Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress 2023 EHA Congress 2023 ASCO Annual Meeting
Clinical Collections
Advances in Alzheimer’s

At a glance: The ONWARDS insulin icodec trials

A round-up of the ONWARDS phase 3 clinical trials evaluating the novel weekly insulin icodec in people with diabetes.
ADVANCED SEARCH
Log in
Top
Strahlentherapie und Onkologie
Published in: Strahlentherapie und Onkologie 10/2020

01-10-2020 | Original Article

Segmentation of prostate and prostate zones using deep learning

A multi-MRI vendor analysis

Authors: Olmo Zavala-Romero, PhD, Adrian L. Breto, MSc, Isaac R. Xu, Yu-Cherng C. Chang, PhD, Nicole Gautney, Alan Dal Pra, MD, Matthew C. Abramowitz, MD, Alan Pollack, MD,PhD, Radka Stoyanova, PhD

Published in: Strahlentherapie und Onkologie | Issue 10/2020

Login to get access

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.
Literature
1.
Litjens G et al (2014) Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. Med Image Anal 18(2):359–373PubMedCrossRef
2.
Chowdhury N et al (2012) Concurrent segmentation of the prostate on MRI and CT via linked statistical shape models for radiotherapy planning. Med Phys 39(4):2214–2228PubMedPubMedCentralCrossRef
3.
Toth R, Madabhushi A (2012) Multifeature landmark-free active appearance models: application to prostate MRI segmentation. IEEE Trans Med Imaging 31(8):1638–1650PubMedCrossRef
4.
Klein S et al (2008) Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Med Phys 35(4):1407–1417PubMedCrossRef
5.
Cheng R et al (2014) Atlas Based AAM and SVM Model for Fully Automatic MRI Prostate Segmentation. 2014 36th Annual International Conference of the Ieee Engineering in Medicine and Biology Society (Embc),, pp 2881–2885
6.
Xie QL, Ruan D (2014) Low-complexity atlas-based prostate segmentation by combining global, regional, and local metrics. Med Phys 41(4):41909PubMedCrossRef
7.
8.
Korsager AS et al (2015) The use of atlas registration and graph cuts for prostate segmentation in magnetic resonance images. Med Phys 42(4):1614–1624PubMedCrossRef
9.
10.
Padgett KR et al (2019) Towards a universal MRI atlas of the prostate and prostate zones: Comparison of MRI vendor and image acquisition parameters. Strahlenther Onkol 195(2):121–130PubMedCrossRef
11.
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90CrossRef
12.
Simonyan K, Zisserman A, Criminisi A (2011) Immediate structured visual search for medical images. Med Image Comput Comput Interv 6893:288 (Pt Iii)
13.
Yu L et al (2017) Volumetric ConvNets with mixed residual connections for automated prostate segmentation from 3D MR images. In: Thirty-first AAAI conference on artificial intelligence
14.
Ronneberger O, Fischer P, Brox T (2015) U‑net: Convolutional networks for biomedical image segmentation. Med Imag Comput Comput Interv 9351(Iii):234–241
15.
Meyer A et al (2018) Automatic high resolution segmentation of the prostate from multi-planar MRI. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) Washington, DC, pp 177–181CrossRef
16.
17.
18.
Yoo TS et al (2002) Engineering and algorithm design for an image processing API: a technical report on ITK-the insight toolkit. Stud Health Technol Inform 85:586–592PubMed
19.
Farnebäck G (2003) Two-frame motion estimation based on polynomial expansion. In: Scandinavian conference on Image analysis. Springer, Berlin
20.
Çiçek Ö et al (2016) 3D U‑Net: learning dense volumetric segmentation from sparse annotation. In: International conference on medical image computing and computer-assisted intervention. Springer, Berlin
21.
Zeiler MD et al (2010) Deconvolutional networks. In: 2010 IEEE conference on computer vision and pattern recognition (Cvpr), pp 2528–2535CrossRef
22.
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning Lille. vol 37, pp 448–456 (JMLR.org)
23.
Hinton GE et al (2012) Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580
24.
Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302CrossRef
25.
26.
Abadi M et al (2016) Tensorflow: A system for large-scale machine learning. In: 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16)
27.
Brownlee J (2019) Deep learning for computer vision: image classification, object detection, and face recognition in python
28.
Gibson E et al (2018) Inter-site variability in prostate segmentation accuracy using deep learning. Med Image Comput Comput Assist Interv 11073:506–514 (Pt Iv)
29.
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
30.
Ronneberger O, Fischer P, Brox T (2015) U‑net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer, Berlin
31.
Milletari F, Navab N, Ahmadi S‑A (2016) V‑net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV) IEEE.
32.
Guo Y, Gao Y, Shen D (2016) Deformable MR prostate segmentation via deep feature learning and sparse patch matching. IEEE Trans Med Imaging 35(4):1077–1089PubMedCrossRef
33.
Lozoya RC et al (2018) Assessing the relevance of multi-planar MRI acquisitions for prostate segmentation using deep learning techniques. Medical imaging 2018: imaging Informatics for Healthcare, research, and applications vol 10579
34.
Jia H et al (2018) 3D global convolutional adversarial network\\for prostate MR volume segmentation. arXiv preprint arXiv:1807.06742
35.
Litjens G et al (2012) A pattern recognition approach to zonal segmentation of the prostate on MRI. Med Image Comput Comput Interv 7511:413–420 (Pt Ii)
36.
Mooij G, Bagulho I, Huisman H (2018) Automatic segmentation of prostate zones. arXiv preprint arXiv:1806.07146
37.
Toth R et al (2013) Simultaneous segmentation of prostatic zones using active appearance models with multiple coupled levelsets. Comput Vis Image Underst 117(9):1051–1060PubMedPubMedCentralCrossRef
38.
To NN et al (2018) Deep dense multi-path neural network for prostate segmentation in magnetic resonance imaging. Int J CARS 13(11):1687–1696CrossRef
39.
Hesamian MH et al (2019) Deep learning techniques for medical image segmentation: achievements and challenges. J Digit Imaging 32(4):582–596PubMedPubMedCentralCrossRef
40.
Tajbakhsh N et al (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35(5):1299–1312PubMedCrossRef
Metadata
Title
Segmentation of prostate and prostate zones using deep learning
A multi-MRI vendor analysis
Authors
Olmo Zavala-Romero, PhD
Adrian L. Breto, MSc
Isaac R. Xu
Yu-Cherng C. Chang, PhD
Nicole Gautney
Alan Dal Pra, MD
Matthew C. Abramowitz, MD
Alan Pollack, MD,PhD
Radka Stoyanova, PhD
Publication date
01-10-2020
Publisher
Springer Berlin Heidelberg
Published in
Strahlentherapie und Onkologie / Issue 10/2020
Print ISSN: 0179-7158
Electronic ISSN: 1439-099X
DOI
https://doi.org/10.1007/s00066-020-01607-x

Other articles of this Issue 10/2020

Strahlentherapie und Onkologie 10/2020 Go to the issue

Review Article

Radiomic biomarkers for head and neck squamous cell carcinoma

Review Article

Radiomics in radiation oncology—basics, methods, and limitations

Literatur kommentiert

Vielversprechende Langzeitergebnisse zum Einsatz von Anastrozol zur Prävention von Brustkrebs bei postmenopausalen Hochrisikopatientinnen

Literatur kommentiert

Die Herzmortalität nach Strahlentherapie, Chemotherapie und endokriner Therapie des Mammakarzinoms

Short Communication

Cone-beam computed tomography-based radiomics in prostate cancer: a mono-institutional study

Review Article

Radiomics and deep learning in lung cancer