Artificial Intelligence and Uterine Fibroids: A Useful Combination for Diagnosis and Treatment

Abstract

This manuscript examines the role of artificial intelligence (AI) in the diagnosis and treatment of uterine fibroids and uterine sarcomas, offering a comprehensive assessment of AI-supported diagnostic and therapeutic techniques. Through the use of radiomics, machine learning, and deep neural network models, AI shows promise in identifying benign and malignant uterine lesions, directing therapeutic decisions, and improving diagnostic accuracy. It also demonstrates significant capabilities in the timely detection of fibroids. Additionally, AI improves surgical precision, real-time structure detection, and patient outcomes by transforming surgical techniques such as myomectomy, robot-assisted laparoscopic surgery, and High-Intensity Focused Ultrasound (HIFU) ablation. By helping to forecast treatment outcomes and monitor progress during procedures like uterine fibroid embolization, AI also offers a fresh and fascinating perspective for improving the clinical management of these conditions. This review critically assesses the current literature, identifies the advantages and limitations of various AI approaches, and provides future directions for research and clinical implementation.

Keywords: artificial intelligence; deep neural network; high-intensity focused ultrasound; machine learning; magnetic resonance imaging; myoma; uterine fibroids; uterine leiomyosarcoma.

Figure 1

Radiomics pipeline for uterine fibroid analysis illustrated by a diagram showing the following sequence: Image Acquisition → Segmentation → Feature Extraction → Model Development → Clinical Application.

Figure 2

Methodological comparison between traditional radiomics and deep learning approaches illustrated by a diagram comparing the feature engineering in radiomics with the automatic feature learning in deep learning [28,29].

Figure 3

Comparison of radiomics-based approaches (left) [28,44], and deep learning approaches (right) [19,29] in the diagnosis of uterine fibroids versus sarcomas. Radiomics approaches require manual feature extraction but offer greater interpretability, while deep learning methods automatically learn features directly from images but function as “black boxes”.

Figure 4

Haptic feedback system for uterine fibroid detection, developed by Doria et al. [45].

Figure 5

Comparison of AUC values across different AI models for HIFU ablation prediction. Higher values indicate better predictive performance.

Figure 6

Schematic representation of the deep learning model for UAE outcome prediction.

Figure 7

AI-integrated diagnostic flowchart for uterine fibroids.