Marianna Ciancia

Value of frozen section to tailor surgical staging in apparent early-stage epithelial ovarian cancer

Frozen section (FS) has been shown to have high accuracy in determining ovarian malignancy. However, its utility in guiding surgical approaches, particularly, lymph node staging, for early-stage epithelial ovarian cancer remains unclear. This study aimed to evaluate the post-test positive probability of FSs in identifying cases requiring lymph node or peritoneal staging. The secondary aims were sensitivity, specificity, and accuracy assessments. This retrospective study analyzed patients undergoing surgery for early-stage epithelial ovarian cancer with FS performed on ovarian masses between July 2007 and March 2023 at a tertiary center. The FS results were compared with the final histology (gold standard paraffin sections). The FS cases were categorized based on further actions as follows: lymph node staging (type A), peritoneal staging only (type B), or no additional procedures (type C). The patients were divided into group 1 (requiring lymph node and peritoneal staging) and group 2 (requiring only peritoneal staging). A comparison between specialized and general pathology diagnoses was also performed. Incorrect FS assessments were classified as under-diagnosed or over-diagnosed. Of the 715 patients, group 1 had appropriate staging in 425 of 447 cases, with 4.9% over-treatment. In group 2, staging was correct in 109 of 195 cases, with 44.1% under-treatment. For type A FSs, the post-test positive probability was 95% (95% CI 93% to 97%), with sensitivity, specificity, and accuracy rates of 76.4%, 86.1%, and 78.6%, respectively. For type B FSs, the post-test positive probability was 56% (95% CI 50% to 61%), with sensitivity, specificity, and accuracy rates of 68.6%, 84.5%, and 81%, respectively. There was no significant difference in the agreement between the specialized and general pathology groups (p = 0.92). Frozen sections suggestive of a cancer diagnosis requiring peritoneal and lymph node staging in a population with apparent early-stage epithelial ovarian cancer are highly reliable. In the case of FSs suggesting only peritoneal staging, malignancy is frequently underestimated.

Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta‐analysis

AbstractIntroductionWe present the state of the art of ultrasound‐based machine learning (ML) radiomics models in the context of ovarian masses and analyze their accuracy in differentiating between benign and malignant adnexal masses.Material and MethodsWeb of Science, PubMed, and Scopus databases were searched. All studies were imported into RAYYAN QCRI software. All studies that developed and internally or externally validated ML models using only radiomics features extracted from ultrasound images were included. The overall quality of the included studies was assessed using the QUADAS‐AI tool. Summary sensitivity and specificity analyses with corresponding 95% confidence intervals (CIs) were reported.Results12 studies developed ML models including only radiomics features extracted from ultrasound images, and six of them were included in the meta‐analysis. The overall sensitivity and specificity for differentiating benign from malignant adnexal masses were 0.80 (95% CI 0.74–0.87) and 0.86 (95% CI 0.80–0.90), respectively, in the validation set. All studies demonstrated a high risk of bias in subject selection (e.g., lack of details on image sources or scanner models; absence of image preprocessing), and the majority also showed a high risk in the index test (e.g., models were not validated on external datasets) domain. In contrast, the risk of bias was generally low for the reference standard (i.e., most studies used a reference that accurately identified the target condition) and the testing workflow (i.e., the time interval between the index test and reference standard was appropriate) domains.ConclusionsThe good performance of ultrasound‐based radiomics models in the validation set supports that radiomics is worth exploring to improve the diagnosis of adnexal masses. So far, the studies have a high risk of bias due to the small sample size, single‐setting design, and no external validation included.

Role of artificial intelligence applied to ultrasound in endometrial cancer: a systematic review

