BRCA Mutation Patients: Are There Other Predisposing Factors for Ovarian Cancer Occurrence? A Multicenter Retrospective Study.

OBJECTIVES: The objective of this multicenter retrospective study aimed to evaluate the association of clinical variables and the incidence of ovarian cancer in patients with BRCA 1-2 mutation carriers who underwent risk-reducing salpingo-oophorectomy (RRSO). DESIGN: Patients with a pathogenic mutation of BRCA 1-2 genes and with no evidence of disease are considered eligible. The exclusion criterion was the refusal to undergo the surgery. The retrospective study included all RRSO performed from May 2015 to April 2022 in the three gynecological Institutions of Southern Italy for were included in this retrospective study. PARTICIPANTS/MATERIALS, SETTING, METHODS: Age, menarche age, BMI, menopause at time of RRSO, breast cancer first- and second-degree relatives, ovarian cancer first- and second-degree relatives, estroprogestin use, pregnancy normal full-term delivery, history of endometriosis, previous breast cancer and histologic type, previous abdominal/pelvic surgery, BRCA 1 or BRCA 2 status, preoperative serum CA-125 levels (IU/mL), age at time of RRSO and histological analysis were collected. RESULTS: 184 were recruited. One was excluded. To assess cancer risk, the outcome variable was classified into three classes: no event, cancer, and other conditions excluding cancer. 14 women presented ovarian cancer and tubal intraepithelial carcinoma (STIC) on histopathologic final report. Ovarian cancer was found in 8 patients, whereas the presence of STIC was found in 6 of them. LIMITATIONS: The low incidence of patients diagnosed with ovarian cancer or STIC compared with the total number of patients undergoing RRSO is a potential bias. CONCLUSIONS: Our study did not demonstrate a correlation between clinical features and the occurrence of precancerous or cancerous lesions in BRCA mutation carrier patients.

Machine learning applied to MRI evaluation for the detection of lymph node metastasis in patients with locally advanced cervical cancer treated with neoadjuvant chemotherapy.

PURPOSE: Concurrent cisplatin-based chemotherapy and radiotherapy (CCRT) plus brachytherapy is the standard treatment for locally advanced cervical cancer (LACC). Platinum-based neoadjuvant chemotherapy (NACT) followed by radical hysterectomy is an alternative for patients with stage IB2-IIB disease. Therefore, the correct pre-treatment staging is essential to the proper management of this disease. Pelvic magnetic resonance imaging (MRI) is the gold standard examination but studies about MRI accuracy in the detection of lymph node metastasis (LNM) in LACC patients show conflicting data. Machine learning (ML) is emerging as a promising tool for unraveling complex non-linear relationships between patient attributes that cannot be solved by traditional statistical methods. Here we investigated whether ML might improve the accuracy of MRI in the detection of LNM in LACC patients. METHODS: We analyzed retrospectively LACC patients who underwent NACT and radical hysterectomy from 2015 to 2020. Demographic, clinical and MRI characteristics before and after NACT were collected, as well as information about post-surgery histopathology. Random features elimination wrapper was used to determine an attribute core set. A ML algorithm, namely Extreme Gradient Boosting (XGBoost) was trained and validated with tenfold cross-validation. The performances of the algorithm were assessed. RESULTS: Our analysis included n.92 patients. FIGO stage was IB2 in n.4/92 (4.3%), IB3 in n.42/92 (45%), IIA1 in n.1/92 (1.1%), IIA2 in n.16/92 (17.4%) and IIB in n.29/92 (31.5%). Despite detected neither at pre-treatment and post-treatment MRI in any patients, LNM occurred in n.16/92 (17%) patients. The attribute core set used to train ML algorithms included grading, histotypes, age, parity, largest diameter of lesion at either pre- and post-treatment MRI, presence/absence of fornix infiltration at pre-treatment MRI and FIGO stage. XGBoost showed a good performance (accuracy 89%, precision 83%, recall 78%, AUROC 0.79). CONCLUSIONS: We developed an accurate model to predict LNM in LACC patients in NACT, based on a ML algorithm requiring few easy-to-collect attributes.

Pregnancy by Oocyte Donation: Reviewing Fetal-Maternal Risks and Complications.

