Next Article in Journal
Applications and Limits of Time-to-Energy Mapping of Protein Crystal Diffraction Using Energy-Chirped Polychromatic XFEL Pulses
Next Article in Special Issue
Classification of Lentigo Maligna at Patient-Level by Means of Reflectance Confocal Microscopy Data
Previous Article in Journal
A New Analytical Approach for Nonlinear Global Buckling of Spiral Corrugated FG-CNTRC Cylindrical Shells Subjected to Radial Loads
Previous Article in Special Issue
Evaluation of Effectiveness of Digital Technologies During Anatomy Learning in Nursing School
Article

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

1
School of Electrical Engineering and Computing, The University of Newcastle, Callaghan, NSW 2308, Australia
2
School of Mathematical and Physical Sciences, The University of Newcastle, Callaghan, NSW 2308, Australia
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(7), 2601; https://doi.org/10.3390/app10072601
Received: 19 February 2020 / Revised: 3 April 2020 / Accepted: 3 April 2020 / Published: 9 April 2020
(This article belongs to the Special Issue Computer-aided Biomedical Imaging 2020: Advances and Prospects)
In this paper, we develop an optimised state-of-the-art 2D U-Net model by studying the effects of the individual deep learning model components in performing prostate segmentation. We found that for upsampling, the combination of interpolation and convolution is better than the use of transposed convolution. For combining feature maps in each convolution block, it is only beneficial if a skip connection with concatenation is used. With respect to pooling, average pooling is better than strided-convolution, max, RMS or L2 pooling. Introducing a batch normalisation layer before the activation layer gives further performance improvement. The optimisation is based on a private dataset as it has a fixed 2D resolution and voxel size for every image which mitigates the need of a resizing operation in the data preparation process. Non-enhancing data preprocessing was applied and five-fold cross-validation was used to evaluate the fully automatic segmentation approach. We show it outperforms the traditional methods that were previously applied on the private dataset, as well as outperforming other comparable state-of-the-art 2D models on the public dataset PROMISE12. View Full-Text
Keywords: convolutional neural networks; medical image application; prostate segmentation; magnetic resonance imaging; MRI convolutional neural networks; medical image application; prostate segmentation; magnetic resonance imaging; MRI
Show Figures

Figure 1

MDPI and ACS Style

Astono, I.P.; Welsh, J.S.; Chalup, S.; Greer, P. Optimisation of 2D U-Net Model Components for Automatic Prostate Segmentation on MRI. Appl. Sci. 2020, 10, 2601. https://doi.org/10.3390/app10072601

AMA Style

Astono IP, Welsh JS, Chalup S, Greer P. Optimisation of 2D U-Net Model Components for Automatic Prostate Segmentation on MRI. Applied Sciences. 2020; 10(7):2601. https://doi.org/10.3390/app10072601

Chicago/Turabian Style

Astono, Indriani P., James S. Welsh, Stephan Chalup, and Peter Greer. 2020. "Optimisation of 2D U-Net Model Components for Automatic Prostate Segmentation on MRI" Applied Sciences 10, no. 7: 2601. https://doi.org/10.3390/app10072601

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop