ESGO/ISUOG/IOTA/ESGE Consensus Statement on preoperative diagnosis of ovarian tumours

Role of artificial intelligence applied to ultrasound in gynecology oncology: A systematic review

The aim of this paper was to explore the role of artificial intelligence (AI) applied to ultrasound imaging in gynecology oncology. Web of Science, PubMed, and Scopus databases were searched. All studies were imported to RAYYAN QCRI software. The overall quality of the included studies was assessed using QUADAS-AI tool. Fifty studies were included, of these 37/50 (74.0%) on ovarian masses or ovarian cancer, 5/50 (10.0%) on endometrial cancer, 5/50 (10.0%) on cervical cancer, and 3/50 (6.0%) on other malignancies. Most studies were at high risk of bias for subject selection (i.e., sample size, source, or scanner model were not specified; data were not derived from open-source datasets; imaging preprocessing was not performed) and index test (AI models was not externally validated) and at low risk of bias for reference standard (i.e., the reference standard correctly classified the target condition) and workflow (i.e., the time between index test and reference standard was reasonable). Most studies presented machine learning models (33/50, 66.0%) for the diagnosis and histopathological correlation of ovarian masses, while others focused on automatic segmentation, reproducibility of radiomics features, improvement of image quality, prediction of therapy resistance, progression-free survival, and genetic mutation. The current evidence supports the role of AI as a complementary clinical and research tool in diagnosis, patient stratification, and prediction of histopathological correlation in gynecological malignancies. For example, the high performance of AI models to discriminate between benign and malignant ovarian masses or to predict their specific histology can improve the diagnostic accuracy of imaging methods.

Diagnostic Performance of Ultrasonography-Based Risk Models in Differentiating Between Benign and Malignant Ovarian Tumors in a US Cohort

Importance

Ultrasonography-based risk models can help nonexpert clinicians evaluate adnexal lesions and reduce surgical interventions for benign tumors. Yet, these models have limited uptake in the US, and studies comparing their diagnostic accuracy are lacking.

Objective

To evaluate, in a US cohort, the diagnostic performance of 3 ultrasonography-based risk models for differentiating between benign and malignant adnexal lesions: International Ovarian Tumor Analysis (IOTA) Simple Rules with inconclusive cases reclassified as malignant or reevaluated by an expert, IOTA Assessment of Different Neoplasias in the Adnexa (ADNEX), and Ovarian-Adnexal Reporting and Data System (O-RADS).

Design, Setting, and Participants

This retrospective diagnostic study was conducted at a single US academic medical center and included consecutive patients aged 18 to 89 years with adnexal masses that were managed surgically or conservatively between January 2017 and October 2022.

Exposure

Evaluation of adnexal lesions using the Simple Rules, ADNEX, and O-RADS.

Main Outcomes and Measures

The main outcome was diagnostic performance, including area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, positive and negative predictive values, and positive and negative likelihood ratios. Surgery or follow-up were reference standards. Secondary analyses evaluated the models' performances stratified by menopause status and race.

Results

The cohort included 511 female patients with a 15.9% malignant tumor prevalence (81 patients). Mean (SD) ages of patients with benign and malignant adnexal lesions were 44.1 (14.4) and 52.5 (15.2) years, respectively, and 200 (39.1%) were postmenopausal. In the ROC analysis, the AUCs for discriminative performance of the ADNEX and O-RADS models were 0.96 (95% CI, 0.93-0.98) and 0.92 (95% CI, 0.90-0.95), respectively. After converting the ADNEX continuous individualized risk into the discrete ordinal categories of O-RADS, the ADNEX performance was reduced to an AUC of 0.93 (95% CI, 0.90-0.96), which was similar to that for O-RADS. The Simple Rules combined with expert reevaluation had 93.8% sensitivity (95% CI, 86.2%-98.0%) and 91.9% specificity (95% CI, 88.9%-94.3%), and the Simple Rules combined with malignant classification had 93.8% sensitivity (95% CI, 86.2%-98.0%) and 88.1% specificity (95% CI, 84.7%-91.0%). At a 10% risk threshold, ADNEX had 91.4% sensitivity (95% CI, 83.0%-96.5%) and 86.3% specificity (95% CI, 82.7%-89.4%) and O-RADS had 98.8% sensitivity (95% CI, 93.3%-100%) and 74.4% specificity (95% CI, 70.0%-78.5%). The specificities of all models were significantly lower in the postmenopausal group. Subgroup analysis revealed high performances independent of race.

