Uncertainty estimation and evaluation of deformation image registration based convolutional neural networks

Rivetti, Luciano (author), Studen, Andrej (author), Sharma, Manju (author), Chan, Jason (author), Jeraj, Robert (author)

Objective. Fast and accurate deformable image registration (DIR), including DIR uncertainty estimation, is essential for safe and reliable clinical deployment. While recent deep learning models have shown promise in predicting DIR with its uncertainty, challenges persist in proper uncertainty evaluation and hyperparameter optimization for these methods. This work aims to develop and evaluate a model that can perform fast DIR and predict its uncertainty in seconds. Approach. This study introduces a novel probabilistic multi-resolution image registration model utilizing convolutional neural networks to estimate a multivariate normal distributed dense displacement field (DDF) in a multimodal image registration problem. To assess the quality of the DDFdistribution predicted by the model, we propose a new metric based on the Kullback–Leibler divergence. The performance of our approach was evaluated against three other DIR algorithms (VoxelMorph, Monte Carlo dropout, and Monte Carlo B-spline) capable of predicting uncertainty. The evaluation of the models included not only the quality of the deformation but also the reliability of the estimated uncertainty. Our application investigated the registration of a treatment planning computed tomography (CT) to follow-up cone beam CT for daily adaptive radiotherapy. Main results. The hyperparameter tuning of the models showed a trade-off between the estimated uncertainty’s reliability and the deformation’s accuracy. In the optimal trade-off, our model excelled in contour propagation and uncertainty estimation (p < 0.05) compared to existing uncertainty estimation models. We obtained an average dice similarity coefficient of 0.89 and a KL-divergence of 0.15. Significance. By addressing challenges in DIR uncertainty estimation and evaluation, our work showed that both the DIR and its uncertainty can be reliably predicted, paving the way for safe deployment in a clinical environment.

• Language: English
• Keywords: medical physics, medical images, deformable image registration, adaptive radiotherapy, deep learning, neural networks, uncertainty estimation
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FMF - Faculty of Mathematics and Physics
• Publication status: Published
• Publication version: Version of Record
• Year: 2024
• Number of pages: 15 str.
• Numbering: Vol. 69, no. 11, art. no. 115045
• PID: 20.500.12556/RUL-168151
• UDC: 004.93:616-073
• ISSN on article: 0031-9155
• DOI: 10.1088/1361-6560/ad4c4f
• COBISS.SI-ID: 230884611
• Publication date in RUL: 31.03.2025

Record is a part of a journal

• Title: Physics in Medicine & Biology
• Shortened title: Phys. Med. Biol.
• Publisher: American Institute of Physics
• ISSN: 0031-9155
• COBISS.SI-ID: 26128896

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: medicinska fizika, medicinske slike, deformabilna poravnava slik, adaptivna radioterapija, globoko učenje, nevronske mreže, ocena negotovosti

Projects

• Funder: EC - European Commission
• Project number: 955956
• Name: Real-time Adaptive Particle Therapy of Cancer
• Acronym: RAPTOR