Purpose: To predict deep myometrial infiltration (DMI), clinical risk category, histological type, and lymphovascular space invasion (LVSI) in women with endometrial cancer using machine learning classification methods based on clinical and image signatures from T2-weighted MR images. Methods: A training dataset containing 413 patients and an independent testing dataset consisting of 82 cases were employed in this retrospective study. Manual segmentation of the whole tumor volume on sagittal T2-weighted MRI was performed. Clinical and radiomic features were extracted to predict: (i) DMI of endometrial cancer patients, (ii) endometrial cancer clinical high-risk level, (iii) histological subtype of tumor, and (iv) presence of LVSI. A classification model with different automatically selected hyperparameter values was created. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, F1 score, average recall, and average precision were calculated to evaluate different models. Results: Based on the independent external testing dataset, the AUCs for DMI, high-risk endometrial cancer, endometrial histological type, and LVSI classification were 0.79, 0.82, 0.91, and 0.85, respectively. The corresponding 95% confidence intervals (CI) of the AUCs were [0.69, 0.89], [0.75, 0.91], [0.83, 0.97], and [0.77, 0.93], respectively. Conclusion: It is possible to classify endometrial cancer DMI, risk, histology type, and LVSI using different machine learning methods.

Background: Determination of survival time in women with endometrial cancer using clinical features remains imprecise. Features from MRI may improve the survival estimation allowing improved treatment planning.Purpose: To identify clinical features and imaging signatures on T2‐weighted MRI that can be used in an integrated model to estimate survival time for endometrial cancer subjects.Study Type: Retrospective.Population: Four hundred thirteen patients with endometrial cancer as training (N = 330, 66.41 ± 11.42 years) and validation (N = 83, 67.60 ± 11.89 years) data and an independent set of 82 subjects as testing data (63.26 ± 12.38 years).Field Strength/Sequence: 1.5‐T and 3‐T scanners with sagittal T2‐weighted spin echo sequence.Assessment: Tumor regions were manually segmented on T2‐weighted images. Features were extracted from segmented masks, and clinical variables including age, cancer histologic grade and risk score were included in a Cox proportional hazards (CPH) model. A group least absolute shrinkage and selection operator method was implemented to determine the model from the training and validation datasets.Statistical Tests: A likelihood‐ratio test and decision curve analysis were applied to compare the models. Concordance index (CI) and area under the receiver operating characteristic curves (AUCs) were calculated to assess the model.Results: Three radiomic features (two image intensity and volume features) and two clinical variables (age and cancer grade) were selected as predictors in the integrated model. The CI was 0.797 for the clinical model (includes clinical variables only) and 0.818 for the integrated model using training and validation datasets, the associated mean AUC value was 0.805 and 0.853. Using the testing dataset, the CI was 0.792 and 0.882, significantly different and the mean AUC was 0.624 and 0.727 for the clinical model and integrated model, respectively.Data Conclusion: The proposed CPH model with radiomic signatures may serve as a tool to improve estimated survival time in women with endometrial cancer.Evidence Level: 4Technical Efficacy: Stage 2

Introduction Human papillomavirus (HPV) is necessary but not sufficient for cervical cancer development. During cervical carcinogenesis, methylation levels increase across host and HPV DNA. DNA methylation has been proposed as a test to diagnose cervical intraepithelial neoplasia (CIN); we present a protocol to evaluate the accuracy of methylation markers to detect high-grade CIN and cervical cancer. Methods and analysis We will search electronic databases (Medline, Embase and Cochrane Library), from inception, to identify studies examining DNA methylation as a diagnostic marker for CIN or cervical cancer, in a cervical screening population. The primary outcome will be to assess the diagnostic test accuracy of host and HPV DNA methylation for high-grade CIN; the secondary outcomes will be to examine the accuracy of different methylation cut-off thresholds, and accuracy in high-risk HPV positive women. Our reference standard will be histology. We will perform meta-analyses using Cochrane guidelines for diagnostic test accuracy. We will use the number of true positives, false negatives, true negatives and false positives from individual studies. We will use the bivariate mixed effect model to estimate sensitivity and specificity with 95% CIs; we will employ different bivariate models to estimate sensitivity and specificity at different thresholds if sufficient data per threshold. For insufficient data, the hierarchical summary receiver operating curve model will be used to calculate a summary curve across thresholds. If there is interstudy and intrastudy variation in thresholds, we will use a linear mixed effects model to calculate the optimum threshold. If few studies are available, we will simplify models by assuming no correlation between sensitivity and specificity and perform univariate, random-effects meta-analysis. We will assess the quality of studies using QUADAS-2 and QUADAS-C. Ethics and dissemination Ethical approval is not required. Results will be disseminated to academic beneficiaries, medical practitioners, patients and the public. PROSPERO registration number CRD42022299760.

