Search Results (541)

Background: Autopsy pathology remains the reference standard for determining the cause of death, reconstructing disease and injury mechanisms, ensuring diagnostic quality, and supporting medical education and forensic investigations. However, declining autopsy rates, workforce shortages, biosafety concerns, increasing diagnostic complexity, and the rapid evolution of digital technologies have stimulated the development of complementary investigative approaches. This review critically examines whether artificial intelligence (AI) and emerging technologies are driving a genuine paradigm shift toward digitally integrated death investigation. Methods: A structured narrative review informed by a systematic literature search was conducted in PubMed/MEDLINE, Embase, Scopus, and Web of Science, covering publications from January 2000 through June 2026. Evidence addressing postmortem imaging, virtopsy, digital pathology, computational pathology, molecular autopsy, robotics, artificial intelligence, machine learning, and emerging omics technologies was critically appraised. Owing to the methodological heterogeneity of the available literature, findings were synthesized qualitatively according to technological maturity, forensic applicability, validation status, and implementation readiness. Results: The reviewed evidence demonstrates substantial progress in postmortem computed tomography, postmortem CT angiography, postmortem magnetic resonance imaging, whole-slide imaging, molecular autopsy, robotic-assisted postmortem procedures, three-dimensional reconstruction, and AI-assisted forensic analysis. These technologies enhance trauma evaluation, vascular imaging, ballistic reconstruction, digital documentation, remote consultation, diagnostic reproducibility, and multimodal integration of forensic evidence. Nevertheless, the level of evidence varies considerably across technological domains. Postmortem imaging represents the most mature and extensively validated technology, whereas most AI applications remain supported predominantly by retrospective proof-of-concept studies with limited multicenter external validation. Current systematic evidence further indicates that AI should presently be regarded as an assistive technology that augments expert forensic interpretation rather than replacing conventional autopsy or autonomous medicolegal decision-making. Conclusions: Contemporary autopsy pathology is evolving toward a hybrid model of digitally integrated death investigation in which conventional autopsy, imaging, digital pathology, molecular diagnostics, robotics, and AI function as complementary components of a unified forensic workflow. Current evidence supports a conceptual paradigm shift characterized by transformation of evidence acquisition, preservation, interpretation, and integration, while reaffirming that conventional autopsy remains the indispensable biological reference standard for the development, validation, and medicolegal interpretation of all emerging technologies. Future implementation should prioritize multicenter validation, standardized forensic datasets, explainable AI, digital chain-of-custody procedures, and robust regulatory governance to ensure safe and scientifically reliable integration into forensic practice. Full article

Reliable medical image segmentation remains challenging because models must preserve fine boundary details while maintaining global semantic consistency. CNNs capture local structures effectively but have limited long-range modeling ability, whereas Transformer-based methods improve global context at high computational cost. Mamba-based state space models offer efficient long-range modeling, but may weaken high-frequency textures and boundary cues. To address these limitations, we propose DIG-MambaNet, a Dual-path Interactive Guided Mamba Network for medical image segmentation. The network introduces a dual-path complementary modeling block (DCM Block), where a cross-feature spatial interaction module (CSIM) adaptively integrates CNN-based local features and Mamba-based global features. A source image-guided module (SIGM) injects high-frequency information from the original image to compensate for downsampling-induced detail loss, while an inter-layer detail refinement fusion module (IDRFM) improves encoder–decoder feature alignment during reconstruction. Experiments on 2018DSB, ISIC2018, JSUAH-Cerebellum, and CVC-ClinicDB, covering nuclei segmentation in microscopy images, skin lesion segmentation in dermoscopic images, fetal cerebellum segmentation in ultrasound images, and polyp segmentation in colonoscopy images, demonstrate that DIG-MambaNet achieves consistent and competitive performance across diverse target structures and imaging conditions, with improved boundary delineation and favorable overlap-based accuracy compared with representative CNN-, Transformer-, and Mamba-based methods. Full article

