BACKGROUND: While echocardiography is pivotal for detecting left ventricular hypertrophy (LVH), it struggles with etiology differentiation. To enhance LVH assessment, we aimed to develop an artificial intelligence algorithm using echocardiography-based radiomics. This algorithm is designed to detect LVH and differentiate its common etiologies, such as hypertrophic cardiomyopathy (HCM), cardiac amyloidosis (CA), and hypertensive heart disease (HHD), based on echocardiographic images. METHODS: The developmental data sets from multiple medical centers included 867 subjects, with an independent external test set from a single tertiary medical center containing 619 subjects. Radiomic feature analysis was conducted on 4 echocardiographic views, extracting both conventional and harmonization-driven myocardial textures along with myocardial geographic features. Then, we developed classification models for each condition. Variable contributions were evaluated using Shapley Additive Explanations analysis. RESULTS: The radiomics-based LightGBM model, selected from internal validation, maintained strong performance in the external test set (area under the curve of 0.96 for HCM, 0.89 for CA, and 0.86 for HHD). Compared with the logistic regression model using conventional echocardiographic parameters (left ventricular ejection fraction, left ventricular mass index, left atrial volume index, and E/e′), the final model demonstrated superior sensitivity (0.89 versus 0.80 for HCM, 0.80 versus 0.80 for CA, and 0.75 versus 0.33 for HHD) and F1-score (0.87 versus 0.57 for HCM, 0.84 versus 0.72 for CA, and 0.82 versus 0.50 for HHD). Feature analysis highlighted that harmonization-driven textures played a key role in differentiating HCM, while conventional textures and myocardial thickness were influential in differentiating CA and HHD. CONCLUSIONS: This study confirms that artificial intelligence-enhanced echocardiography-based radiomics effectively differentiate the etiology of LVH, highlighting the potential of artificial intelligence-driven texture and geographic analysis in LVH evaluation.

Computed tomography (CT) imaging is vital for diagnosing and monitoring diseases in both humans and animals, yet radiation exposure remains a significant concern, especially in animal imaging. Low-dose CT (LDCT) minimizes radiation exposure but often compromises image quality due to a reduced signal-to-noise ratio (SNR). Recent advancements in deep learning, particularly with CycleGAN, offer promising solutions for denoising LDCT images, though challenges in preserving anatomical detail and image sharpness persist. This study introduces a novel framework tailored for animal LDCT imaging, integrating deep learning techniques within the CycleGAN architecture. Key components include BlurPool for mitigating high-resolution image distortion, PixelShuffle for enhancing expressiveness, hierarchical feature synthesis (HFS) networks for feature retention, and spatial channel squeeze excitation (scSE) blocks for contrast reproduction. Additionally, a multi-scale discriminator enhances detail assessment, supporting effective adversarial learning. Rigorous experimentation on veterinary CT images demonstrates our framework’s superiority over traditional denoising methods, achieving significant improvements in noise reduction, contrast enhancement, and anatomical structure preservation. Extensive evaluations show that our method achieves a precision of 0.93 and a recall of 0.94. This validates our approach’s efficacy, highlighting its potential to enhance diagnostic accuracy in veterinary imaging. We confirm the scSE method’s critical role in optimizing performance, and robustness to input variations underscores its practical utility.

Aims: Pericardial disease spans a wide spectrum from small effusions to life-threatening tamponade or constriction. Transthoracic echocardiography (TTE) is the main diagnostic tool, but its interpretation is limited by operator dependence and incomplete functional assessment. Existing deep learning (DL) models focus mainly on effusion detection, lacking broader evaluation. Methods and results: We developed a DL-based framework that performs sequential assessment of pericardial disease: (i) morphological features, including effusion amount (normal/small/moderate/large) and pericardial thickening/adhesion (yes/no), from five B-mode views, and (ii) haemodynamic significance (yes/no), incorporating Doppler and inferior vena cava measurements. The developmental dataset comprises 2253 TTEs from multiple Korean institutions (225 for internal testing), and the independent external test set consists of 274 TTEs. In the internal test set, diagnostic accuracy was 81.8–97.3% for effusion, 91.6% for thickening/adhesion, and 86.2% for haemodynamic significance. External test set accuracy was 80.3–94.2%, 94.5%, and 85.5%, respectively. Area under the receiver operating curves for the three tasks were 0.92–0.99, 0.90, and 0.79 internally, and 0.95–0.98, 0.85, and 0.76 externally. Sensitivity for thickening/adhesion and haemodynamic significance improved from 66.7% to 77.3%, and 68.8% to 80.8%, respectively, when poor image quality were excluded. Similar performance gains were observed in subgroups with complete target views and a higher number of available video clips. Conclusion: This study presents the first DL-based TTE model for broader pericardial disease evaluation, integrating morphological with supportive functional assessments. The proposed framework demonstrated strong generalizability and aligned with the real-world diagnostic workflow. However, caution is warranted when interpreting results under suboptimal imaging conditions.

Background: Pericardial disease spans a wide spectrum from small effusions to life-threatening tamponade or constriction. Transthoracic echocardiography (TTE) is the main diagnostic tool, but its interpretation is limited by operator dependence and incomplete functional assessment. Existing deep learning (DL) models focus mainly on effusion detection, lacking broader evaluation. Methods: We developed a DL-based framework that performs sequential assessment of pericardial disease: (1) morphological features, including effusion amount (normal/small/moderate/large) and pericardial thickening/adhesion (yes/no), from five B-mode views, and (2) hemodynamic significance (yes/no), incorporating Doppler and inferior vena cava measurements. The developmental dataset comprises 2,253 TTEs from multiple Korean institutions (225 for internal testing), and the independent external test set consists of 274 TTEs. Results: In the internal test set, diagnostic accuracy was 81.8-97.3% for effusion, 91.6% for thickening/adhesion, and 86.2% for hemodynamic significance. External test set accuracy was 80.3-94.2%, 94.5%, and 85.5%, respectively. Area under the receiver operating curves (AUROCs) for the three tasks was 0.92-0.99, 0.90, and 0.79 internally, and 0.95-0.98, 0.85, and 0.76 externally. Sensitivity for thickening/adhesion and hemodynamic significance improved from 66.7% to 77.3%, and 68.8% to 80.8%, respectively, when poor image quality were excluded. Similar performance gains were observed in subgroups with complete target views and a higher number of available video clips. Conclusions: This study presents the first DL-based TTE model for broader pericardial disease evaluation, integrating morphological with supportive functional assessments. The proposed framework demonstrated strong generalizability and aligned with the real-world diagnostic workflow. However, caution is warranted when interpreting results under suboptimal imaging conditions.

Radiomics, a medical imaging technique, extracts quantitative handcrafted features from images to predict diseases. Harmonization in those features ensures consistent feature extraction across various imaging devices and protocols. Methods for harmonization include standardized imaging protocols, statistical adjustments, and evaluating feature robustness. Myocardial diseases such as Left Ventricular Hypertrophy (LVH) and Hypertensive Heart Disease (HHD) are diagnosed via echocardiography, but variable imaging settings pose challenges. Harmonization techniques are crucial for applying handcrafted features in disease diagnosis in such scenario. Self-supervised learning (SSL) enhances data understanding within limited datasets and adapts to diverse data settings. ConvNeXt-V2 integrates convolutional layers into SSL, displaying superior performance in various tasks. This study focuses on convolutional filters within SSL, using them as preprocessing to convert images into feature maps for handcrafted feature harmonization. Our proposed method excelled in harmonization evaluation and exhibited superior LVH classification performance compared to existing methods.