Oocyte donation (OD) has greatly improved over the last three decades, becoming a preferred practice of assisted reproductive technology (ART) for infertile women wishing for motherhood. Through OD, indeed, it has become possible to overcome the physiological limitation due to the ovarian reserve (OR) exhaustion as well as the poor gamete reliability which parallels the increasing age of women. However, despite the great scientific contribution related to the success of OD in the field of infertility, this practice seems to be associated with a higher rate of major risky events during pregnancy as recurrent miscarriage, infections and placental diseases including gestational hypertension, pre-eclampsia and post-partum hemorrhage, as well as several maternal-fetal complications due to gametes manipulation and immune system interaction. Here, we will revisit this questioned topic since a number of studies in the medical literature focus on the successful aspects of the OD procedure in terms of pregnancy rate without, however, neglecting the risks and complications potentially linked to external manipulation or heterologous implantation.

Rapidly evolving pelvic lymphangioleiomyomatosis (LAM) mimicking bilateral hydrosalpinx: report of a rare case and literature review.

Lymphangioleiomyomatosis (LAM) represents a rare neoplasm affecting almost exclusively women of reproductive age. This condition mainly affects the lungs, but extrapulmonary locations such as the pelvis and the retroperitoneum are possible. Clinical evaluation and ultrasound imaging are usually non-specific, and the diagnosis is obtained through surgical excision and histopathological examination. We report a very rare case of abdominal LAM in a young female patient. A thorough literature review of this rare condition with emphasis on gynecologic implications will be presented. The patient was referred for gynecologic consultation due to pelvic pain and infertility. Unfortunately, despite prompt diagnosis and treatment, the course of the disease was severe and led to patient's exitus in a short time. We encountered an extremely rare deadly pathology mimicking a very common gynecologic condition. The gynecologist must always be alert of possible unexpected conditions that will require prompt attention.

A machine learning approach applied to gynecological ultrasound to predict progression-free survival in ovarian cancer patients.

In a growing number of social and clinical scenarios, machine learning (ML) is emerging as a promising tool for implementing complex multi-parametric decision-making algorithms. Regarding ovarian cancer (OC), despite the standardization of features that can support the discrimination of ovarian masses into benign and malignant, there is a lack of accurate predictive modeling based on ultrasound (US) examination for progression-free survival (PFS). This retrospective observational study analyzed patients with epithelial ovarian cancer (EOC) who were followed in a tertiary center from 2018 to 2019. Demographic features, clinical characteristics, information about the surgery and post-surgery histopathology were collected. Additionally, we recorded data about US examinations according to the International Ovarian Tumor Analysis (IOTA) classification. Our study aimed to realize a tool to predict 12 month PFS in patients with OC based on a ML algorithm applied to gynecological ultrasound assessment. Proper feature selection was used to determine an attribute core set. Three different machine learning algorithms, namely Logistic Regression (LR), Random Forest (RFF), and K-nearest neighbors (KNN), were then trained and validated with five-fold cross-validation to predict 12 month PFS. Our analysis included n. 64 patients and 12 month PFS was achieved by 46/64 patients (71.9%). The attribute core set used to train machine learning algorithms included age, menopause, CA-125 value, histotype, FIGO stage and US characteristics, such as major lesion diameter, side, echogenicity, color score, major solid component diameter, presence of carcinosis. RFF showed the best performance (accuracy 93.7%, precision 90%, recall 90%, area under receiver operating characteristic curve (AUROC) 0.92). We developed an accurate ML model to predict 12 month PFS.

Venous Thromboembolism Prophylaxis in Gynecologic Oncology: A MITO-MaNGO Survey.

Cancer-associated thrombosis is the second leading cause of death in cancer patients, and its incidence has been increasing in recent years. This survey was aimed at gathering information regarding the management of thromboembolic prophylaxis within the MITO (Multicenter Italian Trials in Ovarian Cancer)-MaNGO (Mario Negri Gynecologic Oncology) groups. We designed a self-administered, multiple-choice online questionnaire available only for MITO-MaNGO members for one month, starting in May 2022 and ending in June 2022. We processed one response form per center, and 50 responses were analyzed, with most of the respondents (78%) over 40 years old. We found that 82% of them consider thromboembolic prophylaxis in gynecologic oncology to be relevant. In 82% of the centers, a standardized protocol on venous thromboembolism (VTE) prophylaxis is used, which is applied to both patients undergoing surgery and those undergoing chemotherapy. In the remaining 18% of centers, prophylaxis is used exclusively for patients undergoing chemotherapy treatment. Prophylaxis of patients undergoing surgery and chemotherapy treatment is managed in most cases by the surgeon (72%) and oncologist (76%), respectively. Only 26% of respondents use a thromboembolic risk assessment scale, and of these, those used are the Caprini Score (6%), Khorana Score (6%), and Wells Score (2%). The respondents have good knowledge of low-molecular-weight heparin (90%) and average knowledge of dicumarolics (40%), direct oral anticoagulants (DOACs) (68%), and antiplatelet agents (40%). The results of our survey indicate that there is a good awareness of thromboembolic prophylaxis in gynecologic oncology. Nevertheless, it is used less in outpatients than in patients undergoing surgery. Moreover, the thromboembolic risk assessment scores are barely used.

