The latest medical research on Radiology

Our primary aim was to identify radiomic ultrasound features that can distinguish benign from malignant adnexal masses with solid ultrasound morphology, and primary invasive from metastatic solid ovarian masses, and to develop ultrasound-based machine learning models that include radiomics features to discriminate between benign and malignant solid adnexal masses. Our secondary aim was to compare the diagnostic performance of our radiomics models with that of the ADNEX model and subjective assessment by an experienced ultrasound examiner.

This is a retrospective observational single center study. Patients with a histological diagnosis of an adnexal tumor with solid morphology at preoperative ultrasound examination performed between 2014 and 2021 were included. The patient cohort was split into training and validation sets with a ratio of 70:30 and with the same proportion of benign and malignant (borderline, primary invasive and metastatic) tumors in the two subsets. The extracted radiomic features belonged to two different families: intensity-based statistical features and textural features. Models to predict malignancy were built based on a random forest classifier, fine-tuned using 5-fold cross-validation over the training set, and tested on the held-out validation set. The variables used in model building were patient's age, and those radiomic features that were statistically significantly different between benign and malignant adnexal masses (Wilcoxon-Mann-Whitney Test with Benjamini-Hochberg correction for multiple comparisons) and assessed as not redundant based on the Pearson correlation coefficient. We describe discriminative ability as area under the receiver operating characteristics curve (AUC) and classification performance as sensitivity and specificity.

326 patients were identified and 775 preoperative ultrasound images were analyzed. 68 radiomic features were extracted, 52 differed statistically significantly between benign and malignant tumors in the training set, and 18 features were selected for inclusion in model building. The same 52 radiomic features differed statistically significantly between benign, primary invasive malignant and metastatic tumors. However, the values of the features manifested overlap between primary malignant and metastatic tumors and did not differ statistically significantly between them. In the validation set, 25/98 tumors (25.5%) were benign, 73/98 (74.5%) were malignant (6 borderline, 57 primary invasive, 10 metastases). In the validation set, a model including only radiomics features had an AUC of 0.80, and 78% sensitivity and 76% specificity at its optimal risk of malignancy cutoff (68% based on Youden's index). The corresponding results for a model including age and radiomics features were 0.79, 86% and 56% (cutoff 60% based on Youden's method), while those of the ADNEX model were 0.88, 99% and 64% (at 20% malignancy cutoff). Subjective assessment had sensitivity 99% and specificity 72%.

Even though our radiomics models had discriminative ability inferior to that of the ADNEX model, our results are promising enough to justify continued development of radiomics analysis of ultrasound images of adnexal masses. This article is protected by copyright. All rights reserved.

To reach a Delphi-generated international expert consensus on the diagnosis, prognostic, management, and core outcome set (COS) of fetal Lower Urinary Tract Obstruction (LUTO).

A three-round Delphi procedure was conducted among an international panel of LUTO experts. The panel was provided with a list of literature review-generated parameters for the diagnosis, prognostic, management, and outcomes. A parallel procedure was conducted along with patient groups during the development of COS.

A total of 160 experts were approached, of whom 99 completed the first round and 80 (80/99, 80.8%) completed all three rounds. In the first trimester, an objective measurement of longitudinal bladder diameter (with ≥7 mm being abnormal) should be used to suspect LUTO. In the second trimester, imaging parameters of LUTO could include: a) an enlarged bladder, b) a keyhole sign, c) bladder wall thickening, d) bilateral hydro (uretero) nephrosis, and e) male sex. There was a lack of consensus on the current prognostic scoring literature. However, experts agreed on the value of amniotic fluid volume (< 24 weeks) to predict survival and that the value of fetal intervention is to improve neonatal survival. While experts endorsed the role of sonographic parameters of renal dysplasia, at least one vesicocentesis, and urine biochemistry for prognosis and counseling, these items did not reach a consensus for determining fetal intervention candidacy. On the other hand, imaging parameters suggestive of LUTO, absence of life-limiting structural or genetic anomalies, gestational age of ≥16 weeks, and oligohydramnios defined as deepest vertical pocket (DVP) <2 cm should be used as candidacy criteria for fetal intervention based on experts' consensus. If a bladder refill was evaluated, it should be assessed subjectively. Vesicoamniotic shunt should be the first line of fetal intervention. In the presence of suspected fetal renal failure, serial amnioinfusion should only be offered as an experimental procedure under research protocols. The core outcome set for future studies was agreed upon.

International consensus on the diagnosis, prognosis, and management of fetal LUTO, as well as the Core Outcome Set, should inform clinical care and research to optimize perinatal outcomes. This article is protected by copyright. All rights reserved.

Hemoglobin (Hb) Bart's disease is a severe manifestation of alpha thalassemia, resulting in fetal tissue hypoxia and severe anemia. There is limited research available on assessing fetal speckle tracking analysis as a response to fetal anemia caused by Hb Bart's disease and its utility as a sonographic predictor for Hb Bart's disease. This study aimed to assess the diagnostic performance of fetal cardiac parameters derived from speckle tracking echocardiography for distinguishing between affected and unaffected fetuses in pregnancies at risk of Hb Bart's disease during the 17-24 gestational weeks.

A total of 115 pregnant women at risk for fetal Hb Bart's disease, who underwent either amniocentesis or cordocentesis at Siriraj Hospital, Bangkok Thailand, were included. Speckle tracking analysis was performed on the 4-chamber view (4CV) of the fetal heart, assessing heart size, shape, ventricular contractility, and left ventricular function prior to invasive prenatal testing. Logistic regression analysis determined significant cardiac predictors and calculated the probability of a fetus having Hb Bart's disease.

Among the cohort, 38 fetuses (33%) were diagnosed with Hb Bart's disease, and 9 cases (7.8%) exhibited frank hydropic signs. In comparison to the control group, affected fetuses displayed a notable enlargement of the 4CV and a more globular shape specifically in the right ventricular chamber. Additionally, there were significant differences in the left global and longitudinal contractility between affected and unaffected fetuses. However, at mid-gestation, no significant distinctions were observed in terms of transverse contractility and left ventricular function between the two groups. Based on logistic regression analysis, combined cardiac parameters derived from speckle tracking analysis as a function of head circumference, could differentiate non-hydropic fetuses with Hb Bart's disease from unaffected fetuses, achieving a maximum sensitivity of 100%, specificity of 98.7%, and overall accuracy of 99.06%.

Speckle tracking echocardiography has the potential to accurately identify early fetal heart changes in individuals at risk of developing Bart's anemia during the second trimester. This not only offers a novel predictive marker for Hb Bart's disease but also helps address the question of the underlying mechanisms of heart failure associated with anemia. This article is protected by copyright. All rights reserved.