Pre-eclampsia is a severe pregnancy-related complication that manifests as a syndrome with multisystem involvement and damage. It has significantly grown in frequency during the past 30 years and could be considered as one of the major causes of maternal and fetal morbidity and mortality. However, the specific etiology and molecular mechanisms of pre-eclampsia are still poorly known and could have a variety of causes, such as altered angiogenesis, inflammations, maternal infections, obesity, metabolic disorders, gestational diabetes, and autoimmune diseases. Perhaps the most promising area under investigation is the imbalance of maternal angiogenic factors and its effects on vascular function, though studies in placental oxidative stress and maternal immune response have demonstrated intriguing findings. However, to determine the relative importance of each cause and the impact of actions aiming to significantly reduce the incidence of this illness, more research is needed. Moreover, it is necessary to better understand the etiologies of each subtype of pre-eclampsia as well as the pathophysiology of other major obstetrical syndromes to identify a clinical tool able to recognize patients at risk of pre-eclampsia early.

Neoadjuvant chemotherapy plus radical surgery could be a safe alternative to chemo-radiation in cervical cancer patients who are not willing to receive radiotherapy. The response to neoadjuvant chemotherapy is the main factor influencing the need for adjunctive treatments and survival. In the present paper we aim to develop a machine learning model based on cervix magnetic resonance imaging (MRI) images to stratify the single-subject risk of cervical cancer. We collected MRI images from 72 subjects. Among these subjects, 28 patients (38.9%) belonged to the “Not completely responding” class and 44 patients (61.1%) belonged to the ’Completely responding‘ class according to their response to treatment. This image set was used for the training and cross-validation of different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic features could be able to capture the disease heterogeneity among the two groups. Three models consisting of three ensembles of machine learning classifiers (random forests, support vector machines, and k-nearest neighbor classifiers) were developed for the binary classification task of interest (“Not completely responding” vs. “Completely responding”), based on supervised learning, using response to treatment as the reference standard. The best model showed an ROC-AUC (%) of 83 (majority vote), 82.3 (mean) [79.9–84.6], an accuracy (%) of 74, 74.1 [72.1–76.1], a sensitivity (%) of 71, 73.8 [68.7–78.9], and a specificity (%) of 75, 74.2 [71–77.5]. In conclusion, our preliminary data support the adoption of a radiomic-based approach to predict the response to neoadjuvant chemotherapy.

Objectives: To analyze prospectively the ability of ultrasound to detect metastatic omentum in patients with suspicious pelvic masses and to describe the sonographic features of metastatic omental disease.Methods: One hundred and eighty‐four patients were evaluated preoperatively by ultrasound examination and of these 173 were used in the analysis. We defined as an ultrasound‐positive examination one which visualized intra‐abdominal aperistaltic solid tissue, located above the bowel loops and below the anterior peritoneal surface. Preoperative sonographic findings were compared with pathological results.Results: Sonographic detection of metastatic omentum was achieved in 104 of 173 patients (60.1%), appearing as either solid aperistaltic tissue (80.8% of cases), or as solid discrete nodules (19.2%). When considering the echostructure of the surrounding bowel loops, this tissue appeared hypoechoic in 46 (44.2%) cases and isoechoic or slightly hyperechoic in the other 58 (55.8%) cases. In the overall series, the negative and positive predictive values (NPV and PPV) and the accuracy of ultrasound examination were 92.7%, 91.3% and 91.9%, respectively. When considering only the group of ovarian tumors, the NPV, PPV and accuracy were 91.9%, 94.6%, and 93.8%, respectively.Conclusion: Ultrasound examination is highly accurate in detecting metastatic omental involvement in cases with suspicious pelvic masses. Copyright © 2005 ISUOG. Published by John Wiley & Sons, Ltd.

(1) Background: The number of adnexal masses detected during pregnancy has increased due to the use of first-trimester screening and increasingly advanced maternal age. Despite their low risk of malignancy, other risks associated with these masses include torsion, rupture and labor obstruction. Correct diagnosis and management are needed to guarantee both maternal and fetal safety. Adnexal masses may be troublesome to classify during pregnancy due to the increased volume of the uterus and pregnancy-related hormonal changes. Management should be based on ultrasound examination to provide the best treatment. The aim of this study was to describe the ultrasound features of ovarian masses detected during pregnancy and to optimize and personalize their management with the expertise of gynecologists, oncologists and sonographers. (2) Methods: Clinical, ultrasound, histological parameters and type of management (surveillance vs. surgery) were retrospectively retrieved. Patient management, perinatal outcomes and follow-up were also evaluated. (3) Results: according to the literature, these masses are most frequently benign, ultrasound follow-up is the best management, and obstetric outcomes are not considerably influenced by the presence of adnexal masses. (4) Conclusions: the management of patients with ovarian masses detected during pregnancy should be based on ultrasound examination, and a centralization in referral centers for ovarian masses should be considered.