arXiv subjects

Atle Bjørnerud

Publications and source records attributed to Atle Bjørnerud.

12 recordsLinked to original sources

arXiv2026

Forecasting Intrathecal Tracer Enhancement from Pre-Contrast Brain MRI: Direct Regression versus Flow Matching

Intrathecal contrast-enhanced MRI tracks how a cerebrospinal-fluid tracer spreads through the brain, but requires repeated scans over 24--48\,h. Forecasting enhancement from a pre-contrast scan could one day help select patients for intrathecal drug treatment and plan their dose. We ask how much of the enhancement at a given time can be predicted from the pre-contrast scan and the elapsed time alone. Training on 104 patients, we compared direct image-to-image regression (I2I) with conditional flow matching (CFM) using the same 3D U-Net and protocol, and tested on 23 held-out patients and 51 external patients with normal pressure hydrocephalus. All models were measured against simply copying the pre-contrast scan. I2I removed about 60\% of this copying error internally and 25\% externally, outperformed CFM on both test sets (mean absolute error 0.036 vs.\ 0.058 and 0.056 vs.\ 0.063), and predicted each volume in a single forward pass, whereas CFM ran its network ten times. CFM uncertainty located errors but was poorly calibrated. Much of tracer enhancement is thus predictable from anatomy and timing, and direct regression is the more accurate and cheaper choice at this data scale.

eess.IV↗

arXiv2026

Deep Learning Segmentation of Diffusion-Weighted MRI Acute Ischaemic Stroke: A Pragmatic Evaluation Across Three Datasets

Objective: Diffusion-weighted MRI (DWI-MRI) is the gold standard for visualizing and quantifying acute ischaemic stroke (AIS). Although deep learning methods can accurately segment AIS lesions, the optimal image inputs and model architecture remain uncertain. We evaluated whether accurate AIS lesion segmentation can be achieved using a pragmatic deep learning approach with minimal preprocessing and clinically feasible inference times. Materials and Methods: Self-configured nnU-Net models were trained on 1,744 DWI cases from local, national, and open-access datasets and tested on 436 cases. Four experimental conditions were evaluated using five-fold cross-validation: with or without brain extraction and using either DWI alone or DWI plus apparent diffusion coefficient (ADC) images as inputs. Two architectures were compared: the baseline nnU-Net (base) and a residual encoder nnU-Net (ResEnc). Performance was benchmarked against the DeepISLES ensemble model from the 2022 ISLES challenge. Results: In the test set (n=436), the base model achieved a median (IQR) Dice similarity coefficient (DSC) of 0.84 (0.19). For the base model, only two of six pairwise comparisons between input configurations showed significant differences. ResEnc produced small but significant improvements in DSC compared with the base model for DWI, DWI+brain extraction, and DWI+ADC inputs (all p<0.02), but not for DWI+ADC+brain extraction (p>0.50). The base model significantly outperformed DeepISLES, particularly in patients with smaller infarct volumes (signed-rank test, p<0.01). Conclusions: A baseline nnU-Net trained on DWI alone, without preprocessing, enabled fast and accurate AIS lesion segmentation. This streamlined approach may facilitate clinical research and support acute stroke imaging workflows

cs.CV↗

arXiv2026

Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation

Instance-level lesion detection has been an increasingly larger focal point in medical image segmentation besides the more standard voxel-level overlap. Still, most pipelines are trained and post-processed for voxel overlap alone. In particular, the mismatch is most pronounced for small lesions, where a near-miss prediction---substantial overlap that falls just short of the instance-matching threshold---scores the same as a complete miss. In our ISLES'26 submission, we found that closing this gap mattered far more in post-processing than in architecture design. Our Volume-Conditioned Adaptive Post-Processing (VCAP) scheme adjusts component-size thresholds to each case's predicted lesion burden, improving Lesion-F1 by 0.032 (unbiased cross-fold estimate)---approximately 6 times larger than any architectural change we tested. A resolution-aware attention architecture (Viola2Plus), designed for small-lesion segmentation, shows why the distinction matters: it left small-lesion Dice unchanged but raised small-lesion detection rate by 3.7\%, a real effect voxel-overlap metrics alone would have missed. Under 5-fold cross-validation on the 1,453-case training set, our post-processed two-architecture ensemble achieves Dice 0.651 and Lesion-F1 0.614, versus 0.644 and 0.573 for the unprocessed single-model baseline.

