Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
31 08 2020
31 08 2020
Historique:
received:
27
04
2020
accepted:
10
08
2020
entrez:
2
9
2020
pubmed:
2
9
2020
medline:
20
3
2021
Statut:
epublish
Résumé
Magnetic resonance imaging (MRI) provides detailed anatomical images of the prostate and its zones. It has a crucial role for many diagnostic applications. Automatic segmentation such as that of the prostate and prostate zones from MR images facilitates many diagnostic and therapeutic applications. However, the lack of a clear prostate boundary, prostate tissue heterogeneity, and the wide interindividual variety of prostate shapes make this a very challenging task. To address this problem, we propose a new neural network to automatically segment the prostate and its zones. We term this algorithm Dense U-net as it is inspired by the two existing state-of-the-art tools-DenseNet and U-net. We trained the algorithm on 141 patient datasets and tested it on 47 patient datasets using axial T2-weighted images in a four-fold cross-validation fashion. The networks were trained and tested on weakly and accurately annotated masks separately to test the hypothesis that the network can learn even when the labels are not accurate. The network successfully detects the prostate region and segments the gland and its zones. Compared with U-net, the second version of our algorithm, Dense-2 U-net, achieved an average Dice score for the whole prostate of 92.1± 0.8% vs. 90.7 ± 2%, for the central zone of [Formula: see text]% vs. [Formula: see text] %, and for the peripheral zone of 78.1± 2.5% vs. [Formula: see text]%. Our initial results show Dense-2 U-net to be more accurate than state-of-the-art U-net for automatic segmentation of the prostate and prostate zones.
Identifiants
pubmed: 32868836
doi: 10.1038/s41598-020-71080-0
pii: 10.1038/s41598-020-71080-0
pmc: PMC7459118
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Validation Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
14315Références
Aldoj, N., Lukas, S., Dewey, M. & Penzkofer, T. Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network. Eur. Radiol. 30, 1243–1253 (2020).
doi: 10.1007/s00330-019-06417-z
Siegel, R. . L., Miller, K. . D. & Jemal, A. Cancer statistics, 2016. CA Cancer J. Clin. 66, 7–30 (2016).
doi: 10.3322/caac.21332
Wang, Y. et al. Towards personalized statistical deformable model and hybrid point matching for robust MR-TRUS registration. IEEE Trans. Med. Imaging 35, 589–604 (2016).
doi: 10.1109/TMI.2015.2485299
Terris, M. K. & Stamey, T. A. Determination of prostate volume by transrectal ultrasound. J. Urol. 145, 984–987 (1991).
doi: 10.1016/S0022-5347(17)38508-7
Zettinig, O. et al. Multimodal image-guided prostate fusion biopsy based on automatic deformable registration. Int. J. Comput. Assist. Radiol. Surg. 10, 1997–2007 (2015).
doi: 10.1007/s11548-015-1233-y
Sabouri, S. et al. MR measurement of luminal water in prostate gland: quantitative correlation between MRI and histology. J. Magn. Reson. Imaging 46, 861–869 (2017).
doi: 10.1002/jmri.25624
Mahapatra, D. & Buhmann, J. M. Prostate MRI segmentation using learned semantic knowledge and graph cuts. IEEE Trans. Bio-Med. Eng. 61, 756–764 (2014).
doi: 10.1109/TBME.2013.2289306
Yu, L., Yang, X., Chen, H., Qin, J. & Heng, P.-A. Volumetric ConvNets with mixed residual connections for automated prostate segmentation from 3D MR images. In AAAI Conference on Artificial Intelligence.31 (2017).
