IEEE Transactions on Medical Imaging

Viscoelastic characterization of tissue has significant diagnostic value in oncology, as tumor progression alters both elasticity and viscosity in ways that neither property alone can fully capture. Existing acoustic radiation force (ARF)-based methods such as Viscoelastic Response (VisR) ultrasound estimate relative elasticity and viscosity through per-A-line nonlinear model fitting, which is computationally intensive and requires auxiliary simulations to correct elasticity-dependent bias. This work presents VESTA (Machine Learning-Enabled Estimation of ViscoElastic Ratios from On-Axis Spatio-Temporal ARFI Features), a two-stage data-driven pipeline that predicts elasticity ratio (ER) and viscosity ratio (VR) directly from seven normalized ARFI displacement features at the A-line level, without model fitting or compensation. Stage~1 is an MLP classifier that detects inclusion boundaries from normalized peak displacement and negative peak velocity ratios; Stage~2 is a dilated Conv1D regression model that estimates ER and VR along the full axial sequence using the predicted mask alongside displacement features. The pipeline was trained on 500 simulated inclusion scenarios spanning three geometries, five focal depths, two F-numbers, and a broad range of material contrasts. In silico, mean predicted ER and VR were within 12\% of ground truth across all geometries, with performance best when ER and VR were moderate or decoupled. Experimental validation on a chicken breast phantom demonstrated plausible generalization to real tissue heterogeneity. Applied to an in vivo murine 4T1 breast cancer model, the pipeline tracked treatment-related attenuation of mechanical contrast in paclitaxel-treated tumors relative to controls over a 36-day imaging period, supporting its relevance for tumor monitoring.

The development of digital twins in medicine, i.e., virtual replicas of human organs, offers a promising path toward precision medicine by enabling interpretable, mechanistic, and actionable insights. In the brain, cerebrovascular twins support individualized modeling of hemodynamics and bio-transport, with broad applications. A major bottleneck, however, is the lack of robust methods to transform in vivo cerebrovascular images into simulation-ready cerebrovascular meshes or graphs. Here, we present CerebroVascular Imaging to Graph reconstruction (CVIG), a robust and multiscale framework for reconstructing whole brain cerebrovascular graphs from in vivo cerebrovascular images. CVIG integrates vessel vectorization, with tolerance to discontinuity in vessel structures, using a topology-guided assembly of vessel trees to generate cerebrovascular graphs from medical images. We demonstrate the ability of CVIG to generate vascular graphs with improved vascular coverage and topological correctness, the capability essential for high fidelity brain biophysical simulations. This work establishes a vascular graph framework for individualized modeling and analysis, providing a key foundation for digital twins of the human brain.

Constitutive models of myocardial mechanics form a cornerstone of personalized cardiac simulations and cardiac digital twins. Researchers traditionally prescribe these models a priori and calibrate them from ex vivo tissue experiments, even though tissue excision alters loading conditions, removes residual stresses, and eliminates important physiological interactions. Multimodal cardiac MRI now provides subject-specific ventricular geometry, deformation, and myocardial microstructure, yet current inverse approaches still rely on predefined constitutive laws. Here we present the first framework to discover constitutive models of passive myocardial mechanics directly from in vivo cardiac imaging data by embedding a constitutive artificial neural network within a nonlinear finite element model of ventricular filling. Using multimodal cardiac MRI that combines ventricular geometry, deformation, and microstructure from a representative healthy individual, the framework identifies sparse, mechanically admissible strain-energy functions without prescribing their form a priori. The best-performing model contains only two fiber- and two sheet-invariant terms, achieves a mean displacement error of 1.62 mm, and reduces the error of the widely used Guccione and Holzapfel models by 34.14% and 26.01%. The discovered models indicate that fiber- and sheet-related anisotropic mechanisms dominate the passive mechanical response during physiological ventricular filling. More broadly, this work establishes a non-invasive strategy for subject-specific constitutive discovery from cardiac imaging data and lays the foundation for personalized cardiac simulations and cardiac digital twins.

