A propagation-DNN: Deep combination learning of multi-level features for MR prostate segmentation. (March 2019)

• Record Type: Journal Article
• Authors: Yan, Ke; Wang, Xiuying; Kim, Jinman; Khadra, Mohamed; Fulham, Michael; Feng, Dagan
• Is Part Of: Computer methods and programs in biomedicine. Volume 170(2019)
• Page Start: 11
• Page End: 21
• Publication Date: 2019-03
• Subjects: Prostate segmentation -- Deep neural network -- Multi-level features; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2018.12.031
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A deep combination learning of multi-level features for MR prostate segmentation. We propose a new deep neural network, P-DNN, to extract complementary features from MR images. We validate the proposed method on a well-recognized benchmarking dataset. The experimental results show that the proposed method outperforms the conventional deep neural network for MR prostate segmentation. Abstract: Background and objective: Prostate segmentation on Magnetic Resonance (MR) imaging is problematic because disease changes the shape and boundaries of the gland and it can be difficult to separate the prostate from surrounding tissues. We propose an automated model that extracts and combines multi-level features in a deep neural network to segment prostate on MR images. Methods: Our proposed model, the Propagation Deep Neural Network (P-DNN), incorporates the optimal combination of multi-level feature extraction as a single model. High level features from the convolved data using DNN are extracted for prostate localization and shape recognition, while labeling propagation, by low level cues, is embedded into a deep layer to delineate the prostate boundary. Results: A well-recognized benchmarking dataset (50 training data and 30 testing data from patients) was used to evaluate the P-DNN. When compared it to existing DNN methods, the P-DNN statistically outperformed the baseline DNN models with an average improvement in the DSC of 3.19%. When compared to the state-of-the-art non-DNN prostate segmentation methods, P-DNN was competitive by achieving 89.9 ± 2.8% DSC and 6.84 ± 2.5 mm HD on training sets and 84.13 ± 5.18% DSC and 9.74 ± 4.21 mm HD on testing sets. Conclusion: Our results show that P-DNN maximizes multi-level feature extraction for prostate segmentation of MR images.