Machine Learning Applied to Pre-Operative Computed-Tomography-Based Radiomic Features Can Accurately Differentiate Uterine Leiomyoma from Leiomyosarcoma: A Pilot Study.

BACKGROUND: The accurate discrimination of uterine leiomyosarcomas and leiomyomas in a pre-operative setting remains a current challenge. To date, the diagnosis is made by a pathologist on the excised tumor. The aim of this study was to develop a machine learning algorithm using radiomic data extracted from contrast-enhanced computed tomography (CECT) images that could accurately distinguish leiomyosarcomas from leiomyomas. METHODS: Pre-operative CECT images from patients submitted to surgery with a histological diagnosis of leiomyoma or leiomyosarcoma were used for the region of interest identification and radiomic feature extraction. Feature extraction was conducted using the PyRadiomics library, and three feature selection methods combined with the general linear model (GLM), random forest (RF), and support vector machine (SVM) classifiers were built, trained, and tested for the binary classification task (malignant vs. benign). In parallel, radiologists assessed the diagnosis with or without clinical data. RESULTS: A total of 30 patients with leiomyosarcoma (mean age 59 years) and 35 patients with leiomyoma (mean age 48 years) were included in the study, comprising 30 and 51 lesions, respectively. Out of nine machine learning models, the three feature selection methods combined with the GLM and RF classifiers showed good performances, with predicted area under the curve (AUC), sensitivity, and specificity ranging from 0.78 to 0.97, from 0.78 to 1.00, and from 0.67 to 0.93, respectively, when compared to the results obtained from experienced radiologists when blinded to the clinical profile (AUC = 0.73 95%CI = 0.62-0.84), as well as when the clinical data were consulted (AUC = 0.75 95%CI = 0.65-0.85). CONCLUSIONS: CECT images integrated with radiomics have great potential in differentiating uterine leiomyomas from leiomyosarcomas. Such a tool can be used to mitigate the risks of eventual surgical spread in the case of leiomyosarcoma and allow for safer fertility-sparing treatment in patients with benign uterine lesions.

Lymph node staging in grade 1-2 endometrioid ovarian carcinoma apparently confined to the ovary: Is it worth?

OBJECTIVE: The aim of this study was to assess the disease-free survival (DFS) and overall survival (OS) of patients with grade 1-2 endometrioid ovarian carcinoma apparently confined to the ovary, according to surgical staging. METHODS: Multicenter, retrospective, observational cohort study. Patients with endometrioid ovarian carcinoma, surgical procedure performed between May 1985 and December 2019, stage pT1 N0/N1/Nx, grade 1-2 were included. Patients were stratified according to lymphadenectomy (defined as removal of any lymph node versus no lymph node assessment), and subgroup analyses according to tumor grade were performed. Kaplan-Meier curves and cox regression analyses were used to perform survival analyses. RESULTS: 298 patients were included. 199 (66.8 %) patients underwent lymph node assessment. Of these, 166 (83.4 %) had unilateral/bilateral pelvic and para-aortic/caval lymphadenectomy. Eleven (5.5 %) patients of those who underwent lymph node assessment showed pathologic metastatic lymph nodes (FIGO stage IIIA1). Twenty-seven patients (9.1 %) had synchronous endometrioid endometrial cancer. After a median follow up of 45 months (95 %CI:37.5-52.5), 5-year DFS and OS of the entire cohort were 89.8 % and 96.2 %, respectively. Age ≤ 51 years (HR=0.24, 95 %CI:0.06-0.91; p = 0.036) and performance of lymphadenectomy (HR=0.25, 95 %CI: 0.07-0.82; p = 0.022) represented independent protective factors toward risk of death. Patients undergoing lymphadenectomy had better 5-year DFS and OS compared to those not receiving lymphadenectomy, 92.0 % versus 85.6 % (p = 0.016) and 97.7 % versus 92.8 % (p = 0.013), respectively. This result was confirmed after exclusion of node-positive patients. When stratifying according to tumor grade (node-positive excluded), patients with grade 2 who underwent lymphadenectomy had better 5-year DFS and OS than those without lymphadenectomy (93.0 % versus 83.1 %, p = 0.040 % and 96.5 % versus 90.6 %, p = 0.037, respectively). CONCLUSION: Staging lymphadenectomy in grade 2 endometrioid ovarian carcinoma patients was associated with improved DFS and OS. Grade 1 and grade 2 might be considered as two different entities, which could benefit from different approach in terms of surgical staging. Prospective studies, including molecular profiles are needed to confirm the survival drivers in this rare setting.

A Radiomic-Based Machine Learning Model Predicts Endometrial Cancer Recurrence Using Preoperative CT Radiomic Features: A Pilot Study.

BACKGROUND: Current prognostic models lack the use of pre-operative CT images to predict recurrence in endometrial cancer (EC) patients. Our study aimed to investigate the potential of radiomic features extracted from pre-surgical CT scans to accurately predict disease-free survival (DFS) among EC patients. METHODS: Contrast-Enhanced CT (CE-CT) scans from 81 EC cases were used to extract the radiomic features from semi-automatically contoured volumes of interest. We employed a 10-fold cross-validation approach with a 6:4 training to test set and utilized data augmentation and balancing techniques. Univariate analysis was applied for feature reduction leading to the development of three distinct machine learning (ML) models for the prediction of DFS: LASSO-Cox, CoxBoost and Random Forest (RFsrc). RESULTS: In the training set, the ML models demonstrated AUCs ranging from 0.92 to 0.93, sensitivities from 0.96 to 1.00 and specificities from 0.77 to 0.89. In the test set, AUCs ranged from 0.86 to 0.90, sensitivities from 0.89 to 1.00 and specificities from 0.73 to 0.90. Patients classified as having a high recurrence risk prediction by ML models exhibited significantly worse DSF (p-value < 0.001) across all models. CONCLUSIONS: Our findings demonstrate the potential of radiomics in predicting EC recurrence. While further validation studies are needed, our results underscore the promising role of radiomics in forecasting EC outcomes.