Hyperspectral imaging (HSI) has gained increasing attention for bone assessment because it captures rich wavelength dependent information associated with mineralised tissue. HSI provides detailed spectral information related to material composition, while 3D geometric information supports the analysis of surface morphology and structural detail. However, integrating spectral and geometric information remains challenging, particularly when conventional reconstruction pipelines depend on external pose estimation. To address this challenge, we propose BoNeRF-HS, a self-calibrated hyperspectral neural radiance field for 3D reconstruction. BoNeRF-HS jointly optimises camera intrinsics, volume density, and hyperspectral radiance, removing the need for COLMAP based poses. To improve spectral modelling, we incorporate a gated spectral adapter head that learns wavelength dependent radiance features for hyperspectral view synthesis. We evaluate BoNeRF-HS on a multi-view hyperspectral dataset containing mouse bone, trabecular bone analogue, and cortical bone analogue samples. Experimental results demonstrate that our framework achieves improved reconstruction quality, and better preservation of bone surface details compared with existing approaches.

Diffusion MRI (dMRI) enables noninvasive characterization of white-matter fiber orientations and tissue microstructure, but widely used approaches, such as constrained spherical deconvolution (CSD) and parametric multicompartment models, typically address these features separately. The diffusion tensor distribution (DTD) framework jointly represents fiber orientation and microstructure, but estimating DTD from finite, noisy measurements is severely ill-posed. Existing inversion methods either rely on nonnegativity constrained basis representations, which are challenging to sale to high-dimensional and high-resolution distributions, or use sampling-based approaches with limited reliability. We propose MaxEnt-DTD, a maximum-entropy algorithm for DTD estimation from finite and noisy dMRI data. By deriving the Lagrange dual formulation, we reformulate a constrained infinite-dimensional optimization problem into a finite-dimensional unconstrained convex optimization problem, substantially reducing the parameter space and enabling tractable whole-brain DTD estimation. We evaluate MaxEnt-DTD using both synthetic and in vivo data from the Human Connectome Project protocol and a second dataset using advanced B-tensor diffusion encoding. We compare MaxEnt-DTD-derived fiber orientation distributions with results from CSD and Monte-Carlo inversion methods, and assess fiber-specific microstructure measures and rotation-invariant metrics based on the cumulants of DTD. The results demonstrate that MaxEnt-DTD provides a reliable and efficient framework for joint fiber-orientation and microstructure analysis in dMRI.

Objective: This study aims to develop and validate a quantitative, depth-resolved anisotropy imaging framework that extends ARFI-based focal degree-of-anisotropy (DoA) estimation into two-dimensional mapping by modeling the depth-dependent relationship between shear modulus ratio (SMR) and peak displacement ratio (PDR). Methods: We propose APRIL (Adaptive Polynomial Regression for anisotropy Imaging via ARFI-induced DispLacements), a framework for quantitative, depth-resolved DoA imaging that adaptively selects polynomial regression or shape-preserving spline interpolation based on excitation PSF asymmetry. Training data were generated using an LS-DYNA3D + Field II simulation pipeline in homogeneous transversely isotropic media (SMR 0.9-4.9). Testing included shifted SMRs under varied acoustic conditions and three heterogeneous inclusion configurations (anisotropic inclusion in isotropic background and vice versa). Experimental validation was performed in an in-vivo murine tumor model over the time, ex-vivo chicken breast, and tissue-mimicking gelatin phantoms, using a Verasonics system with an L11-5v transducer. Results: APRIL achieved depth-resolved SMR prediction errors below 9% over 10-30 mm, with highest accuracy in the focal region (MAE 2.3%, RMSE < 0.1) and stable performance across PSF transition zones. In heterogeneous phantoms, it reconstructed anisotropy maps with SSIM up to 86% and MPE below 7%, accurately delineating inclusion boundaries. Under acoustic parameter variations, mean absolute errors remained below 10%, demonstrating robustness to system and tissue heterogeneity. Conclusion: APRIL enables robust, two-dimensional anisotropy imaging beyond focal estimates. Significance: The method provides a physically grounded and generalizable framework for clinically viable anisotropy biomarkers in muscle, tendon, kidney, tumor and breast tissues.

This study presents the use of sub-micron nanobubbles (NBs) as contrast agents for ultrasound localization microscopy (ULM), a super-resolution imaging technique that visualizes microvascular structure and flow beyond the acoustic diffraction limit. While ULM has traditionally relied on micron-sized microbubbles (MBs), the reduced dimensions and prolonged circulation times of NBs make them attractive candidates for localization-based imaging. However, their weaker acoustic responses present significant challenges for reliable detection and tracking. To address this challenge, we developed the ULM Master GUI, an interactive framework for optimization of the complete ULM processing pipeline. Using custom ultrasound-compatible wall-less gelatin flow phantoms containing vessel-mimicking channels and bifurcations ranging from 100 to 500 m, we demonstrate that NB-based ULM achieves velocity reconstruction and flow partitioning measurements comparable to conventional MB-based ULM. Across all investigated geometries, NBs faithfully reproduced the underlying flow patterns and hemodynamic behavior despite their substantially reduced acoustic scattering. These findings establish the feasibility of NB-based ULM, expand the range of contrast agents available for localization microscopy, and provide a foundation for future super-resolution ultrasound imaging using nanoscale acoustic contrast agents. The ULM processing GUI is publicly available at https://github.com/grisha1998/ulm-super-resolution-toolbox.

Medical foundation models compress biomedical data into embeddings that support diverse downstream clinical tasks. However, successful model deployment is hampered by performance degradation on external data. It is recognized that embeddings capture acquisition signatures, such as hardware and technical differences, in addition to biology. Effective harmonization must remove the acquisition signature while preserving biological signals, a trade-off that current methods fail to balance adequately. Input-level normalization fails to eliminate acquisition signatures from embeddings, whereas embedding-level methods adjust features in an untargeted manner. We present FEATMAP, a harmonization approach that models acquisition signatures as geometric distortions between manifolds of similarly arranged embeddings. Using paired data that isolate the effect of acquisition signatures, FEATMAP fits a single global affine transformation per foundation model to correct acquisition signatures directly in the embedding space. This targeted, reusable correction aims to preserve biological and demographic variation while harmonizing across acquisition signatures. Across scanner and foundation-model harmonization in digital pathology and field-strength harmonization in brain MRI, FEATMAP improves cross-condition embedding similarity, reduces performance gaps without retraining, and suggests potential for the alignment of disparate embedding spaces.

Clinical treatment planning of near-infrared (NIR) brain stimulation requires patient-specific light dosimetry to optimize fluence delivery to cortical targets. The gold-standard Monte Carlo (MC) photon transport forward solver is accurate but computationally expensive and non-differentiable for personalized inverse design across subjects. Here, we present a foundation-model (FM)-encoded, differentiable implicit-neural surrogate for the MC solver. A pretrained 3D MRI/CT foundation model, VISTA3D, is domain-adapted to head phantoms with known optical properties to encode the subject anatomy. Next, an implicit neural representation is used to predict light fluence at arbitrary continuous coordinates. This formulation enables off-grid queries and gradients with respect to illumination parameters. Trained with a physics-informed, decade-stratified loss, the surrogate attains R2 {approx} 0.90 on held-out subjects. Ablation results show that the FM benefit is contingent on domain adaptation. Benchmarked against standard learned surrogates, our model is the most accurate in the high-dose region and best on dose-fidelity metrics ({gamma}-index, treated-volume DICE). Finally, gradient-based optimization through the surrogate recovers MC-consistent illumination configurations 50-240 x faster.

AO_SCPLOWBSTRACTC_SCPLOWEarly tumor detection is critical for improving patient survival and recovery. Clinically, tissue palpation is routinely used to identify regions of abnormal stiffness, a hallmark of many pathological conditions. However, palpation is restricted to anatomically accessible sites and remains highly operator dependent. Here, we introduce a method for real-time quantitative stiffness mapping using an unmodified commercial endoscope, with the goal of enhancing diagnostic capabilities and restoring mechanical feedback during endoscopic procedures. Our approach combines shear wave elastography with speckle imaging and an innovative synchronization strategy that enables the measurement of shear wave propagation using an unmodified commercial endoscope. The resulting wave fields are analyzed with the noise-correlation-inspired (NCI) method[1], providing pixel-wise estimates of shear wave velocity and, consequently, quantitative maps of local tissue stiffness. The method demonstrated robust performance in both benchtop and endoscopic configurations. Validation was achieved on polymer phantoms as well as on ex vivo and in vivo biological tissues, highlighting its potential for minimally invasive biomechanical imaging and real-time tissue characterization.

Minimally invasive surgery is a powerful technique that enables operations deep within the body while minimizing patient trauma and recovery time. Optical endoscopes are key to providing intraoperative vision but still face challenges due to the loss of essential senses, including depth perception and tactile feedback for tissue evaluation. Thus, it is critical to develop endoscopic imaging technologies that can augment operators with critical information. In this work, we explore a prototype multimodal 3D imaging endoscope that integrates volumetric light-field imaging with laser-speckle contrast imaging to simultaneously capture 3D structure and blood-flow information in a clinically relevant form factor.

As machine learning and artificial intelligence systems are increasingly used in healthcare, rigorous evaluation of their classification performance has become critical. The F1 and F{beta} scores are widely adopted metrics for assessing performance in imbalanced biomedical data. Recently, we introduced psF1, a unified statistical framework for inference and study design for single and comparative F1 and F{beta} scores under the assumption of independent classifiers. In practice, however, benchmarking two classifiers on the same dataset creates a correlated paired setting. Ignoring this intrinsic dependency leads to overestimation of the standard error and a substantial loss of statistical power. To address this, we develop psF1pair, an advanced framework for statistical inference and power analysis that explicitly accounts for correlations between classifier pairs. Extensive simulation studies demonstrate the performance of psF1pair, and its utility is further illustrated through application to a real-world imaging classification system. As expected, higher correlation between classifiers yields narrower confidence intervals and enhanced statistical power. A freely available R package is provided to facilitate implementation, supporting accurate evaluation and study design for predictive and classification models in biomedical research.

Deep learning models deployed in clinical imaging frequently encounter distribution shifts, yet most out-of-distribution (OOD) detection methods are evaluated only on controlled research datasets. As a result, it is unclear whether existing approaches can reliably identify segmentation failures that arise in real-world clinical practice. We evaluated six OOD detection methods on a deployed liver CT segmentation model (3D nnU-Net) using internal data from 400 patients and external data from 100 patients collected across nearly 70 sites in 7 countries. One method was Pairwise Surface DSC, a surface-based extension of Pairwise DSC, that we introduced. OOD performance was measured using sensitivity, AUROC, and balanced accuracy, with thresholds determined on an independent cohort of 400 patients using the Youden J statistic. Statistical significance was assessed using McNemar tests and stratified bootstraps ( = 0.05) with Benjamini-Hochberg correction. Pairwise Surface DSC was the top-performing method, with perfect sensitivities (1.00), near-perfect AUROCs (0.97 internal; 1.00 external), and the highest balanced accuracies (0.94 internal; 0.88 external; p<0.001). These results show that automated failure detection for liver CT segmentation is clinically feasible and that Pairwise Surface DSC is a promising candidate for deployment. Our code is available at https://github.com/mckellwoodland/liver_ct_ood_translation.

Soft X-ray tomography (SXT) is an emerging modality for whole-cell 3D imaging in near-native states. However, the effective spatial resolution is limited by optical artifacts characterized by the point spread function (PSF). To achieve optimal resolution via PSF inversion, we propose a measurement-supervised deep learning framework. Bypassing purely data-driven neural networks that are prone to hallucinations, we employ a measurement-supervised, instance-specific optimization strategy strictly constrained by a differentiable SXT formation forward model. The structural fidelity was validated using split-tilt Fourier ring correlation (FRC), ensuring the recovered high-frequency features reflect genuine specimen features rather than random artifacts. Our results demonstrate that this optimization consistently increases FRC resolution and enhances visual ultrastructural details across diverse biological structures. Furthermore, by recovering high-frequency features from sparse-angular projections, we show that spatial resolution can be maintained using only half the radiation exposure. This approach effectively compensates for the degradations caused by angular sparsity, providing a hardware-free computational solution to minimize radiation damage, maximize imaging speed, and overcome the optical and dosimetric limits of SXT.

