Segmentation of prostate and prostate zones using deep learning
- PDF / 3,011,929 Bytes
- 11 Pages / 612.419 x 808.052 pts Page_size
- 103 Downloads / 201 Views
ORIGINAL ARTICLE
Segmentation of prostate and prostate zones using deep learning A multi-MRI vendor analysis Olmo Zavala-Romero1 · Adrian L. Breto1 · Isaac R. Xu1 · Yu-Cherng C. Chang2 · Nicole Gautney1 · Alan Dal Pra1 · Matthew C. Abramowitz1 · Alan Pollack1 · Radka Stoyanova1 Received: 23 August 2019 / Accepted: 10 March 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Purpose Develop a deep-learning-based segmentation algorithm for prostate and its peripheral zone (PZ) that is reliable across multiple MRI vendors. Methods This is a retrospective study. The dataset consisted of 550 MRIs (Siemens-330, General Electric[GE]-220). A multistream 3D convolutional neural network is used for automatic segmentation of the prostate and its PZ using T2-weighted (T2-w) MRI. Prostate and PZ were manually contoured on axial T2-w. The network uses axial, coronal, and sagittal T2-w series as input. The preprocessing of the input data includes bias correction, resampling, and image normalization. A dataset from two MRI vendors (Siemens and GE) is used to test the proposed network. Six different models were trained, three for the prostate and three for the PZ. Of the three, two were trained on data from each vendor separately, and a third (Combined) on the aggregate of the datasets. The Dice coefficient (DSC) is used to compare the manual and predicted segmentation. Results For prostate segmentation, the Combined model obtained DSCs of 0.893 ± 0.036 and 0.825 ± 0.112 (mean ± standard deviation) on Siemens and GE, respectively. For PZ, the best DSCs were from the Combined model: 0.811 ± 0.079 and 0.788 ± 0.093. While the Siemens model underperformed on the GE dataset and vice versa, the Combined model achieved robust performance on both datasets. Conclusion The proposed network has a performance comparable to the interexpert variability for segmenting the prostate and its PZ. Combining images from different MRI vendors on the training of the network is of paramount importance for building a universal model for prostate and PZ segmentation.
Keywords Prostate segmentation · Peripheral zone · Deep learning · Convolutional neuro Network
Introduction Accurate prostate segmentation on MRI datasets is required for many clinical and research applications. In addition, due to the different imaging properties of the peripheral (PZ) and transition zones (TZ) of the prostate, accurate zonal
Radka Stoyanova, PhD
[email protected] 1
Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
2
University of Miami Miller School of Medicine, Miami, FL, USA
segmentation is also necessary. The prostate and zonal contours are required for computer-aided diagnosis (CAD) applications for staging, diagnosis, and treatment planning for prostate cancer. In a series of applications, prostate contours are fused with ultrasound images to guide prostate biopsies. Automatic segmentation of the prostate, PZ and TZ on MR images provides an oppo
Data Loading...