cs.CV↗

arXiv2026

Beyond Random Partitioning: Unsupervised Spatio-Temporal Stratification for Cohort Balancing in Longitudinal Medical Imaging

Rigorous dataset partitioning is a foundational, yet frequently overlooked, prerequisite for reliable deep learning in longitudinal medical imaging. Naively shuffling small clinical cohorts routinely introduces covariate shifts and temporal sampling imbalances across training, validation, and test subsets, exposing downstream models to out-of-distribution evaluation. We address this vulnerability with an auditable Tripartite Dataset Analytics Framework that systematically characterizes spatial grid integrity, multi-parametric intensity fingerprints, and longitudinal temporal trajectories, quantifying the heavy-tailed feature dispersion and irregular, episodic sampling intervals typical of real-world clinical cohorts. Building on this characterization, we formalize an unsupervised spatio-temporal cohort-balancing standard operating procedure (SOP) that combines elbow-optimized K-means clustering over a standardized, six-dimensional joint intensity-temporal feature space with intra-cluster proportionate stratified sampling. On a longitudinal, contrast-enhanced $T1$-weighted brain MRI cohort (N=149), the protocol reduces the maximum cross-subset intensity bias from 34.1% under conventional random shuffling to under 2.1%, while aligning longitudinal follow-up intervals closely around the population mean. Monte Carlo stress testing across ten random seeds and three split configurations confirms that this alignment remains tightly bounded, in clear contrast to the substantial variability of random partitioning. The resulting protocol offers a reproducible, generalizable procedure for cohort engineering in variable-length longitudinal clinical imaging workflows.

cs.CV↗

arXiv2025

Manganese-based macrocyclic chelates as novel MRI contrast agents: In vivo imaging in a porcine model

Objectives: Mn-based MRI contrast agents (MBCAs) have recently been proposed as alternatives to the currently used class of Gd-chelates. Unlike Gd, Mn is an endogenous paramagnetic metal with known biochemical pathways in the human body for excretion and metal regulation, which may alleviate the raised concerns about the safety of existing GBCAs. The aim of this study was to investigate the distribution, kinetics and image enhancement properties of a class of novel Mn-based macrocyclic chelates in a porcine model. Methods: Macrocyclic MBCAs, AH114608, GEH300017 and GEH200486, were tested and compared to gadoterate meglumine. Twelve female adult pigs were divided into four groups (n=3 for each CA). At 3 T MRI, T1 relaxometry analysis were measured longitudinally in multiple organs at five timepoints 30 minutes apart. CA kinetics was estimated from analysis of plasma CA concentrations by ICP-OES. Results: All four CAs exhibited T1-enhancing properties in the blood pool with GEH200486 having the largest increase in T1 relaxation rate (R1), GEH300017 and gadoterate meglumine having similar R1 increase and AH114608 a lower peak R1 change. A persistent increase in liver, kidney and myocardium R1 was observed with AH114608. To a lesser extent, a persistent increase of liver enhancement was also observed in T1-weighted images for GEH300017 and GEH200486 compared to gadoterate meglumine. All four CAs had similar bi-exponential plasma kinetics characterized by a rapid distribution phase and a slower elimination phase. Discussion: We have identified MBCA candidates with predominantly renal clearance and comparable efficacy in terms of vascular T1 relaxation, and comparable to the reference GBCA. The T1-enhancing properties of these novel Mn macrocyclic CAs can be used with routine clinical protocols and could be potentially utilised as an alternative to GBCAs for contrast-enhanced MRI procedures.

physics.med-ph↗

arXiv2025

Examining Deployment and Refinement of the VIOLA-AI Intracranial Hemorrhage Model Using an Interactive NeoMedSys Platform

Background: There are many challenges and opportunities in the clinical deployment of AI tools in radiology. The current study describes a radiology software platform called NeoMedSys that can enable efficient deployment and refinements of AI models. We evaluated the feasibility and effectiveness of running NeoMedSys for three months in real-world clinical settings and focused on improvement performance of an in-house developed AI model (VIOLA-AI) designed for intracranial hemorrhage (ICH) detection. Methods: NeoMedSys integrates tools for deploying, testing, and optimizing AI models with a web-based medical image viewer, annotation system, and hospital-wide radiology information systems. A prospective pragmatic investigation was deployed using clinical cases of patients presenting to the largest Emergency Department in Norway (site-1) with suspected traumatic brain injury (TBI) or patients with suspected stroke (site-2). We assessed ICH classification performance as VIOLA-AI encountered new data and underwent pre-planned model retraining. Performance metrics included sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). Results: NeoMedSys facilitated iterative improvements in the AI model, significantly enhancing its diagnostic accuracy. Automated bleed detection and segmentation were reviewed in near real-time to facilitate re-training VIOLA-AI. The iterative refinement process yielded a marked improvement in classification sensitivity, rising to 90.3% (from 79.2%), and specificity that reached 89.3% (from 80.7%). The bleed detection ROC analysis for the entire sample demonstrated a high area-under-the-curve (AUC) of 0.949 (from 0.873). Model refinement stages were associated with notable gains, highlighting the value of real-time radiologist feedback.

