Recent works in medical image registration have proposed the use of Implicit Neural Representations, demonstrating performance that rivals state-of-the-art learning-based methods. However, these implicit representations need to be optimized for each new image pair, which is a stochastic process that may fail to converge to a global minimum. To improve robustness, we propose a deformable registration method using pairs of cycle-consistent Implicit Neural Representations: each implicit representation is linked to a second implicit representation that estimates the opposite transformation, causing each network to act as a regularizer for its paired opposite. During inference, we generate multiple deformation estimates by numerically inverting the paired backward transformation and evaluating the consensus of the optimized pair. This consensus improves registration accuracy over using a single representation and results in a robust uncertainty metric that can be used for automatic quality control. We evaluate our method with a 4D lung CT dataset. The proposed cycle-consistent optimization method reduces the optimization failure rate from 2.4% to 0.0% compared to the current state-of-the-art. The proposed inference method improves landmark accuracy by 4.5% and the proposed uncertainty metric detects all instances where the registration method fails to converge to a correct solution. We verify the generalizability of these results to other data using a centerline propagation task in abdominal 4D MRI, where our method achieves a 46% improvement in propagation consistency compared with single-INR registration and demonstrates a strong correlation between the proposed uncertainty metric and registration accuracy.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2023.3321425DOI Listing

Publication Analysis

Top Keywords

uncertainty metric
12
image registration
8
cycle-consistent implicit
8
implicit representations
8
implicit neural
8
neural representations
8
registration method
8
implicit representation
8
registration accuracy
8
proposed uncertainty
8

Similar Publications

Comparing the Robustness of Intensity-modulated Proton Therapy and Proton-arc Therapy Against Interplay Effects of 4D Robust-optimised Plans for Lung Stereotactic Body Radiotherapy.

Clin Oncol (R Coll Radiol)

January 2025

Department of Radiation Oncology, Cancer Center, West China Hospital, Sichuan University, Chengdu, Sichuan 610041, China; Department of Radiotherapy Physics & Technology, West China Hospital, Sichuan University, Chengdu, Sichuan 610041, China.

Aims: To assess the robustness of 4D-optimised IMPT and PAT plans against interplay effects in non-small cell lung cancer (NSCLC) patients with respiratory motion over 10 mm, and to provide insights into the use of proton-based stereotactic body radiotherapy (SBRT) for lung cancer with significant tumour movement.

Materials And Methods: Fourteen patients with early-stage NSCLC and tumour motion >10 mm were selected. Three hypofraction regimens were generated using 4D robust optimisation with the IMPT and PAT techniques.

View Article and Find Full Text PDF

Background: The perception of Subjective Visual Vertical (SVV) is crucial for postural orientation and significantly reflects an individual's postural control ability, relying on vestibular, visual, and somatic sensory inputs to assess the Earth's gravity line. The neural mechanisms and aging effects on SVV perception, however, remain unclear.

Objective: This study seeks to examine aging-related changes in SVV perception and uncover its neurological underpinnings through functional near-infrared spectroscopy (fNIRS).

View Article and Find Full Text PDF

The development and validation of an accurate, selective, and eco-friendly capillary zone electrophoretic detection (CZE) method has been presented for concurrent measurement of inorganic and organic anions including chloride, sulfate, formic acid, citric acid, acetic acid, phosphate, and glutamic acid in Human Milk Oligosaccharides (HMOs) for the first time. An electrolyte composed of an aqueous solution of benzoic acid, 16.38 mM; l-histidine, 24.

View Article and Find Full Text PDF

Understanding the biomechanics of osteoarthritis is necessary for designing a biomedical knee implant to reduce pain, increase mobility, and enhance the patient's quality of life. The most appropriate implant design may be chosen by using Multi-Attribute Group Decision-Making (MAGDM) techniques, which include a number of variables including material characteristics, biomechanical performance, cost-effectiveness, and patient-specific requirements. Compared to conventional fuzzy set structures, Spherical Fuzzy -Number Sets ( S) provide an enhanced method for resolving uncertainty in MAGDM and are more suited for handling complicated decision-making situations.

View Article and Find Full Text PDF

Covariate Model Selection Approaches for Population Pharmacokinetics: A Systematic Review of Existing Methods, From SCM to AI.

CPT Pharmacometrics Syst Pharmacol

January 2025

Pharmacokinetics Dynamics and Metabolism/Translational Medicine and Early Development, Sanofi R&D Montpellier, Montpellier, France.

A growing number of covariate modeling methods have been proposed in the field of popPK modeling, but limited information exists on how they all compare. The objective of this study was to perform a systematic review of all popPK covariate modeling methods, focusing on assessing the existing knowledge on their performances. For each method of each article included in this review, evaluation setting, performance metrics along with their associated values, and relative computational times were reported when available.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!