Magnetic particle imaging (MPI), as an emerging radiation-free, high-sensitivity molecular imaging technique, holds broad application prospects in fields such as medical diagnosis, angiography, and targeted drug tracking. However, traditional three-dimensional MPI reconstruction algorithms face a problem in balancing reconstruction speed and image resolution. A hybrid reconstruction algorithm (Full Hybrid) based on spatial density constraints and residual iterative optimization is proposed in this work. This paper simulates Lissajous trajectory scanning and the non-linear response of magnetic particles based on the three-dimensional MPI simulation framework. The proposed hybrid method first utilizes the X-space method to obtain a basic spatial prior, then introduces field-free point (FFP) trajectory density to impose spatial weighting constraints on the reconstructed image. Experimental results demonstrated that this hybrid algorithm performs better in the reconstruction of complex three-dimensional topological structures (an H-shaped phantom). Comprehensive evaluation demonstrated that the reconstructed outputs reach a peak signal-to-noise ratio (PSNR) of 12.85 dB, a structural similarity index measure (SSIM) of 0.7321, and a root mean square error (RMSE) of 0.2278. Ablation experiments and comparison experiments further reinforced the advantages of the proposed method. These results demonstrate the numerical feasibility of the proposed reconstruction method for a three-dimensional phantom and provide a basis for further evaluation under multiple simulation conditions and real-scanner measurements. Full article

The super-resolution (SR) of Magnetic Resonance Imaging (MRI) is essential for utilizing clinical scans with limited resolution, noise, and anisotropic sampling, such as multi-modal brain tumor imaging. In this work, we propose a Tri-Representation hybrid framework for MRI SR, TRT-GLA, that redefines the MRI SR task as a joint spatial–spectral–structural high-resolution image generation problem. TRT-GLA utilizes (i) spatial global–local attentions for modeling the spatial anatomy, (ii) a Fourier spectral transfer mechanism for upholding spectral consistency, and (iii) multi-scale hierarchical spectral decomposition for improved edge details. To adapt the learning framework to medical imaging characteristics, we introduce a tri-representation consistent loss function that explicitly combines pixel-wise, spectral, and edge structure priors from the high-resolution ground-truth, as well as a progressive resolution learning strategy. Our large-scale brain tumor experiments, on the IXI, BraTS 2019, 2020, and 2023 datasets, show that TRT-GLA achieves state-of-the-art results at upsampling factors of ×2, ×4, and ×8, respectively, achieving substantial improvements across CNN, GAN, and transformer-based methods in Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Multi-scale Structural Similarity Index (MS-SSIM). We further demonstrate how SR benefits brain tumor segmentation through the downstream task evaluation of a dual-branch segmentation framework. TRT-GLA produces highly accurate tumor segmentation results from low-resolution inputs, improving over native high-resolution inputs at ×8 in critical tumor boundary regions and in small tumor regions. There remains a small gap between native, high-resolution imaging and SR-enhanced performance, which TRT-GLA nearly closes under realistic scenarios. Our results highlight the importance of synthesizing unified priors over spatial, spectral, and structural domains within a transformer for anatomically faithful reconstructions. Importantly, we also establish the utility of TRT-GLA in supporting quantitative analysis through a downstream tumor segmentation experiment that is clinically relevant. Full article

