Development and validation of a model that includes two ultrasound parameters and the plasma D-dimer level for predicting malignancy in adnexal masses: an observational study

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.

Comparison of the ADNEX and ROMA risk prediction models for the diagnosis of ovarian cancer: a multicentre external validation in patients who underwent surgery

BACKGROUND

Several diagnostic prediction models to help clinicians discriminate between benign and malignant adnexal masses are available. This study is a head-to-head comparison of the performance of the Assessment of Different NEoplasias in the adneXa (ADNEX) model with that of the Risk of Ovarian Malignancy Algorithm (ROMA).

METHODS

This is a retrospective study based on prospectively included consecutive women with an adnexal tumour scheduled for surgery at five oncology centres and one non-oncology centre in four countries between 2015 and 2019. The reference standard was histology. Model performance for ADNEX and ROMA was evaluated regarding discrimination, calibration, and clinical utility.

RESULTS

The primary analysis included 894 patients, of whom 434 (49%) had a malignant tumour. The area under the receiver operating characteristic curve (AUC) was 0.92 (95% CI 0.88-0.95) for ADNEX with CA125, 0.90 (0.84-0.94) for ADNEX without CA125, and 0.85 (0.80-0.89) for ROMA. ROMA, and to a lesser extent ADNEX, underestimated the risk of malignancy. Clinical utility was highest for ADNEX. ROMA had no clinical utility at decision thresholds <27%.

CONCLUSIONS

ADNEX had better ability to discriminate between benign and malignant adnexal tumours and higher clinical utility than ROMA.

CLINICAL TRIAL REGISTRATION

clinicaltrials.gov NCT01698632 and NCT02847832.

ADNEX risk prediction model for diagnosis of ovarian cancer: systematic review and meta-analysis of external validation studies

Objectives

To conduct a systematic review of studies externally validating the ADNEX (Assessment of Different Neoplasias in the adnexa) model for diagnosis of ovarian cancer and to present a meta-analysis of its performance.

Design

Systematic review and meta-analysis of external validation studies.

Data sources

Medline, Embase, Web of Science, Scopus, and Europe PMC, from 15 October 2014 to 15 May 2023.

Eligibility criteria for selecting studies

All external validation studies of the performance of ADNEX, with any study design and any study population of patients with an adnexal mass. Two independent reviewers extracted the data. Disagreements were resolved by discussion. Reporting quality of the studies was scored with the TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) reporting guideline, and methodological conduct and risk of bias with PROBAST (Prediction model Risk Of Bias Assessment Tool). Random effects meta-analysis of the area under the receiver operating characteristic curve (AUC), sensitivity and specificity at the 10% risk of malignancy threshold, and net benefit and relative utility at the 10% risk of malignancy threshold were performed.

Results

47 studies (17 007 tumours) were included, with a median study sample size of 261 (range 24-4905). On average, 61% of TRIPOD items were reported. Handling of missing data, justification of sample size, and model calibration were rarely described. 91% of validations were at high risk of bias, mainly because of the unexplained exclusion of incomplete cases, small sample size, or no assessment of calibration. The summary AUC to distinguish benign from malignant tumours in patients who underwent surgery was 0.93 (95% confidence interval 0.92 to 0.94, 95% prediction interval 0.85 to 0.98) for ADNEX with the serum biomarker, cancer antigen 125 (CA125), as a predictor (9202 tumours, 43 centres, 18 countries, and 21 studies) and 0.93 (95% confidence interval 0.91 to 0.94, 95% prediction interval 0.85 to 0.98) for ADNEX without CA125 (6309 tumours, 31 centres, 13 countries, and 12 studies). The estimated probability that the model has use clinically in a new centre was 95% (with CA125) and 91% (without CA125). When restricting analysis to studies with a low risk of bias, summary AUC values were 0.93 (with CA125) and 0.91 (without CA125), and estimated probabilities that the model has use clinically were 89% (with CA125) and 87% (without CA125).

