Fetal biometry and amniotic fluid volume assessment end-to-end automation using Deep Learning.

Fetal biometry and amniotic fluid volume assessments are two essential yet repetitive tasks in fetal ultrasound screening scans, aiding in the detection of potentially life-threatening conditions. However, these assessment methods can occasionally yield unreliable results. Advances in deep learning have opened up new avenues for automated measurements in fetal ultrasound, demonstrating human-level performance in various fetal ultrasound tasks. Nevertheless, the majority of these studies are retrospective in silico studies, with a limited number including African patients in their datasets. In this study we developed and prospectively assessed the performance of deep learning models for end-to-end automation of fetal biometry and amniotic fluid volume measurements. These models were trained using a newly constructed database of 172,293 de-identified Moroccan fetal ultrasound images, supplemented with publicly available datasets. the models were then tested on prospectively acquired video clips from 172 pregnant people forming a consecutive series gathered at four healthcare centers in Morocco. Our results demonstrate that the 95% limits of agreement between the models and practitioners for the studied measurements were narrower than the reported intra- and inter-observer variability among expert human sonographers for all the parameters under study. This means that these models could be deployed in clinical conditions, to alleviate time-consuming, repetitive tasks, and make fetal ultrasound more accessible in limited-resource environments.

Real-time visual analytics for in-home medical rehabilitation of stroke patient-systematic review.

This paper is focused on real-time visual analytics for home-based rehabilitation dedicated for brain stroke survivors. This research is at the intersection of three main domains: visual analytics for time-oriented data and dynamic visual analytics with specific focus on data analytics for rehabilitation systems. This study has emphasized the analysis of the most important research works in these domains. The studies included in this review are published between January 2008 and December 2020 that met eligibility criteria. From 243 papers retrieved from research including the Google Scholar database and manual research, 69 papers were finally included. This paper presents a classification of the reviewed research based on key features required by the visual analytics for real-time monitoring of patients. The findings suggested that real-time monitoring visual analytics for biodata captured during the rehabilitation sessions was not sufficiently addressed by previous research. To provide real-time monitoring visual analytics of biodata, the concept of a unified framework that combines the processing of batch and stream data in a distributed architecture is proposed. The system is currently under development; its validation will be carried out by an experimental study and the evaluation of the system performance.