Human brain magnetic resonance imaging (MRI) revolutionized our ability to non-invasively probe individual differences in neuroanatomy. These anatomical scans, in turn, also allow us to accurately localize functional MRI (fMRI) activity. However, extracting anatomical labels and structural characteristics, such as cortical surface area or thickness, is a computationally demanding task, taking on the order of hours per brain volume. This is an intrinsically multi-scale problem given that local image structure defines fine boundaries, whereas accurate assignments depend on broader anatomical context. Here, we introduce ScaleSurfer, a three-dimensional convolutional vision transformer model based on multi-scale learning. Convolution blocks capture local anatomical detail and a transformer bottleneck integrates the distributed spatial context. This approach provides rapid, whole-brain morphometric feature estimation, including volume, cortical thickness, surface area, and curvature. Importantly, ScaleSurfer accomplishes this nearly five orders of magnitude faster than current pipelines, taking 150-500 ms instead of ~5 hours. We validated ScaleSurfer on multiple datasets, showing stable learning across heterogeneous MRI collections, and demonstrate feasibility by training an interpretable Alzheimer's disease classifier that identifies reductions in primarily medial temporal lobe subregions compared to healthy controls. ScaleSurfer positions multi-scale representation learning as a practical route toward faster, anatomically faithful structural MRI processing, whose speed paves the way for nearly real-time anatomical quality control during scanning.

Pneumonia is a leading cause of infectious disease mortality worldwide, accounting for approximately 2.5 million deaths annually and 15% of deaths in children under five. Chest X-ray imaging remains the primary diagnostic tool, but accurate interpretation requires radiological expertise that is disproportionately concentrated in high-income settings, creating a diagnostic gap where disease burden is highest. Automated deep learning offers a scalable complement to specialist-dependent diagnosis, yet clinical adoption requires both high accuracy and transparent, interpretable reasoning. Convolutional neural networks (CNNs) have shown strong potential for pneumonia detection from chest X-rays, but two barriers impede clinical translation: the interpretability of black-box models and the computational feasibility of large architectures in resource-constrained settings. Explainable AI (XAI) methods such as Grad-CAM, Grad-CAM++, and Score-CAM address the interpretability barrier, yet systematic quantitative comparisons across multiple CNN architectures remain scarce. Furthermore, CNN architectures widely used for medical image classification carry high parameter counts that limit feasibility in resource-constrained settings, motivating architectures that achieve competitive accuracy with substantially fewer parameters. Here we propose a parameter-efficient deep learning framework for pneumonia detection based on transfer learning, evaluated across three CNN architectures representing distinct architectural families: EfficientNet-B0 with fine-tuning (proposed method), ResNet50, and DenseNet121, trained under identical conditions on the Kaggle chest X-ray dataset (5,863 images). Our method achieved 90% classification accuracy, outperforming both baselines while requiring 4.8x fewer parameters than ResNet50. To evaluate explainability, Grad-CAM, Grad-CAM++, and Score-CAM were applied across all three architectures and compared quantitatively using Intersection over Union against manually annotated lung segmentation masks, Insertion score, and Deletion score, with pairwise statistical validation via Wilcoxon signed-rank tests and Bonferroni correction. Findings show that classification accuracy and XAI explanation quality must be evaluated independently, and that the proposed parameter-efficient architecture offers a favorable trade-off for resource-constrained clinical deployment.

Non-contrast head CT is the first-line imaging modality for acute neurological emergencies, with demand rising worldwide. However, existing foundation models for head CT interpretation are ill-suited for emergency use because they target general or chronic-disease assessment and optimize reports for lexical overlap rather than the risk-relevant findings central to emergency triage. Here we present CHIEF, a Chinese-language Head CT Interpretation Emergency Foundation model, pretrained on emergency head CT volumes and paired reports with contrastive, generative, and geometry-regularization objectives. Trained and evaluated on 16,563 examinations from seven hospitals, CHIEF achieved an AUROC of 0.9646 for emergency triage and drafted triage-oriented radiology reports, while also supporting image-to-text retrieval for reference-case support and zero-shot abnormality recognition. CHIEF generated reports of substantially higher quality than those from commercial multimodal large language models, which could not be reliably distinguished from human-written ones by radiologists in a blinded Turing test. Overall, CHIEF provides a generalizable foundation for emergency head CT interpretation and radiologist-in-the-loop clinical decision support.

