Anatomical Plausibility in Deformable Image Registration Using Bayesian Optimization for Brain MRI Analysis

被引:0
作者
Castano-Aguirre, Mauricio [1 ]
Garcia, Hernan Felipe [2 ]
Cardenas-Pena, David [1 ]
Porras-Hurtado, Gloria Liliana [3 ]
Orozco-Gutierrez, Alvaro angel [1 ]
机构
[1] Technol Univ Pereira, Automat Res Grp, Pereira 660001, Colombia
[2] Univ Antioquia, SISTEM Res Grp, Medellin 050010, Colombia
[3] Salud Comfamiliar Caja Compensac Familiar Risarald, Pereira, Colombia
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 23期
关键词
Bayesian optimization; deformable registration; Gaussian processes; anatomical plausibility; LEARNING FRAMEWORK;
D O I
10.3390/app142310890
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Deformable image registration plays a crucial role in medical imaging by aligning anatomical structures across multiple datasets, which is essential for accurate diagnosis and treatment planning. However, existing deep learning-based deformable registration models often face challenges in ensuring anatomical plausibility, leading to unnatural deformations in critical brain structures. This paper proposes a novel framework that uses Bayesian optimization to address these challenges, focusing on registering 3D point clouds that represent brain structures. Our method uses probabilistic modeling to optimize non-rigid transformations, providing smooth and interpretable deformations that align with anatomical constraints. The proposed framework is validated using MRI data from patients diagnosed with hypoxic-ischemic encephalopathy (HIE) due to perinatal asphyxia. These datasets include brain scans taken at multiple time points, enabling the modeling of structural changes over time. By incorporating Bayesian optimization, we enhance the accuracy of the registration process while maintaining anatomical fidelity. Our results demonstrate that the approach provides interpretable, anatomically plausible deformations, outperforming conventional methods in terms of accuracy and reliability. This work offers an improved tool for brain MRI analysis, aiding healthcare professionals in better understanding disease progression and guiding therapeutic interventions.
引用
收藏
页数:15
相关论文
共 50 条
[41]   Infant Brain Deformable Registration Using Global and Local Label-Driven Deep Regression Learning [J].
Hu, Shunbo ;
Zhang, Lintao ;
Li, Guoqiang ;
Liu, Mingtao ;
Fu, Deqian ;
Zhang, Wenyin .
MACHINE LEARNING IN MEDICAL IMAGING (MLMI 2019), 2019, 11861 :106-114
[42]   Validation of a robust method for quantification of three-dimensional growth of the thoracic aorta using deformable image registration [J].
Bian, Zhangxing ;
Zhong, Jiayang ;
Dominic, Jeffrey ;
Christensen, Gary E. ;
Hatt, Charles R. ;
Burris, Nicholas S. .
MEDICAL PHYSICS, 2022, 49 (04) :2514-2530
[43]   Deformable registration using edge-preserving scale space for adaptive image-guided radiation therapy [J].
Li, Dengwang ;
Wang, Hongjun ;
Yin, Yong ;
Wang, Xiuying .
JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, 2011, 12 (04) :105-123
[44]   Automation of Experimental Modal Analysis Using Bayesian Optimization [J].
Ellinger, Johannes ;
Beck, Leopold ;
Benker, Maximilian ;
Hartl, Roman ;
Zaeh, Michael F. .
APPLIED SCIENCES-BASEL, 2023, 13 (02)
[45]   User-customized brain computer interfaces using Bayesian optimization [J].
Bashashati, Hossein ;
Ward, Rabab K. ;
Bashashati, Ali .
JOURNAL OF NEURAL ENGINEERING, 2016, 13 (02)
[46]   Cross contrast multi-channel image registration using image synthesis for MR brain images [J].
Chen, Min ;
Carass, Aaron ;
Jog, Amod ;
Lee, Junghoon ;
Roy, Snehashis ;
Prince, Jerry L. .
MEDICAL IMAGE ANALYSIS, 2017, 36 :2-14
[47]   Utility of deformable image registration for adaptive prostate cancer treatment. Analysis and comparison of two commercially available algorithms [J].
Posiewnik, Michal ;
Piotrowski, Tomasz .
ZEITSCHRIFT FUR MEDIZINISCHE PHYSIK, 2022, 32 (03) :369-377
[48]   dPIRPLE: a joint estimation framework for deformable registration and penalized-likelihood CT image reconstruction using prior images [J].
Dang, H. ;
Wang, A. S. ;
Sussman, Marc S. ;
Siewerdsen, J. H. ;
Stayman, J. W. .
PHYSICS IN MEDICINE AND BIOLOGY, 2014, 59 (17) :4799-4826
[49]   Multimodal Deformable Image Registration for Long-COVID Analysis Based on Progressive Alignment and Multi-perspective Loss [J].
Li, Jiahua ;
Grist, James T. ;
Gleeson, Fergus, V ;
Papie, Bartlomiej W. .
MEDICAL IMAGE UNDERSTANDING AND ANALYSIS, PT II, MIUA 2024, 2024, 14860 :216-226
[50]   Brain Deformable Registration Using Global and Local Label-Driven Deep Regression Learning in the First Year of Life [J].
Hu, Shunbo ;
Zhang, Lintao ;
Li, Guoqiang ;
Liu, Mingtao ;
Fu, Deqian ;
Zhang, Wenyin .
IEEE ACCESS, 2020, 8 :25691-25705