A Prostate Boundary Localization and Edge Denoising Algorithm
Abstract
This research aimed at presenting a two-step method for prostate segmentation in TRUS images. The research used a prostate boundary localization and prostate edge denoising approach. The proposed method contribution is the use of the optimized Hodge’s method as the boundary operator and the use of the Bidirectional Exponential moving average to perform edge denoising. The results showed that the proposed method is effective in completing the prostate segmentation task. (1) The prostate region is effectively initialized and localized. (2) The recovery of noise points is accomplished and the segmentation result being consistent with the general shape of the prostate. The experimental results showed that this method can improve the overall segmentation accuracy. The process uses a combination of traditional and unsupervised methods, eliminating the need to rely on large data sets compared to current deep learning methods. The proposed method achieved excellent segmentation accuracy, with the Dice similarity coefficient (DICE) value of 0.9679, an average Intersection over Union (IoU) value of 0.9377, and an average False Positive Rate (FPR) of 0.0399. The results obtained from this study have significant implications for clinical practice. Accurate prostate segmentation is crucial for various applications, including radiation therapy planning, image-guided interventions, and computer-aided diagnosis. The proposed method has the potential to improve these applications by providing more precise and reliable prostate segmentations. However, it is important to acknowledge some limitations of this study. First, the proposed method was evaluated on a limited dataset, which may not fully represent the diversity of prostate images encountered in clinical practice. Further validation on larger datasets is necessary to assess its generalizability. Additionally, the proposed method relied on manual annotations for training, which can introduce inter-observer variability. Incorporating automated or semi-automated annotation techniques could enhance the robustness of the method
Downloads
References
M. A., Kasban, Hany, M. El-Bendary, and D. H. Salama. "A comparative study of medical imaging techniques”, International Journal of Information Science and Intelligent System, Vol. 4, issue 2, pp 37-58, 2015.
Y., Wang, J. Z., Cheng, Z., D., Ni. et al. “Towards Personalized Statistical Deformable Model and Hybrid Point Matching for Robust MR-TRUS Registration. [M]”. Springer International Publishing, Vol. 20, issue 6, pp 807-58, 2016.
K.K., Hodge, J.E., McNeal, M.K., Terris, T.A., Stamey. “Random systematic versus directed ultrasound guided transrectal core biopsies of the prostate”. Journal Urol. Vol. 142, issue 1, pp 71-4; discussion 74-5, July 1989.
Y., Gao, et al. (2018). "A Modified Level Set Method for Prostate Segmentation in MRI." Journal of Medical Imaging and Health Informatics, vol. 8, no. 1, pp. 108-115. (Print)
M., Ghafoorian, N., Karssemeijer, T., Heskes, I.W.M., van Uden, C.I., Sanchez, G., Litjens et al. “Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities”. Sci Rep, vol. 7, issue 1, 2017.
B.V., Ginneken, C.M., Schaefer-Prokop, M., Prokop. “Computer-aided Diagnosis: How to Move from the Laboratory to the Clinic”. Radiology. Vol. 261, issue 3, pp 719–32, 2011.
X., Chen, B.M., Williams, R., S., Vallabhaneni, G., Czanner, R., Williams, and Y., Zheng. "Learning active contour models for medical image segmentation." In Proceedings of the conference on Computer vision and pattern recognition, IEEE/CVF, 2019, pp. 11632-11640.
F., Liao, M., Liang, Z., Li et al. “Evaluate the malignancy of pulmonary nodules using the 3D Deep Leaky Noisy‐or Network”. 2017. arXiv preprint arXiv:1711.08324.
L., Chen, Z., Yukun, G., Papandreou, F. Schroff, and A., Hartwig. "Encoder-decoder with atrous separable convolution for semantic image segmentation." In Proceedings of the European conference on computer vision (ECCV), 2018, pp. 801-818.
A. A. A., Setio, A., Traverso, de Bel T et al. “Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge”. Med Image Anal, Vol. 42, pp 1–13, 2017.
T.F., Cootes, C.J., Taylor, D.H., Cooper, and J. Graham. "Active shape models-their training and application. Computer vision and image understanding”, Med Image Anal, Vol. 61, issues 1, pp 38-59, 1995.
B., Etienne (2021), Introduction to machine learning, Wolfram Media, Incorporated, Chapter 7, [Online], Available: https://books.google.co.uk/books?id=x6K7zgEACAAJ
X., Gao, S., Ya, L., Xuelong, and T., Dacheng. "A review of active appearance models, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol. 40, issue 2, pp 145-158, 2010.
