A Supervised Learning Framework for Automatic Prostate Segmentation in Trans Rectal Ultrasound Images

Abstract

Abstract. Heterogeneous intensity distribution inside the prostate gland, significant variations in prostate shape, size, inter dataset contrast variations, and imaging artifacts like shadow regions and speckle in Trans Rectal Ultrasound (TRUS) images challenge computer aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose a supervised learning schema based on random forest for automatic initialization and propagation of statistical shape and appearance model. Parametric representation of the statistical model of shape and appearance is derived from principal component analysis (PCA) of the probability distribution inside the prostate and PCA of the contour landmarks obtained from the training images. Unlike traditional statistical models of shape and intensity priors, the appearance model in this paper is derived from the posterior probabilities obtained from random forest classification. This probabilistic information is then used for the initialization and propagation of the statistical model. The proposed method achieves mean Dice Similarity Coefficient (DSC) value of 0.96±0.01, with a mean segmentation time of 0.67±0.02 seconds when validated with 24 images from 6 datasets with considerable shape, size, and intensity variations, in a leave-one-patient-out validation framework. The model achieves statistically significant t-test p-value<0.0001 in mean DSC and mean mean absolute distance (MAD) values compared to traditional statistical models of shape and intensity priors.

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

“…The supervised methods can be grouped into support vector machines (SVM)‐based, random forest‐based, and the deep learning‐based methods. The SVM‐based and random forest‐based methods use TRUS contour boundary information, such as texture features or shape statistic information, to train a SVM or random forest classifier for future segmentation . To address the problem that traditional machine‐learning‐based methods are challenging to handcrafted, high‐dimensional, and ill‐posed mapping from TRUS image to binary segmentation, a deep learning method has been introduced into medical image segmentation .…”

Machine Learning Optimization for Prostate Brachytherapy Treatment Planning

“…Extracting key imaging features using image processing techniques alone has been employed in convolutional neural networks for feature extraction and would be of interest to explore for the brachytherapy-specific ML algorithm evaluated in this thesis [122]. Supervised ML algorithms for auto-contouring of the prostate gland on Transrectal Ultrasound (TRUS) imaging alone have also been evaluated with excellent results [123].…”

“…Multicenter learning for prostate treatment plan creation (for both external radiotherapy and brachytherapy) is a possibility; anonymized meta-data may be transferrable between centers and offers an indirect method of sharing expertise, or even aggregating data for predicting outcomes more accurately [130,131]. More common applications that focus on workflow efficiencies include methods for automated contouring of target structures such as the prostate gland [123,132], and treatment planning assistance tools in Intensity Modulated Radiotherapy (IMRT) [133]. An excellent book by El Naqa et al…”

A survey of prostate modeling for image analysis

“…Another combination was also tested: the shape and a posteriori probability distribution [9,54,118,119]. Three types of features were employed by Li et al [15] to obtain information about the movement of the prostate in the pelvis: appearance, the histogram of the oriented gradient, and the coordinates of each pixel.…”