Conclusions and Relevance

In this diagnostic study of a US cohort, the Simple Rules, ADNEX, and O-RADS models performed well in differentiating between benign and malignant adnexal lesions; this outcome has been previously reported primarily in European populations. Risk stratification models can lead to more accurate and consistent evaluations of adnexal masses, especially when used by nonexpert clinicians, and may reduce unnecessary surgeries.

Ovarian Masses: The Value of Acoustic Shadowing on Ultrasound Examination

Adnexal lesions are a common finding in women and pose a clinical challenge since ovarian cancer is a highly lethal disease. However, most adnexal masses are benign, benefiting from a more conservative approach. In preoperative assessment, transvaginal ultrasound plays a key role in evaluating morphologic features that correlate with the risk of malignancy. The acoustic shadow is the loss of echo behind sound-absorbing components, such as calcifications or fibrous tissues, which are predominantly found in benign lesions. However, recognizing the acoustic shadow is a difficult skill to master, and its usefulness may be underappreciated.

Transvaginal ultrasound-guided biopsy in patients with suspicious primary advanced tubo-ovarian carcinoma

OBJECTIVE

To assess the accuracy of pathological diagnosis by transvaginal ultrasound-guided biopsy versus surgery in patients with suspicious primary advanced tubo-ovarian carcinoma. The Feasibility, adequacy, and safety of the procedure were also evaluated.

METHODS

Consecutive women with pre-operative suspicious primary advanced tubo-ovarian carcinoma presenting between July 2019 and September 2021 were enrolled. Accuracy was calculated including only cases who underwent surgery. Feasibility was defined as the number of cases in which ultrasound-guided biopsy was possible according to tumor characteristics (morphology and site). Adequacy was defined as the number of conclusive diagnoses out of the samples collected. Safety was defined by the number of major complications which were defined as hospitalization, surgery, and/or blood transfusion.

RESULTS

A total of 278 patients were eligible for the study; 158 were enrolled, while 120 were excluded for logistic reasons or patient refusal. Ultrasound-guided biopsy was not feasible in 30 (19%) patients. The samples obtained in the remaining 128 patients were all adequate (100%), and no major complications were noted. A total of 26 (20%) patients started neoadjuvant chemotherapy on the basis of the diagnosis obtained by ultrasound, whereas 102 (80%) patients underwent surgery. Accuracy of ultrasound-guided biopsy versus surgery was 94% (96/102), with six false negative cases at ultrasound (6%). Site (prevesical peritoneum) and size (<8 mm) of the nodules resulted as major predictive factors for ultrasound-guided biopsy failure (false negative). Ultrasound-guided biopsy correctly identified 86 primary invasive tubo-ovarian carcinomas and 10 metastatic tumors.

CONCLUSION

Ultrasound-guided biopsy is a feasible, safe, and accurate method to provide histological diagnosis in suspicious advanced tubo-ovarian cancer patients.

Evaluation of Adnexal Masses: The IOTA Concept

Ovarian lesions have a wide range of sonomorphological features with numerous different underlying benign and malignant histologies. Based on the studies conducted by the International Ovarian Tumor Analysis (IOTA) group, ovarian masses can currently be reliably characterized by ultrasound. In the following article, we explain how to use the IOTA terms and definitions and we provide insight into how to safely triage patients with an ovarian mass.

