A Deep Learning Framework for Enhanced Ovarian Adnexal Mass Classification Using Routinely Acquired Ultrasound Images.

This study aimed to evaluate the diagnostic value of combining Ovarian-Adnexal Reporting and Data System (O-RADS), contrast-enhanced ultrasound (CEUS) scoring, and serum human epididymis protein 4 (HE4) in differentiating benign and malignant adnexal masses. A retrospective analysis was performed on 41 surgically resected adnexal masses confirmed by pathology between May 2022 and July 2025. All patients underwent routine ultrasound, CEUS, and preoperative serum HE4 testing. Adnexal masses were classified using O-RADS and assessed with three CEUS qualitative scores (initial enhancement time, enhancement intensity, and washout pattern) alongside HE4 levels. O-RADS alone showed a sensitivity of 69.2% for borderline and malignant adnexal masses (AUC 0.794). Adding CEUS increased sensitivity to 88.5% (AUC 0.906), and including HE4 further raised it to 96.2% (AUC 0.947). CEUS parameters differed significantly between benign and malignant adnexal masses (p < 0.001). The combined model markedly improved classification of intermediate-risk adnexal masses and reduced misclassification. Interobserver agreement was excellent (Kappa >0.85). The integration of O-RADS with CEUS scoring and HE4 testing significantly improves the diagnostic accuracy for adnexal masses. This improvement is particularly notable in intermediate-risk adnexal masses. Our findings support the clinical utility of this integrated approach for risk stratification and decision-making.

The aim of this study was to identify the role of preoperative serum vascular endothelial growth factor (VEGF) and migration inhibitor factor (MIF) in differentiation of benign and malignant adnexal masses, as well as the relationship between prognostic factors and VEGF and MIF in ovarian cancer patients. This prospective study included 41 patients who were admitted between November 2010 and March 2012. In the malignant group, there were 21 patients, and remaining 20 had benign adnexal masses. Age, CA125 levels, grade, stage, presence of ascites and the degree of cytoreduction performed were noted. There was no significant difference between two groups in preoperative serum VEGF and MIF levels (p = 0.118 and p = 0.297, respectively). CA125 levels were significantly higher in the malignant group (p < 0.0001). There was no significant difference for VEGF and MIF between the groups evaluated for tumour grade, stage, presence of ascites and degree of cytoreduction performed in the malignant group. Preoperative serum, VEGF and MIF levels are not suitable for the differentiation of malignant and benign adnexal masses, and they do not correlate with the prognostic factors of ovarian cancer in this cohort of patients.

Objective: To compare the diagnostic accuracy of transvaginal sonography and serum CA125 assay for a clinical diagnosis of malignant nature of adnexal masses. Materials and methods: This prospective study was carried out in the department of Obstetrics and Gynaecology of Bangabandhu Sheikh Mujib Medical University (BSMMU), Dhaka, during the period of January 2001 to December 2002. The study included 86 patients scheduled for laparotomy for an adnexal mass. Among them, 56 patients were pre- menopausal and 30 were postmenopausal. Adnexal masses had been diagnosed by bimanual pelvic examination and by both transabdominal and transvaginal sonography before planning surgery. Results: Considering separately the women with benign or malignant masses, the sensitivity and specificity of transvaginal sonography for the diagnosis of malignant ovarian condition in premenopausal women were 80% and 96.08% and in postmenopausal women these were 60% and 80%, positive and negative predictive values in premenopausal women were 66.67% and 98.00%, whereas in postmenopausal women those were 60% and 80%. Therefore the sensitivity, specificity, positive and negative predictive values of transvaginal sonography in premenopausal women were higher than in postmenopausal women. The diagnostic accuracy of transvaginal sonography in premenopausal women was 94.64% and in postmenopausal women was 73.33%. The sensitivity, specificity, positive predictive value and the diagnostic accuracy of serum CA125 for the diagnosis of malignant ovarian condition in postmenopausal women were higher than premenopausal women. But the negative predictive value in premenopausal women was higher 94.87% than in postmenopausal women 88.90%. Conclusion: Transvaginal sonography used alone is the best method for differentiating between benign and malignant adnexal masses with a good diagnostic accuracy in premenopausal women in addition to clinical symptoms and pelvic examination. The good diagnostic accuracy of transvaginal sonography in premenopausal women may suggest that the addition of further test is not warranted. On the contrary in postmenopausal women, lower diagnostic accuracy of transvaginal sonography may require help of further test to improve it. Keyword: Adnexal mass; Transvaginal sonography; Serum CA125. Bangladesh J Obstet Gynaecol, 2009; Vol. 24(2) : 56-62 DOI: http://dx.doi.org/10.3329/bjog.v24i2.8529

