The use of an active appearance model for automated prostate segmentation in magnetic resonance

Abstract

Background. The prostate gland is delineated as the clinical target volume (CTV) in treatment planning of prostate cancer. Therefore, an accurate delineation is a prerequisite for efficient treatment. Accurate automated prostate segmentation methods facilitate the delineation of the CTV without inter-observer variation. The purpose of this study is to present an automated three-dimensional (3D) segmentation of the prostate using an active appearance model. Material and methods. Axial T2-weighted magnetic resonance (Mr) scans were used to build the active appearance model. The model was based on a principal component analysis of shape and texture features with a level-set representation of the prostate shape instead of the selection of landmarks in the traditional active appearance model. To achieve a better fit of the model to the target image, prior knowledge to predict how to correct the model and pose parameters was incorporated. The segmentation was performed as an iterative algorithm to minimize the squared difference between the target and the model image. Results. The model was trained using manual delineations from 30 patients and was validated using leave-one-out cross validation where the automated segmentations were compared with the manual reference delineations. The mean and median dice similarity coefficient was 0.84 and 0.86, respectively. Conclusion. This study demonstrated the feasibility for an automated prostate segmentation using an active appearance with results comparable to other studies.

Simple low-cost approaches to semantic segmentation in radiation therapy planning for prostate cancer using deep learning with non-contrast planning CT images

“…For decades, automated segmentation has been investigated enthusiastically. In terms of prostate imaging, Korsager et al reported prostate segmentation with a mean Dice similarity coefficient (DSC) of 0.84 on T2-weighted magnetic resonance imaging (MRI) using a levelset method, which utilized an implicit representation of the contour to be tracked [8]. The DSC is a common index of segmentation accuracy.…”

A semiautomatic approach for prostate segmentation in MR images using local texture classification and statistical shape modeling

“…There are several automatic, and semiautomatic segmentation techniques have been investigated and developed to perform prostate MRI segmentation faster and more reproducible compared to manual contouring [7][8][9][10][11][12][13][14][15][16][17]. Korsager et al [10] presented an automatic segmentation algorithm based on atlas registration combined with intensity and shape information in a graph cut segmentation framework.…”

The use of atlas registration and graph cuts for prostate segmentation in magnetic resonance images

“…A few studies have used a combination of shape and intensity information of the prostate to model and segment the prostate. Toth and Madabhushi 17 used image derived features in an active appearance model and Korsager et al 18 used an active appearance model to combine shape and image intensities with a level-set representation of the prostate shape. The use of active shape models and active appearance models has shown to be feasible for MR prostate segmentation.…”

“…The use of active shape models and active appearance models has shown to be feasible for MR prostate segmentation. 17,18 However, the underlying assumption that the shape and appearance can be described statistically using a Gaussian distribution might not be valid due to, e.g., large variation between patients. 19 The assumption of Gaussian distributions was addressed by Guo et al 19 by guiding a deformable model by sparse learning methods for both the prostate appearance and for the prostate shape modeling.…”