Improving diagnostic strategies for ovarian cancer in Filipino women using ultrasound imaging and a multivariate index assay

OBJECTIVE

To evaluate the clinical performance and overall utility of imaging and biomarker assays in discriminating between benign and malignant ovarian masses in a Filipino population.

METHODS

This is a prospective cohort study among Filipino women undergoing assessment for an ovarian mass in a tertiary center. All included patients underwent a physical examination before level III specialist ultrasonographic and Doppler evaluation, multivariate index assay (MIA2G), and surgery for an adnexal mass. Ovarian tumors were classified as high-risk for malignancy based on the International Ovarian Tumour Analysis (IOTA) - Logistic Regression 2 (LR2) score. The ovarian imaging and biomarker results were correlated with the reference standard: histological findings.

RESULTS

Among the 379 women with adnexal masses enrolled in this study, 291 were evaluable with ultrasound imaging, biomarker assays, and histopathological results. The risk of malignancy was higher for women classified as high-risk based on IOTA-LR2 (≥10%). The sensitivity, specificity, and diagnostic accuracy for the prediction of malignancy were 81.2%, 81%, and 0.81 (95% CI: 0.77-0.86) for IOTA-LR2; 77.5%, 66.7%, and 0.72 (95% CI: 0.67-0.77) for CA-125; and 91.3%, 41.2%, and 0.66 (95% CI: 0.62-0.71) for MIA2G. A combination of IOTA-LR2 and MIA2G significantly influenced the diagnostic performance and the result. When MIA2G was combined with IOTA-LR2 in parallel, the sensitivity (94.2%) and NPV (87.7%) increased, but the specificity (37.3%) decreased. When combined with IOTA-LR2 in series, there were fewer false positives, which resulted in improved specificity (85%).

CONCLUSION

This study determined the utility of ovarian imaging and a second-generation multivariate index assay in predicting the risk of ovarian malignancy. IOTA-LR2 and MIA2G were useful in classifying patients with a high risk for ovarian malignancy.

Defining Models to Classify between Benign and Malignant Adnexal Masses Using Routine Laboratory Parameters

Simple Summary

In patients with adnexal masses, classification into benign or malignant tumors is essential for optimal treatment planning, but remains challenging. In the search for new models applicable in a routine clinical setting, we compared classical single parameters to multiparameter predictive models.

Abstract

Discrimination between benign and malignant adnexal masses is essential for optimal treatment planning, but still remains challenging in a routine clinical setting. In this retrospective study, we aimed to compare albumin as a single parameter to calculate models by analyzing laboratory parameters of 1552 patients with an adnexal mass (epithelial ovarian cancer (EOC): n= 294; borderline tumor of the ovary (BTO): n = 66; benign adnexal mass: n = 1192) undergoing surgery. Models comprising classical laboratory parameters show better accuracies (AUCs 0.92–0.93; 95% CI 0.90–0.95) compared to the use of single markers, and could easily be implemented in clinical practice by containing only readily available markers. This has been incorporated into a nomogram.

Complications in laparoscopic and robotic-assisted surgery: definitions, classifications, incidence and risk factors - an up-to-date review

Almost all gynecological and general-surgical operations are - or can be - performed laparoscopically. In comparison to an abdominal approach, the minimally invasive access offers several advantages; however, laparoscopy (both conventional and robotic-assisted) can be associated with a number of approach-specific complications. Although the majority of them are related to the laparoscopic entry, adverse events may also occur due to the presence of pneumoperitoneum or the use of laparoscopic instruments. Unfortunately, a high proportion of complications (especially affecting the bowel and ureter) remain unrecognized during surgery. This narrative review provides comprehensive up-to-date information about definitions, classifications, risk factors and incidence of surgical complications in conventional and robotic-assisted laparoscopy, with a special focus on gynecology. The topic is discussed from various perspectives, e.g. in the context of stage of surgery, injured organs, involved instruments, and in relation to malpractice claims.