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 clinical and ultrasound examinations in assessing the parametria in patients with deep infiltrating endometriosis: a multicentre prospective study.

RESEARCH QUESTION: How do clinical rectovaginal examination and transvaginal ultrasound examination perform in the diagnosis of parametrial infiltration in patients with endometriosis? DESIGN: This was a multicentre prospective observational study. Patients with suspected deep endometriosis at clinical examination and/or at ultrasound evaluation and scheduled for surgery were included. Following multicentre multidisciplinary meetings, consensus was obtained on terms and methodology to define the parametrium at pelvic anatomy, ultrasound and surgery. Sensitivity, specificity, accuracy, and positive and negative likelihood ratios were calculated for clinical and ultrasound examinations with respect to surgery. RESULTS: In total, 195 women were selected for the present study and 164 were included in the analysis. Ultrasound examination had good to high specificity (>80%) for all parameters, except the left lateral parametrium (78.8%). The sensitivity of ultrasound examination was good to high for fixity of the right and left ovaries, uterosacral ligaments, retrocervix and rectovaginal space; and low for the anterior and lateral parametria, vagina, bladder and bowel. Clinical examination had good to high specificity for fixity of the left ovary, anterior parametrium, right uterosacral ligament, retrocervix and vagina; and low specificity for fixity of the right ovary, lateral parametrium, left uterosacral ligament and rectovaginal space. The sensitivity of clinical examination was good for the uterosacral ligaments and rectovaginal space, and low for the remaining parameters. CONCLUSION: Ultrasound examination provided good specificity for all the parameters, but sensitivity was low for the anterior and lateral parametria. Clinical examination provided good specificity for the anterior and posterior parametria, but sensitivity was low for the anterior and lateral parametria. Further prospective studies are needed to validate this methodology and confirm the results.

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.