Conclusions

The results of the meta-analysis indicated that ADNEX performed well in distinguishing between benign and malignant tumours in populations from different countries and settings, regardless of whether the serum biomarker, CA125, was used as a predictor. A key limitation was that calibration was rarely assessed.

Systematic review registration

PROSPERO CRD42022373182.

D-dimer, Fibrinogen and Tumor Marker Levels in Patients with benign and Malignant Ovarian Tumors

Limited studies have investigated the differences between the levels of plasma coagulants and tumor markers in ovarian cancer. Therefore, we conducted this study to determine and compare the level of coagulation, fibrinolysis and tumor markers in patients with benign and malignant ovarian tumors. This cross-sectional study was conducted between January 2022 and February 2023 in Imam Hossein Hospital on patients with ovarian mass. Laboratory tests included platelet count, PT, INR, PTT, fibrinogen and D-dimer were sent to the pathology laboratory to be examined by a pathologist. Based on histopathology, patients were divided into benign, borderline and malignant groups. Logistic regression was used for determine predictors of malignancy. Receiver operating characteristics (ROC) curves and their corresponding 95% CI were determined for the predictor value of the full model. From 141 investigated patients, tumor type in 124 (87.94%) patients were benign, in 12 (8.51%) was malignant and in 5 (3.55%) was borderline. D-dimer, Ca-125 and HE4 were significantly higher in the patients with malignant tumor type (P<0.001), whereas AFP was significantly higher in patients with borderline tumor type (P<0.001). With one-unit increase in D-dimer odds of borderline/malignant tumor 0.3% increases (OR=1.003, 95% CI: 1.001, 1.006) and with one-unit increase in Ca-125 odds of borderline/malignant tumor 1% increases (OR=1.01, 95% CI: 1.003, 1.02). We found that plasma fibrinogen, D-dimer and Ca-125 levels are independently associated with malignant ovarian tumors and combined use of these markers has the high discriminant power for distinction of benign and malignant ovarian masses.
.

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.

Comparison of ultrasound-based ADNEX model with magnetic resonance imaging for discriminating adnexal masses: a multi-center study

Objectives

The ADNEX model offered a good diagnostic performance for discriminating adnexal tumors, but research comparing the abilities of the ADNEX model and MRI for characterizing adnexal tumors has not been reported to our knowledge. The aim of this study was to evaluate the diagnostic accuracy of the ultrasound-based ADNEX (Assessment of Different NEoplasias in the adneXa) model in comparison with that of magnetic resonance imaging (MRI) for differentiating benign, borderline and malignant adnexal masses.

Methods

This prospective study included 529 women with adnexal masses who underwent assessment via the ADNEX model and subjective MRI analysis before surgical treatment between October 2019 and April 2022 at two hospitals. Postoperative histological diagnosis was considered the gold standard.

Results

Among the 529 women, 92 (17.4%) masses were diagnosed histologically as malignant tumors, 67 (12.7%) as borderline tumors, and 370 (69.9%) as benign tumors. For the diagnosis of malignancy, including borderline tumors, overall agreement between the ADNEX model and MRI pre-operation was 84.9%. The sensitivity of the ADNEX model of 0.91 (95% confidence interval [CI]: 0.85-0.95) was similar to that of MRI (0.89, 95% CI: 0.84-0.94; P=0.717). However, the ADNEX model had a higher specificity (0.90, 95% CI: 0.87-0.93) than MRI (0.81, 95% CI: 0.77-0.85; P=0.001). The greatest sensitivity (0.96, 95% CI: 0.92-0.99) and specificity (0.94, 95% CI: 0.91-0.96) were achieved by combining the ADNEX model and subjective MRI assessment. While the total diagnostic accuracy did not differ significantly between the two methods (P=0.059), the ADNEX model showed greater diagnostic accuracy for borderline tumors (P<0.001).

Conclusion

The ultrasound-based ADNEX model demonstrated excellent diagnostic performance for adnexal tumors, especially borderline tumors, compared with MRI. Accordingly, we recommend that the ADNEX model, alone or with subjective MRI assessment, should be used for pre-operative assessment of adnexal masses.

