Texture Guided Active Appearance Model Propagation for Prostate Segmentation

Abstract

Abstract. Fusion of Magnetic Resonance Imaging (MRI) and TransRectal Ultra Sound (TRUS) images during TRUS guided prostate biopsy improves localization of the malignant tissues. Segmented prostate in TRUS and MRI improve registration accuracy and reduce computational cost of the procedure. However, accurate segmentation of the prostate in TRUS images can be a challenging task due to low signal to noise ratio, heterogeneous intensity distribution inside the prostate, and imaging artifacts like speckle noise and shadow. We propose to use texture features from approximation coefficients of Haar wavelet transform for propagation of a shape and appearance based statistical model to segment the prostate in a multi-resolution framework. A parametric model of the propagating contour is derived from Principal Component Analysis of prior shape and texture informations of the prostate from the training data. The parameters are then modified with prior knowledge of the optimization space to achieve optimal prostate segmentation. The proposed method achieves a mean Dice Similarity Coefficient value of 0.95 ± 0.01, and mean segmentation time of 0.72 ± 0.05 seconds when validated on 25 TRUS images, grabbed from video sequences, in a leaveone-out validation framework. Our proposed model performs computationally efficient accurate prostate segmentation in presence of intensity heterogeneity and imaging artifacts.

Statistical Shape and Probability Prior Model for Automatic Prostate Segmentation

“…We have used most of the popular prostate segmentation evaluation metrics like Dice similarity coefficient (DSC), 95% Hausdorff Distance (HD) [19], mean absolute distance (MAD) [2], maximum distance (MaxD), specificity, sensitivity, and accuracy [3] to evaluate our method. Furthermore, the results are compared with the traditional AAM proposed by Cootes et al [9], Ghose et al [10] and to B-AAM (that uses posterior probability of the prostate region and a single mean model for segmentation).…”

“…It is observed from Table I that a probabilistic representation of the prostate texture in TRUS images and the use of multiple mean models significantly improves segmentation accuracy when compared to traditional AAM and to [10]. We used posterior probability information for automatic initialization and training of our statistical shape and texture model.…”

“…To address the challenges involved with prostate segmentation in TRUS images we propose a novel approach using multiple mean parametric models derived from principal component analysis (PCA) of prostate shape and posterior probabilistic values of the prostate region to segment the prostate in a multi-resolution framework. The performance of our method is compared with the traditional AAM [9] and also with our previous work [10]. In contrast, to the use of intensity and one mean model as in [9] and to the use of texture from Haar wavelet features of [10], posterior probabilistic information of the prostate region obtained in a Bayesian framework is used to train, initialize and propagate multiple statistical models of shape and texture.…”

“…The performance of our method is compared with the traditional AAM [9] and also with our previous work [10]. In contrast, to the use of intensity and one mean model as in [9] and to the use of texture from Haar wavelet features of [10], posterior probabilistic information of the prostate region obtained in a Bayesian framework is used to train, initialize and propagate multiple statistical models of shape and texture. Statistically significant improvement is achieved with the use of multiple mean models when validated with 23 datasets, that have significant shape, size, and contrast variations of the prostate, in leave-one-patient-out validation framework.…”

A comparison of thin-plate splines with automatic correspondences and B-splines with uniform grids for multimodal prostate registration

“…However, we are also investigating on automatic prostate segmentation. 8 The US image is treated as the reference and the MR as the moving image. The TPS registration involves a set of correspondences generated by a geometric method based on the geometry of the segmented prostate contours in the respective modalities.…”