Objective: To evaluate uterine artery Doppler parameters and assess their diagnostic accuracy in differentiating benign from malignant adnexal masses. Study design: It was a descriptive study. Place and duration of study: This study included 385 women aged 18–65 years with suspected adnexal masses who underwent transabdominal Doppler ultrasound between August and December 2024 at Sammar Diagnostic Lab, Lahore. Material and Methods: This descriptive study included 385 women aged 18–65 years with suspected adnexal masses who underwent transabdominal Doppler ultrasound between August and December 2024 at Sammar Diagnostic Lab, Lahore. Doppler parameters from bilateral uterine arteries were measured and correlated with adnexal mass characteristics. Data were analyzed using SPSS 25.0 with Pearson correlation and t-tests; p &lt; 0.05 was considered statistically significant. Results: Among 385 patients evaluated, mixed-type adnexal masses were most common (24.2%), followed by malignant (20.5%) and solid or benign lesions (19.7% each). Pearson correlation analysis showed a significant negative correlation between malignancy and both Right Uterine Artery Resistance Index (r = –0.503) and Pulsatility Index (r = –0.476). The Left Uterine Artery RI also showed a moderate negative correlation (r = –0.423), while Peak Systolic Velocity was moderately positively correlated with malignancy (r = 0.371; p &lt; 0.001). One-sample t-tests confirmed that the mean values of Doppler parameters were statistically significant (p &lt; 0.001), supporting their diagnostic relevance. Conclusion: Uterine artery Doppler parameters, particularly low RI and PI and elevated PSV, are significantly associated with malignant adnexal masses. These indices serve as valuable non-invasive markers for early malignancy detection and can complement grayscale ultrasound in improving diagnostic accuracy. Further multicenter studies are recommended to validate these findings and standardize Doppler criteria.

Background: Ovarian cancer is the 5th common cause of death in women. patients older than 30 years are high malignant potential group. The lifetime risk of dying from invasive ovarian cancer is about 1 in 95. Modern imaging techniques have demonstrated significant accuracy in the diagnosis and staging of adnexal masses that help the clinician in surgical and post-surgical treatment planning. Objective: To determine the accuracy of multidetector computed tomography (MDCT) in diagnoses of benign and malignant adnexal masses, compare it with histopathological diagnoses and find out the sensitivity, specificity, positive predictive value, negative predictive value of MDCT in diagnoses of benign and malignant adnexal masses. Materials and Methods: This cross-sectional observational study was carried out between January 2013 to December 2014 with 45 patients referred for an MDCT scan of the pelvic organ with a suspicion of adnexal mass in Dhaka Medical College, Dhaka. All the patients were evaluated by detailed history and clinical examination. CT scan of the pelvic organ was performed in all cases and the report was checked by the radiologists of DMCH. Operated patients were followed up after surgery up to histopathological diagnosis and correlated with CT scan findings. Results: CT diagnosis for evaluation of benign adnexal mass, sensitivity was 90.0%, specificity 92.0%, accuracy 91.1%, PPV was 90.0% and NPV 92.0%. In the case of malignant mass, sensitivity is 92.0%, specificity 90.0%, accuracy 91.1%, PPV 92.0% and NPV 90.0%. Conclusion: MDCT is a valuable modality in the diagnosis of benign and malignant adnexal masses.KYAMC Journal Vol. 14, No. 02, July 2023: 74-78.

