Radiomics in the evaluation of ovarian masses

Ovarian cancer (OC) is the leading cause of death from gynaecological cancer and the seventh commonest malignancy, accounting for 5% of all cancer deaths in women and 3% of overall cancer deaths. Ovarian tumours include a heterogeneous group of benign, borderline and malignant lesions with variable morphology. The high morbidity and mortality from OC stem from a lack of validated screening and the late presentation of non-specific symptoms.

Histopathological evaluation is the diagnostic gold standard. Tissue samples are in the main acquired during surgical staging whereas in other malignancies, biopsy diagnosis precedes further patient management. Imaging aims to differentiate benign adnexal lesions from malignancy.

First-line imaging of a clinically suspected ovarian mass usually involves trans-abdominal and trans-vaginal ultrasound assessment for suspicious features. The Risk of Malignancy Index (RMI), Ovarian-Adnexal Reporting and Data System (O-RADS) [10], or International Ovarian Tumor Analysis (IOTA) clinical support tools are often employed in conjunction with ultrasound assessment. RMI is a predictive model incorporating ultrasound features, menopausal status, and serum cancer antigen (CA-125) levels to estimate malignancy risk. O-RADS and IOTA, on the other hand, are categorization systems that use ultrasound characteristics to stratify ovarian masses into different risk categories.

Staging is through contrast-enhanced computed tomography CT of the abdomen and pelvis. Magnetic resonance imaging (MRI) is used to characterize indeterminate ovarian lesions or confirm dermoid/endometriotic cysts identified on ultrasound scans. Fluorine-18 fluorodeoxyglucose positron emission tomography-computed tomography (FDG PET-CT) has a less established role in OC. Patients may undergo unnecessary or inappropriate surgery when non-invasive investigations are inconclusive; adverse consequences include disease progression, decreased fertility and premature menopause.

Radiomics involves the extraction of high-dimensional data from medical imaging, allowing quantitative analysis of the distribution and relationship of pixel levels. This technique has been extensively studied in oncology for outcome prediction modelling. The study aim is to appraise the published literature reporting application of radiomics to different imaging modalities in suspected OC, provide an overview of progress and remaining challenges in the field and outline future recommendations.

This systematic review looked at the literature reporting the application of radiomics to imaging techniques in ovarian lesion patients. The authors found that radiomics showed promising results and great potential as a clinical diagnostic tool in patients with ovarian masses when it comes to improving lesion stratification, treatment selection, and outcome prediction. However, much larger and more diverse patient cohorts are required before real-world evaluation.

Key points

• Radiomics is emerging as a tool for enhancing clinical decisions in patients with ovarian masses.
• Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction.
• Modelling with larger cohorts and real-world evaluation is required before clinical translation.

Credit: Pratik Adusumilli, Nishant Ravikumar, Geoff Hall, Sarah Swift, Nicolas Orsi & Andrew Scarsbrook.

AMN | Anochie’s Report | Vienna.