Search

IntroductionDiagnosis of prenatal megacystis has a significant impact on the pregnancy, as it can have severe adverse effects on fetal and neonatal survival and renal and pulmonary function. The study aims to investigate the natural history of fetal megacystis, to try to differentiate in utero congenital lower urinary tract obstruction (LUTO) from non-obstructive megacystis, and, possibly, to predict postnatal outcome.Materials and methodsA retrospective single-center observational study was conducted from July 2015 to November 2023. The inclusion criteria were a longitudinal bladder diameter (LBD) >7 mm in the first trimester or an overdistended/thickened-walled bladder failing to empty in the second and third trimesters. Close ultrasound follow-up, multidisciplinary prenatal counseling, and invasive and non-invasive genetic tests were offered. Informed consent for fetal autopsy was obtained in cases of termination of pregnancy or intrauterine fetal demise (IUFD). Following birth, neonates were followed up at the same center. Patients were stratified based on diagnosis: LUTO (G1), urogenital anomalies other than LUTO (“non-LUTO”) (G2), and normal urinary tract (G3).ResultsThis study included 27 fetuses, of whom 26 were males. Megacystis was diagnosed during the second and third trimesters in 92% of the fetuses. Of the 27 fetuses, 3 (11.1%) underwent an abortion, and 1 had IUFD. Twenty-three newborns were live births (85%) at a mean gestational age (GA) of 34 ± 2 weeks. Two patients (neonates) died postnatally due to severe associated malformations. Several prenatal parameters were evaluated to differentiate patients with LUTO from those with non-LUTO, including the severity of upper tract dilatation, keyhole sign, oligohydramnios, LBD, and GA at diagnosis. However, none proved predictive of the postnatal diagnosis. Similarly, none of the prenatal parameters evaluated were predictive of postnatal renal function.DiscussionThe diagnosis of megacystis in the second and third trimesters was associated with live births in up to 85% of cases, with LUTO identified as the main cause of fetal megacystis. This potentially more favorable outcome, compared to the majority reported in literature, should be taken into account in prenatal counseling. Megacystis is an often misinterpreted antennal sign that may hide a wide range of diagnoses with different prognoses, beyond an increased risk of adverse renal and respiratory outcomes.

Object recognition is a quite critical task that involves the identification and potential localization of a target inside a monitored area. Target detection usually relies on material, shape and size identification in order to infer higher level information, and it can be employed in many different frameworks and applications. In this connection, we carry out a performance evaluation campaign on WiFi Channel State Information (CSI)-based object recognition techniques used to automatically identify material, category and specific objects among daily life items. The main contribution of this work is to provide a thorough comparison of the performance of different machine learning algorithms on recognition using a real-life experimental testbed. The performance study shows that the Random Forest (RF) classifier proves very accurate in terms of correct target recognition, independently of the considered task. The employed deep learning algorithm, Long Short-Term Memory (LSTM), is similarly able to attain very good results. In particular, accuracy values reach 94.8% in material identification, 97.1% in category differentiation and 98.1% in object recognition tasks.

Objective: Placental chorioangioma is the most common non-trophoblastic vascular benign tumor of the placenta, with an estimated incidence of 1% of all pregnancies. Most chorioangiomas are small asymptomatic lesions that are found incidentally only postnatally during histologic examination of the placenta. Voluminous chorioangiomas (>4–5 cm), however, are less common and are more often diagnosed prenatally, through ultrasound imaging. Color Doppler demonstrates either a single blood vessel feeding the lesion or substantial vascularity within the mass. Large tumors have been associated with multiple adverse perinatal outcomes, including fetal growth restriction, preterm birth, polyhydramnios, fetal congestive heart failure, fetal anemia, fetal hydrops and intrauterine death. Case(s): A 35-years-old primigravida woman with uncomplicated pregnancy was referred to the Ultrasound Centre of Obstetric and Gynecologic of Sant’Anna Hospital, Turin, due to a suspect placental mass seen during the ultrasound performed at 32 weeks of gestation. In this case, detailed ultrasound scans with grey scale and Doppler examination were performed (using Aplio 550; Canon Medical Systems Europe BV, Zoetermeer, The Netherlands). We also decided to study the vascularization of the mass with SMI (superb microvascular imaging) technology. In particular, with the use of SMI, it was possible to visualize the vascularization of the mass more completely which was conspicuous at first but disappeared after thrombosis of feeding vessels with favorable pregnancy outcome. Conclusion: SMI is a new vascularity imaging method that can visualize vessels that exhibit slow flow rates. It uses a system to reduce artifacts by greatly reducing interference from tissue movement.