Urinary stone disease is a common urological condition with increasing incidence, particularly in developed countries. Laser lithotripsy (LL) has become a preferred minimally invasive treatment due to its high precision and low tissue damage. Recent studies suggest that cavitation plays a critical role in stone damage during LL, and three-dimensional passive cavitation mapping (3D-PCM) has emerged as a promising tool for detecting these events. However, clinical translation of 3D-PCM remains challenging due to limitations in imaging depth, field of view (FOV), and procedural compatibility. Here, we present a large-FOV dual-modality imaging system (3D-PCM and B-mode ultrasound) based on a large-aperture planar ultrasound array. Through array optimization and model-based reconstruction, our system achieves an expanded FOV of ~40*40mm^2 at a clinically relevant imaging depth of ~110mm, while maintaining high spatial resolution of ~0.6 mm laterally and ~0.4 mm axially. In vivo experiments in a porcine model demonstrate that the reconstructed cavitation distribution correlates well with stone damage. Our technology has the potential to provide real-time treatment feedback during LL without disrupting the standard workflow.

Converting medical images into anatomically detailed, subject-specific finite element (FE) models is a long-standing bottleneck in brain computational modelling. These models are used to predict brain tissue deformation, e.g. in traumatic brain injury, particle diffusion in brain drug delivery, and other biophysical phenomena across neurological disorders. However, existing model creation workflows depend on manual image segmentation, proprietary meshing software, and labour-intensive repair of meningeal and interface structures, limiting reproducibility and cohort analysis. Here we present PARS, a fully automated, open-source pipeline that converts a T1-weighted MRI scan into a simulation-ready FE head model. PARS combines anatomical parcellation with tissue maps and uses iterative neighbourhood-based reclassification, yielding a gap-free whole-head label volume. The volume is directly converted into a hexahedral mesh, augmented with algorithmically reconstructed falx, tentorium, pia and dura mater, and refined by Laplacian smoothing under a node-locking scheme that controls element quality and the explicit-solver stable timestep. We evaluated PARS on 23 subjects spanning cranial volumes of 832 to 1,329 cubic centimeter, at 1.0, 1.5 and 2.0 mm MRI resolutions. At 1 mm, meshes achieved a median Scaled Jacobian of 0.976, and total intracranial volume error of ~0.54; quality remained high at 1.5 mm (SJ of 0.933) and 2 mm (SJ of 0.921). Model creation runtime ranged from 9 to 38 minutes per subject. Models generated by PARS have been validated against cadaveric brain displacement data and demonstrated utility across traumatic brain injury and normal pressure hydrocephalus research. PARS provides an open-access, reproducible resource that substantially lowers the barriers to subject-specific brain modelling.

We developed a standardized, reproducible preprocessing framework for computed tomography (CT) imaging data from multi-institutional repositories such The Cancer Imaging Archive (TCIA), enabling consistent radiomics and artificial intelligence (AI) analyses. Imaging data from TCGA-KIRC patients available on TCIA were used as a representative heterogeneous dataset characterized by variation in acquisition protocols, inconsistent metadata, and differing image quality. The proposed modular pipeline includes series filtering, DICOM-to-NIfTI conversion, orientation harmonization to a canonical coordinate system, voxel spacing normalization, intensity clipping and normalization, segmentation integration, and metadata validation, and is implemented in a reproducible, notebook-based framework compatible with common radiomics and deep learning workflows. This pipeline standardizes imaging data into analysis-ready volumes with consistent geometry, intensity distributions, and spatial alignment, reducing non-biological variability that can adversely affect radiomic feature stability and model performance. The modular design enables task-specific adaptation of individual preprocessing steps while maintaining overall consistency. Although demonstrated on TCIA, this framework is generalizable to other heterogeneous imaging datasets and provides a foundation for robust, large-scale computational imaging studies.