Primary malignant melanoma (MM) of the cervix uteri is a rare and aggressive malignancy of the female reproductive tract. Considering that clinical data on this cancer are scarce, we aimed to comprehensively examine the currently available literature and provide an overview of the reported cases of cervical MM focusing on the clinical characteristics, diagnosis and therapeutic management. We conducted a systematic review of the literature by screening three electronic databases until June 2022. The critical appraisal checklist provided by the Joanna Briggs Institute was employed to evaluate the overall quality of the studies. We included 96 reports, which comprised 137 patients diagnosed with MM of the cervix. The mean age of the patients was 56.5 (median: 58, age range: 33–88). Data regarding menopausal status were provided for 98 patients with 15 being premenopausal and 83 being postmenopausal. The most common presenting symptom was vaginal bleeding (83%, 100/121). Biopsy (either excisional or punch biopsy) was used as the first diagnostic modality in most of the patients (67%, 64/95), followed by cytology (18%, 17/95). In 74 cases, the FIGO staging system for cervical cancer was used with the most common stage being FIGO stage I (38%, 28/74), followed by FIGO stage II (36%, 27/74), FIGO stage III (19%, 14/74) and FIGO stage IV (7%, 5/74). Most of the patients were managed surgically (90%, 119/131) with a hysterectomy (either radical or total), and a salpingo-oophorectomy with/without lymphadenectomy was the most common approach utilized (40%, 48/119). The data of clinical outcomes were provided for 105 patients, of whom 61 died (58%, 61/105) and 44 survived (42%, 44/105). Knowledge regarding the rare occurrence of MM in the cervix and the increased awareness of clinicians can prevent clinical misdiagnosis and ultimately improve further the clinical outcomes of patients developing this rare malignancy.

Human papillomavirus (HPV) is detected in 99.7% of cervical cancers. Current vaccines target types 16 and 18. Prior to vaccination implementation, a prospective cohort study was conducted to determine baseline HPV prevalence in unvaccinated women in Wales; after HPV16 and HPV18, HPV 51 was found to be most prevalent. This study aimed to re-assess the unexpected high prevalence of HPV 51 and consider its potential for type-replacement. Two hundred HPV 51 positive samples underwent re-analysis by repeating the original methodology using HPV 51 GP5+/6+ PCR-enzyme immunoassay, and additionally a novel assay of HPV 51 E7 PCR. Data were correlated with age, social deprivation and cytology. Direct repeat of HPV 51 PCR-EIA identified 146/195 (75.0%) samples as HPV 51 positive; E7 PCR identified 166/195 (85.1%) samples as HPV 51 positive. HPV 51 prevalence increased with cytological grade. The prevalence of HPV 51 in the pre-vaccinated population was truly high. E7 DNA assays may offer increased specificity for HPV genotyping. Cross-protection of current vaccines against less-prevalent HPV types warrants further study. This study highlights the need for longitudinal investigation into the prevalence of non-vaccine HPV types, especially those phylogenetically different to vaccine types for potential type-replacement. Ongoing surveillance will inform future vaccines.

Background: The World Health Organization (WHO) aims to eliminate cervical cancer by 2030 through a global strategy, centred on high-risk Human papillomavirus (hrHPV)-based screening and treatment. Implementing these strategies in low-resource settings remains challenging, due to barriers associated with limited healthcare infrastructure and patient awareness. Self-sampling for hrHPV has shown higher acceptability and similar diagnostic accuracy compared to clinician-taken samples. This study proposes a protocol to evaluate the clinical efficacy of a cervical cancer screening program utilising hrHPV self-sampling in Ghana. Methods and Analysis: 1000 non-pregnant women aged 30-65 years will be invited to self-collect hrHPV samples. Those testing hrHPV positive will undergo visual inspection with acetic acid. Those diagnosed with high-grade squamous intraepithelial lesions will be offered ablation. In any case where there is a suspicion of invasion, or equivocal diagnosis, biopsies will be taken. Follow-up for women who are test positive for hrHPV and/or undergo treatment, will involve hrHPV self-sampling after 6 months. HrHPV-negative women will rescreen after 3 years. Biopsies will be taken where immediate treatment is not suitable, and women with confirmed or suspected invasive cervical carcinoma will be referred for surgical and/or oncological care. The primary outcome will be the proportion of women successfully screened, defined as the proportion of women with a valid HPV test result out of those invited to attend cervical screening. Secondary outcomes include screening uptake, disease detection rate, hrHPV genotype prevalence, treatment acceptance rate, successful treatment response, missed disease during treatment, number lost to follow-up, and disease recurrence. Discussion: In low-resource settings, hrHPV self-sampling offers an accessible method to increase screening uptake. This study will inform strategies for broader implementation of cervical cancer screening and contribute to achieving the WHO’s goal of elimination by 2030. Trial Registration: Ethical approval for this study was obtained from the Kintampo Health Research Centre Institutional Ethics Committee (IEC), Bono East, Ghana, West Africa, on 24 May 2024 (IEC IRB Registration No. 0004854; Study ID: KHRCIEC/2024-03).