Drone deployment has become crucial in a variety of applications, including solutions to traffic issues in metropolitan areas and highways. On the other hand, data collected via drones suffers from several problems, including a wide range of object scales, angle variations, truncation, and occlusion. To process and manipulate visual data from the drones, a variety of image processing algorithms have been employed, each with a distinct aim. Additionally, recent breakthroughs in the field of Artificial Intelligence, particularly deep learning, have attracted broad interest and are being applied to many domains in the framework of smart cities, including road traffic monitoring. The purpose of this study is to conduct a systematic review of drone-based traffic monitoring systems from a deep learning perspective. This work focuses on vehicle detection, tracking, and counting, since they are fundamental building blocks towards founding solutions for traffic congestion, flow rate and vehicle speed estimation. Additionally, drone-based datasets are examined, which face issues and problems caused by the diversity of features inherent of drone devices. The review analysis presented in this work summarizes the literature solutions provided and deployed so far and discusses future research trends in establishing a comprehensive traffic monitoring system in support of the development of smart cities.

The Internet of Things (IoT) framework is moving the research community to provide smart systems and solutions aimed at revolutionizing medical sciences and healthcare. Given the extreme diffusion of Alzheimer’s disease (AD) and Parkinson’s disease (PD), the demand for a solution to early detect neurological symptoms of such diseases strongly arose. According to the medical literature, such early detection can be obtained through the correlation between PD and AD and some external symptoms: the Essential Tremor (ET) and the number of Eye Blinks (EBs). In this paper, which can be considered as an extended version of [1], we present a prototype of wearable smart glasses able to detect the presence of ET of the head and to count the number of EBs at the same time, in a transparent way with respect to the final user. Numerical results demonstrate the reliability of the proposed approach: the proposed algorithms are able to i) correctly recognize the ET with an overall accuracy above 97% and ii) count the number of EBs with an overall error around 9%.

The demographic shift of the population toward an increased number of elder citizens, together with the sedentary lifestyle we are adopting, is reflected in the increasingly debilitated physical health of the population [...]

This prospective observational study aimed to evaluate whether women with SARS-CoV-2 infection during the first trimester of pregnancy are at higher risk of noninvasive prenatal screening test alterations and/or of congenital fetal anomalies at the second-trimester fetal anatomy scan. Maternal symptoms were secondly investigated. The study was carried out on 12-week pregnant women admitted for noninvasive prenatal testing (16 April and 22 June 2020). The cohort had seromolecular tests for SARS-CoV-2, after which they were divided into a positive case group and a negative control group. Both groups had 20-week ultrasound screening. Seventeen out of the 164 women tested positive for SARS-CoV-2 (10.3%). There were no significant differences in mean nuchal translucency thickness or biochemical markers (pregnancy-associated plasma protein A, alpha-fetoprotein, human chorionic gonadotropin, unconjugated estriol) between cases and controls (p = 0.77, 0.63, 0.30, 0.40, 0.28) or in the fetal incidence of structural anomalies at the second-trimester fetal anatomy scan (p = 0.21). No pneumonia or hospital admission due to COVID-19-related symptoms were observed. Asymptomatic or mildly symptomatic SARS-CoV-2 infection during the first trimester of pregnancy did not predispose affected women to more fetal anomalies than unaffected women. COVID-19 had a favorable maternal course at the beginning of pregnancy in our healthy cohort.