Ovarian Mass

Investigators developed an interactive agentic system designed to guide newly qualified sonographers in ovarian lesion scanning and improve their scanning quality and diagnostic performance toward expert-level standards. Our agentic system is capable of capturing key features including the max-diameter plane of ovarian lesions from dynamic ultrasound videos, translating these findings into standardized International Ovarian Tumor Analysis (IOTA) descriptors, and providing multi-turn guidance for subsequent scanning, and ultimately generating an AI-assisted diagnostic assessment based on embedded expert knowledge. In this multicenter study, participants are asked to undergo gynecological ultrasonography performed by sonographers with less than 3 years of experience with or without AI assistance. Our researchers will compare the performance of operators working with AI against that of operators working without AI, as well as against the performance of expert sonographers, to see whether AI assistance enhances the proficiency of less experienced operators and help them approach the scanning quality and diagnostic accuracy of expert sonographers in real-world clinical scenarios.

Ovarian mass occur in women of all ages, and their etiology and frequency range age accordingly. The ovarian mass may come from functional or physiological changes, inflammatory processes, endometriosis, benign and malignant tumor(1). Ovarian cancer (OC), the most lethal gynecological malignancy, usually presents in advanced stages. Characterized by peritoneal and lymphatic dissemination, OC necessitates a complex surgical approach usually involving the upper abdomen with the aim of achieving optimal cytoreduction without visible macroscopic disease (R0)(2). The presence of a residual tumor at the end of surgery is indeed recognized as the main negative prognostic factor for patients with AOC. In this context, complete cytoreductive surgery (R0) achieving no gross residual disease is associated with the best survival outcomes(3). Despite the increasing adoption of diagnostic laparoscopy, laparotomic assessment during definitive cytoreductive surgery remains the gold standard for evaluating the true extent of disease and determining resectability(4). Over the years, different score systems have been proposed and evaluated, aiming to assess the peritoneal spread of the disease and predict whether it is possible to obtain R0. Several imaging-based scoring models, using computed tomography (CT), have been suggested to predict the outcomes of PDS. These models included different radiological criteria, such as peritoneal thickening, ascites, para-aortic lymphadenopathy, and bowel involvement. Although the overall good predictive performance, the main limitation is represented by the unsuccessful rate when cross-validations datasets were used(3). Staging laparoscopy has shown to be a minimally invasive tool able to properly drive the therapeutic choice between primary cytoreductive surgery and neoadjuvant chemotherapy. To quickly select candidates for upfront surgery, and to decrease the delay to cytoreductive surgery or neoadjuvant chemotherapy, we offer patients a two-step surgical management protocol in which diagnostic laparoscopy is performed a few weeks prior to cytoreductive surgery(5). a laparoscopic scoring algorithm (predictive index, (PI) which developed by Fagotti et al.2015 including seven parameters based on intra-abdominal distribution of the disease. Although the accuracy of the laparoscopic model is 75% at predicting surgical outcome, the percentage of unnecessary laparotomies remains 33%, even after the inclusion of upper abdominal surgical score. Moreover, concordance between PI scores and PDS varies by anatomical location, with the lowest concordance in predicting bowel infiltration(6).

This observational study will evaluate how well an ultrasound scoring system called O-RADS can distinguish between benign (non-cancerous) and malignant (cancerous) ovarian masses in women aged 18 to 70 years. Women who are found to have an ovarian cyst or mass during routine pelvic or transabdominal ultrasound at Women's Health Hospital will be invited to participate and will receive standard care, including detailed transvaginal ultrasound, MRI when indicated, surgery if needed, and histopathology (tissue examination). The main question is how accurately O-RADS ultrasound categories predict the final tissue diagnosis; the study will also look at how ultrasound findings relate to MRI results in characterizing ovarian masses.

Adnexal masses are growths that can form in the ovaries or fallopian tubes for different reasons, such as hormonal changes, infection, or cancer. These masses may cause pelvic discomfort, pain, constipation, or no symptoms at all. When adnexal masses are found on scans, they are described in a certain way to indicate if they could represent early-stage cancer, and the word "complex" is used to refer to these masses. Surgery is often recommended, where the mass is removed and examined under the microscope during surgery in a process called (frozen section analysis); to determine its true nature. It is still difficult to confirm cancer before surgery, and many of these masses turn out to be benign (not cancerous) or borderline (slow-growing tumours). Currently, doctors use open surgery with a cut from at least the belly button to the pubic bone to remove these masses. Patients with a cancer diagnosis will then have more surgical steps including assessment and sampling of various areas inside the abdomen (known as staging surgery) to see how far the cancer has spread. Recovery after open surgery can be long and painful, with a slow return to normal daily activities. The trial investigators know from practice that robotic surgery has replaced open surgery for most benign adnexal diseases and other types of women's cancers, such as womb cancer. Recovery is quicker, with less pain and blood loss, allowing for a faster return to daily activities. This study, MIRRORS-FROZEN (pilot), compares robotic versus the standard open surgery in managing women with complex adnexal masses of eight centimetres or less. The hope is to decrease the need for open surgery in patients with benign or borderline disease and to assess if robotic surgery has similar, worse, or better outcomes for patients with cancer. MIRRORS-FROZEN is funded by Intuitive Foundation and GRACE Charity. The investigators will establish the feasibility of conducting a large multicentre randomized controlled trial in the future comparing certain cancer outcomes between robotic and open surgery.