Clinical Research Directory

AI-Assisted 2D Fetal Brain Ultrasound for Intracranial Anomaly Detection

Timely detection of fetal brain anomalies is critical for improving prenatal counseling and postnatal neurological outcomes. Ultrasonography is the most commonly used and effective imaging method for evaluating fetal structures; however, diagnostic accuracy can be affected by operator experience, fetal position, and image quality, leading to variability in interpretation. Artificial intelligence (AI)-based image analysis offers a new opportunity to standardize diagnostic assessment and reduce subjectivity in ultrasound interpretation. This study aims to evaluate the diagnostic accuracy and clinical applicability of an AI-assisted model (Alyssia) designed to analyze archived 2D fetal brain ultrasound images. The model will be trained and validated to distinguish between normal and abnormal intracranial findings, focusing particularly on the lateral ventricles and other relevant brain regions. The research employs an observational, retrospective design using anonymized ultrasound data obtained during routine prenatal examinations between 18 and 24 weeks of gestation. Expert clinicians will review and label all eligible images to establish ground truth classifications for model training and validation. A deep learning-based algorithm will be developed to automatically classify these images, and its performance will be evaluated using accuracy, sensitivity, specificity, precision, and F1-score metrics. Misclassified cases will be qualitatively analyzed to determine contributing factors such as image quality, anatomical variability, and gestational differences. By comparing AI model outputs with expert-labeled references, the study will assess the model's ability to enhance diagnostic standardization and reduce inter-observer variability. The findings are expected to provide valuable insights into the integration of AI-based decision support systems in prenatal neurosonography. Ultimately, this research aims to support earlier and more reliable detection of fetal brain anomalies, contributing to improved prenatal care and healthier outcomes for mothers and infants.

Ultrasound and Respiratory Physiological Signals in Lung Diseases

The use of lung ultrasound is instrumental in the evaluation of many chest pathologies and its ability to detect pleuro-pulmonary pathology is widely accepted. However, the use of ultrasound to explore the state of the peripheral lung parenchyma, when the organ is still aerated, is a relatively new application. Horizontal and vertical artifacts are separate and distinct artifacts that can be seen during ultrasound examination of the lungs. While the practical role of lung ultrasound artifacts is accepted to detect and monitor many conditions, further research is needed for the physical interpretation of ultrasound artifacts. These artifacts are diagnostic signs, but we don't fully understand their origin. The artifactual information deriving from the surface acoustic interaction, beyond the pleural line, in the ultrasound images of the normally aerated and non-deflated lung, represents the final result of complex interactions of acoustic waves with a specific three-dimensional structure of the biological tissue. Thus, the umbrella term "vertical artifacts" oversimplifies many physical phenomena associated with a pathological pleural plane. There is growing evidence that vertical artifacts are caused by physiological and pathological changes in the superficial lung parenchyma. Therefore, the need emerges to explore the physical phenomena underlying the artifactual ultrasound information deriving from the surface acoustic interaction of ultrasound with the pleuro-pulmonary structures.

Artificial Intelligence for Learning Point-of-Care Ultrasound

Point-of care-ultrasonography has the potential to transform healthcare delivery through its diagnostic and therapeutic utility. Its use has become more widespread across a variety of clinical settings as more investigations have demonstrated its impact on patient care. This includes the use of point-of-care ultrasound by trainees, who are now utilizing this technology as part of their diagnostic assessments of patients. However, there are few studies that examine how efficiently trainees can learn point-of-care ultrasound and which training methods are more effective. The primary objective of this study is to assess whether artificial intelligence systems improve internal medicine interns' knowledge and image interpretation skills with point-of-care ultrasound. Participants shall be randomized to receive personal access to handheld ultrasound devices to be used for learning with artificial intelligence vs devices with no artificial intelligence. The primary outcome will assess their interpretive ability with ultrasound images/videos. Secondary outcomes will include rates of device usage and performance on quizzes.

Automated Ultrasound Cardiac Guidance Tool

This research examines echocardiography images taken from cardiac patients in relation to the guidance tool developed

Remote Breast Cancer Screening Study

A multi-center, prospective, cohort study to evaluate the efficiency of breast cancer screening based on Automated Breast Ultrasound (AB US) with remote reading mode.