Fully Automated Mouse Echocardiography Analysis Using Deep Convolutional Neural Networks

Diagnosing Severe Low-Gradient vs Moderate Aortic Stenosis with Artificial Intelligence Based on Echocardiography Images

Diagnosis of aortic valve stenosis (AS) is performed manually by a physician experienced in echocardiography imaging. A specific subtype of AS, a severe low-gradient AS, is the most challenging one in terms of differentiating it from the moderate AS. In this study, an artificial intelligence (AI)-based model was used to diagnose the severe low-gradient AS in a fully automatic manner. Data from 158 consecutive patients undergoing echocardiography examination to assess AS severity were used. The obtained performance of our fully automatic approach was AUC = 0.719, 95% confidence interval, 0.640-0.798. It is an important step towards a comprehensive and automatic, image-only-based clinical decision support system for determining the presence of AS and its severity, especially in AS subtypes, such as low-gradient AS.

Realistic Aspects of Cardiac Ultrasound in Rats: Practical Tips for Improved Examination

Echocardiography is a reliable and non-invasive method for assessing cardiac structure and function in both clinical and experimental settings, offering valuable insights into disease progression and treatment efficacy. The successful application of echocardiography in murine models of disease has enabled the evaluation of disease severity, drug testing, and continuous monitoring of cardiac function in these animals. However, there is insufficient standardization of echocardiographic measurements for smaller animals. This article aims to address this gap by providing a guide and practical tips for the appropriate acquisition and analysis of echocardiographic parameters in adult rats, which may also be applicable in other small rodents used for scientific purposes, like mice. With advancements in technology, such as ultrahigh-frequency ultrasonic transducers, echocardiography has become a highly sophisticated imaging modality, offering high temporal and spatial resolution imaging, thereby allowing for real-time monitoring of cardiac function throughout the lifespan of small animals. Moreover, it allows the assessment of cardiac complications associated with aging, cancer, diabetes, and obesity, as well as the monitoring of cardiotoxicity induced by therapeutic interventions in preclinical models, providing important information for translational research. Finally, this paper discusses the future directions of cardiac preclinical ultrasound, highlighting the need for continued standardization to advance research and improve clinical outcomes to facilitate early disease detection and the translation of findings into clinical practice.

Real-Time Automatic M-Mode Echocardiography Measurement With Panel Attention

Motion mode (M-mode) echocardiography is essential for measuring cardiac dimension and ejection fraction. However, the current diagnosis is time-consuming and suffers from diagnosis accuracy variance. This work resorts to building an automatic scheme through well-designed and well-trained deep learning to conquer the situation. That is, we proposed RAMEM, an automatic scheme of real-time M-mode echocardiography, which contributes three aspects to address the challenges: 1) provide MEIS, the first dataset of M-mode echocardiograms, to enable consistent results and support developing an automatic scheme; For detecting objects accurately in echocardiograms, it requires big receptive field for covering long-range diastole to systole cycle. However, the limited receptive field in the typical backbone of convolutional neural networks (CNN) and the losing information risk in non-local block (NL) equipped CNN risk the accuracy requirement. Therefore, we 2) propose panel attention embedding with updated UPANets V2, a convolutional backbone network, in a real-time instance segmentation (RIS) scheme for boosting big object detection performance; 3) introduce AMEM, an efficient algorithm of automatic M-mode echocardiography measurement, for automatic diagnosis; The experimental results show that RAMEM surpasses existing RIS schemes (CNNs with NL & Transformers as the backbone) in PASCAL 2012 SBD and human performances in MEIS.

Artificial intelligence-enhanced automation for M-mode echocardiographic analysis: ensuring fully automated, reliable, and reproducible measurements

To enhance M-mode echocardiography's utility for measuring cardiac structures, we developed and evaluated an artificial intelligence (AI)-based automated analysis system for M-mode images through the aorta and left atrium [M-mode (Ao-LA)], and through the left ventricle [M-mode (LV)]. Our system, integrating two deep neural networks (DNN) for view classification and image segmentation, alongside an auto-measurement algorithm, was developed using 5,958 M-mode images [3,258 M-mode (LA-Ao), and 2,700 M-mode (LV)] drawn from a nationwide echocardiographic dataset collated from five tertiary hospitals. The performance of view classification and segmentation DNNs were evaluated on 594 M-mode images, while automatic measurement accuracy was tested on separate internal test set with 100 M-mode images as well as external test set with 280 images (140 sinus rhythm and 140 atrial fibrillation). Performance evaluation showed the view classification DNN's overall accuracy of 99.8% and segmentation DNN's Dice similarity coefficient of 94.3%. Within the internal test set, all automated measurements, including LA, Ao, and LV wall and cavity, resonated strongly with expert evaluations, exhibiting Pearson's correlation coefficients (PCCs) of 0.81-0.99. This performance persisted in the external test set for both sinus rhythm (PCC, 0.84-0.98) and atrial fibrillation (PCC, 0.70-0.97). Notably, automatic measurements, consistently offering multi-cardiac cycle readings, showcased a stronger correlation with the averaged multi-cycle manual measurements than with those of a single representative cycle. Our AI-based system for automatic M-mode echocardiographic analysis demonstrated excellent accuracy, reproducibility, and speed. This automated approach has the potential to improve efficiency and reduce variability in clinical practice.

