Personalized Respiratory Motion Modeling Incorporating Longitudinal Data through Two-stage Transfer Learning

Peizhi Chen; Xupeng Zou; Yifan Guo

doi:10.2174/0115734056325170250114210309

ISSN: 1573-4056
E-ISSN: 1875-6603

HTML

oa Personalized Respiratory Motion Modeling Incorporating Longitudinal Data through Two-stage Transfer Learning
Authors: Peizhi Chen¹, Xupeng Zou¹ and Yifan Guo¹
View Affiliations Hide Affiliations

¹ Xiamen University of Technology, College of Computer and Information Engineering, Xiamen, China
Source: Current Medical Imaging, Volume 21, Issue 1, Jan 2025, E15734056325170
DOI: https://doi.org/10.2174/0115734056325170250114210309
- Received: 16 May 2024
- Accepted: 20 Nov 2024
- Available online: 21 Jan 2025

Abstract

Purpose

This study aims to develop an accurate image registration framework for personalized respiratory motion modeling.

Methods

The proposed framework incorporates longitudinal data through a two-stage transfer learning approach. In the first stage, transfer learning is employed on longitudinal data collected from the same device. In the second stage, a personalized model is constructed using the transfer learning approach, reusing the model from the first stage. A novel cross-error function is introduced to guide the customized adaptation stage.

Results

The experiments demonstrate the effectiveness of the proposed framework in respiratory motion modeling. Integrating longitudinal data allows for improved accuracy for personalized respiratory motion modeling.

Conclusion

The study presents a novel approach that incorporates longitudinal data into a two-stage transfer learning process for personalized respiratory motion modeling. The framework demonstrates improved accuracy. The results highlight the potential of leveraging longitudinal data to provide personalized image registration solutions.

This is an open access article published under CC BY 4.0 https://creativecommons.org/licenses/by/4.0/legalcode

Article metrics loading...

/content/journals/cmir/10.2174/0115734056325170250114210309

2025-01-21

2025-11-01

From This Site

/content/journals/cmir/10.2174/0115734056325170250114210309

dcterms_title,dcterms_subject,pub_keyword

-contentType:Contributor -contentType:Concept -contentType:Institution

10

5

Full text loading...

/deliver/fulltext/cmir/21/1/CMIR-21-E15734056325170.html?itemId=/content/journals/cmir/10.2174/0115734056325170250114210309&mimeType=html&fmt=ahah