Multimodal Medical Image Fusion (MMIF) aims to exploit the correlation and complementarity of different imaging modalities to integrate cross-modal information and provide more potential support for clinical diagnosis. However, effectively preserving both shallow and deep features of each modality while integrating multi-source representations remains challenging, often leading to blurred edges and loss of fine details in fused images. To address this issue, this paper proposes a novel Dual-stream Decoupled Feature parallel alignment fusion network (DDFNet). Built upon an autoencoder (AE) framework, the encoder adopts a dual-branch multi-scale design, consisting of a Detail Feature Extraction Module (DFEM) and a Global Context Feature Extraction Module (GCFEM). These two parallel branches leverage the complementary advantages of CNNs and Transformers to capture local details and global contextual dependencies, respectively, while operating independently without feature interference. In addition, an Improved Multi-scale Cross-alignment and Spatial Attention Fusion module (IMSC-SAF) is introduced to enhance feature integration. It performs complementary feature alignment and cross-attention to strengthen multiscale interactions, while a spatial attention mechanism highlights spatially salient regions. The decoder then reconstructs the fused representation and generates the final fused image. Extensive experiments on publicly available datasets from Harvard Medical School demonstrate that the proposed method achieves competitive fusion performance. In particular, DDFNet consistently obtains the highest MI, VIF, and SSIM values across the evaluated datasets while maintaining competitive results in the remaining objective metrics. Qualitative comparisons further demonstrate that the proposed method effectively preserves complementary anatomical and functional information, producing visually balanced fusion results. Full article

Image reconstruction from incomplete measurements is a fundamental problem in signal and image processing, with applications ranging from medical imaging to computational photography. In recent years, deep learning approaches have shown promising performance, particularly when combined with physics-inspired formulations such as deep unrolling. This paper presents a systematic comparative study of classical interpolation and variational reconstruction methods, direct convolutional neural networks (CNNs), and unrolled data-consistency CNN architectures for image reconstruction under different sampling patterns. We consider three representative mask types: structured block masks, nonuniform masks, and random sampling patterns, with sampling ratios ranging from 10% to 50%. Experiments are conducted on the public BSDS500 image dataset, using a fixed grayscale preprocessing pipeline and a reproducible train/validation/test split. Experimental results demonstrate that reconstruction performance strongly depends on the sampling pattern. For random masks, the full unrolled DC-CNN achieves the best quantitative and qualitative performance, reaching a PSNR of 30.98 dB and an SSIM of 0.921 at 50% sampling. In contrast, for structured block and nonuniform masks, TV-based inpainting provides the strongest overall performance, showing that classical model-based reconstruction remains highly competitive when the sampling pattern contains spatially coherent missing regions. A block-size sensitivity analysis further confirms that the difficulty of structured-mask reconstruction is governed by the geometric severity of the missing region. Statistical analysis using paired tests with Holm correction confirms that the main performance differences are significant across the evaluated configurations. Furthermore, we show that a lightweight unrolled model with shared weights and reduced depth achieves a substantially lower parameter count and lower computational cost than the full unrolled architecture, although with reduced accuracy in the most favorable random-sampling cases. These findings provide practical insights into the relationship between sampling strategies and reconstruction performance, offering guidance for the design of efficient and robust learning-based reconstruction systems. Full article

Federated learning lets hospitals train shared diagnostic models without exchanging patient images, yet the updates they exchange each round can be inverted to reconstruct training images. Homomorphic encryption (HE) protects these updates, but encrypting an entire model with CKKS inflates communication and computation to impractical levels for cross-silo medical use. We present PASHE-FL, which exploits the structure of personalized federated learning: the client-specific classifier head stays local and is never uploaded, so encryption need only cover the shared backbone. The server ranks backbone coordinates by importance from the public global model and selects the same top-$\rho$ set for all clients, avoiding mask negotiation; these are encrypted with CKKS, the remaining coordinates are quantized, and the encrypted fraction is annealed over training. On four medical image-classification tasks, PASHE-FL matches the personalized FedPer baseline within about one accuracy point while cutting per-round uplink by roughly $7.1$–$7.6\times$ and encryption time by about $8\times$ relative to full-model HE; this accuracy comes from personalization, not encryption. Under a gradient-inversion attack, encrypting only the top 5–10% most important coordinates collapses reconstruction quality, whereas encrypting random coordinates does not. PASHE-FL offers an empirical privacy–cost trade-off under the stated threat model rather than a formal privacy guarantee. Full article

