Abstract
Medical image registration is vital for precise healthcare diagnosis, treatment planning, and disease progression tracking, but traditional methods fail to capture complex spatial transformations and anatomical variations. A Kernel Principal Component Analysis (KPCA) driven Teaching Learning based optimization (TLBO) approach is proposed to overcome these limitations. The proposed approach is categorized into three phases, i.e., pre-processed phase, contour extraction phase with feature extraction using KPCA, and evaluating robust affine transformation parameters leveraging TLBO for accurate alignment. In the pre-processing phase, gaussian filter is applied to remove noise from source and target images, followed by normalization process. Afterwards, contour extraction is carried out to create a feature image that represents the boundaries of an image. Centroid localization is then utilized to compute translation parameters, which determine the spatial alignment between the images. By utilizing KPCA, this method captures non-linear relationships in the data to enhance the representation of image features. TLBO is employed to optimize the rigid transformation parameters to improve the accurate alignment of source and target images. Extensive experiments are carried out on monomodal and multimodal medical images such as CT and MRI taken from the Harvard Brain ATLAS, Kaggle as well as in-house clinical dataset to demonstrate the effectiveness of the proposed approach. The proposed approach significantly outperforms state-of-the-art methods, with improvements of 44.37% in Root Mean Square Error (RMSE), 19.93% in Structural Similarity Index Measure (SSIM), 20.01% in Peak Signal-to-Noise Ratio (PSNR), and 16.21% in Cross Correlation (CC) quality assessment metrics.
Similar content being viewed by others
Data availability
The datasets used for the experimental work in the present study are considered from the publicly available datasets “Harvard Atlas Brain dataset [10]–[15]” and real time clinically dataset taken from the Fortis Hospital Mohali under the supervision of Dr. Harsimrat Bir Singh Sodhi, who holds degrees in MBBS, MS - General Surgery, and MCh - Neuro Surgery, specializing in neurosurgery upon reasonable request.
References
Jiang, X., Ma, J., Xiao, G., Shao, Z., Guo, X.: A review of multimodal image matching: Methods and applications. Information Fusion 73(2020), 22–71 (2020). https://doi.org/10.1016/j.inffus.2021.02.012
Nandi, D., Ashour, A.S., Samanta, S., Chakraborty, S., Salem, M.A.M., Dey, N.: Principal component analysis in medical image processing: A study. Int. J. Image Min. 1(1), 65–86 (2015). https://doi.org/10.1504/ijim.2015.070024
Hu, J., et al.: Towards Accurate and Robust Multi-modal Medical Image Registration using Contrastive Metric Learning. IEEE Access. 7, 132816–132827 (2019). https://doi.org/10.1109/ACCESS.2019.2938858
Arora, P., Mehta, R., Ahuja, R.: An adaptive medical image registration using hybridization of teaching learning-based optimization with affine and speeded up robust features with projective transformation. Cluster Comput. (2023). https://doi.org/10.1007/s10586-023-03974-3
Leng, C., Xiao, J., Li, M., Zhang, H.: Robust Adaptive Principal Component Analysis Based on Intergraph Matrix for Medical Image Registration,. Computational Intelligence and Neuroscience 2015(1), 55–65 (2015). https://doi.org/10.1155/2015/829528
Vishwakarma, H., Katiyar, S.K.: Accuracy assessment of projective transformation based hybrid approach for automatic satellite image registration. Int. J. Civil Eng. Technol. 9(13), 1514–1523 (2018)
Shehanaz, S., Daniel, E., Guntur, S.R., Satrasupalli, S.: Optimum weighted multimodal medical image fusion using particle swarm optimization. Optik. 231(1), 166413 (2021). https://doi.org/10.1016/j.ijleo.2021.166413
Saoji, S.U., Sarode, M.V.: Speckle and rician noise removal from medical images and Ultrasound images. Int. J. Recent Technol. Eng. 8(5), 1851–1854 (2020). https://doi.org/10.35940/ijrte.e5993.018520
Handa, B., Singh, G., Kamal, R., Oinam, A.S., Kumar, V.: Evaluation method for the optimization of 3D rigid image registration on multimodal image datasets. Int. J. Eng. Adv. Technol. 9(1), 5539–5545 (2019). https://doi.org/10.35940/ijeat.A2078.109119
Keith, A., Johnson, Becker, J.A.: The Whole Brain ATLAS. Harvard University. https://www.med.harvard.edu/aanlib/home.html (2008). Accessed July 2023
VBOOKSHELF: Brain CT Images with Intracranial Hemorrhage Masks. https://www.kaggle.com/vbookshelf/computed-tomography-ct-images (2019). Accessed August 2023
Feltrin, F.: Brain Tumor MRI images 44 classes. Kaggle. https://www.kaggle.com/datasets/fernando2rad/brain-tumor-mri-images-44c (2022). Accessed August 2023
Sartaj: Brain Tumor Classification (MRI). Kaggle https://www.kaggle.com/datasets/sartajbhuvaji/brain-tumor-classification-mri (2019). Accessed July 2023
Simeon, A.: Brain Tumor Images Dataset. Kaggle https://www.kaggle.com/datasets/simeondee/brain-tumor-images-dataset (2019). Accessed August 2023
Chakrabarty, N.: Brain MRI Images for Brain Tumor Detection. Kaggle https://www.kaggle.com/navoneel/brain-mri-images-for-brain-tumor-detection (2019). Accessed August 2023
Shang, L., Lv, J.C., Yi, Z.: Rigid medical image registration using PCA neural network. Neurocomputing. 69, 13–15 (2006). https://doi.org/10.1016/j.neucom.2006.01.007