Value of Assessment of Different Neoplasias in the Adnexa in the Differential Diagnosis of Malignant Ovarian Tumor and Benign Ovarian Tumor: A Meta-analysis

To evaluate the accuracy of the assessment of different neoplasias in the adnexa (ADNEX) model in the differential diagnosis of malignant and benign ovarian tumors, the optimal cutoff value and the accuracy in diagnosing ovarian tumors at different stages, PubMed, Web of Science and Cochrane Library databases were retrieved to search literature with per-patient analysis until publication of the last study in November 2021. STATA 14.1, Meta-Disc 1.4 and Revman software 5.3 were used in the performance of meta-analysis. To explore sources of heterogeneity, a subgroup analysis was conducted for the ADNEX model. The pooled sensitivity, specificity, diagnostic odds ratio, positive likelihood, negative likelihood ratio and area under the summary receiver operating characteristic curve were 0.91 (95% confidence interval [CI]: 0.89-0.93), 0.84 (95% CI: 0.80-0.88), 55.55 (95% CI: 40.47-76.26), 5.71 (95% CI: 4.49-7.26), 0.10 (95% CI: 0.08-0.13) and 0.94 (95% CI: 0.92-0.96) in differentiating benign and malignant ovarian tumors, respectively. The area under the curve in identifying benign, borderline, stage I and stages II-IV were 0.93, 0.73, 0.27 and 0.92. The ADNEX model had high diagnostic performance was influential in the diagnosis of benign and stage II-IV ovarian tumors.

Accuracy of Pretreatment Ultrasonography Assessment of Intra-Abdominal Spread in Epithelial Ovarian Cancer: A Prospective Study

The aim of this study was to test the accuracy of ultrasonography performed by gynecological oncologists for the preoperative assessment of epithelial ovarian cancer (EOC) spread in the pelvis and abdominal cavity. A prospective, observational cohort study was performed at a single tertiary cancer care unit. Patients with suspected EOC were recruited and underwent comprehensive transvaginal and abdominal ultrasonography performed by a gynecological oncologist. Sixteen intra-abdominal localizations and parameters were assessed using ultrasonography and compared with surgical-pathological status (reference standard). Sensitivity, specificity, positive and negative predictive values, and overall accuracy were calculated. Differences were analyzed using Fisher's exact and chi-square tests. Ultimately, we included 132 patients (median age 62 years), of whom 67% were in stage IIIC-IVB and 72% had serous cancer. Overall prediction accuracies for the involvement of the omentum, small bowel mesentery root, and frozen pelvis, and detecting ascites were >90%. Detecting the involvement of the pelvis peritoneum, liver and spleen hilum, and rectosigmoid colon, and predictions of disease stage and residual disease had overall accuracies of 80-90%. The lowest accuracy was for involvement of the abdominal peritoneum (69%) and diaphragm peritoneum (right 71%; left 75%) and surgical complexity prediction (77%). Stratification of results by presence or absence of ascites revealed significantly higher specificity of ultrasonography (clinically meaningful) for assessments of the abdominal/pelvic peritoneum, spleen hilum, and rectum wall, if there were ascites. A gynecological oncologist, experienced in surgery and sonology, performing comprehensive ultrasonography on patients with EOC can accurately detect intraperitoneal lesions and recognize critical disease manifestations and predict stage, surgical complexity, and residual disease, which allow accurate qualification of patients for primary debulking surgery or neoadjuvant chemotherapy.

Diagnostic Accuracy of the ADNEX Model for Ovarian Cancer at the 15% Cut-Off Value: A Systematic Review and Meta-Analysis

Objectives

To evaluate the diagnostic accuracy of the ADNEX model for ovarian cancer at the 15% cut-off value.