cs.CV↗

arXiv2025

Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction

Diffuse gliomas are malignant brain tumors that grow widespread through the brain. The complex interactions between neoplastic cells and normal tissue, as well as the treatment-induced changes often encountered, make glioma tumor growth modeling challenging. In this paper, we present a novel end-to-end network capable of future predictions of tumor masks and multi-parametric magnetic resonance images (MRI) of how the tumor will look at any future time points for different treatment plans. Our approach is based on cutting-edge diffusion probabilistic models and deep-segmentation neural networks. We included sequential multi-parametric MRI and treatment information as conditioning inputs to guide the generative diffusion process as well as a joint segmentation process. This allows for tumor growth estimates and realistic MRI generation at any given treatment and time point. We trained the model using real-world postoperative longitudinal MRI data with glioma tumor growth trajectories represented as tumor segmentation maps over time. The model demonstrates promising performance across various tasks, including generating high-quality multi-parametric MRI with tumor masks, performing time-series tumor segmentations, and providing uncertainty estimates. Combined with the treatment-aware generated MRI, the tumor growth predictions with uncertainty estimates can provide useful information for clinical decision-making.

eess.IV↗

arXiv2024

MUSTER: Longitudinal Deformable Registration by Composition of Consecutive Deformations

Longitudinal imaging allows for the study of structural changes over time. One approach to detecting such changes is by non-linear image registration. This study introduces Multi-Session Temporal Registration (MUSTER), a novel method that facilitates longitudinal analysis of changes in extended series of medical images. MUSTER improves upon conventional pairwise registration by incorporating more than two imaging sessions to recover longitudinal deformations. Longitudinal analysis at a voxel-level is challenging due to effects of a changing image contrast as well as instrumental and environmental sources of bias between sessions. We show that local normalized cross-correlation as an image similarity metric leads to biased results and propose a robust alternative. We test the performance of MUSTER on a synthetic multi-site, multi-session neuroimaging dataset and show that, in various scenarios, using MUSTER significantly enhances the estimated deformations relative to pairwise registration. Additionally, we apply MUSTER on a sample of older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. The results show that MUSTER can effectively identify patterns of neuro-degeneration from T1-weighted images and that these changes correlate with changes in cognition, matching the performance of state of the art segmentation methods. By leveraging GPU acceleration, MUSTER efficiently handles large datasets, making it feasible also in situations with limited computational resources.

cs.CV↗

arXiv2024

Deep Learning-based Intraoperative MRI Reconstruction

Purpose: To evaluate the quality of deep learning reconstruction for prospectively accelerated intraoperative magnetic resonance imaging (iMRI) during resective brain tumor surgery. Materials and Methods: Accelerated iMRI was performed during brain surgery using dual surface coils positioned around the area of resection. A deep learning (DL) model was trained on the fastMRI neuro dataset to mimic the data from the iMRI protocol. Evaluation was performed on imaging material from 40 patients imaged between 01.11.2021 - 01.06.2023 that underwent iMRI during tumor resection surgery. A comparative analysis was conducted between the conventional compressed sense (CS) method and the trained DL reconstruction method. Blinded evaluation of multiple image quality metrics was performed by two working neuro-radiologists and a working neurosurgeon on a 1 to 5 Likert scale (1=non diagnostic, 2=poor, 3=acceptable, 4=good, 5=excellent), and the favored reconstruction variant. Results: The DL reconstruction was strongly favored or favored over the CS reconstruction for 33/40, 39/40, and 8/40 of cases for reader 1, 2, and 3, respectively. Two of three readers consistently assigned higher ratings for the DL reconstructions, and the DL reconstructions had a higher score than their respective CS counterparts for 72%, 72%, and 14% of the cases for reader 1, 2, and 3, respectively. Still, the DL reconstructions exhibited shortcomings such as a striping artifact and reduced signal. Conclusion: DL shows promise to allow for high-quality reconstructions of intraoperative MRI with equal to or improved perceived spatial resolution, signal-to-noise ratio, diagnostic confidence, diagnostic conspicuity, and spatial resolution compared to compressed sense.

