An Implicit Registration Framework Integrating Kolmogorov–Arnold Networks with Velocity Regularization for Image-Guided Radiation Therapy

Guardado en:
Detalles Bibliográficos
Publicado en:Bioengineering vol. 12, no. 9 (2025), p. 1005-1024
Autor principal: Sun Pulin
Otros Autores: Zhang Chulong, Yang, Zhenyu, Fang-Fang, Yin, Liu, Manju
Publicado:
MDPI AG
Materias:
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3254472270
003 UK-CbPIL
022 |a 2306-5354 
024 7 |a 10.3390/bioengineering12091005  |2 doi 
035 |a 3254472270 
045 2 |b d20250101  |b d20251231 
100 1 |a Sun Pulin  |u Medical Physics Graduate Program, Duke Kunshan University, Kunshan 215316, China; pulin.sun@duke.edu (P.S.); chulong.zhang@duke.edu (C.Z.); zhenyu.yang893@dukekunshan.edu.cn (Z.Y.); fangfang.yin@duke.edu (F.-F.Y.) 
245 1 |a An Implicit Registration Framework Integrating Kolmogorov–Arnold Networks with Velocity Regularization for Image-Guided Radiation Therapy 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a In image-guided radiation therapy (IGRT), deformable image registration between computed tomography (CT) and cone beam computed tomography (CBCT) images remain challenging due to the computational cost of iterative algorithms and the data dependence of supervised deep learning methods. Implicit neural representation (INR) provides a promising alternative, but conventional multilayer perceptron (MLP) might struggle to efficiently represent complex, nonlinear deformations. This study introduces a novel INR-based registration framework that models the deformation as a continuous, time-varying velocity field, parameterized by a Kolmogorov–Arnold Network (KAN) constructed using Jacobi polynomials. To our knowledge, this is the first integration of KAN into medical image registration, establishing a new paradigm beyond standard MLP-based INR. For improved efficiency, the KAN estimates low-dimensional principal components of the velocity field, which are reconstructed via inverse principal component analysis and temporally integrated to derive the final deformation. This approach achieves a ~70% improvement in computational efficiency relative to direct velocity field modeling while ensuring smooth and topology-preserving transformations through velocity regularization. Evaluation on a publicly available pelvic CT–CBCT dataset demonstrates up to 6% improvement in registration accuracy over traditional iterative methods and ~3% over MLP-based INR baselines, indicating the potential of the proposed method as an efficient and generalizable alternative for deformable registration. 
653 |a Iterative algorithms 
653 |a Formability 
653 |a Deep learning 
653 |a Iterative methods 
653 |a Principal components analysis 
653 |a Image registration 
653 |a Multilayer perceptrons 
653 |a Radiation therapy 
653 |a Optimization 
653 |a Medical imaging 
653 |a Polynomials 
653 |a Topology 
653 |a Computer applications 
653 |a Velocity distribution 
653 |a Registration 
653 |a Radiation 
653 |a Efficiency 
653 |a Velocity 
653 |a Regularization 
653 |a Partial differential equations 
653 |a Computed tomography 
653 |a Neural networks 
653 |a Deformation 
653 |a Computational efficiency 
653 |a Computing costs 
653 |a Ordinary differential equations 
653 |a Neural coding 
700 1 |a Zhang Chulong  |u Medical Physics Graduate Program, Duke Kunshan University, Kunshan 215316, China; pulin.sun@duke.edu (P.S.); chulong.zhang@duke.edu (C.Z.); zhenyu.yang893@dukekunshan.edu.cn (Z.Y.); fangfang.yin@duke.edu (F.-F.Y.) 
700 1 |a Yang, Zhenyu  |u Medical Physics Graduate Program, Duke Kunshan University, Kunshan 215316, China; pulin.sun@duke.edu (P.S.); chulong.zhang@duke.edu (C.Z.); zhenyu.yang893@dukekunshan.edu.cn (Z.Y.); fangfang.yin@duke.edu (F.-F.Y.) 
700 1 |a Fang-Fang, Yin  |u Medical Physics Graduate Program, Duke Kunshan University, Kunshan 215316, China; pulin.sun@duke.edu (P.S.); chulong.zhang@duke.edu (C.Z.); zhenyu.yang893@dukekunshan.edu.cn (Z.Y.); fangfang.yin@duke.edu (F.-F.Y.) 
700 1 |a Liu, Manju  |u Medical Physics Graduate Program, Duke Kunshan University, Kunshan 215316, China; pulin.sun@duke.edu (P.S.); chulong.zhang@duke.edu (C.Z.); zhenyu.yang893@dukekunshan.edu.cn (Z.Y.); fangfang.yin@duke.edu (F.-F.Y.) 
773 0 |t Bioengineering  |g vol. 12, no. 9 (2025), p. 1005-1024 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3254472270/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3254472270/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3254472270/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch