A Hybrid End-to-End Approach Integrating Conditional Random Fields into CNNs for Prostate Cancer Detection on MRI

Abstract

Prostate Cancer (PCa) is the most common oncological disease in Western men. Even though a growing effort has been carried out by the scientific community in recent years, accurate and reliable automated PCa detection methods on multiparametric Magnetic Resonance Imaging (mpMRI) are still a compelling issue. In this work, a Deep Neural Network architecture is developed for the task of classifying clinically significant PCa on non-contrast-enhanced MR images. In particular, we propose the use of Conditional Random Fields as a Recurrent Neural Network (CRF-RNN) to enhance the classification performance of XmasNet, a Convolutional Neural Network (CNN) architecture specifically tailored to the PROSTATEx17 Challenge. The devised approach builds a hybrid end-to-end trainable network, CRF-XmasNet, composed of an initial CNN component performing feature extraction and a CRF-based probabilistic graphical model component for structured prediction, without the need for two separate training procedures. Experimental results show the suitability of this method in terms of classification accuracy and training time, even though the high-variability of the observed results must be reduced before transferring the resulting architecture to a clinical environment. Interestingly, the use of CRFs as a separate postprocessing method achieves significantly lower performance with respect to the proposed hybrid end-to-end approach. The proposed hybrid end-to-end CRF-RNN approach yields excellent peak performance for all the CNN architectures taken into account, but it shows a high-variability, thus requiring future investigation on the integration of CRFs into a CNN.

Decomposed Mean Euler-Poincaré Characteristic Model for a Non-Gaussian Physiological Random Field

“…make it evident that the EKG treated signals cannot be described by the classical GRF model in Adler and Taylor [1, p. 294], Eqs. (7,11,14. So, we use our DMEPC method to describe these NGRF.…”

“…Alsiddiky et al [13] observed spine tumors using a hierarchical hidden Markov random field (HHMRF) and deep neural networks. The conditional random fields (CRF) were engaged as a recurrent neural network to detect prostate cancer [14]. Here CRF is intended to capture a probability distribution from images' observations, as described in some works cited in [15].…”

Optimisation of 2D U-Net Model Components for Automatic Prostate Segmentation on MRI

“…In future work, we suggest that an automatic segmentation model could be used to provide basic guidance for the expert to produce a larger dataset so that a more robust model can be developed. Furthermore, a combination of Multiparametric MRI (such as T1w, T2w, ADC and PDw) can be considered as input to the neural network model to provide more initial features (i.e., information) for the network to perform the segmentation as it has been shown to be significantly beneficial in prostate segmentation [27,62] and prostate cancer detection [63]. Furthermore, integration of Attention Gates (AGs) [64] and Squeeze-and-Excitation (SE) blocks [65,66] are shown to increase the performance of the U-Net model in performing segmentation [64,66] and could be considered as another component for optimisation in the U-Net structure as performed in this paper.…”

Boundary Loss-Based 2.5D Fully Convolutional Neural Networks Approach for Segmentation: A Case Study of the Liver and Tumor on Computed Tomography

“…Then they plugged the RNNs into CNN and applied this method to the problem of semantic image segmentation, obtaining top results on the VOC dataset. Lapa et al [40] also incorporated CRFs into an end-to-end network for medical image segmentation. In addition, many deep learning methods to enhance feature expression have also been proposed for medical image segmentation.…”