To synthesize the application of artificial intelligence (AI) in ultrasound imaging for the assessment of endometrial cancer, with a focus on methodological approaches and diagnostic accuracy in predicting different outcomes. PubMed, Scopus, and Web of Science databases were searched from inception up to January 16, 2025. Studies applying AI to ultrasound imaging in the diagnosis, staging, and management of endometrial malignant pathology were included. Quality assessment of the retrieved studies was performed using the Quality Assessment Tool for Artificial Intelligence-Centered Diagnostic Test Accuracy Studies (QUADAS-AI). The protocol was registered in the PROSPERO database (registration record CRD42025648961). Thirty studies were included: 18 (60%) distinguished between benign and malignant endometrial lesions, 4 (13.3%) focused on predicting lymph node metastases, 3 (10%) evaluated myometrial invasion, and 2 (6.6%) classified tumor risk. Additionally, 2 studies assessed disease-free survival (6.6%), while another developed a model for the automated identification of endometrial lesions (3.3%). According to QUADAS-AI, most studies were at high risk of bias for subject selection (eg, sample size not specified, imaging preprocessing not performed) (27/30, 90%) and the index test (no external validation) (27/30, 90%) domains, and at low risk of bias for the reference standard (target condition correctly classified by the reference standard) (29/30, 97%) and the workflow (reasonable time between index test and reference standard) (29/30, 97%) domains. Models were externally validated in 3/30 studies (10%), internally cross-validated in 3/30 (10%), internally hold-out validated in 13/30 (43.3%), and not validated in 11/30 (36.7%). Published research on AI applications in ultrasound for endometrial cancer primarily focuses on developing classification models to distinguish benign from malignant endometrial lesions and to stage the disease. Overall, ultrasound-based AI models have demonstrated strong predictive performance. However, most studies are limited by small sample sizes and a lack of external validation.

Diagnostic performance of ultrasound-guided biopsy for detecting recurrent or persistent cervical cancer after chemoradiotherapy: a prospective, single-center study

This study aimed to compare the feasibility, diagnostic accuracy, and sample adequacy of trans-vaginal ultrasound-guided biopsy versus per-vagina biopsy for detecting persistent or recurrent pelvic disease after chemoradiotherapy for locally advanced cervical cancer. Procedure-related pain was also evaluated. This prospective, single-center diagnostic study conducted at Fondazione Policlinico Universitario Agostino Gemelli IRCCS (Rome, Italy) from November 2019 to September 2024 included consecutive patients with clinical or radiologic suspicion of persistent or recurrent cervical cancer after chemoradiotherapy. Patients undergoing trans-vaginal ultrasound-guided biopsy and per-vagina biopsy (index tests) were analyzed. Histology from pelvic exenteration or follow-up imaging when surgery was not performed served as the reference standard. Accuracy, sensitivity, and specificity were calculated for each index test and compared using the McNemar test. Feasibility was defined as the rate of successfully performed biopsies and adequacy as the proportion of samples yielding a conclusive histologic diagnosis. Fifty-three patients were included. A total of 44 of 53 patients (83.0%) underwent pelvic exenteration, whereas 9 of 53 (17.0%) underwent imaging follow-up. Ultrasound-guided biopsy was feasible in 52 of 53 cases (98.1%) compared with 40 of 53 cases (75.5%) for per-vagina biopsy. All samples obtained from both techniques were adequate. Ultrasound-guided biopsy showed a sensitivity of 0.84, specificity of 1.00, and accuracy of 0.87. Per-vagina biopsy showed a sensitivity of 0.55, specificity of 0.86, and accuracy of 0.60. Among 39 paired feasible cases, specificity did not differ significantly between the 2 techniques (p = .27); however, ultrasound-guided biopsy showed significantly higher sensitivity and accuracy (p = .022 and p = .021, respectively). Ultrasound-guided biopsy appeared to be a feasible method for histologic confirmation in suspected persistent or recurrent cervical cancer after chemoradiotherapy. It demonstrated superior diagnostic accuracy over per-vagina biopsy and holds potential for routine clinical application. Successful integration into clinical practice requires appropriate clinician training and access to specialized equipment.

Ultrasound-based preoperative assessment for cervical cancer: a pragmatic staging and treatment-planning strategy adaptable to diverse resource settings.

