Denoising Diffusion Probabilistic Models (DDPM) have emerged as a promising generative framework for sample synthesis, yet their limitations in detail preservation hinder practical applications in computed tomography (CT) image reconstruction. To address these technical constraints and enhance reconstruction quality from compromised CT projection data, this study proposes the Projection Hybrid Inverse Reconstruction Framework (PHIRF) - a novel paradigm integrating conventional reconstruction methodologies with DDPM architecture. The framework implements a dual-phase approach: Initially, conventional CT reconstruction algorithms (e.g., Filtered back projection(FBP), Algebraic Reconstruction Technique(ART), Maximum-Likelihood Expectation Maximization (ML-EM)) are employed to generate preliminary reconstructions from incomplete projections, establishing low-dimensional feature representations. These features are subsequently parameterized and embedded as conditional constraints in the reverse diffusion process of DDPM, thereby guiding the generative model to synthesize enhanced tomographic images with improved structural fidelity. Comprehensive evaluations were conducted on three representative ill-posed projection scenarios: limited-angle projections, sparse-view acquisitions, and low-dose measurements. Experimental results demonstrate that PHIRF achieves state-of-the-art performance across all compromised data conditions, particularly in preserving fine anatomical details and suppressing reconstruction artifacts. Quantitative metrics and visual assessments confirm the framework's consistent superiority over existing deep learning-based reconstruction approaches, substantiating its adaptability to diverse projection degradation patterns. This hybrid architecture establishes a new paradigm for combining physical prior knowledge with data-driven generative models in medical image reconstruction tasks.

Electrocardiogram (ECG) is crucial for synchronizing cardiovascular magnetic resonance imaging (CMRI) acquisition with the cardiac cycle and for continuous heart rate monitoring during prolonged scans. However, conventional electrode-based ECG systems in clinical MRI environments suffer from tedious setup, magnetohydrodynamic (MHD) waveform distortion, skin burn risks, and patient discomfort. This study proposes a contactless ECG measurement method in MRI to address these challenges. We integrated Beat Pilot Tone (BPT)-a contactless, high motion sensitivity, and easily integrable RF motion sensing modality-into CMRI to capture cardiac motion without direct patient contact. A deep neural network was trained to map the BPT-derived cardiac mechanical motion signals to corresponding ECG waveforms. The reconstructed ECG was evaluated against simultaneously acquired ground truth ECG through multiple metrics: Pearson correlation coefficient, relative root mean square error (RRMSE), cardiac trigger timing accuracy, and heart rate estimation error. Additionally, we performed MRI retrospective binning reconstruction using reconstructed ECG reference and evaluated image quality under both standard clinical conditions and challenging scenarios involving arrhythmias and subject motion. To examine scalability of our approach across field strength, the model pretrained on 1.5T data was applied to 3T BPT cardiac acquisitions. In optimal acquisition scenarios, the reconstructed ECG achieved a median Pearson correlation of 89% relative to the ground truth, while cardiac triggering accuracy reached 94%, and heart rate estimation error remained below 1 bpm. The quality of the reconstructed images was comparable to that of ground truth synchronization. The method exhibited a degree of adaptability to irregular heart rate patterns and subject motion, and scaled effectively across MRI systems operating at different field strengths. The proposed contactless ECG measurement method has the potential to streamline CMRI workflows, improve patient safety and comfort, mitigate MHD distortion challenges and find a robust clinical application.

This study aimed to validate the utility of commercially available vendor-neutral deep learning (DL) image enhancement software for improving the image quality of multiparametric MRI for gliomas in a multinational setting. A total of 294 patients from three institutions (NYU, Severance, and SNUH) who underwent glioma MRI protocols were included in this retrospective study. DL image enhancement was performed on T2-weighted (T2W), T2 FLAIR, and postcontrast T1-weighted (T1W) imaging using commercially available DL image enhancement software. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated for both conventional and DL-enhanced images. Three neuroradiologists, one from each institution, independently evaluated the following image quality parameters in both images using a 5-point scale: overall image quality, noise, gray-white matter differentiation, truncation artifact, motion artifact, pulsation artifact, and main lesion conspicuity. The quantitative and qualitative image parameters were compared between conventional and DL-enhanced images. Compared with conventional images, DL-enhanced images showed significantly higher SNRs and CNRs in T2W, T2 FLAIR, and postcontrast T1W imaging (all P < 0.001). The average scores of radiologist assessments in overall image quality, noise, gray-white matter differentiation, and main lesion conspicuity were significantly higher for DL-enhanced images than conventional images in T2W, T2 FLAIR, and postcontrast T1W imaging (all P < 0.001). Regarding artifacts, truncation artifacts decreased (all P < 0.001), while pre-existing motion and pulsation artifacts were not further exaggerated in most structural MRI sequences. In conclusion, DL image enhancement using commercially available vendor-neutral software improved image quality and reduced truncation artifacts in multiparametric glioma MRI.