eess.IV↗

arXiv2023

A Densely Interconnected Network for Deep Learning Accelerated MRI

Objective: To improve accelerated MRI reconstruction through a densely connected cascading deep learning reconstruction framework. Materials and Methods: A cascading deep learning reconstruction framework (baseline model) was modified by applying three architectural modifications: Input-level dense connections between cascade inputs and outputs, an improved deep learning sub-network, and long-range skip-connections between subsequent deep learning networks. An ablation study was performed, where five model configurations were trained on the NYU fastMRI neuro dataset with an end-to-end scheme conjunct on four- and eight-fold acceleration. The trained models were evaluated by comparing their respective structural similarity index measure (SSIM), normalized mean square error (NMSE) and peak signal to noise ratio (PSNR). Results: The proposed densely interconnected residual cascading network (DIRCN), utilizing all three suggested modifications, achieved a SSIM improvement of 8% and 11% for four- and eight-fold acceleration, respectively. For eight-fold acceleration, the model achieved a 23% decrease in the NMSE when compared to the baseline model. In an ablation study, the individual architectural modifications all contributed to this improvement, by reducing the SSIM and NMSE with approximately 3% and 5% for four-fold acceleration, respectively. Conclusion: The proposed architectural modifications allow for simple adjustments on an already existing cascading framework to further improve the resulting reconstructions.

eess.IV↗

arXiv2023

Segmenting white matter hyperintensities on isotropic three-dimensional Fluid Attenuated Inversion Recovery magnetic resonance images: Assessing deep learning tools on norwegian imaging database

Automated segmentation of white matter hyperintensities (WMHs) is an essential step in neuroimaging analysis of Magnetic Resonance Imaging (MRI). Fluid Attenuated Inversion Recovery (FLAIR-weighted) is an MRI contrast that is particularly useful to visualize and quantify WMHs, a hallmark of cerebral small vessel disease and Alzheimer's disease (AD). Clinical MRI protocols migrate to a three-dimensional (3D) FLAIR-weighted acquisition to enable high spatial resolution in all three voxel dimensions. The current study details the deployment of deep learning tools to enable automated WMH segmentation and characterization from 3D FLAIR-weighted images acquired as part of a national AD imaging initiative. Among 441 participants (194 male, mean age: (64.91 +/- 9.32) years) from the DDI study, two in-house networks were trained and validated across five national collection sites. Three models were tested on a held-out subset of the internal data from the 441 participants and an external dataset with 29 cases from an international collaborator. These test sets were evaluated independently. Five established WMH performance metrics were used for comparison against ground truth human-in-the-loop segmentation. Results of the three networks tested, the 3D nnU-Net had the best performance with an average dice similarity coefficient score of 0.76 +/- 0.16, performing better than both the in-house developed 2.5D model and the SOTA Deep Bayesian network. With the increasing use of 3D FLAIR-weighted images in MRI protocols, our results suggest that WMH segmentation models can be trained on 3D data and yield WMH segmentation performance that is comparable to or better than state-of-the-art without the need for including T1-weighted image series.

eess.IV↗

arXiv2023

Voxels Intersecting along Orthogonal Levels Attention U-Net for Intracerebral Haemorrhage Segmentation in Head CT

We propose a novel and flexible attention based U-Net architecture referred to as "Voxels-Intersecting Along Orthogonal Levels Attention U-Net" (viola-Unet), for intracranial hemorrhage (ICH) segmentation task in the INSTANCE 2022 Data Challenge on non-contrast computed tomography (CT). The performance of ICH segmentation was improved by efficiently incorporating fused spatially orthogonal and cross-channel features via our proposed Viola attention plugged into the U-Net decoding branches. The viola-Unet outperformed the strong baseline nnU-Net models during both 5-fold cross validation and online validation. Our solution was the winner of the challenge validation phase in terms of all four performance metrics (i.e., DSC, HD, NSD, and RVD). The code base, pretrained weights, and docker image of the viola-Unet AI tool are publicly available at \url{https://github.com/samleoqh/Viola-Unet}.

eess.IV↗