The ADNEX model to triage adnexal masses: An external validation study and comparison with the IOTA two-step strategy and subjective assessment by an experienced ultrasound operator

What is the optimal strategy for preoperative identification of the adnexal mass suspicious for ovarian cancer? What is the most appropriate surgical procedure for a woman who presents with an adnexal mass suspicious for malignancy? In Canada in 2010, 2600 new cases of ovarian cancer were estimated to have been diagnosed, and of those patients, 1750 were estimated to have died, making ovarian cancer the 7th most prevalent form of cancer and the 5th leading cause of cancer death in Canadian women. Women with ovarian cancer typically have subtle, nonspecific symptoms such as abdominal pain, bloating, changes in bowel frequency, and urinary or pelvic symptoms, making early detection difficult. Thus, most ovarian cancer cases are diagnosed at an advanced stage, when the cancer has spread outside the pelvis. Because of late diagnosis, the 5-year relative survival ratio for ovarian cancer in Canada is only 40%. Unfortunately, because of the low positive predictive value of potential screening tests (cancer antigen 125 and ultrasonography), there is currently no screening strategy for ovarian cancer. The purpose of this document is to identify evidence that would inform optimal recommended protocols for the identification and surgical management of adnexal masses suspicious for malignancy. Outcomes of interest for the identification question included sensitivity and specificity. Outcomes of interest for the surgical question included optimal surgery, overall survival, progression-free or disease-free survival, reduction in the number of surgeries, morbidity, adverse events, and quality of life. After a systematic review, a practice guideline containing clinical recommendations relevant to patients in Ontario was drafted. The practice guideline was reviewed and approved by the Gynecology Disease Site Group and the Report Approval Panel of the Program in Evidence-based Care. External review by Ontario practitioners was obtained through a survey, the results of which were incorporated into the practice guideline. These recommendations apply to adult women presenting with a suspicious adnexal mass, either symptomatic or asymptomatic. IDENTIFICATION OF AN ADNEXAL MASS SUSPICIOUS FOR OVARIAN CANCER: Sonography (particularly 3-dimensional sonography), magnetic resonance imaging (mri), and computed tomography (ct) imaging are each recommended for differentiating malignant from benign ovarian masses. However, the working group offers the following further recommendations, based on their expert consensus opinion and a consideration of availability, access, and harm: Where technically feasible, transvaginal sonography should be the modality of first choice in patients with a suspicious isolated ovarian mass.To help clarify malignant potential in patients in whom ultrasonography may be unreliable, mri is the most appropriate test.In cases in which extra-ovarian disease is suspected or needs to be ruled out, ct is the most useful technique.Evaluation of an adnexal mass by Doppler technology alone is not recommended. Doppler technology should be combined with a morphology assessment.Ultrasonography-based morphology scoring systems can be used to differentiate benign from malignant adnexal masses. These scoring systems are based on specific ultrasound parameters, each with several scores base on determined features. All evaluated scoring systems were found to have an acceptable level of sensitivity and specificity; the choice of scoring system may therefore be made based on clinician preference.As a standalone modality, serum cancer antigen 125 is not recommended for distinguishing between benign and malignant adnexal masses.Frozen sections for the intraoperative diagnosis of a suspicious adnexal mass is recommended in settings in which availability and patient preference allow. SURGICAL PROCEDURES FOR AN ADNEXAL MASS SUSPICIOUS FOR MALIGNANCY: To improve survival, comprehensive surgical staging with lymphadenectomy is recommended for the surgical management of patients with early-stage ovarian cancer. Laparoscopy is a reasonable alternative to laparotomy, provided that appropriate surgery and staging can be done. The choice between laparoscopy and laparotomy should be based on patient and clinician preference. Discussion with a gynecologic oncologist is recommended. Fertility-preserving surgery is an acceptable alternative to more extensive surgery in patients with low-malignant-potential tumours and those with well-differentiated surgical stage i ovarian cancer. Discussion with a gynecologic oncologist is recommended.