Magnetic resonance imaging (MRI) requires long acquisition times, raising costs, reducing accessibility, and making scans more susceptible to motion artifacts. Diffusion probabilistic models that learn data-driven priors can potentially assist in reducing acquisition time. However, they typically require large training datasets that can be prohibitively expensive to collect. Patch-based diffusion models have shown promise in learning effective data-driven priors over small real-valued datasets, but have not yet demonstrated clinical value in MRI. We extend the Patch-based Diffusion Inverse Solver (PaDIS) to complex-valued, multi-coil MRI reconstruction, and compare it against a state-of-the-art whole-image diffusion baseline (FastMRI-EDM) for 7x undersampled MRI reconstruction on the FastMRI brain dataset. We show that PaDIS-MRI models trained on small datasets of as few as 25 k-space images outperform FastMRI-EDM on image quality metrics (PSNR, SSIM, NRMSE), pixel-level uncertainty, cross-contrast generalization, and robustness to severe k-space undersampling. In a blinded study with three radiologists, PaDIS-MRI reconstructions were chosen as diagnostically superior in 91.7% of cases, compared to baselines (i) FastMRI-EDM and (ii) classical convex reconstruction with wavelet sparsity. These findings highlight the potential of patch-based diffusion priors for high-fidelity MRI reconstruction in data-scarce clinical settings where diagnostic confidence matters.

To evaluate the diagnostic interchangeability, image quality, and scan time of deep learning (DL)-reconstructed magnetic resonance imaging (MRI) compared with conventional MRI for the temporomandibular joint (TMJ). Patients with suspected TMJ disorder underwent sagittal proton density-weighted (PDW) and T2-weighted fat-suppressed (T2W FS) MRI using both conventional and DL reconstruction protocols in a single session. Three oral radiologists independently assessed disc shape, disc position, and joint effusion. Diagnostic interchangeability for these findings was evaluated by comparing interobserver agreement, with equivalence defined as a 95% confidence interval (CI) within ±5%. Qualitative image quality (sharpness, noise, artifacts, overall) was rated on a 5-point scale. Quantitative image quality was assessed by measuring the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in the condyle, disc, and background air. Image quality scores were compared using the Wilcoxon signed-rank test, and SNR/CNR using paired t-tests. Scan times were directly compared. A total of 176 TMJs from 88 patients (mean age, 37 ± 16 years; 43 men) were analyzed. DL-reconstructed MRI demonstrated diagnostic equivalence to conventional MRI for disc shape, position, and effusion (equivalence indices < 3%; 95% CIs within ±5%). DL reconstruction significantly reduced noise in PDW and T2W FS sequences (p < 0.05) while maintaining sharpness and artifact levels. SNR and CNR were significantly improved (p < 0.05), except for disc SNR in PDW (p = 0.189). Scan time was reduced by 49.2%. DL-reconstructed TMJ MRI is diagnostically interchangeable with conventional MRI, offering improved image quality with a shorter scan time. Question Long MRI scan times in patients with temporomandibular disorders can increase pain and motion-related artifacts, often compromising image quality in diagnostic settings. Findings DL reconstruction is diagnostically interchangeable with conventional MRI for assessing disc shape, disc position, and effusion, while improving image quality and reducing scan time. Clinical relevance DL reconstruction enables faster and more tolerable TMJ MRI workflows without compromising diagnostic accuracy, facilitating broader adoption in clinical settings where long scan times and motion artifacts often limit diagnostic efficiency.

This paper examines the current challenges in computed tomography (CT), with a critical exploration of existing methodologies from a mathematical perspective. Specifically, it aims to identify research directions to enhance image quality in low-dose, cost-effective cone beam CT (CBCT) systems, which have recently gained widespread use in general dental clinics. Dental CBCT offers a substantial cost advantage over standard medical CT, making it affordable for local dental practices; however, this affordability brings significant challenges related to image quality degradation, further complicated by the presence of metallic implants, which are particularly common in older patients. This paper investigates metal-induced artefacts stemming from mismatches in the forward model used in conventional reconstruction methods and explains an alternative approach that bypasses the traditional Radon transform model. Additionally, it examines both the potential and limitations of deep learning-based methods in tackling these challenges, offering insights into their effectiveness in improving image quality in low-dose dental CBCT.This article is part of the theme issue 'Frontiers of applied inverse problems in science and engineering'.

