound (CEUS) characteristics of hepatic perivascular epithelioid cell tumors (PEComas). A retrospective analysis was conducted on eight patients with pathologically confirmed hepatic PEComas at Sun Yat-sen Memorial Hospital, Sun Yat-sen University, between November 2019 and October 2024. The CEUS characteristics of hepatic PEComas were summarized, and the correlation between pathological components and ultrasonographic manifestations was analyzed. A literature review was performed using PubMed to identify studies reporting CEUS features of hepatic PEComas. The study cohort comprised six females and two males, with a mean age of 48.12 ± 16.47 years. On conventional ultrasound (CUS), lesions were either hyperechoic (4/8) or hypoechoic (4/8), with hyperechoic lesions exhibiting a higher mean fat content (27.5% vs. 15%). Lesions with peripheral annular flow demonstrated a slightly higher mean vascular density compared to those without (14.2% vs. 10%). All lesions (8/8) exhibited marked hyper-enhancement in the hepatic arterial phase (HAP), with a mean time-to-enhancement of 12.25 ± 4.06 s and a mean time-to-peak of 20.88 ± 3.91 s. In the portal venous phase (PVP), lesions showed iso-enhancement (6/8) or hypo-enhancement (2/8), while in the delayed phase (DP), they displayed iso-enhancement (5/8) or hypo-enhancement (3/8), consistent with a "fast-in and slow-out" (FISO) enhancement pattern. The literature review identified 10 studies (comprising 20 lesions) published between 2006 and March 2025, which described CEUS characteristics of hepatic PEComas that were consistent with those observed in our cohort. Hepatic PEComa is a rare liver tumor often detected incidentally. It typically demonstrates marked homogeneous hyper-enhancement during the HAP, followed by a "FISO" enhancement pattern. Preoperative diagnosis and differentiation between benign and malignant forms of hepatic PEComa remain challenging using CUS. CEUS provides additional diagnostic characteristics for hepatic PEComas and holds value in the differential diagnosis of focal liver lesions.

Lemierre's syndrome is a rare, life-threatening condition characterized by septic thrombophlebitis of the internal jugular vein, typically following oropharyngeal infection. We report a rare case in a 10-year-old girl presenting with recurrent sore throat and progressive left-sided neck swelling. Ultrasound served as a critical first-line imaging tool, revealing a hypoechoic mass compressing the internal jugular vein. The diagnosis was confirmed by contrast-enhanced CT and fine-needle aspiration, and the patient recovered following antibiotic therapy. This case underscores the rarity of Lemierre's syndrome in pediatric patients and highlights the utility of ultrasound for early detection and timely intervention in atypical presentations.

Bullous pilomatricoma (BP), a rare variant of pilomatricoma, accounts for approximately 2% of pilomatricoma cases. We present the case of a 19-year-old male with a painless, blister-like lesion on the left upper arm, diagnosed as BP based on histopathological examination. This report emphasizes the multimodal ultrasound features of BP, incorporating grayscale ultrasound, color Doppler flow imaging (CDFI), and shear wave elastography (SWE). Notably, to our knowledge, this is the first case to detail the SWE characteristics of BP, demonstrating a mean stiffness value of 52.0 kPa. Our findings indicate that BP can exhibit deceptively high stiffness on elastography, unlike other benign skin masses that appear less stiff, highlighting the importance of integrating multiple sonographic techniques for accurate preoperative assessment of skin tumors.

Image denoising is a crucial pre-processing technique in retinal optical coherence tomography image compression, but existing methods struggle with signal-dependent noise and do not consider hybridized low-contrast residual noise (HLRN), failing to gather information from images. Thus, the novel Smooth Gyrated Texel Quadrivium Network (SGTQN) is proposed to reduce noise and collect self-sufficient information. In the SGTQN, the novel Additive Ascombe Smooth Sifter converts Poisson noise into Gaussian noise using the Ascombe Transform and removes unwanted Gaussian noise and the HLRN by hybridized noise removal, thus effectively gathering useful information from the image. After denoising, existing segmentation methodologies neglect the retinal nerve deviation value, creating a poor self-explanatory image. Thus, a novel Improvised Gyrated Alexa Net incorporates the Standardized Gyrated Layer, which considers the deviation values, thus generating a self-explanatory segmented image. Furthermore, many existing compression methods failed to achieve a higher quality image due to their non-uniform compression. The Texel Quadrivium Convolutional Network modifies the pooling layer into a Texel Quadrivium Layer to perform uniform compression and uses adjuvant vector coordinates to generate a high-resolution compressed image. This proposed model provides high-quality image compression with reduced noise, with a high accuracy of 95% and a lower mean square error of 0.02.