Ovarian masses are most commonly observed in adults; they rarely occur in children.The majority of the ovarian masses encountered in children or patients of pre-menarchal age are non-neoplastic lesions.The clinical signs and symptoms of ovarian masses are usually non-specific.Early management may be necessary to preserve fertility.Gynecological malignant conditions constitute approximately 3% of all types of cancer in children.Ovarian tumors in children account for only 1% of childhood malignancies.However, the true incidence of malignant ovarian tumors in the pediatric population is unknown.is to study the role of magenetic resonace (MR) imaging in evaluation of neoplastic and non-neoplastic masses arising from uterine adnexa in neonates and pediatric age groups.During a period of 12 months (from December 2017 to December 2018), 100 consecutive patients (age range, 1-14 years; mean age, 8.8 years) with different clinical presentations were enrolled in this study.There was a highly significant reduction in the overall sexual satisfaction after hysterectomy (p < 0.001).On the basis of the findings, the study concludes that MRI is good modality for differentiation of benign and malignant adnexal masses.Certain imaging features and the degree of enhancement on MRI images are helpful in differentiating adnexal masses.Thus, imaging findings may contribute incremental value to clinical parameters in providing prognostic information, consequently improving the quality of the data used in therapeutic planning.

Introduction:Precise risk assessment of adnexal masses preoperatively is important for early diagnosis and better prognosis of ovarian malignancy.Although, there are many models for the prediction of ovarian malignancy, risk of malignancy index-1 (RMI-1) and International Ovarian Tumor Analysis-Simple Rules (IOTA-SR) are the most used.The aim of our study was to compare the diagnostic accuracy of IOTA-SR with RMI-1 for preoperative differentiation of benign and malignant adnexal masses.Materials and methods: A total of 121 women with adnexal masses, planned for surgery were enrolled in the study.Serum CA-125 was done, and an ultrasound examination was performed at the time of preoperative assessment by consultants.RMI-1 score of more than 200 was the cut-off value used to denote malignancy.IOTA-SR was applied to find the nature of the mass.Based on the histopathology report the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated.The diagnostic accuracy of RMI-1 and IOTA-SR were compared. Results:The study included 121 adnexal masses, out of which 110 (90.9%) were benign, 8 (6.6%) were malignant and 3 (2.5%) were borderline ovarian tumors.About 22.3% of the cases were found to be inconclusive by IOTA-SR.Sensitivity, specificity, PPV, and NPV of RMI-1 were 63.6, 100, 100, and 96.4%, respectively, whereas that of IOTA-SR was 100, 96.4,73.3, and 100%, respectively.The diagnostic accuracy of IOTA-SR was better than RMI-1 (AUC = 0.98 vs 0.87). Conclusion:The model, IOTA-SR, for the prediction of ovarian malignancy, has better diagnostic accuracy and higher sensitivity when compared to RMI-1 in preoperative discrimination of benign and malignant adnexal mass.

ObjectiveTo evaluate the role of colour Doppler sonography in differentiating between benign and malignant adnexal masses.Materials &amp; MethodsOne hundred women diagnosed with adnexal masses underwent colour Doppler sonography. Resistance index (RI) and Pulsatility index (PI) were calculated in each case and lowest RI and PI obtained at any point in the mass were considered for analysis. Masses which were completely a vascular were considered as benign. Histopathological diagnosis was obtained in each case. Sensitivity, specificity, positive predictive value, negative predictive value and accuracy of colour Doppler were calculated.ResultsMean RI and Mean PI were significantly lower in malignant masses (0.34 &amp; 0.95 respectively) as compared to benign masses (0.72 &amp; 1.97 respectively). Out of 81 benign cases, Doppler could correctly diagnose 78 cases as benign, but labelled 3 cases as malignant which were actually benign. Out of 19 malignant cases, 16 cases were correctly diagnosed, whereas 3 cases were missed by Doppler. Our study showed a sensitivity of 84.2%, specificity of 96.3%, positive predictive value of 84.2%, negative predictive value of 96.3% and accuracy of 94% for colour Doppler.Colour Doppler sonography is helpful in differentiating benign from malignant adnexal masses.

