Deep learning methods for point-of-care ultrasound examination

Point-of-care Test (POCT) is the delivery of medical care at or near the patient’s bedside. Primarily employed in emergencies, where rapid diagnosis and treatment are critical, POCT is now being used in domestic telehealth solutions, as in the TiAssisto project, thanks to technological advances such as the development of portable and affordable devices, high-speed Internet connections, video conferencing, and Artificial Intelligence (AI). Ultrasound (US) images of internal organs and structures are valuable tools in POCT medicine since this examination is portable, quick, and cost-effective. USs can help diagnose different conditions, including heart problems, abdominal pain, and pneumonia. Deep learning algorithms have proven to be highly effective in image recognition, enabling physicians to make informed decisions on-site. This article presents a pipeline approach providing remarkable and reliable results to handle point-of-care ultrasound examinations, making use of methods for: a) automating text cleaning for privacy based on an Optical Character Recognition (OCR) algorithm; b) scrolling through the video frames and annotating them using an ad hoc implemented tool; c) classifying various signs in US using a state of the art deep learning algorithm, that is an adaptive efficient method ensembling two EfficientNet-b0 weak models; d) benchmarking medical plausibility to address transparency and human in the loop setting using a post hoc explanation visual explanation method, i.e. Grad-CAM.The involved physician’s feedback remarks that this system can detect important signs in pulmonary US imaging. However, the dataset is not yet the final one since the TiAssisto project is still ongoing, with a planned conclusion in February 2024. Our ultimate goal is not merely to develop a classification system but to create an effective healthcare support system that can be used beyond primary healthcare facilities.