Artificial intelligence in uterine fibroid imaging: A review of trends, performance, and generalizability

The uterine fibroid is the most prevalent benign gynecologic tumor, affecting up to 80% of women by the age of 50 and serving as the major reason for hysterectomies, infertility, and reproductive morbidity globally. While extensive literature exists on its management, the disease still poses challenges due to its heterogeneous diagnostic criteria, unpredictable growth pattern, and varying treatment efficacy, prompting increased focus on AI techniques for clinical decision-making. This review highlights the recent advancements in AI applications for fibroid management through a narrative review of 39 publications from 2021 to 2026 in five categories: detection and segmentation, differentiation, prediction of high-intensity focused ultrasound (HIFU) treatment results, surgery planning and intraoperative guidance, and monitoring growth and recurrence. Radiomic analysis, machine learning, and deep learning methods have shown strong performance in lesion segmentation and treatment outcome prediction across several retrospective, single-center studies. Nonetheless, most of the research was conducted retrospectively, from single centers, with poor external validation, little emphasis on intraoperative assistance, long-term follow-up, and model explainability. The geographic imbalance in favor of developed regions casts severe ethical concerns. Of the 39 studies reviewed, only one originated from an African institution, a critical gap given that women of African descent bear a disproportionately higher fibroid burden globally. This near-total absence of African clinical data risks producing AI models that perform inequitably in the populations that need them most. Realising AI’s potential in fibroid care demands multicenter prospective trials, standardised methodologies, and deliberate investment in underrepresented regions, particularly sub-Saharan Africa.