M., Zhen, J., Manuel, R.S., Tavares, R. N., Jorge, and T. Mascarenhas. "A review of algorithms for medical image segmentation and their applications to the female pelvic cavity”. Computer Methods in Biomechanics and Biomedical Engineering, Vol. 13, issue 2, pp 235-246, 2010.
N., Ghavami, H., Yipeng, E. Gibson, E. Bonmati, M., Emberton, C.M., Moore, and D.C., Barratt. "Automatic segmentation of prostate MRI using convolutional neural networks: Investigating the impact of network architecture on the accuracy of volume measurement and MRI-ultrasound registration”. Medical image analysis, Vol. 58, pp 1015-58, 2019.
P., Wu, Y., Liu, Y., Li et al. Robust prostate segmentation using intrinsic properties of TRUS images[J]. IEEE transactions on medical imaging, Vol. 34, issue 6, 2015.
X., Yuan, T., Xu, H., Zhang, L. R., Long, and X., Huang. "Segan: Adversarial network with multi-scale l 1 loss for medical image segmentation", Neuro-informatics, Vol. 16, 383-392, 2018.
Yan P, Xu S, Turkbey B, et al. “Discrete Deformable Model Guided by Partial Active Shape Model for TRUS Image Segmentation[J]”. IEEE Trans Biomed Eng, Vol.57 issue, 5), pp 1158-1166, 2010.
M.A., Deeley, Chen, A., Datteri, R., Noble, J.H., Cmelak, A.J., Donnelly, E.F., et al. “Comparison of manual and automatic segmentation methods for brain structures in the presence of space-occupying lesions: a multi-expert study”, Phys Med Biol., Vol. 56, issue 14, pp 4557–7, 2011
S., Ghose, O., Arnau, R., Martí, X., Lladó, Joan C. et al. "A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images”, Computer methods and programs in biomedicine, Vol. 108, issue 1, pp 262-287, 2012.
L., Gong, D., Sayan, D.R., Pathak, P.S., Cho, and K., Yongmin. "Parametric shape modeling using deformable superellipses for prostate segmentation. "IEEE transactions on medical imaging Vol. 23, issue 3, pp 340-349, 2004.
T.X., Peng, T., Wang, Y., Fanzhang et al. (2020). Deep Belief Network and Closed Polygonal Line for Lung Segmentation in Chest Radiographs. The Computer Journal. Vol. 65, issue 10, pp 89-103
O., Ronneberger, P., Fischer, and T., Brox. "U-net: Convolutional networks for biomedical image segmentation." In 18th International Conference on Medical Image Computing and Computer-Assisted Intervention–MICCAI, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp. 234-241. Springer International Publishing, 2015.
N., Orlando, D.J., Gillies, I., Gyacskov, C., Romagnoli, D., D’Souza, and A., Fenster. "Automatic prostate segmentation using deep learning on clinically diverse 3D transrectal ultrasound images. “Medical physics, Vol. 47, issue 6, pp 2413-2426, 2020.
J., Chen and R., Xukan. "Deep learning with edge computing: A review. “Proceedings of the IEEE 107, no. 8 (2019): 1655-1674Gondara, Lovedeep. "Medical image denoising using convolutional denoising autoencoders." In 2016 IEEE 16th international conference on data mining workshops (ICDMW), pp. 241-246. IEEE, 2016.
C., Zhang, X., Sun, K., Dang, Li, K., Guo, X.W., Chang, J., Yu, Z.Q., Huang, F.Y., Wu, Y.S., Liang, Z., Liu, Z.Y., Zhang, X.G., Gao, X.L., Huang, S.H., Qin, J., Feng, W.N., Zhou, T., Zhang, Y.B., Fang, W.J., Zhao, M.F., Yang, X.N., Zhou, Q., Wu, Y.L, Zhong, W.Z., “Toward an Expert Level of Lung Cancer Detection and Classification Using a Deep Convolutional Neural Network”. Oncologist. 2019 Sep;24(9):1159-1165. doi: 10.1634/theoncologist.2018-0908. Epub 2019 Apr 17. PMID: 30996009; PMCID: PMC6738288
G., Kasinathan, J., Selvakumar, H., Amir Gandomi, R., Manikandan, S.J., Fong, and R., Patan. "Automated 3-D lung tumour detection and classification by an active contour model and CNN classifier. “Expert Systems with Applications, Vol. 134, pp 112-119, 2019.