Cervical cancer remains a major global health burden, particularly in low- and middle-income countries, where access to advanced imaging and treatment is often limited. While magnetic resonance imaging is considered the gold standard for loco-regional staging, recent evidence supports transvaginal/transrectal ultrasound as an accurate and cost-effective alternative when performed by trained sonographers and clinicians. Its portability and affordability make ultrasound particularly valuable in resource-constrained settings. In this paper, we present a pragmatic diagnostic and clinical strategy for managing cervical cancer in contexts where magnetic resonance imaging, sentinel lymph node mapping, and radiotherapy are not available. Building on a structured checklist of ultrasound-based parameters, we propose simple, tailored pathways to guide decisions regarding upfront surgery, neoadjuvant chemotherapy, pelvic exenteration, or palliative chemotherapy and supportive care. The approach emphasizes accurate staging through transvaginal/transrectal ultrasound combined with transabdominal scanning, allowing identification of tumor size, local extension, lymph node status, and clear contraindications to surgery. By promoting ultrasound as a reliable tool for loco-regional staging and treatment planning, we aim to improve access to cervical cancer care in low- and middle-income countries and to lay the groundwork for future prospective multi-center studies.

Developing and validating ultrasound‐based machine‐learning models incorporating radiomics features to predict malignancy in adnexal masses

ABSTRACT Objective The primary aim of this study was to develop and internally validate ultrasound‐based radiomics models to discriminate between all types of benign and malignant adnexal masses. The secondary aim was to compare the performance of the radiomics models with that of the Assessment of Different NEoplasias in the adneXa (ADNEX) model. Methods This was a retrospective, observational, single‐center study, for which all patients with an adnexal mass that were included in the ongoing International Ovarian Tumor Analysis phase‐5 and phase‐7 studies and were examined using ultrasound between January 2012 and December 2023 at Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy, were eligible for inclusion. Inclusion criteria were: adnexal mass detected by ultrasound; surgical removal of the adnexal mass within 180 days after the ultrasound examination; histological confirmation of an adnexal mass; and absence of a synchronous malignant tumor. Patients without digital ultrasound images saved in DICOM format were excluded. The patient cohort was split randomly into training and validation sets using a stratified split with a ratio of 70:30, to preserve the proportion of benign and malignant cases in the two sets. Two machine‐learning models for discriminating between benign and malignant adnexal masses were built using one image per tumor, with 5‐fold cross‐validation for hyperparameter tuning, and were tested on the validation set. The variables used in model building were patient age, serum CA 125 level and the radiomics features that differed significantly between benign and malignant tumors (determined using the Mann–Whitney U ‐test with Benjamini–Hochberg correction) and were not redundant based on Pearson correlation analysis. Histology was the reference standard. We assessed the discriminative performance of the radiomics models using the area under the receiver‐operating‐characteristics curve (AUC) and classification performance using sensitivity and specificity at the optimal cut‐off of each model to classify the mass as malignant, as determined by Youden's index. The diagnostic performance of the developed radiomics models was compared with that of the ADNEX model (AUC, sensitivity and specificity at the 10% risk‐of‐malignancy cut‐off, which is the recommended threshold for clinical use of the ADNEX model). Results In total, 4501 patients met the inclusion criteria. Among these, 2428 patients were excluded owing to an absence of ultrasound images or images unsuitable for radiomics analysis. Overall, a total of 2073 patients were included in the analysis, of whom 803 (38.7%) had a histologically confirmed malignant tumor. In the validation set ( n  = 622, including 254 malignancies), the clinical–radiomics model trained using the eXtreme Gradient Boosting algorithm, including age, serum CA 125 level and 14 selected radiomics features, achieved the highest performance, with an AUC of 0.89 (95% CI, 0.86–0.92), sensitivity of 0.83 (95% CI, 0.79–0.88) and specificity of 0.81 (95% CI, 0.77–0.85) at the optimal cut‐off (31% risk of malignancy, based on Youden's index). At a 10% risk‐of‐malignancy cut‐off, it had a sensitivity of 0.94 (95% CI, 0.91–0.97) and specificity of 0.48 (95% CI, 0.42–0.53). The ADNEX model had an AUC of 0.95 (95% CI, 0.93–0.97), sensitivity of 0.97 (95% CI, 0.95–0.99) and specificity of 0.72 (95% CI, 0.68–0.77) at the 10% risk‐of‐malignancy cut‐off in the validation set. Conclusions Our results support further exploration of radiomics analysis for distinguishing between benign and malignant adnexal masses in larger study populations. Future studies should consider using multiple images per tumor and testing alternative model‐building methods, and should perform external validation to assess the generalizability of the radiomics models. © 2026 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.