High-Intensity Focused Ultrasound (HIFU) is a non-invasive therapeutic technique widely used for treating various diseases. However, the success and safety of HIFU treatments depend on real-time monitoring, which is often hindered by interference when using ultrasound to guide HIFU treatment. To address these challenges, we developed HIFU-ILDiff, a novel deep learning-based approach leveraging latent diffusion models to suppress HIFU-induced interference in ultrasound images. The HIFU-ILDiff model employs a Vector Quantized Variational Autoencoder (VQ-VAE) to encode noisy ultrasound images into a lower-dimensional latent space, followed by a latent diffusion model that iteratively removes interference. The denoised latent vectors are then decoded to reconstruct high-resolution, interference-free ultrasound images. We constructed a comprehensive dataset comprising 18,872 image pairs from in vitro phantoms, ex vivo tissues, and in vivo animal data across multiple imaging modalities and HIFU power levels to train and evaluate the model. Experimental results demonstrate that HIFU-ILDiff significantly outperforms the commonly used Notch Filter method, achieving a Structural Similarity Index (SSIM) of 0.796 and Peak Signal-to-Noise Ratio (PSNR) of 23.780 compared to SSIM of 0.443 and PSNR of 14.420 for the Notch Filter under in vitro scenarios. Additionally, HIFU-ILDiff achieves real-time processing at 15 frames per second, markedly faster than the Notch Filter's 5 seconds per frame. These findings indicate that HIFU-ILDiff is able to denoise HIFU interference in ultrasound guiding images for real-time monitoring during HIFU therapy, which will greatly improve the treatment precision in current clinical applications.

LAFOV PET/CT has the potential to unlock new applications such as ultra-low dose PET/CT imaging, multiplexed imaging, for biomarker development and for faster AI-driven reconstruction, but further work is required before these can be deployed in clinical routine. LAFOV PET/CT has unrivalled sensitivity but has a spatial resolution of an equivalent scanner with a shorter axial field of view. AI approaches are increasingly explored as potential avenues to enhance image resolution.

Deep learning reconstruction (DLR) offers a variety of advantages over the current standard iterative reconstruction techniques, including decreased image noise without changes in noise texture and less susceptibility to spatial resolution limitations at low dose. These advances may allow for more aggressive dose reduction in CT imaging while maintaining image quality and diagnostic accuracy. However, performance of DLRs is impacted by the type of framework and training data used. In addition, the patient size and clinical task being performed may impact the amount of dose reduction that can be reasonably employed. Multiple DLRs are currently FDA approved with a growing body of literature evaluating performance throughout this body; however, continued work is warranted to evaluate a variety of clinical scenarios to fully explore the evolving potential of DLR. Depending on the type and strength of DLR applied, blurring and occasionally other artifacts may be introduced. DLRs also show promise in artifact reduction, particularly metal artifact reduction. This commentary focuses primarily on current DLR data for abdominal applications, current challenges, and future areas of potential exploration.

The emergence of new medications for fatty liver conditions has increased the need for reliable and widely available assessment of MRI proton density fat fraction (MRI-PDFF). Whereas low-field MRI presents a promising solution, its utilization is challenging due to the low SNR. This work aims to enhance SNR and enable precise PDFF quantification at low-field MRI using a novel locally low-rank deep learning-based (LLR-DL) reconstruction. LLR-DL alternates between regularized SENSE and a neural network (U-Net) throughout several iterations, operating on complex-valued data. The network processes the spectral projection onto singular value bases, which are computed on local patches across the echoes dimension. The output of the network is recast into the basis of the original echoes and used as a prior for the following iteration. The final echoes are processed by a multi-echo Dixon algorithm. Two different protocols were proposed for imaging at 0.55 T. An iron-and-fat phantom and 10 volunteers were scanned on both 0.55 and 1.5 T systems. Linear regression, t-statistics, and Bland-Altman analyses were conducted. LLR-DL achieved significantly improved image quality compared to the conventional reconstruction technique, with a 32.7% increase in peak SNR and a 25% improvement in structural similarity index. PDFF repeatability was 2.33% in phantoms (0% to 100%) and 0.79% in vivo (3% to 18%), with narrow cross-field strength limits of agreement below 1.67% in phantoms and 1.75% in vivo. An LLR-DL reconstruction was developed and investigated to enable precise PDFF quantification at 0.55 T and improve consistency with 1.5 T results.

