Deformable registration aims to achieve nonlinear alignment of image space by estimating a dense displacement field. It is commonly used as a preprocessing step in clinical and image analysis applications, such as surgical planning, diagnostic assistance, and surgical navigation. We aim to overcome these challenges: Deep learning-based registration methods often struggle with complex displacements and lack effective interaction between global and local feature information. They also neglect the spatial position matching process, leading to insufficient registration accuracy and reduced robustness when handling abnormal tissues. Approach: We propose a dual-branch interactive registration model architecture from the perspective of spatial matching. Implicit regularization is achieved through a consistency loss, enabling the network to balance high accuracy with a low folding rate. We introduced the Dynamic Matching Module (DMM) between the two branches of the registration, which generates learnable offsets based on all the tokens across the entire resolution range of the base branch features. Using trilinear interpolation, the model adjusts its feature expression range according to the learned offsets, capturing highly flexible positional differences. To facilitate the spatial matching process, we designed the Gated Mamba Layer (GML) to globally model pixel-level features by associating all voxel information, while the Detail Enhancement Module (DEM), which is based on channel and spatial attention, enhances the richness of local feature details. Main results: Our study explores the model's performance in single-modal and multi-modal image registration, including normal brain, brain tumor, and lung images. We propose unsupervised and semi-supervised registration modes and conduct extensive validation experiments. The results demonstrate that the model achieves state-of-the-art performance across multiple datasets.. Significance: By introducing a novel perspective of position matching, the model achieves precise registration of various types of medical data, offering significant clinical value in medical applications. .
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1088/1361-6560/adaacd | DOI Listing |
Laryngoscope
January 2025
Department of Otolaryngology/Head & Neck Surgery, University of North Carolina School of Medicine, Chapel Hill, North Carolina, U.S.A.
Objectives: Bimodal cochlear implant (CI) users vary in speech recognition outcomes. This variability may be influenced partly by the CI and contralateral hearing aid (HA) programming procedures, which can result in mismatches in latency and frequency. We assessed the performance of bimodal listeners when latency mismatches were corrected and analyzed how frequency mismatches influenced outcomes.
View Article and Find Full Text PDFInt Conf Indoor Position Indoor Navig
October 2024
Computer Science and Engineering, University of California, Santa Cruz, Santa Cruz, United States.
In this paper, we present PALMS, an innovative indoor global localization and relocalization system for mobile smartphones that utilizes publicly available floor plans. Unlike most vision-based methods that require constant visual input, our system adopts a dynamic form of localization that considers a single instantaneous observation and odometry data. The core contribution of this work is the introduction of a particle filter initialization method that leverages the Certainly Empty Space (CES) constraint along with principal orientation matching.
View Article and Find Full Text PDFMultiplexed Immunofluorescence (MxIF) enables detailed immune cell phenotyping, providing critical insights into cell behavior within the tumor immune microenvironment (TIME). However, signal integrity can be compromised due to the complex cyclic staining processes inherent to MxIF. Hematoxylin and Eosin (H&E) staining, on the other hand, offers complementary information through its depiction of cell morphology and texture patterns and is often visually cross-referenced with MxIF in clinical settings.
View Article and Find Full Text PDFPhys Imaging Radiat Oncol
January 2025
Aarhus University Hospital, Danish Centre for Particle Therapy, Palle Juul-Jensens Blvd. 25, 8200 Aarhus, Denmark.
Background And Purpose: Diffusion tensor imaging (DTI) has been proposed to guide the anisotropic expansion from gross tumor volume to clinical target volume (CTV), aiming to integrate known tumor spread patterns into the CTV. This study investigate the potential of using a DTI atlas as an alternative to patient-specific DTI for generating anisotropic CTVs.
Materials And Methods: The dataset consisted of twenty-eight newly diagnosed glioblastoma patients from a Danish national DTI protocol with post-operative T1-contrast and DTI imaging.
Eur J Neurol
February 2025
IRCCS Istituto delle Scienze Neurologiche di Bologna, Department of Neurology and Stroke Center, Maggiore Hospital, Bologna, Italy.
Background: To investigate the relevance of hyperperfusion on computerised perfusion imaging (CTP) in the emergency setting in people with non-convulsive status epilepticus (NCSE) and previous stroke, to derive relevant aspects on the epileptogenic focus and the network recruited for NCSE propagation.
Methods: We enrolled consecutive adult patients with acute-onset NCSE and a previous stroke at a single institution undergoing CTP and EEG during symptoms. All patients underwent standard imaging including CT, CTP, CT angiograms and standard EEG within 30 min from hospital arrival.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!