Automated contour tracking and trajectory classification of pelvic organs on dynamic MRI

Abstract

A method is presented to automatically track and segment pelvic organs on dynamic magnetic resonance imaging (MRI) followed by multiple-object trajectory classification to improve understanding of pelvic organ prolapse (POP). POP is a major health problem in women where pelvic floor organs fall from their normal position and bulge into the vagina. Dynamic MRI is presently used to analyze the organs' movements, providing complementary support for clinical examination. However, there is currently no automated or quantitative approach to measure the movement of the pelvic organs and their correlation with the severity of prolapse. In the proposed method, organs are first tracked and segmented using particle filters and [Formula: see text]-means clustering with prior information. Then, the trajectories of the pelvic organs are modeled using a coupled switched hidden Markov model to classify the severity of POP. Results demonstrate that the presented method can automatically track and segment pelvic organs with a Dice similarity index above 78% and Hausdorff distance of [Formula: see text] for 94 tested cases while demonstrating correlation between organ movement and POP. This work aims to enable automatic tracking and analysis of multiple deformable structures from images to improve understanding of medical disorders.

Current developments in artificial intelligence from obstetrics and gynecology to urogynecology

“…Furthermore, the model detects reference locations quicker than the old method. In the following years, Nekooeimehr et al (26) proposed a method for automatically monitoring and segmenting pelvic organs on dynamic magnetic resonance imaging (MRI), followed by multiple-object trajectory classification, to aid in the understanding of pelvic organ prolapse (POP). According to their findings, the current method is capable of autonomously tracking and segmenting pelvic organs in 94 cases with a Dice similarity score of more than 78% and a Hausdorff distance of 5.2 mm.…”

Four-dimensional reconstruction and characterization of bladder deformations

“…Several methods have been proposed for the segmentation of pelvic organs using MRI but mainly on 3D static axial images [26,27,28] and only a few semi-automatic methods have already been developed for segmentation of dynamic 2D sagittal T 2 W MRI images [29,30,9]. Although promising, these methods still require manual initialization and have not been able to obtain segmentations with a average Dice similarity coefficient (DSC) greater than 0.90 for the bladder [29,9] or with a mean Hausdorff distance lower than 9 mm [30]. Recently, convolutional networks have shown good results in addressing the complex segmentation of pelvic organs in MRI but mostly with static volumes [31].…”

“…During visual inspection, radiologists assess the displacement of the pelvic organs relative to bone-anchored lines, such as the pubococcygeal line [7]. Beyond manual measurements, automated measures of strain-induced deformation features were proposed to build a quantitative characterization of the pelvic organ dynamics to distinguish pathological cases from healthy ones [8] and to graduate the severity of pelvic organ prolapses [9].…”

Artificial intelligence in functional urology: how it may shape the future

“…One of the other possible limitations of dynamic MRI may be the interobserver reproducibility of its interpretation. Two recent studies explored the interest of deep-learning-based image recognition to diagnose and grade POP on dynamic MRI [15,16]. Analyzing 15 dynamic MRI of female patients with POP, Onal et al found that a semiautomated pelvic floor measurement algorithmic model was accurate for POP detection and quantification.…”