A new scoring system to differentiate benign from malignant adnexal masses

The purpose of this study was to evaluate prospectively the relative usefulness of color Doppler, spectral Doppler, and gray-scale sonography in differentiating benign from malignant adnexal masses. A total of 170 adnexal masses in 161 patients were classified prospectively as suggestive of or not suggestive of malignant tumor on the basis of gray-scale morphology, internal flow versus peripheral or no flow, and spectral Doppler pulsatility, as measured by a pulsatility index (PI) threshold of 1.0 and a resistive index (RI) threshold of 0.4. Surgical pathology revealed 123 benign masses and 46 malignant masses. One malignant mass was confirmed by cytologic evaluation of ascitic fluid. On gray-scale analysis, 46 of the 47 malignant masses were classified as suggestive of tumor, and 76 of the 123 benign masses were classified as not suggestive of tumor (sensitivity, 98%; specificity, 62%; negative predictive value [NPV], 99%; and positive predictive value [PPV], 50%). The use of internal color flow as a predictor of malignant tumor yielded a sensitivity of 77%, a specificity of 69%, an NPV of 89%, and a PPV of 49%. The PI and RI values were significantly lower (p < .0001) in malignant masses than in benign masses, although the values overlapped considerably. For a PI of less than 1.0, sensitivity was 67%, specificity was 66%, NPV was 83%, and PPV was 46%. For an RI of less than 0.4, sensitivity was 24%, specificity was 90%, NPV was 73%, and PPV was 50%. In our series, a gray-scale prediction of benignity was reliable (NPV = 99%), and a prediction of malignancy was unreliable (PPV = 50%). Internal color flow was not useful as a predictor of malignancy (PPV = 49%). Although the absence of internal or peripheral color flow suggested benignity (NPV = 94%), only 17 (16 benign) of the masses (about 10%) had no flow. Spectral Doppler analysis with RI and PI was not useful, as no reliable discriminatory value with both high sensitivity and high specificity could be found for either parameter because of the overlap in values obtained for benign and malignant masses.

Surgically treated adnexal masses in infancy, childhood, and adolescence

Introduction/BackgroundTo externally validate the Assessment of Different NEoplasias in the adneXa (ADNEX) model and evaluate its performance in differentiating benign from malignant adnexal masses. This study aimed to assess the...

To evaluate the diagnostic value of Ovarian-adnexal Reporting and Data System (O-RADS), and to compare it with Assessment of Different NEoplasias in the adnexa (ADNEX) model, Subjective Assessment (SA), and Risk of Malignancy Index (RMI) in differentiating benign and malignant adnexal masses (AMs). Ultrasound characteristics of 445 patients included in the study were retrospectively analyzed and evaluated using diagnostic models. The diagnostic performances of ultrasound diagnostic models were measured by assessing, receiver-operating characteristic curves, sensitivities, positive predictive values, positive likelihood ratios, specificities, negative predictive values, and negative likelihood ratios. Kappa values were used to evaluate inter-reviewer agreement (IRA). Of the 445 AMs, 265 were benign and 180 were malignant. The area under the curve (AUC) of O-RADS (0.941), ADNEX model (0.925), and SA (0.931) were higher than RMI (0.815) (all p < 0.05). The sensitivity of O-RADS (93.3%), ADNEX model (94.4%), and SA (96.1%) were higher than RMI (70.6%) (p > 0.05), and there was no statistical significance among them (p > 0.05). The specificity of O-RADS, ADNEX model, SA, and RMI was 90.2%, 90.6%, 90.2%, and 92.5%, respectively, with no statistical significance (p > 0.05). All four ultrasound diagnostic methods showed better IRA. O-RADS, ADNEX model and SA have better diagnostic value in differentiating benign and malignant AMs than RMI.