Ovarian cancer is the sixth most common malignancy, with a 35% survival rate across all stages at 10 years. Ultrasound is widely used for ovarian tumour diagnosis, and accurate pre-operative diagnosis is essential for appropriate patient management. Artificial intelligence is an emerging field within gynaecology and has been shown to aid in the ultrasound diagnosis of ovarian cancers. For this study, Embase and MEDLINE databases were searched, and all original clinical studies that used artificial intelligence in ultrasound examinations for the diagnosis of ovarian malignancies were screened. Studies using histopathological findings as the standard were included. The diagnostic performance of each study was analysed, and all the diagnostic performances were pooled and assessed. The initial search identified 3726 papers, of which 63 were suitable for abstract screening. Fourteen studies that used artificial intelligence in ultrasound diagnoses of ovarian malignancies and had histopathological findings as a standard were included in the final analysis, each of which had different sample sizes and used different methods; these studies examined a combined total of 15,358 ultrasound images. The overall sensitivity was 81% (95% CI, 0.80–0.82), and specificity was 92% (95% CI, 0.92–0.93), indicating that artificial intelligence demonstrates good performance in ultrasound diagnoses of ovarian cancer. Further prospective work is required to further validate AI for its use in clinical practice.

Background: Ovarian cancer has the worst prognosis among all gynaecological cancers. The pre-operative and intraoperative diagnosis of ovarian tumours is imperative to ensure the right operation is performed and to improve patients’ outcomes. Methodology: A retrospective review of cases with a confirmed histological diagnosis of ovarian cases was undertaken from January 2017 to December 2021. Comparison was undertaken between this final diagnosis and the pre-operative ultrasound, MRI and frozen section (FS) to assess diagnostic accuracy of each. In the ultrasound cases, the level of the examiner was collected. Statistical analysis was performed using Stata MP v17.0 software (USA, 2023). Results: In total, 156 ovarian masses were examined by FS. In the histopathological examination, 123/156 of these tumours were epithelial tumours. Pre-operative US subjective impression was made in 63/156 cases and preoperative MRI subjective impression was made in 129/156 cases. For benign, borderline and malignant tumours, FS demonstrated a sensitivity of 90.8% (95%CI:81.9–96.2), 86.8% (95%CI:71.9–95.6) and 97.6% (95%CI:87.4–99.9) respectively. Ultrasound’s sensitivities were 95.2% (95%CI:76.2–99.9), 20% (95%:4.33–48.1), 57.1% (95%CI:28.9–82.3) and MRI’s sensitivities were 100% (95%CI:80.5–100), 31.5% (95%CI:19.5–45.6) and 63.2% (95%CI:46–78.2) respectively. Conclusions: FS remains an accurate tool for diagnosing ovarian malignancy. However, across both imaging modalities and FS, the diagnosis of borderline ovarian tumours remains challenging.

This abstract describes a case of the growth of a serous borderline tumour recurrence and cyst to papillary projection ratio with associated ultrasound images. The aetiology, presentation and management of such cases are explored and compared to the literature.

Background & Objectives: The ultrasound features of ovarian mature teratomas are well defined. However, literature regarding the ultrasound features of immature teratomas is lacking and features can often be confused with those of mature teratomas. The objective of this study was to evaluate the subjective assessment of ultrasound examiners of anonymised static B mode ultrasound images of immature and mature teratomas. Method: An electronic questionnaire was distributed to levels 1 to 3 ultrasound examiners containing 23 anonymised ultrasound images including nine different immature teratomas and nine different mature teratomas. The images were collected retrospectively, and the reference test was the final histology of the surgically removed masses. The sensitivity and specificity test of the subjective assessment for each histological group was calculated. The live (at the time the scan was performed) subjective impression of each tumour was also recorded and the level of the examiner that performed the scan was noted. Results: There were a total of 43 responses (30 from level 1, 9 from level 2 and 4 from level 3 examiners. The sensitivity and specificity of subjective assessment ranged from 16.3% to 97.7% and 81.6% to 96.1%, respectively, for all histological groups. The sensitivity and specificity to correctly diagnose mature teratomas and immature teratomas were 41.3% (95% CI: 36.3%–46.4%), 82.2% (95% CI: 78.9%–85.1%) and 41.2 % (95% CI: 36.2%–46.3%), 81.6 % (95% CI: 78.3%–84.7%), respectively. There was no statistical difference in the diagnostic performance of the subjective assessment of examiners between mature and immature teratomas ( p = 0.975). Conclusions: Diagnostic performance of static 2D ultrasound images for mature and immature teratomas is low. Immature teratoma still pose a diagnostic challenge.