Abstract
In this paper, we investigate if the MR prostate segmentation performance could be improved, by only providing one-point labeling information in the prostate region. To achieve this goal, by asking the physician to first click one point inside the prostate region, we present a novel segmentation method by simultaneously integrating the boundary detection results and the patch-based prediction. Particularly, since the clicked point belongs to the prostate, we first generate the location-prior maps, with two basic assumptions: (1) a point closer to the clicked point should be with higher probability to be the prostate voxel, (2) a point separated by more boundaries to the clicked point, will have lower chance to be the prostate voxel. We perform the Canny edge detector and obtain two location-prior maps from horizontal and vertical directions, respectively. Then, the obtained location-prior maps along with the original MR images are fed into a multi-channel fully convolutional network to conduct the patch-based prediction. With the obtained prostate-likelihood map, we employ a level-set method to achieve the final segmentation. We evaluate the performance of our method on 22 MR images collected from 22 different patients, with the manual delineation provided as the ground truth for evaluation. The experimental results not only show the promising performance of our method but also demonstrate the one-point labeling could largely enhance the results when a pure patch-based prediction fails.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cokkinides, V., Albano, J., Samuels, A., et al.: American Cancer Society: Cancer Facts and Figures. American Cancer Society, Atlanta (2005)
Ghose, S., Oliver, A., Mart, R., et al.: A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images. Comput. Methods Programs Biomed. 108(1), 262–287 (2012)
Klein, S., van der Heide, U.A., Lips, I.M., et al.: Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Med. Phys. 35(4), 1407–1417 (2008)
Gao, Y., Sandhu, R., Fichtinger, G., et al.: A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery. IEEE Trans. Med. Imaging 29(10), 1781–1794 (2010)
Toth, R., Tiwari, P., Rosen, M., et al.: A magnetic resonance spectroscopy driven initialization scheme for active shape model based prostate segmentation. Med. Image Anal. 15(2), 214–225 (2011)
Liao, S., Gao, Y., Oto, A., Shen, D.: Representation learning: a unified deep learning framework for automatic prostate MR segmentation. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8150, pp. 254–261. Springer, Heidelberg (2013). doi:10.1007/978-3-642-40763-5_32
Shi, Y., Liao, S., Gao, Y., Zhang, D., Gao, Y., Shen, D.: Transductive prostate segmentation for CT image guided radiotherapy. In: Wang, F., Shen, D., Yan, P., Suzuki, K. (eds.) MLMI 2012. LNCS, vol. 7588, pp. 1–9. Springer, Heidelberg (2012). doi:10.1007/978-3-642-35428-1_1
Park, S.H., Yun, I.D., Lee, S.U.: Data-driven interactive 3D medical image segmentation based on structured patch model. In: Gee, J.C., Joshi, S., Pohl, K.M., Wells, W.M., Zöllei, L. (eds.) IPMI 2013. LNCS, vol. 7917, pp. 196–207. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38868-2_17
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Shi, Y., Liao, S., Gao, Y., et al.: Prostate segmentation in CT images via spatial-constrained transductive lasso. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2227–2234 (2013)
Shi, Y., Gao, Y., Liao, S., et al.: Semi-automatic segmentation of prostate in CT images via coupled feature representation and spatial-constrained transductive lasso. IEEE Trans. Pattern Anal. Mach. Intell. 37(11), 2286–2303 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv: 1502.03167 (2015)
Kingma, D., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv: 1412.6980 (2014)
Abadi, M., Barham, P., Chen, J., et al.: TensorFlow: a system for large-scale machine learning. In: Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI), Savannah, Georgia, USA (2016)
Li, C., Xu, C., Gui, C., et al.: Distance regularized level set evolution and its application to image segmentation. IEEE Trans. Image Process. 19(12), 3243–3254 (2010)
Coupé, P., Manjnó, J.V., Fonov, V., et al.: Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation. NeuroImage 54(2), 940–954 (2011)
Klein, S., van der Heide, U.A., Lips, I.M., et al.: Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information. Med. Phys. 35(4), 1407–1417 (2008)
Acknowledgement
This work was supported by NSFC (61673203, 61432008), Nanjing Science and Technique Development Foundation (201503041), Young Elite Scientists Sponsorship Program by CAST (YESS 20160035) and NIH Grant (CA206100).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Sun, J., Shi, Y., Gao, Y., Shen, D. (2017). A Point Says a Lot: An Interactive Segmentation Method for MR Prostate via One-Point Labeling. In: Wang, Q., Shi, Y., Suk, HI., Suzuki, K. (eds) Machine Learning in Medical Imaging. MLMI 2017. Lecture Notes in Computer Science(), vol 10541. Springer, Cham. https://doi.org/10.1007/978-3-319-67389-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-67389-9_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67388-2
Online ISBN: 978-3-319-67389-9
eBook Packages: Computer ScienceComputer Science (R0)