Background: Rapid, disproportionate expansion of post-infarction left ventricular (LV) aneurysms represents a high-risk remodeling phenotype characterized by progressive mechanical deterioration and severe geometric distortion. Methods: A 54-year-old male presented with late anterior myocardial infarction complicated by a partially thrombosed apical LV aneurysm with an initial left ventricular ejection fraction (LVEF) of 35%. Despite clinical stability under optimal guideline-directed medical therapy, serial multimodality imaging at 7 weeks revealed an aggressive, disproportionate expansion of the aneurysmal component to 120 mL, inducing severe ventricular geometric distortion and secondary functional degradation (LVEF 20%). Multimodality imaging demonstrated a favorable geometry of the functional ventricle with preserved contractile function. Results: The patient underwent prompt surgical ventricular restoration using a double-patch Dor technique, effectively excluding the large aneurysm and restoring physiological ventricular geometry. The postoperative course was uneventful. At 6-month follow-up, cardiovascular magnetic resonance confirmed sustained reverse remodeling and significant recovery of systolic LV function (LVEF 47%). Conclusions: This case illustrates that rapid post-infarction aneurysmal expansion may occur despite apparent clinical stability. Comprehensive multimodality imaging may help identify selected patients in whom a reconstructible myocardial substrate supports surgical ventricular restoration despite severely reduced LVEF, even when conventional clinical indications for aneurysmectomy are absent. Full article

Millimeter-wave (mm-wave) near-field imaging using frequency-modulated continuous wave (FMCW) radar has emerged as a pivotal technology for high-resolution applications, including security screening, non-destructive testing, and medical diagnostics. This review evaluates the performance and evolution of key imaging algorithms, categorized into spatial-domain and frequency-domain frameworks. We analyze the delay-and-sum (DAS) beamformer for its real-time utility and the back-projection algorithm (BPA) for its baseline phase precision and robust adaptability to irregular scanning trajectories. To address the high computational demands of standard spatial-domain processing, we examine fast alternatives such as the range migration algorithm (RMA). The exact RMA leverages Fourier-domain operations and Stolt coordinate mapping to achieve optimal computational scaling on uniform grids while preserving diffraction-limited spatial resolutions. Concurrently, we evaluate fast spatial-domain approximations, including Fast Back-Projection (Fast-BPA), which introduces localized Taylor-series expansions to linearize near-field range paths within sub-apertures, accelerating voxel reconstruction times at a reduced computational cost. Furthermore, this study explores advanced modifications designed to overcome physical and operational constraints, such as motion-compensated matched filtering (MF) to eliminate the “stop-and-go” assumption in continuous scanning, and sparse multiple-input multiple-output (MIMO) configurations to mitigate aliasing in undersampled environments. Comparative analysis reveals that while spatial-domain methods (DAS/BPA) generally offer higher robustness to non-uniform aperture perturbations, frequency-domain migration pathways (RMA) maximize the computational throughput required for large-volume three-dimensional (3D) reconstructions. The findings demonstrate that achievable resolution is primarily governed by signal bandwidth and aperture synthesis, though practical performance is often limited by calibration errors and computational overhead. Collectively, these advancements validate the potential of mm-wave FMCW systems to achieve sub-millimeter 3D imaging, bridging the gap between theoretical diffraction limits and real-world indoor sensing challenges. Full article

Clinical AI systems rely on evolving machine learning pipelines and large-scale medical imaging data, creating persistent challenges in trust, auditability, consent governance, and reproducibility. This paper proposes a decentralized governance framework for clinical AI that uses blockchain as a verification and policy-enforcement overlay without decentralizing sensitive medical data storage or clinical inference. Raw images and clinical artifacts remain in secure repositories, while cryptographic commitments, consent states, access events, and reproducibility manifests are anchored to a tamper-evident ledger. The framework enables verifiable provenance, programmable consent enforcement, auditable execution, and deterministic reconstruction of AI-assisted decisions while preserving regulatory alignment and clinical usability. In a medical imaging proof-of-concept spanning nine simulated scenarios and approximately 43,500 inference attempts across cohorts of 50 to 1000 subjects, the framework achieved a mean Governance Quality Index of 0.93, governance overhead below 11 ms per operation under routine settings, and throughput above 220 requests per second on average. Complementary validation over a real-world paired imaging-and-clinical dataset structure further showed that the same governance abstractions can be instantiated for 625 subjects and 6349 MR images. Overall, the framework separates governance from data and computation, providing verifiable auditability and reproducibility without disrupting existing clinical infrastructures. Full article