An explainable machine learning model to solid adnexal masses diagnosis based on clinical data and qualitative ultrasound indicators.

BACKGROUND: Accurate characterization of newly diagnosed a solid adnexal lesion is a key step in defining the most appropriate therapeutic approach. Despite guidance from the International Ovarian Tumor Analyzes Panel, the evaluation of these lesions can be challenging. Recent studies have demonstrated how machine learning techniques can be applied to clinical data to solve this diagnostic problem. However, ML models can often consider as black-boxes due to the difficulty of understanding the decision-making process used by the algorithm to obtain a specific result. AIMS: For this purpose, we propose an Explainable Artificial Intelligence model trained on clinical characteristics and qualitative ultrasound indicators to predict solid adnexal masses diagnosis. MATERIALS & METHODS: Since the diagnostic task was a three-class problem (benign tumor, invasive cancer, or ovarian metastasis), we proposed a waterfall classification model: a first model was trained and validated to discriminate benign versus malignant, a second model was trained to distinguish nonmetastatic versus metastatic malignant lesion which occurs when a patient is predicted to be malignant by the first model. Firstly, a stepwise feature selection procedure was implemented. The classification performances were validated on Leave One Out scheme. RESULTS: The accuracy of the three-class model reaches an overall accuracy of 86.36%, and the precision per-class of the benign, nonmetastatic malignant, and metastatic malignant classes were 86.96%, 87.27%, and 77.78%, respectively. DISCUSSION: SHapley Additive exPlanations were performed to visually show how the machine learning model made a specific decision. For each patient, the SHAP values expressed how each characteristic contributed to the classification result. Such information represents an added value for the clinical usability of a diagnostic system. CONCLUSIONS: This is the first work that attempts to design an explainable machine-learning tool for the histological diagnosis of solid masses of the ovary.

Overlap of Suspicious and Non-Suspicious Features in the Ultrasound Evaluations of Leiomyosarcoma: A Single-Center Experience.

Leiomyosarcoma (LMS) is a rare type of mesenchymal tumor. Suspecting LMS before surgery is crucial for proper patient management. Ultrasound is the primary method for assessing myometrial lesions. The overlapping of clinical, laboratory, as well as ultrasound features between fibroids and LMS makes differential diagnosis difficult. We report our single-center experience in ultrasound imaging assessment of LMS patients, highlighting that misleading findings such as shadowing and absent or minimal vascularization may also occur in LMS. To avoid mistakes, a comprehensive evaluation of potentially overlapping ultrasound features is necessary in preoperative ultrasound evaluations of all myometrial tumors.

Use of Sotrovimab in a cohort of pregnant women with a high risk of COVID 19 progression: a single-center experience.

Neutralizing monoclonal antibodies (mAbs) have been shown to reduce disease progression in patients with underlying predisposing conditions. Unfortunately, there is no evidence on the use of Sotrovimab in pregnant women. Herein we present a case series of pregnant women who received mAbs with Sotrovimab following the Italian Drug Agency (AIFA) indications. Since February 1, 2022 all pregnant women - regardless of gestational age - admitted to Obstetrics & Gynaecology of Policlinico University of Bari, with positive nasopharyngeal NAAT for SARS-CoV-2 were screened according to the AIFA indications for Sotrovimab and, if eligible, were proposed for treatment. Data on COVID-19, pregnancy, delivery, newborn outcomes, and adverse events were collected. From February 1 to May 15, 2022, 58 pregnant women were screened. Fifty (86%) patients were eligible, 19 of them (32.7%) denied their consent, in 18 cases (31%), the drug was temporarily unavailable, and the remaining 13 (22%) were treated with Sotrovimab. Out of these 13 patients, 6 (46%) were in the 3rd and 7 (54%) in the 2nd trimester of pregnancy. None of the 13 patients experienced adverse reactions due to Sotrovimab and all had a good clinical outcome. Furthermore, evaluating pre- and post-infusion clinical status and hematochemical profile, a reduction in D-dimers and an increase in SARS-CoV-2 antibodies (p < 0.01) during the 72 h following the infusion were observed. Our data, the first on the use of Sotrovimab in pregnant women, showed the safety and efficacy drug profile and its potential crucial role in preventing COVID-19 disease progression.