Applying deep learning to segmentation of murine lung tumors in pre-clinical micro-computed tomography

Lung cancer remains a leading cause of cancer-related death, but scientists have made great strides in developing new treatments recently, partly owing to the use of genetically engineered mouse models (GEMMs). GEMM tumors represent a translational model that recapitulates human disease better than implanted models because tumors develop spontaneously in the lungs. However, detection of these tumors relies on in vivo imaging tools, specifically micro-Computed Tomography (micro-CT or µCT), and image analysis can be laborious with high inter-user variability. Here we present a deep learning model trained to perform fully automated segmentation of lung tumors without the interference of other soft tissues. Trained and tested on 100 3D µCT images (18,662 slices) that were manually segmented, the model demonstrated a high correlation to manual segmentations on the testing data (r2=0.99, DSC=0.78) and on an independent dataset (n = 12 3D scans or 2328 2D slices, r2=0.97, DSC=0.73). In a comparison against manual segmentation performed by multiple analysts, the model (r2=0.98, DSC=0.78) performed within inter-reader variability (r2=0.79, DSC=0.69) and close to intra-reader variability (r2=0.99, DSC=0.82), all while completing 5+ hours of manual segmentations in 1 minute. Finally, when applied to a real-world longitudinal study (n = 55 mice), the model successfully detected tumor progression over time and the differences in tumor burden between groups induced with different virus titers, aligning well with more traditional analysis methods. In conclusion, we have developed a deep learning model which can perform fast, accurate, and fully automated segmentation of µCT scans of murine lung tumors.

Applications of Deep Learning Algorithms to Ultrasound Imaging Analysis in Preclinical Studies on In Vivo Animals

BACKGROUND AND AIM

Ultrasound (US) imaging is increasingly preferred over other more invasive modalities in preclinical studies using animal models. However, this technique has some limitations, mainly related to operator dependence. To overcome some of the current drawbacks, sophisticated data processing models are proposed, in particular artificial intelligence models based on deep learning (DL) networks. This systematic review aims to overview the application of DL algorithms in assisting US analysis of images acquired in in vivo preclinical studies on animal models.

METHODS

A literature search was conducted using the Scopus and PubMed databases. Studies published from January 2012 to November 2022 that developed DL models on US images acquired in preclinical/animal experimental scenarios were eligible for inclusion. This review was conducted according to PRISMA guidelines.

RESULTS

Fifty-six studies were enrolled and classified into five groups based on the anatomical district in which the DL models were used. Sixteen studies focused on the cardiovascular system and fourteen on the abdominal organs. Five studies applied DL networks to images of the musculoskeletal system and eight investigations involved the brain. Thirteen papers, grouped under a miscellaneous category, proposed heterogeneous applications adopting DL systems. Our analysis also highlighted that murine models were the most common animals used in in vivo studies applying DL to US imaging.

CONCLUSION

DL techniques show great potential in terms of US images acquired in preclinical studies using animal models. However, in this scenario, these techniques are still in their early stages, and there is room for improvement, such as sample sizes, data preprocessing, and model interpretability.

Diagnosis of Monkeypox Disease Using Transfer Learning and Binary Advanced Dipper Throated Optimization Algorithm

The virus that causes monkeypox has been observed in Africa for several years, and it has been linked to the development of skin lesions. Public panic and anxiety have resulted from the deadly repercussions of virus infections following the COVID-19 pandemic. Rapid detection approaches are crucial since COVID-19 has reached a pandemic level. This study's overarching goal is to use metaheuristic optimization to boost the performance of feature selection and classification methods to identify skin lesions as indicators of monkeypox in the event of a pandemic. Deep learning and transfer learning approaches are used to extract the necessary features. The GoogLeNet network is the deep learning framework used for feature extraction. In addition, a binary implementation of the dipper throated optimization (DTO) algorithm is used for feature selection. The decision tree classifier is then used to label the selected set of features. The decision tree classifier is optimized using the continuous version of the DTO algorithm to improve the classification accuracy. Various evaluation methods are used to compare and contrast the proposed approach and the other competing methods using the following metrics: accuracy, sensitivity, specificity, p-Value, N-Value, and F1-score. Through feature selection and a decision tree classifier, the following results are achieved using the proposed approach; F1-score of 0.92, sensitivity of 0.95, specificity of 0.61, p-Value of 0.89, and N-Value of 0.79. The overall accuracy of the proposed methodology after optimizing the parameters of the decision tree classifier is 94.35%. Furthermore, the analysis of variation (ANOVA) and Wilcoxon signed rank test have been applied to the results to investigate the statistical distinction between the proposed methodology and the alternatives. This comparison verified the uniqueness and importance of the proposed approach to Monkeypox case detection.

Echo2Pheno: a deep-learning application to uncover echocardiographic phenotypes in conscious mice

Echocardiography, a rapid and cost-effective imaging technique, assesses cardiac function and structure. Despite its popularity in cardiovascular medicine and clinical research, image-derived phenotypic measurements are manually performed, requiring expert knowledge and training. Notwithstanding great progress in deep-learning applications in small animal echocardiography, the focus has so far only been on images of anesthetized rodents. We present here a new algorithm specifically designed for echocardiograms acquired in conscious mice called Echo2Pheno, an automatic statistical learning workflow for analyzing and interpreting high-throughput non-anesthetized transthoracic murine echocardiographic images in the presence of genetic knockouts. Echo2Pheno comprises a neural network module for echocardiographic image analysis and phenotypic measurements, including a statistical hypothesis-testing framework for assessing phenotypic differences between populations. Using 2159 images of 16 different knockout mouse strains of the German Mouse Clinic, Echo2Pheno accurately confirms known cardiovascular genotype-phenotype relationships (e.g., Dystrophin) and discovers novel genes (e.g., CCR4-NOT transcription complex subunit 6-like, Cnot6l, and synaptotagmin-like protein 4, Sytl4), which cause altered cardiovascular phenotypes, as verified by H&E-stained histological images. Echo2Pheno provides an important step toward automatic end-to-end learning for linking echocardiographic readouts to cardiovascular phenotypes of interest in conscious mice.