A.C., Hodge, A., Fenster, D.B., Downey, and H.M., Ladak. "Prostate boundary segmentation from ultrasound images using 2D active shape models: Optimisation and extension to 3D."Computer methods and programs in biomedicine Vol. 84, issue 2-3, pp 99-113, 2006.
T., Hastie, R., Tibshirani, J.H., Friedman, and J.H. Friedman. “The elements of statistical learning: data mining, inference, and prediction”. Vol. 2. New York: springer, 2009.
M., Liang, W., Tang, X., Xu, et al “Comparison of manual and computer-aided liver tumour segmentation methods for MR images”. J Digit Imaging, Vol. 27(6), pp 729-736, 2014.
L., Xiangbin, L., Song, S., Liu, and Y., Zhang. "A review of deep-learning-based medical image segmentation methods”, Sustainability, Vol. 13, issue 3, pp 1224, 2021.
M., Mirza, X., Bing, D., Warde-Farley, O., Sherjil, A., Courville, Y., Bengio, I. J. Goodfellow, and J. Pouget-Abadie. "Generative adversarial nets. Advances in neural information processing systems, Vol. 27, pp 2672-2680, 2014.
M.T., Michael. Machine learning. Vol. 1. New York: McGraw-hill, 2007.
O., Nobuyuki. "A threshold selection method from gray-level histograms", IEEE transactions on systems, man, and cybernetics, Vol. 9, issue 1, pp 62-66, 1979.
V., Gulshan, L., Peng, M., Coram et al. “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs”. JAMA, 316: pp 2402–2410, 2016.
S., Rahnamayan, H.R., Tizhoosh, and M.M.A., Salama. "Automated snake initialization for the segmentation of the prostate in ultrasound images." In Image Analysis and Recognition: Second International Conference, ICIAR, Toronto, Canada, Springer Berlin Heidelberg, September, 2005. Proceedings 2, pp. 930-937.
D.E., Rumelhart, G.E., Hinton, and R.J., Williams. "Learning representations by back-propagating errors”, Nature, 323, no. 6088, pp 533-536, 1986.
S., Saradwata, and D., Sudipta. "A review of imaging methods for prostate cancer detection: supplementary issue: image and video acquisition and processing for clinical applications." Biomedical engineering and computational biology 7, BECB-S34255, 2016.
J.L., Speiser, M.E., Miller, J., Tooze et al. "A comparison of random forest variable selection methods for classification prediction modeling. Expert systems with applications”, Vol. 134, pp 93-10, 2019.
L.A., Torre, F., Bray, R.L., Siegel, J., Ferlay, J., Lortet‐Tieulent, and A., Jemal. "Global cancer statistics, 2012." CA: a cancer journal for clinicians, Vol. 65, issue 2, pp 87-108, 2015.
V., Pascal, et al. “Extracting and composing robust features with denoising autoencoders.” Proceedings of the 25th international conference on Machine learning. ACM, 2008.
Wang, G., Li, W., Aertsen, M., Deprest, J., & Ourselin, S. (2019). Automatic fetal brain segmentation from 2D MRI slices for motion correction. Medical Image Analysis, 52, 291-303. (Web)
L., Wang, L., Bin, H., Mengjie, Y., Wang, Z., Wang, and L., Du. (2022). "Prostate cancer incidence and mortality: global status and temporal trends in 89 countries from 2000 to 2019." Frontiers in Public Health, Vol. 10, issue 1, pp 811-44, 2019.
Y., Changqian, G., Changxin, J., Wang, G., Yu, C., Shen, and N., Sang. "Bisenet v2: Bilateral network with guided aggregation for real- time semantic segmentation." International Journal of Computer Vision, Vol. 129, pp 3051-3068, 2021.
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.
Han, C., Zhu, L., Liu, X. et al. Differential diagnosis of uncommon prostate diseases: combining mpMRI and clinical information. Insights Imaging, 12, 79 (2021). https://doi.org/10.1186/s13244-021-01024-3.
Copyright (c) 2024 Daisy Thembelihle Mukondiwa, YongTao Shi, PhD, Chao Gao
This work is licensed under a Creative Commons Attribution 4.0 International License.