Microwave Imaging (MWI) is a promising modality due to its noninvasive nature and lower cost compared to other medical imaging techniques. These characteristics make it a potential alternative to traditional imaging techniques. It has various medical applications, particularly exploited in breast and brain imaging. Machine Learning (ML) has also been increasingly used for medical applications. This paper provides a scoping review of the role of ML in MWI, focusing on two key areas: image reconstruction and classification. The reconstruction section discusses various ML algorithms used to enhance image quality and computational efficiency, highlighting methods such as Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). The classification section delves into the application of ML for distinguishing between different tissue types, including applications in breast cancer detection and neurological disorder classification. By analyzing the latest studies and methodologies, this review aims review to the current state of ML-enhanced MWI and sheds light on its potential for clinical applications.

Undersampled magnetic resonance imaging (MRI) reconstruction reduces scanning time while preserving image quality, improving patient comfort and clinical efficiency. Current parallel reconstruction strategies leverage k-space and image domains information to improve feature extraction and accuracy. However, most existing dual-domain reconstruction methods rely on simplistic fusion strategies that ignore spatial feature variations, suffer from constrained receptive fields limiting complex anatomical structure modeling, and employ static frameworks lacking adaptability to the heterogeneous artifact profiles induced by diverse undersampling patterns. This paper introduces a Spatial Adaptive Fusion Network (SAFNet) for dual-domain undersampled MRI reconstruction. SAFNet comprises two parallel reconstruction branches. A Dynamic Perception Initialization Module (DPIM) in each encoder enriches receptive fields for multi-scale information capture. Spatial Adaptive Fusion Modules (SAFM) within each branch's decoder achieve pixel-wise adaptive fusion of dual-domain features and incorporate original magnitude information, ensuring faithful preservation of intensity details. The Weighted Shortcut Module (WSM) enables dynamic strategy adaptation by scaling shortcut connections to adaptively balance residual learning and direct reconstruction. Experiments demonstrate SAFNet's superior accuracy and adaptability over state-of-the-art methods, offering valuable insights for image reconstruction and multimodal information fusion.

Diffusion models have found extensive use in solving numerous inverse problems. Such diffusion inverse problem solvers aim to sample from the posterior distribution of data given the measurements, using a combination of the unconditional score function and an approximation of the posterior related to the forward process. Recently, consistency models (CMs) have been proposed to directly predict the final output from any point on the diffusion ODE trajectory, enabling high-quality sampling in just a few NFEs. CMs have also been utilized for inverse problems, but existing CM-based solvers either require additional task-specific training or utilize data fidelity operations with slow convergence, not amenable to large-scale problems. In this work, we reinterpret CMs as proximal operators of a prior, enabling their integration into plug-and-play (PnP) frameworks. We propose a solver based on PnP-ADMM, which enables us to leverage the fast convergence of conjugate gradient method. We further accelerate this with noise injection and momentum, dubbed PnP-CM, and show it maintains the convergence properties of the baseline PnP-ADMM. We evaluate our approach on a variety of inverse problems, including inpainting, super-resolution, Gaussian deblurring, and magnetic resonance imaging (MRI) reconstruction. To the best of our knowledge, this is the first CM trained for MRI datasets. Our results show that PnP-CM achieves high-quality reconstructions in as few as 4 NFEs, and can produce meaningful results in 2 steps, highlighting its effectiveness in real-world inverse problems while outperforming comparable CM-based approaches.

To quantify radiation dose reduction in radiotherapy treatment-planning CT (RTCT) using a deep learning-based reconstruction (DLR; AiCE) algorithm compared with adaptive iterative dose reduction (IR; AIDR). To evaluate its potential to inform RTCT-specific diagnostic reference levels (DRLs). In this single-institution retrospective study, 4-part RTCT scans (head, head and neck, lung, and pelvis) were acquired on a large-bore CT. Scans reconstructed with IR (n = 820) and DLR (n = 854) were compared. The 75th-percentile CTDI_vol and DLP (CTDI_IR, DLP_IR vs. CTDI_DLR, DLP_DLR) were determined per site. Dose reduction rates were calculated as (CTDI_DLR - CTDI_IR)/CTDI_IR × 100% and similarly for DLP. Statistical significance was assessed by the Mann-Whitney U-test. DLR yielded CTDI_vol reductions of 30.4-75.4% and DLP reductions of 23.1-73.5% across sites (p < 0.001), with the greatest reductions in head and neck RTCT (CTDI_vol: 75.4%; DLP: 73.5%). Variability also narrowed. Compared with published national DRLs, DLR achieved 34.8 mGy and 18.8 mGy lower CTDI_vol for head and neck versus UK-DRLs and Japanese multi-institutional data, respectively. DLR substantially lowers RTCT dose indices, providing quantitative data to guide RTCT-specific DRLs and optimize clinical workflows.