A human-interpretable machine learning pipeline based on ultrasound to support leiomyosarcoma diagnosis.

The preoperative evaluation of myometrial tumors is essential to avoid delayed treatment and to establish the appropriate surgical approach. Specifically, the differential diagnosis of leiomyosarcoma (LMS) is particularly challenging due to the overlapping of clinical, laboratory and ultrasound features between fibroids and LMS. In this work, we present a human-interpretable machine learning (ML) pipeline to support the preoperative differential diagnosis of LMS from leiomyomas, based on both clinical data and gynecological ultrasound assessment of 68 patients (8 with LMS diagnosis). The pipeline provides the following novel contributions: (i) end-users have been involved both in the definition of the ML tasks and in the evaluation of the overall approach; (ii) clinical specialists get a full understanding of both the decision-making mechanisms of the ML algorithms and the impact of the features on each automatic decision. Moreover, the proposed pipeline addresses some of the problems concerning both the imbalance of the two classes by analyzing and selecting the best combination of the synthetic oversampling strategy of the minority class and the classification algorithm among different choices, and the explainability of the features at global and local levels. The results show very high performance of the best strategy (AUC = 0.99, F1 = 0.87) and the strong and stable impact of two ultrasound-based features (i.e., tumor borders and consistency of the lesions). Furthermore, the SHAP algorithm was exploited to quantify the impact of the features at the local level and a specific module was developed to provide a template-based natural language (NL) translation of the explanations for enhancing their interpretability and fostering the use of ML in the clinical setting.

Preoperative sonographic assessment of a leiomyoma of the round ligament.

NA.

A Rare Case of Collision Tumours of the Ovary: An Ovarian Serous Cystadenoma Coexisting with Fibrothecoma.

The incidence of epithelial tumours of the ovary ranges from 9-17 per 100,000 and is the highest in high-income countries, with the exception of the Japan. The coexistence of neoplastic Müllerian epithelial and sex cord-stromal elements within a single tumour is extremely rare. We describe the case of a 74-year-old woman with a voluminous left adnexal formation. Pre-operative assessment with ultrasound evaluation made a suspicious diagnosis of benignity of the lesion. Bilateral salpingo-ovariectomy was performed. Intraoperative frozen section analysis results in the diagnosis of fibrothecoma in the context of serous cystadenoma. The diagnosis is confirmed by histological examination. Some authors suggest labelling this phenomenon as collision tumours.

The Application of Sonovaginography for Implementing Ultrasound Assessment of Endometriosis and Other Gynaecological Diseases.

Sonovaginography is a way of assessing gynaecological diseases that can be described as cheap yet accurate and non-invasive. It consists of distention of the vagina with ultrasound gel or saline solution while performing transvaginal sonography to clearly visualize and assess a host of local cervical, as well as any vaginal, disorders. With endometriosis being a steadily growing gynaecological pathology affecting 8-15% of women of fertile age, transvaginal sonography (TVS) can be considered as one of the most accurate and comprehensive imaging techniques in its diagnosis. Nevertheless, the accuracy may vary depending on scan sites. The purpose of this narrative review is to assess the performance of sonovaginography in detecting endometriosis in those sites where TVS has a low sensitivity.

Vulvar Malignant Melanoma: A Narrative Review.

Malignant melanoma is a fatal disease that affects all skin sites. Among these, vulvar melanoma (VM) is a rare gynecological condition that accounts for 5% of all vulvar neoplasms. VM primarily affects older Caucasian women and its relationship to sun exposure is undefined. Diagnosis is defined by biopsy but many clinical, dermatoscopic, and confocal microscopic features can guide doctors. The molecular profile is characterized by the KIT mutation, revealed by all of the technologies that are used (classical sequencing, next-generation sequencing, and immunohistochemical staining). BRAF and NRAS mutations are also common in VM. All of these mutations are possible therapeutic targets. Today, surgery remains the first treatment choice for primary VM. The role of neoadjuvant and adjuvant therapy is scarce and the treatment of relapses is widely debated.