References

SchweikardA. GlosserG. BodduluriM. MurphyM.J. AdlerJ.R. Robotic motion compensation for respiratory movement during radiosurgery.Comput. Aided Surg.20005426327710.3109/1092908000914889411029159
[Google Scholar]
RomagueraL.V. MezheritskyT. KadouryS. Personalized respiratory motion model using conditional generative networks for mr-guided radiotherapy.Available from: https://api.semanticscholar.org/CorpusID:237621025 2021
FayadH. PanT. PradierO. VisvikisD. Patient specific respiratory motion modeling using a 3D patient’s external surface.Med. Phys.2012396Part13386339510.1118/1.471857822755719
[Google Scholar]
FassiA. SeregniM. RiboldiM. CerveriP. SarrutD. IvaldiG.B. Fatisd.P.T. LiottaM. BaroniG. Surrogate-driven deformable motion model for organ motion tracking in particle radiation therapy.Phys. Med. Biol.20156041565158210.1088/0031‑9155/60/4/156525615399
[Google Scholar]
WangT. HeT. ZhangZ. ChenQ. ZhangL. XiaG. YangL. WangH. WongS.T.C. LiH. A personalized image-guided intervention system for peripheral lung cancer on patient-specific respiratory motion model.Int. J. CARS202217101751176410.1007/s11548‑022‑02676‑235639202
[Google Scholar]
McClellandJ.R. HawkesD.J. SchaeffterT. KingA.P. Respiratory motion models: A review.Med. Image Anal.2013171194210.1016/j.media.2012.09.00523123330
[Google Scholar]
ShenD. DavatzikosC. Hammer: Hierarchical attribute matching mechanism for elastic registration.Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA 2001)09-10 DecemberKauai, HI, USA2001293610.1109/MMBIA.2001.991696
[Google Scholar]
AvantsB. EpsteinC. GrossmanM. GeeJ. Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain.Med. Image Anal.2008121264110.1016/j.media.2007.06.00417659998
[Google Scholar]
KleinS. StaringM. MurphyK. ViergeverM.A. PluimJ. Elastix: A toolbox for intensity-based medical image registration.IEEE Trans. Med. Imaging201029119620510.1109/TMI.2009.203561619923044
[Google Scholar]
BalakrishnanG. ZhaoA. SabuncuM.R. GuttagJ. DalcaA.V. Voxel- morph: A learning framework for deformable medical image registration.IEEE Trans. Med. Imaging20193881788180010.1109/TMI.2019.2897538
[Google Scholar]
BalikS. WeissE. JanN. RomanN. SleemanW.C. FatygaM. ChristensenG.E. ZhangC. MurphyM.J. LuJ. KeallP. WilliamsonJ.F. HugoG.D. Evaluation of 4-dimensional computed tomography to 4-dimensional cone-beam computed tomography deformable image registration for lung cancer adaptive radiation therapy.Int. J. Radiat. Oncol. Biol. Phys.201386237237910.1016/j.ijrobp.2012.12.02323462422
[Google Scholar]
ClarkK. VendtB. SmithK. FreymannJ. KirbyJ. KoppelP. MooreS. PhillipsS. MaffittD. PringleM. TarboxL. PriorF. The cancer imaging archive (TCIA): Maintaining and operating a public information repository.J. Digit. Imaging20132661045105710.1007/s10278‑013‑9622‑723884657
[Google Scholar]
HugoG.D. WeissE. SleemanW.C. BalikS. KeallP.J. LuJ. WilliamsonJ.F. A longitudinal four‐dimensional computed tomography and cone beam computed tomography dataset for image‐guided radiation therapy research in lung cancer.Med. Phys.201744276277110.1002/mp.1205927991677
[Google Scholar]
ChenP. GuoY. WangD. ChenC. Dlung: Unsupervised few-shot diffeomorphic respiratory motion modeling.J. Shanghai Jiaotong Univ.20232853654536406811
[Google Scholar]

/content/journals/cmir/10.2174/0115734056325170250114210309

Personalized Respiratory Motion Modeling Incorporating Longitudinal Data through Two-stage Transfer Learning

Curr. Med. Imaging 21, E15734056325170 (2025); https://doi.org/10.2174/0115734056325170250114210309

/content/journals/cmir/10.2174/0115734056325170250114210309

Data & Media loading...

Article Type: Research Article

Keyword(s): 4D-CT images; adaptive radiotherapy; Longitudinal data; motion analysis; Respiratory motion modeling; Transfer learning

oa Personalized Respiratory Motion Modeling Incorporating Longitudinal Data through Two-stage Transfer Learning

Abstract

From This Site

Most Read This Month

Most Cited Most Cited RSS feed

Small Animal Computed Tomography Imaging

Brain Tumor Detection Using Machine Learning and Deep Learning: A Review

Low-dose COVID-19 CT Image Denoising Using CNN and its Method Noise Thresholding

SegEIR-Net: A Robust Histopathology Image Analysis Framework for Accurate Breast Cancer Classification

How to Collect and Interpret Medical Pictures Captured in Highly Challenging Environments that Range from Nanoscale to Hyperspectral Imaging

An Efficient Ensemble-based Machine Learning approach for Predicting Chronic Kidney Disease

Is Gadoxetic Acid Disodium (Gd-EOB-DTPA)-Enhanced Magnetic Resonance Imaging an Accurate Diagnostic Method for Hepatocellular Carcinoma? A Systematic Review with Meta-Analysis

Effectiveness of the Neuroimaging Techniques in the Recognition of Psychiatric Disorders: A Systematic Review and Meta-analysis of RCTs

Prediction of Lumbar Pedicle Screw Loosening Using Hounsfield Units in Computed Tomography

Deep Learning-based Automated Knee Joint Localization in Radiographic Images Using Faster R-CNN