Methods

Studies on the identified diagnosis of the ADNEX model for ovarian cancer published in PubMed, Embase, the Cochrane Library and Web of Science databases from January 1st, 2014 to February 20th, 2021 were searched. Two researchers independently screened the retrieved studies and extracted the basic features and parameter data. The quality of the eligible studies was evaluated by Quality Assessment of Diagnostic Accuracy Studies-2, and the result was summarized by Review Manager 5.3. Meta-Disc 1.4 and STATA 16.0 were used in statistical analysis. Heterogeneity of this meta-analysis was calculated. Meta-regression was performed to investigate the potential sources of heterogeneity. Sensitivity analysis and Deek's funnel plot analysis were conducted to evaluate the stability and publication bias, respectively.

Results

280 studies were initially retrieved through the search strategy, and 10 eligible studies were ultimately included. The random-effects model was selected for data synthesis. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio and the area under the summary receiver operating characteristic curve were 0.92 (95% CI: 0.89-0.94), 0.82 (95% CI: 0.78-0.86), 5.2 (95% CI: 4.1-6.4), 0.10 (95% CI: 0.07-0.13), 54.0 (95% CI: 37.0-77.0) and 0.95 (95% CI: 0.91-0.95). Meta-regression based on study design, country, enrollment and blind method was not statistically significant. This meta-analysis was stable with no obvious publication bias.

Conclusions

The ADNEX model at the 15% cut-off had high diagnostic accuracy in identifying ovarian cancer.

The value of human epididymis 4, D-dimer, and fibrinogen compared with CA 125 alone in triaging women presenting with pelvic masses: a retrospective cohort study

INTRODUCTION

CA 125, the biomarker in common clinical use for ovarian cancer, is limited by low sensitivity for early disease and high false positives. The aim of this study was to evaluate several candidate biomarkers, alone or in combination, compared with CA 125 in the prediction of malignant/borderline vs benign tumor status in premenopausal and postmenopausal women with pelvic masses.

MATERIAL AND METHODS

This was a retrospective observational cohort study set in St James's Hospital, a tertiary referral center for gynecological malignancy in Dublin, Ireland. Women undergoing surgery for pelvic masses between 2012 and 2018 were included. Preoperative human epididymis protein 4 (HE4), the Risk of Ovarian Malignancy Algorithm, the Risk of Malignancy Index I and II, D-dimer, and fibrinogen were assessed. Logistic regression models were fitted for each biomarker alone and in combination. Receiver operating characteristics-area under the curve (ROC-AUC) and partial AUCs in the 90%-100% specificity range were determined.

RESULTS

In all, 89 premenopausal and 185 postmenopausal women were included. In premenopausal women, no biomarker(s) outperformed CA 125 (AUC 0.73; 95% CI 0.63-0.84). In postmenopausal women, HE4 had a partial AUC (pAUC) of 0.71 (95% CI 0.64-0.79) compared with 0.57 (95% CI 0.51-0.69) for CA 125 (p = 0.009). HE4 + D-dimer had an improved pAUC of 0.74 (95% CI 0.68-0.81, p < 0.001) and HE4 + D-dimer + fibrinogen had a pAUC of 0.75 (95% CI 0.68-0.82).

CONCLUSIONS

A novel biomarker panel of HE4 ± D-dimer ± fibrinogen outperformed CA 125 alone as a high-specificity biomarker in postmenopausal women and could aid in the preoperative triaging of pelvic masses. No biomarker(s) outperformed CA 125 in premenopausal women.

Validation of models to diagnose ovarian cancer in patients managed surgically or conservatively: multicentre cohort study

OBJECTIVE

To evaluate the performance of diagnostic prediction models for ovarian malignancy in all patients with an ovarian mass managed surgically or conservatively.

DESIGN

Multicentre cohort study.

SETTING

36 oncology referral centres (tertiary centres with a specific gynaecological oncology unit) or other types of centre.

PARTICIPANTS

Consecutive adult patients presenting with an adnexal mass between January 2012 and March 2015 and managed by surgery or follow-up.