The purpose of this work was to develop and evaluate a novel method that leverages neural networks and physical modeling for 3D motion correction at different levels of corruption. The novel method ("UNet+JE") combines an existing neural network ("UNet_mag") with a physics-informed algorithm for jointly estimating motion parameters and the motion-compensated image ("JE"). UNet_mag and UNet+JE were trained on two training datasets separately with different distributions of motion corruption severity and compared to JE as a benchmark. All five resulting methods were tested on T₁w 3D MPRAGE scans of healthy participants with simulated (n = 40) and in vivo (n = 10) motion corruption ranging from mild to severe motion. UNet+JE provided better motion correction than UNet_mag ( <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mi>p</mi> <mo><</mo> <msup><mn>10</mn> <mrow><mo>-</mo> <mn>2</mn></mrow> </msup> </mrow> <annotation>$$ p<{10}^{-2} $$</annotation></semantics> </math> for all metrics for both simulated and in vivo data), under both training datasets. UNet_mag exhibited residual image artifacts and blurring, as well as greater susceptibility to data distribution shifts than UNet+JE. UNet+JE and JE did not significantly differ in image correction quality ( <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mi>p</mi> <mo>></mo> <mn>0.05</mn></mrow> <annotation>$$ p>0.05 $$</annotation></semantics> </math> for all metrics), even under strong distribution shifts for UNet+JE. However, UNet+JE reduced runtimes by a median reduction factor of between 2.00 to 3.80 as well as 4.05 for the simulation and in vivo studies, respectively. UNet+JE benefitted from the robustness of joint estimation and the fast image improvement provided by the neural network, enabling the method to provide high quality 3D image correction under a wide range of motion corruption within shorter runtimes.

Accelerated Cardiovascular Magnetic Resonance (CMR) image reconstruction remains a critical challenge due to the trade-off between scan time and image quality, particularly when generalizing across diverse acquisition settings. We propose GENRE-CMR, a generative adversarial network (GAN)-based architecture employing a residual deep unrolled reconstruction framework to enhance reconstruction fidelity and generalization. The architecture unrolls iterative optimization into a cascade of convolutional subnetworks, enriched with residual connections to enable progressive feature propagation from shallow to deeper stages. To further improve performance, we integrate two loss functions: (1) an Edge-Aware Region (EAR) loss, which guides the network to focus on structurally informative regions and helps prevent common reconstruction blurriness; and (2) a Statistical Distribution Alignment (SDA) loss, which regularizes the feature space across diverse data distributions via a symmetric KL divergence formulation. Extensive experiments confirm that GENRE-CMR surpasses state-of-the-art methods on training and unseen data, achieving 0.9552 SSIM and 38.90 dB PSNR on unseen distributions across various acceleration factors and sampling trajectories. Ablation studies confirm the contribution of each proposed component to reconstruction quality and generalization. Our framework presents a unified and robust solution for high-quality CMR reconstruction, paving the way for clinically adaptable deployment across heterogeneous acquisition protocols.

The labyrinth is a complex anatomical structure in the temporal bone. However, high-resolution imaging of its membranous portion is challenging due to its small size and the limitations of current MRI techniques. Deep Learning Reconstruction (DLR) represents a promising approach to advancing MRI image quality, enabling higher spatial resolution and reduced noise. This study aims to evaluate DLR-High-Resolution 3D-T2 MRI sequences for visualizing the labyrinthine structures, comparing them to conventional 3D-T2 sequences. The goal is to improve spatial resolution without prolonging acquisition times, allowing a more detailed view of the labyrinthine microanatomy. High-resolution heavy T2-weighted TSE SPACE images were acquired in patients using 3D-T2 and DLR-3D-T2. Two radiologists rated structure visibility on a four-point qualitative scale for the spiral lamina, scala tympani, scala vestibuli, scala media, utricle, saccule, utricular and saccular maculae, membranous semicircular ducts, and ampullary nerves. Ex vivo 9.4T MRI served as an anatomical reference. DLR-3D-T2 significantly improved the visibility of several inner ear structures. The utricle and utricular macula were systematically visualized, achieving grades ≥3 in 95% of cases (p < 0.001), while the saccule remained challenging to assess, with grades ≥3 in only 10% of cases. The cochlear spiral lamina and scala tympani were better delineated in the first two turns but remained poorly visible in the apical turn. Semicircular ducts were only partially visualized, with grades ≥3 in 12.5-20% of cases, likely due to resolution limitations relative to their diameter. Ampullary nerves were moderately improved, with grades ≥3 in 52.5-55% of cases, depending on the nerve. While DLR does not yet provide a complete anatomical assessment, it represents a significant step forward in the non-invasive evaluation of inner ear structures. Pending further technical refinements, this approach may help reduce reliance on delayed gadolinium-enhanced techniques for imaging membranous structures. 3D-T2 = Three-dimensional T2-weighted turbo spin-echo; DLR-3D-T2 = improved T2 weighted turbo spinecho sequence incorporating Deep Learning Reconstruction; DLR = Deep Learning Reconstruction.