Sadruddin, S., Ali, R.: Use of wavelet-fuzzy features with PCA for Image Registration. BVICA M’s International Journal of Information Technology. 6(1), 672–676 (2014)
Reel, P.S., Dooley, L.S., Wong, P.: Efficient image registration using fast principal component analysis. 19th IEEE International Conference on Image Processing 1, 1661–1664 (2012). https://doi.org/10.1109/ICIP.2012.6467196
Hazra, J., Chowdhury, A.R., Dasgupta, K., Dutta, P.: A hybrid structural feature extraction-based intelligent predictive approach for image registration. Innov. Syst. Softw. Eng. (2022). https://doi.org/10.1007/s11334-022-00436-8
Jin, J., Bi, X., Jiang, M., Chang, J., Cui, J.: Medical image registration based on PCA and M _ PSNR. J. Complex. Health Sci. 3(1), 62–72 (2020). https://doi.org/10.21595/chs.2020.21266
Reel, P.S., Dooley, L.S., Wong, K.C.P.: Multimodal retinal image registration using a fast principal component analysis hybrid based similarity measure. IEEE International Conference on Image Processing 9, 1428–1432 (2013). https://doi.org/10.1109/ICIP.2013.6738293
Xu, A., Jin, X., Guo, P., Bie, R.: KICA feature extraction in application to FNN based Image Registration. IEEE Int. Joint Conf. Neural Netw. Proc. no 7, 3602–3608 (2006). https://doi.org/10.1109/IJCNN.2006.247371
Duan, X., Tian, Z., Ding, M., Zhao, W.: Registration of remote-sensing images using robust weighted kernel principal component analysis. AEUE - International Journal of Electronics and Communications. 67(1), 20–28 (2013). https://doi.org/10.1016/j.aeue.2012.05.011
Chen, Y., Lin, C.: PCA based regional mutual information for robust medical image registration. IEICE Technical Report. 109 (65), 355–362 (2011). [Online]. Available: https://doi.org/10.1007/978-3-642-21111-9_40
Garg, S., Ahuja, R., Singh, R., Perl, I.: GMM-LSTM: A component driven resource utilization prediction model leveraging LSTM and gaussian mixture model. Cluster Comput. 26(6), 3547–3563 (2023). https://doi.org/10.1007/s10586-022-03747-4
Nazir, I., Haq, I., Alqahtani, S.A., Jadoon, M.M., Dahshan, M.: Machine Learning-Based Lung Cancer Detection Using Multiview Image Registration and Fusion. Journal of Sensors 2023, 6683438 (2023)
Huizinga, W., et al.: PCA-based groupwise image registration for quantitative MRI. Med. Image. Anal. 29(4), 65–78 (2016). https://doi.org/10.1016/j.media.2015.12.004
Narayanan, A., Rajasekaran, M.P., Zhang, Y., Govindaraj, V., Thiyagarajan, A.: ScienceDirect multi-channeled MR brain image segmentation: A novel double optimization approach combined with clustering technique for tumor identification and tissue segmentation. Integr. Med. Res. 39(2), 350–381 (2018). https://doi.org/10.1016/j.bbe.2018.12.003
Azam, M.A., Khan, K.B., Ahmad, M., Mazzara, M.: Multimodal Medical Image Registration and Fusion for Quality Enhancement. Computers Mater. Continua. 68(1), 821–840 (2021). https://doi.org/10.32604/cmc.2021.016131
Senthilvel, V., Zhang, V.G.Y., Rajasekaran, P., Arun, M., Thiyagarajan, P.: A smartly designed automated map based clustering algorithm for the enhanced diagnosis of pathologies in brain MR images. Expert Systems (2020). https://doi.org/10.1111/exsy.12625
Su, M., Zhang, C., Chen, Z., Jiang, S.: Registration of multimodal brain images based on optical flow, 10th International Congress on Image and Signal Processing. BioMedical Engineering and Informatics, CISP-BMEI 2017. 2017 (10), 1–5 (2017).
Natarajan, S., Govindaraj, V., Zhang, Y.: Biomedical Signal Processing and Control minimally parametrized segmentation framework with dual metaheuristic optimisation algorithms and FCM for detection of anomalies in MR brain images. Biomed. Signal Process. Control. 78, 103866 (2022). https://doi.org/10.1016/j.bspc.2022.103866
Zheng, Q., Wang, Q., Ba, X., Liu, S., Nan, J., Zhang, S.: A Medical Image Registration Method Based on Progressive Images. Computational and Mathematical Methods in Medicine 2021(7), 1–10 (2021). https://doi.org/10.1155/2021/4504306.
Chen, J., Frey, E.C., He, Y., Segars, W.P., Li, Y., Du, Y.: TransMorph: Transformer for unsupervised medical image registration. Medical image analysis (2022). https://doi.org/10.1016/j.media.2022.102615
Singh Gill, H., Singh Khehra, B., Singh, A., Kaur, L.: Teaching-learning-based optimization algorithm to minimize cross entropy for selecting multilevel threshold values. Egypt. Inf. J. 20(1), 11–25 (2019). https://doi.org/10.1016/j.eij.2018.03.006
Kher, H.R.: Implementation of Image Registration for Satellite Images using Mutual Information and Particle Swarm Optimization Techniques. Int. J. Comput. Appl. 97(1), 7–14 (2014). https://doi.org/10.5120/16969-5475
Funding
There is no funding for this research paper.
Author information
Authors and Affiliations
Contributions
PA have made a substantial contribution to the concept or design, interpretation of data for the article. RM drafted the article for important intellectual content. RA revised the draft and approved the version for final submission.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Arora, P., Mehta, R. & Ahuja, R. An integration of meta-heuristic approach utilizing kernel principal component analysis for multimodal medical image registration. Cluster Comput (2024). https://doi.org/10.1007/s10586-024-04281-1
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10586-024-04281-1