MAIN OUTCOME MEASURES

Overall and centre specific discrimination, calibration, and clinical utility of six prediction models for ovarian malignancy (risk of malignancy index (RMI), logistic regression model 2 (LR2), simple rules, simple rules risk model (SRRisk), assessment of different neoplasias in the adnexa (ADNEX) with or without CA125). ADNEX allows the risk of malignancy to be subdivided into risks of a borderline, stage I primary, stage II-IV primary, or secondary metastatic malignancy. The outcome was based on histology if patients underwent surgery, or on results of clinical and ultrasound follow-up at 12 (±2) months. Multiple imputation was used when outcome based on follow-up was uncertain.

RESULTS

The primary analysis included 17 centres that met strict quality criteria for surgical and follow-up data (5717 of all 8519 patients). 812 patients (14%) had a mass that was already in follow-up at study recruitment, therefore 4905 patients were included in the statistical analysis. The outcome was benign in 3441 (70%) patients and malignant in 978 (20%). Uncertain outcomes (486, 10%) were most often explained by limited follow-up information. The overall area under the receiver operating characteristic curve was highest for ADNEX with CA125 (0.94, 95% confidence interval 0.92 to 0.96), ADNEX without CA125 (0.94, 0.91 to 0.95) and SRRisk (0.94, 0.91 to 0.95), and lowest for RMI (0.89, 0.85 to 0.92). Calibration varied among centres for all models, however the ADNEX models and SRRisk were the best calibrated. Calibration of the estimated risks for the tumour subtypes was good for ADNEX irrespective of whether or not CA125 was included as a predictor. Overall clinical utility (net benefit) was highest for the ADNEX models and SRRisk, and lowest for RMI. For patients who received at least one follow-up scan (n=1958), overall area under the receiver operating characteristic curve ranged from 0.76 (95% confidence interval 0.66 to 0.84) for RMI to 0.89 (0.81 to 0.94) for ADNEX with CA125.

CONCLUSIONS

Our study found the ADNEX models and SRRisk are the best models to distinguish between benign and malignant masses in all patients presenting with an adnexal mass, including those managed conservatively.

TRIAL REGISTRATION

ClinicalTrials.gov NCT01698632.

Performance of Selected Models for Predicting Malignancy in Ovarian Tumors in Relation to the Degree of Diagnostic Uncertainty by Subjective Assessment With Ultrasound

OBJECTIVES

The study's main aim was to evaluate the relationship between the performance of predictive models for differential diagnoses of ovarian tumors and levels of diagnostic confidence in subjective assessment (SA) with ultrasound. The second aim was to identify the parameters that differentiate between malignant and benign tumors among tumors initially diagnosed as uncertain by SA.

METHODS

The study included 250 (55%) benign ovarian masses and 201 (45%) malignant tumors. According to ultrasound findings, the tumors were divided into 6 groups: certainly benign, probably benign, uncertain but benign, uncertain but malignant, probably malignant, and certainly malignant. The performance of the risk of malignancy index, International Ovarian Tumor Analysis assessment of different neoplasias in the adnexa model, and International Ovarian Tumor Analysis logistic regression model 2 was analyzed in subgroups as follows: SA-certain tumors (including certainly benign and certainly malignant) versus SA-probable tumors (probably benign and probably malignant) versus SA-uncertain tumors (uncertain but benign and uncertain but malignant).

RESULTS

We found a progressive decrease in the performance of all models in association with the increased uncertainty in SA. The areas under the receiver operating characteristic curve for the risk of malignancy index, logistic regression model 2, and assessment of different neoplasias in the adnexa model decreased between the SA-certain and SA-uncertain groups by 20%, 28%, and 20%, respectively. The presence of solid parts and a high color score were the discriminatory features between uncertain but benign and uncertain but malignant tumors.

CONCLUSIONS

Studies are needed that focus on the subgroup of ovarian tumors that are difficult to classify by SA. In cases of uncertain tumors by SA, the presence of solid components or a high color score should prompt a gynecologic oncology clinic referral.