Automatic prostate segmentation based on fusion between deep network and variational methods

Segmentation of prostate from magnetic resonance images (MRI) is a critical process for guiding prostate puncture and biopsy. Currently, the best results are obtained by Convolutional Neural Network (CNN). However, challenges still exist when applying CNN to segment prostate, such as data distribution issue caused by insubstantial and inconsistent intensity levels and vague boundaries in MRI.

To segment prostate gland from a MRI dataset including different prostate images with limited resolution and quality.

We propose and apply a global histogram matching approach to make intensity distribution of the MRI dataset closer to uniformity. To capture the real boundaries and improve segmentation accuracy, we employ a module of variational models to help improve performance.

Using seven evaluation metrics to quantify improvements of our proposed fusion approach compared with the state of art V-net model resulted in increase in the Dice Coefficient (11.2%), Jaccard Coefficient (13.7%), Volumetric Similarity (12.3%), Adjusted Rand Index (11.1%), Area under ROC Curve (11.6%), and reduction of the Mean Hausdorff Distance (16.1%) and Mahalanobis Distance (2.8%). The 3D reconstruction also validates the advantages of our proposed framework, especially in terms of smoothness, uniformity, and accuracy. In addition, observations from the selected examples of 2D visualization show that our segmentation results are closer to the real boundaries of the prostate, and better represent the prostate shapes.

Our proposed approach achieves significant performance improvements compared with the existing methods based on the original CNN or pure variational models.