Optimal number of neoadjuvant chemotherapy cycles prior to interval debulking surgery in advanced epithelial ovarian cancer: a systematic review and meta-analysis of progression-free survival and overall survival.

OBJECTIVE: Neoadjuvant chemotherapy (NACT) represents a treatment option in patients with advanced epithelial ovarian cancer (AEOC) who are not good candidates for primary debulking surgery. Usually, 3 cycles of chemotherapy before surgery have been considered the best option for patient survival, although quite often some patients receive more than 3 cycles. The aim of this systematic review and meta-analysis was to identify the optimal number of NACT cycles reporting better survival in AEOC patients. METHODS: PubMed, Cochrane Library, and Scopus were searched for original articles that analyzed the relationship between the number of chemotherapy cycles and clinical outcomes in AEOC patients before interval debulking surgery (IDS). The main outcomes were progression-free survival (PFS) and overall survival (OS). RESULTS: A total of 22 studies comprising 7,005 patients diagnosed with AEOC were included in our analysis. In terms of survival, the reviewed studies dividing the patients in ≤3 NACT cycles vs. >3, showed a trend for a decrease in PFS and a significant reduction in OS with an increasing number of cycles, while a difference in both PFS and OS was revealed if early IDS included patients with 4 NACT cycles. These results should be interpreted with caution due to the complex characteristics of AEOC patients. CONCLUSION: In conclusion, our review and meta-analysis revealed that there is not enough evidence to determine the optimal number of NACT treatments before surgery. Further research in the form of well-designed randomized controlled trials is necessary to address this issue. TRIAL REGISTRATION: PROSPERO Identifier: CRD42022334959.

Can miRNAs be useful biomarkers in improving prognostic stratification in endometrial cancer patients? An update review.

Endometrial cancer (EC) is the most common gynecological cancer, with annual incidence rates in Western countries ranging between 15 and 25 per 100 000 women. About 15% to 20% of patients with EC have high-risk disease and follow an aggressive clinical course. Unfortunately, the assessment of histologic parameters is poorly reproducible and conventional clinicopathological and molecular features do not reliably predict either the patient's response to the available treatments or the definition of personalized therapeutic approaches. In this context, the identification of novel diagnostic and prognostic biomarkers, which can be integrated in the current classification schemes, represents an unmet clinical need and an important challenge. miRNAs are key players in cancer by regulating the expression of specific target genes. Their role in EC, in association with clinical and prognostic tumor biomarkers, has been investigated but, so far, with little consensus among the studies. The present review aims to describe the recent advances in miRNAs research in EC taking into consideration the current classification schemes and to highlight the most promising miRNAs. Finally, a perspective point of view sheds light on the challenges ahead in the landscape of EC.

Electrochemotherapy in Vulvar Cancer and Cisplatin Combined with Electroporation. Systematic Review and In Vitro Studies.

Electrochemotherapy (ECT) is an emerging treatment for solid tumors and an attractive research field due to its clinical results. This therapy represents an alternative local treatment to the standard ones and is based on the tumor-directed delivery of non-ablative electrical pulses to maximize the action of specific cytotoxic drugs such as cisplatin (CSP) and bleomycin (BLM) and to promote cancer cell death. Nowadays, ECT is mainly recommended as palliative treatment. However, it can be applied to a wide range of superficial cancers, having an impact in preventing or delaying tumor progression and therefore in improving quality of life. In addition, during the natural history of the tumor, early ECT may improve patient outcomes. Our group has extensive clinical and research experience on ECT in vulvar tumors in the palliative setting, with 70% overall response rate. So far, in most studies, ECT was based on BLM. However, the potential of CSP in this setting seems interesting due to some theoretical advantages. The purpose of this report is to: (i) compare the efficacy of CSP and BLM-based ECT through a systematic literature review; (ii) report the results of our studies on CSP-resistant squamous cell tumors cell lines and the possibility to overcome chemoresistance using ECT; (iii) discuss the future ECT role in gynecological tumors and in particular in vulvar carcinoma.

Classification Systems of Endometrial Cancer: A Comparative Study about Old and New.

Endometrial cancer is the most common gynecological malignancy of the female reproductive organs. Historically it was divided into type I and type II, until 2013 when the Cancer Genome Atlas molecular classification was proposed. Here, we applied the different classification types on our endometrial cancer patient cohort in order to identify the most predictive one. We enrolled 117 endometrial cancer patients available for the study and collected the following parameters: age, body mass index, stage, menopause, Lynch syndrome status, parity, hypertension, type of localization of the lesion at hysteroscopy, type of surgery and complications, and presence of metachronous or synchronous tumors. The tumors were classified according to the European Society for Medical Oncology, Proactive Molecular Risk Classifier for Endometrial Cancer, Post-Operative Radiation Therapy in Endometrial Carcinoma, and Cancer Genome Atlas classification schemes. Our data confirmed that European Society for Medical Oncology risk was the strongest predictor of prognosis in our cohort. The parameters correlated with poor prognosis were the histotype, FIGO stage, and grade. Our study cohort shows that risk stratification should be based on the integration of histologic, clinical, and molecular parameters.