Abstract:

Changes in the structure and function of female pelvic floor organs, muscles and surrounding connective tissue are the main causes of pelvic floor disorders (PFD), and a detailed understanding of the spatial anatomy of the pelvic floor under physiological and pathological conditions can help clinicians make accurate diagnoses and optimize treatment strategies. The widespread use of magnetic resonance imaging (MRI) technology has improved clinicians' understanding of the pelvic floor structure, but presentation of the pelvic floor structure is still limited to two-dimensional planar images and the three-dimensional (3D) spatial structure cannot be visualized. The 3D reconstruction technology based on MRI can transform the structure of the female pelvic floor organs into digital models for observation, measurement and even 3D printing for inverse analysis, which greatly promotes the clinical understanding of the pathogenesis and treatment of PFD and provides basis for individualized treatment. However, the existing MRI-based 3D reconstruction technology is not yet mature, for example different advantages and disadvantages of different commercial softwares, different algorithms of different image recognition techniques, lack of uniform evaluation criteria for 3D reconstruction models, and difficulty of balancing modeling efficiency and quality, which limit it as an effective medical research tool for PFD. This paper reviews the research of 3D digital model reconstruction of female pelvic floor tissue and organs based on MRI, aiming to provide reference for clinical diagnosis, treatment and scientific research of PFD.

Key words: pelvic floor, magnetic resonance imaging (MRI), three-dimensional imaging, pattern recognition, deep learning