Klein, S. et al. Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Med. Phys. 35, 1407–1417 (2017).
doi: 10.1118/1.2842076
Toth, R. & Madabhushi, A. Multifeature landmark-free active appearance models: application to prostate MRI segmentation. IEEE Trans. Med. Imaging 31, 1638–1650 (2012).
doi: 10.1109/TMI.2012.2201498
Qiu, W. et al. Dual optimization based prostate zonal segmentation in 3D MR images. Med. Image Anal. 18, 660–673 (2014).
doi: 10.1016/j.media.2014.02.009
Zheng, Y. & Comaniciu, D. Marginal Space Learning for Medical Image Analysis (Springer, Berlin, 2014).
doi: 10.1007/978-1-4939-0600-0
Makni, N. et al. Zonal segmentation of prostate using multispectral magnetic resonance images. Med. Phys. 38, 6093–6105 (2011).
doi: 10.1118/1.3651610
Litjens, G., Debats, O., van de Ven, W., Karssemeijer, N. & Huisman, H. A pattern recognition approach to zonal segmentation of the prostate on MRI. In International Conference on Medical Image Computing and Computer-Assisted Intervention 413–420 (2012).
Christ, P. F. et al. Automatic liver and tumor segmentation of ct and mri volumes using cascaded fully convolutional neural networks. arXiv:1702.05970 (2017).
Li, X. et al. H-DenseUNet: hybrid densely connected UNet for liver and liver tumor segmentation from CT volumes. IEEE Trans. Med. Imaging 37, 2663–2674 (2018).
doi: 10.1109/TMI.2018.2845918
Roth, H. R. et al. An application of cascaded 3D fully convolutional networks for medical image segmentation. Comput. Med. Imaging Graph. 66, 90–99 (2018).
doi: 10.1016/j.compmedimag.2018.03.001
Deniz, C. M. et al. Segmentation of the proximal femur from MR images using deep convolutional neural networks. Sci. Rep. 8, 16485 (2018).
doi: 10.1038/s41598-018-34817-6
Kushibar, K. et al. Supervised domain adaptation for automatic sub-cortical brain structure segmentation with minimal user interaction. Sci. Rep. 9, 6742 (2019).
doi: 10.1038/s41598-019-43299-z
Zhu, Q., Du, B., Turkbey, B., Choyke, P. L. & Yan, P. Deeply-supervised CNN for prostate segmentation. In:International Joint Conference on Neural Networks IEEE. 178–184 (2017).
Milletari, F., Navab, N. & Ahmadi, S.-A. V-net: fully convolutional neural networks for volumetric medical image segmentation. In Fourth International Conference on 3D Vision, 565–571 (2016).
Zabihollahy, F., Schieda, N., Krishna Jeyaraj, S. & Ukwatta, E. Automated segmentation of prostate zonal anatomy on T2-weighted (T2W) and apparent diffusion coefficient (ADC) map MR images using U-Nets. Med. Phys. 46, 3078–3090 (2019).
doi: 10.1002/mp.13550
Clark, T., Wong, A., Haider, A. .M. & Khalvati, F. Fully deep convolutional neural networks for segmentation of the prostate gland in diffusion-weighted MR images. J. Med. Imaging 4, 97–104 (2017).
doi: 10.1117/1.JMI.4.4.041307
Ronneberger, O., Fischer, P. & Brox, T. U-net: convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention 234–241 (2015).
Szegedy, C., Ioffe, S., Vanhoucke, V. & Alemi, A. A. Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-first AAAI Conference on Artificial Intelligence. 4, 12 (2017).
Zhu, Y. et al. Fully automatic segmentation on prostate MR images based on cascaded fully convolution network. J. Magn. Reson. Imaging 49, 1149–1156 (2019).
doi: 10.1002/jmri.26337
Chilali, O. et al. Gland and zonal segmentation of prostate on T2W MR images. J. Digit. Imaging 29, 730–736 (2016).
doi: 10.1007/s10278-016-9890-0
Tian, Z., Liu, L., Zhang, Z. & Fei, B. PSNet: prostate segmentation on MRI based on a convolutional neural network. J. Med. Imaging 5, 1–6 (2018).
doi: 10.1117/1.JMI.5.2.021208
Rundo, L. et al. USE-Net: incorporating squeeze-and-excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets. Neurocomputing 365, 31–43 (2019).
doi: 10.1016/j.neucom.2019.07.006
Rundo, L. et al. CNN-based prostate zonal segmentation on T2-weighted MR images: a cross-dataset study. In Neural Approaches to Dynamics of Signal Exchanges 269–280 (2020).