Medical images contain anatomical identifiers that persist beyond explicit metadata removal. We empirically characterize how Gerchberg–Saxton (GS) transformation affects subject-identification risk and diagnostic signal across two modalities and four adversary classes. We evaluate transformation impact on OASIS-1 brain MRI and NIH-CXR chest radiography using ResNet18 and DenseNet121, measuring diagnostic utility via subject-level AUC and subject-identification risk under cross-domain and in-domain supervised re-identification (closed-set), embedding-based linkage (open-set), and reconstruction-based inversion using U-Net and diffusion posterior sampling. Cross-domain supervised re-identification collapses to near-chance by GS-10% (OASIS-1 ResNet18: 0.6% [95% CI: 0.0–0.9]; NIH-CXR DenseNet121: 0.6% [0.3–0.8]), from respective RAW baselines of 83.9% and 72.4%. Reconstruction models achieve high perceptual fidelity (U-Net SSIM: 0.937 [0.932–0.942] at GS-0%) but do not restore RAW-baseline re-identification accuracy despite direct training exposure to all evaluation subjects. In-domain supervised and embedding-based re-identification decline consistently across masking levels, with modality-dependent magnitudes. Diagnostic AUC reductions remain within 3.6–6.1 percentage points at GS-50%. GS transformation produces a consistent empirical asymmetry between subject-identification risk reduction and diagnostic signal retention across modalities, architectures, and adversary classes. Masking strength $p$ tunes this asymmetry, yielding a range of empirical operating points. Results reflect empirical evaluation under assessed adversary classes and do not constitute formal privacy guarantees. Full article

Self-supervised learning can reduce the dependence of 3D medical image analysis on expensive voxel-level annotations, but masked image modeling remains inefficient when uniform random masking is applied to volumetric data with large redundant backgrounds. Random masks often generate easy reconstruction targets that can be recovered through local interpolation, limiting the learning of anatomical semantics. Therefore, an effective masking strategy should adapt to image-specific structural difficulty rather than sample regions uniformly. We propose Active Region Masking (ARM), a self-supervised pre-training method that treats 3D mask generation as a patch-wise actor–critic decision process. Patch-level decision units share an actor–critic policy and use reconstruction error with a masking-ratio constraint as an intrinsic reward to identify regions that are difficult to reconstruct and potentially informative for anatomical representation learning. The reconstructor is trained with an asymmetric 3D Swin Transformer encoder–decoder, encouraging global anatomical reasoning from visible context. For segmentation tasks, the ARM pre-trained encoder is used to initialize the downstream Swin-UNETR framework; classification is evaluated with a matched downstream protocol. Across 12 task-level downstream evaluations, including BTCV, MSD, MM-WHS, AMOS22, FLARE22, CC-CCII, and BraTS21, ARM consistently improves over the evaluated contrastive and masked-modeling baselines. With 1k scans as pre-training data, ARM achieves an average Dice score of 89.80% on the BTCV-and-unseen-dataset benchmark, and scaling to 10k scans increases the average Dice score to 90.66%. These results indicate that active region masking improves label efficiency, segmentation robustness, and CT-to-MRI transfer in 3D medical image analysis. Full article

