摘要
Magnetic resonance imaging (MRI) measurements are essential for the diagnosis of pelvic organ prolapse given the inaccuracy of clinical examination. However, MRI pelvic floor measurements are currently performed manually and can be inconsistent and time-consuming. In this paper, we present a scheme for semi-automatic measurement modeling on MRI based on image segmentation and intersecting point identification methods. The segmentation algorithm is a multi-stage mechanism based on block grouping, support vector machine classification, morphological operation and prior shape information. Block grouping is achieved by classifying blocks as bone or background based on image texture features. The classified blocks are then used to find the initial segmentation by the first phase morphological opening. Prior shape information is incorporated into the initial segmentation to obtain the final segmentation using registration with the similarity type transformation. After segmentation, points of reference that are used for pelvic floor measurements are identified using morphological skeleton operation. The experiments on the MRI images show that the presented scheme can detect the points of reference on the pelvic floor structure to determine the reference lines needed for the assessment of pelvic organ prolapse. This will lead towards more consistent and faster pelvic organ prolapse diagnosis on dynamic MRI studies, and possible screening procedures for predicting predisposition to pelvic organ prolapse by radiologic evaluation of pelvic floor measurements.
Magnetic resonance imaging (MRI) measurements are essential for the diagnosis of pelvic organ prolapse given the inaccuracy of clinical examination. However, MRI pelvic floor measurements are currently performed manually and can be inconsistent and time-consuming. In this paper, we present a scheme for semi-automatic measurement modeling on MRI based on image segmentation and intersecting point identification methods. The segmentation algorithm is a multi-stage mechanism based on block grouping, support vector machine classification, morphological operation and prior shape information. Block grouping is achieved by classifying blocks as bone or background based on image texture features. The classified blocks are then used to find the initial segmentation by the first phase morphological opening. Prior shape information is incorporated into the initial segmentation to obtain the final segmentation using registration with the similarity type transformation. After segmentation, points of reference that are used for pelvic floor measurements are identified using morphological skeleton operation. The experiments on the MRI images show that the presented scheme can detect the points of reference on the pelvic floor structure to determine the reference lines needed for the assessment of pelvic organ prolapse. This will lead towards more consistent and faster pelvic organ prolapse diagnosis on dynamic MRI studies, and possible screening procedures for predicting predisposition to pelvic organ prolapse by radiologic evaluation of pelvic floor measurements.