In this work, we propose a novel framework to enhance the efficiency and accuracy of neural operators through self-composition, offering both theoretical guarantees and practical benefits. Inspired by iterative methods in solving numerical partial differential equations (PDEs), we design a specific neural operator by repeatedly applying a single neural operator block, we progressively deepen the model without explicitly adding new blocks, improving the model's capacity. To train these models efficiently, we introduce an adaptive train-and-unroll approach, where the depth of the neural operator is gradually increased during training. This approach reveals an accuracy scaling law with model depth and offers significant computational savings through our adaptive training strategy. Our architecture achieves state-of-the-art (SOTA) performance on standard benchmarks. We further demonstrate its efficacy on a challenging high-frequency ultrasound computed tomography (USCT) problem, where a multigrid-inspired backbone enables superior performance in resolving complex wave phenomena. The proposed framework provides a computationally tractable, accurate, and scalable solution for large-scale data-driven scientific machine learning applications.

A recent investigation into deep learning-based denoising for early Monte Carlo (MC) Path Tracing in computed tomography (CT) volume visualization yielded promising quantitative outcomes but inconsistent qualitative assessments. This research probes the underlying causes of this incongruity by deploying a web-based SurveyMonkey questionnaire distributed among healthcare professionals. The survey targeted radiologists, residents, orthopedic surgeons, and veterinarians, leveraging the authors' professional networks for dissemination. To evaluate perceptions, the questionnaire featured randomized sections gauging attitudes towards AI-enhanced image and video quality, confidence in reference images, and clinical applicability. Seventy-four participants took part, encompassing a spectrum of experience levels: <1 year (n=11), 1-3 years (n=27), 3-5 years (n=12), and >5 years (n=24). A substantial majority (77%) expressed a preference for AI-enhanced images over traditional MC estimates, a preference influenced by participant experience (adjusted OR 0.81, 95% CI 0.67-0.98, p=0.033). Experience correlates with confidence in AI-generated images (adjusted OR 0.98, 95% CI 0.95-1, p=0.018-0.047) and satisfaction with video previews, both with and without AI (adjusted OR 0.96-0.98, 95% CI 0.92-1, p = 0.033-0.048). Significant monotonic relationships emerged between experience, confidence (σ= 0.25-0.26, p = 0.025-0.029), and satisfaction (σ= 0.23-0.24, p = 0.037-0.046). The findings underscore the potential of AI post-processing to improve the rendering of biomedical volumes, noting enhanced confidence and satisfaction among experienced participants. The study reveals that participants' preferences may not align perfectly with quality metrics such as peak signal-to-noise ratio and structural similarity index, highlighting nuances in evaluating AI's qualitative impact on CT image denoising.

This retrospective study evaluates U-Net-based artifact reduction for dose-reduced sparse-sampling CT (SpSCT) in terms of image quality and diagnostic performance using a reader study and automated detection. CT pulmonary angiograms from 89 patients were used to generate SpSCT data with 16 to 512 views. Twenty patients were reserved for a reader study and test set, the remaining 69 were used to train (53) and validate (16) a dual-frame U-Net for artifact reduction. U-Net post-processed images were assessed for image quality, diagnostic performance, and automated pulmonary embolism (PE) detection using the top-performing network from the 2020 RSNA PE detection challenge. Statistical comparisons were made using two-sided Wilcoxon signed-rank and DeLong two-sided tests. Post-processing with the dual-frame U-Net significantly improved image quality in the internal test set, with a structural similarity index of 0.634/0.378/0.234/0.152 for FBP and 0.894/0.892/0.866/0.778 for U-Net at 128/64/32/16 views, respectively. The reader study showed significantly enhanced image quality (3.15 vs. 3.53 for 256 views, 0.00 vs. 2.52 for 32 views), increased diagnostic confidence (0.00 vs. 2.38 for 32 views), and fewer artifacts across all subsets (P < 0.05). Diagnostic performance, measured by the Sørensen-Dice coefficient, was significantly better for 64- and 32-view images (0.23 vs. 0.44 and 0.00 vs. 0.09, P < 0.05). Automated PE detection was better at fewer views (64 views: 0.77 vs. 0.80, 16 views: 0.59 vs. 0.80), although the differences were not statistically significant. U-Net-based post-processing of SpSCT data significantly enhances image quality and diagnostic performance, supporting substantial dose reduction in CT pulmonary angiography.