Background/Objectives: Accurate breast lesion segmentation using deep learning models requires precise understanding of both global contextual relevance and finer lesion structure details, which remains a challenge for existing convolutional and transformer-based approaches. This study aims to address these limitations by proposing a new segmentation model capable of improving context-aware dense segmentation tasks for ultrasound images. Method: We propose LTM-UNet, a novel segmentation method integrating transformer-based encoding with state-space-driven decoding in a U-Net-style framework. The architecture utilizes an efficient vision transformer encoder to extract multi-scale global representations. These features are refined through an attention-guided skip-fusion mechanism incorporating spatial-channel attention preserving finer spatial details and thereby minimizes the semantic gap between encoder and decoder features. Additionally, a direction-aware decoder based on a state-space model is introduced to efficiently capture long-range dependencies and enhance relevant feature reconstruction. Results: Extensive experiments on benchmark ultrasound medical imaging datasets demonstrate the effectiveness of the proposed method. The model achieves dice-score coefficients of 82.41% on the BUSI dataset and 86.62% on Dataset B (UDIAT), outperforming several existing segmentation approaches in both dice-score coefficient and Intersection-over-Union (IoU) metrics. Conclusions: The integration of efficient transformer-based global feature extraction, attention-enhanced feature fusion, and state-space-driven decoding enables LTM-UNet to effectively capture both structural details and contextual information, resulting in superior segmentation performance compared to existing methods. Full article

Whole-body dynamic positron emission tomography/computed tomography (WBD-PET/CT) has transformed medical imaging, enabling the fusion between (i) detailed anatomical maps of the human body and (ii) quantitative multi-parametric functional maps of specific biochemical and physiological processes across the human body beyond the semi-quantitative limitations of static PET/CT imaging. Latest developments in systems hardware, particularly with the introduction of long-axial-field-of-view (LAFOV) and Time-of-Flight (TOF) PET scanners and low-dose CT scanners, and in data analysis, primarily with direct parametric PET image reconstruction and Artificial Intelligence, offer unprecedented opportunities towards the wide clinical adoption of the superior quantitative accuracy and precision of WBD-PET/CT imaging overcoming current challenges, such as data acquisition complexity and long scan durations. This review aims to summarize the latest developments, current challenges, and emerging opportunities in WBD-PET/CT, emphasizing its potential to broaden the diagnostic and theranostic role of PET/CT in clinical practice. Full article

Background/Objectives: The early identification of skin cancer by standard RGB dermoscopy is a clinical difficulty because of the complex visual differences between impacted lesions and healthy tissue. Methods: For the biomedical challenge, a novel approach to signal processing and image reconstruction is introduced in this study, called the spectrum-aided visual enhancer (SAVE). The proposed SAVE mechanism aims at reconstructing the diagnostically relevant spectral information from the conventional RGB dermoscopic images using the principles of hyperspectral imaging (HSI) and band selection (BS). After quality control and pre-processing, the images in the ISIC2019 dataset were selected, with 865 images that contain basal cell carcinoma (BCC), seborrheic keratosis (SK), and actinic keratosis (AK) lesions. To reduce data leakage, the dataset was split into training, validation, and testing subsets of 70%, 20%, and 10%, respectively. Five supervised deep learning object detection models were trained and tested on the conventional RGB image dataset and on the SAVE-enhanced dataset. Five supervised deep learning object detection models, namely, YOLOv8, YOLOv10, YOLOv11, SSDLite, and SSD, were trained and tested on the conventional RGB image dataset and the SAVE-enhanced dataset. Additional repeated experimental assessments and statistical comparisons were also carried out to evaluate the improvement in performance. Results: The experimental results showed that the SAVE-based pre-processing always yielded better performance in terms of lesion detection than conventional RGB image processing. The SAVE framework for SSD was evaluated and compared with all other evaluated models and was found to be the most successful, with an accuracy of 96%, a precision of 97%, a recall of 96%, and an F1 score of 96%. Conclusions: The results indicate that the proposed SAVE framework could be a promising RGB-compatible spectral enhancement technique for boosting skin cancer detection and computer-aided dermatologic analysis with the aid of AI. Full article