Karimi, D., Samei, G., Kesch, C., Nir, G. & Salcudean, S. E. Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models. Int. J. Comput. Assist. Radiol. Surg. 13, 1211–1219 (2018).
doi: 10.1007/s11548-018-1785-8
Jia, H. et al. Atlas registration and ensemble deep convolutional neural network-based prostate segmentation using magnetic resonance imaging. Neurocomputing. 275, 1358–1369 (2018).
doi: 10.1016/j.neucom.2017.09.084
Cheng, R. et al. Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks. J. Med. Imaging. 4, 041302 (2017).
Meyer, A. et al. Automatic high resolution segmentation of the prostate from multi-planar MRI. In IEEE International Symposium on Biomedical Imaging177–181 (2018).
Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1, 3 (2017).
Zhao, H., Shi, J., Qi, X., Wang, X. & Jia, J. Pyramid scene parsing network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2881–2890 (2017).
Guan, M. Y., Gulshan, V., Dai, A. M. & Hinton, G. E. Who said what: modeling individual labelers improves classification. In Thirty-Second AAAI Conference on Artificial Intelligence (2018).
Drozdzal, M., Vorontsov, E., Chartrand, G., Kadoury, S. & Pal, C. The importance of skip connections in biomedical image segmentation. In Deep Learning and Data Labeling for Medical Applications 179–187 (2016).
Desai, A. D., Gold, G. E., Hargreaves, B. A. & Chaudhari, A. S. Technical considerations for semantic segmentation in MRI using convolutional neural networks. arXiv:1902.01977 (2019).
Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N. & Huisman, H. ProstateX Challenge data. Cancer Imag. Arch. 10, K9TCIA (2017).
Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N. & Huisman, H. Computer-aided detection of prostate cancer in MRI. IEEE Trans. Med. Imaging. 33, 1083–1092 (2014).
doi: 10.1109/TMI.2014.2303821
Clark, K. et al. The cancer imaging archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26, 1045–1057 (2013).
doi: 10.1007/s10278-013-9622-7
Armato, S. G. et al. PROSTATEx challenges for computerized classification of prostate lesions from multiparametric magnetic resonance images. J. Med. Imaging 5, 044501 (2018).
doi: 10.1117/1.JMI.5.4.044501
Simard, P. Y., Steinkraus, D. & Platt, J. C. Best practices for convolutional neural networks applied to visual document analysis. In Seventh International Conference on Document Analysis and Recognition 958–963 (2003).
Gu, J. et al. Recent advances in convolutional neural networks. arXiv:1512.07108 (2015).
Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. Pattern Recognit. 77, 354–377 (2014).
Springenberg, J. T., Dosovitskiy, A., Brox, T. & Riedmiller, M. Striving for simplicity: the all convolutional net. arXiv:1412.6806 (2014).
Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Dollár, P. Focal loss for dense object detection. In IEEE Transactions on Pattern Analysis and Machine Intelligence 2980–2988 (2018).
Kinga, D. & Adam, J. B. A method for stochastic optimization. In International Conference on Learning Representations (ICLR).5 (2015).
Dice, L. R. Measures of the amount of ecologic association between species. Ecology 26, 297–302 (1945).
doi: 10.2307/1932409
Taha, A. A. & Hanbury, A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med. Imaging 15, 29 (2015).
doi: 10.1186/s12880-015-0068-x
Taha, A. A. & Hanbury, A. An efficient algorithm for calculating the exact hausdorff distance. IEEE Trans. Pattern Anal. Mach. Intell. 37, 2153–2163 (2015).
doi: 10.1109/TPAMI.2015.2408351