To assess the utility of dual-type deep learning (DL)-based image reconstruction with DL-based image denoising and super-resolution processing by comparing images reconstructed with the conventional method in head and neck fat-suppressed (Fs) T2-weighted imaging (T2WI). We retrospectively analyzed the cases of 43 patients who underwent head/neck Fs-T2WI for the assessment of their head and neck lesions. All patients underwent two sets of Fs-T2WI scans with conventional- and DL-based reconstruction. The Fs-T2WI with DL-based reconstruction was acquired based on a 30% reduction of its spatial resolution in both the x- and y-axes with a shortened scan time. Qualitative and quantitative assessments were performed with both the conventional method- and DL-based reconstructions. For the qualitative assessment, we visually evaluated the overall image quality, visibility of anatomical structures, degree of artifact(s), lesion conspicuity, and lesion edge sharpness based on five-point grading. In the quantitative assessment, we measured the signal-to-noise ratio (SNR) of the lesion and the contrast-to-noise ratio (CNR) between the lesion and the adjacent or nearest muscle. In the qualitative analysis, significant differences were observed between the Fs-T2WI with the conventional- and DL-based reconstruction in all of the evaluation items except the degree of the artifact(s) (p < 0.001). In the quantitative analysis, significant differences were observed in the SNR between the Fs-T2WI with conventional- (21.4 ± 14.7) and DL-based reconstructions (26.2 ± 13.5) (p < 0.001). In the CNR assessment, the CNR between the lesion and adjacent or nearest muscle in the DL-based Fs-T2WI (16.8 ± 11.6) was significantly higher than that in the conventional Fs-T2WI (14.2 ± 12.9) (p < 0.001). Dual-type DL-based image reconstruction by an effective denoising and super-resolution process successfully provided high image quality in head and neck Fs-T2WI with a shortened scan time compared to the conventional imaging method.

Attention Mechanism (AM) selectively focuses on essential information for imaging tasks and captures relationships between regions from distant pixel neighborhoods to compute feature representations. Accelerated magnetic resonance image (MRI) reconstruction can benefit from AM, as the imaging process involves acquiring Fourier domain measurements that influence the image representation in a non-local manner. However, AM-based models are more adept at capturing low-frequency information and have limited capacity in constructing high-frequency representations, restricting the models to smooth reconstruction. Secondly, AM-based models need mode-specific retraining for multimodal MRI data as their knowledge is restricted to local contextual variations within modes that might be inadequate to capture the diverse transferable features across heterogeneous data domains. To address these challenges, we propose a neuromodulation-based discriminative multi-spectral AM for scalable MRI reconstruction, that can (i) propagate the context-aware high-frequency details for high-quality image reconstruction, and (ii) capture features reusable to deviated unseen domains in multimodal MRI, to offer high practical value for the healthcare industry and researchers. The proposed network consists of a spectral filtering convolutional neural network to capture mode-specific transferable features to generalize to deviated MRI data domains and a dynamic high-pass kernel generation transformer that focuses on high-frequency details for improved reconstruction. We have evaluated our model on various aspects, such as comparative studies in supervised and self-supervised learning, diffusion model-based training, closed-set and open-set generalization under heterogeneous MRI data, and interpretation-based analysis. Our results show that the proposed method offers scalable and high-quality reconstruction with best improvement margins of ∼1 dB in PSNR and ∼0.01 in SSIM under unseen scenarios. Our code is available at https://github.com/sriprabhar/SHFormer.

Respiratory motion during PET acquisition may produce lesion blurring. Ultra-fast 20-second breath-hold (U2BH) PET reduces respiratory motion artifacts, but the shortened scanning time increases statistical noise and may affect diagnostic quality. This study aims to denoise the U2BH PET images using a deep learning (DL)-based method. The study was conducted on two datasets collected from five scanners where the first dataset included 1272 retrospectively collected full-time PET data while the second dataset contained 46 prospectively collected U2BH and the corresponding full-time PET/CT images. A robust and data-efficient DL method called mask vision transformer (Mask-ViT) was proposed which, after fine-tuned on a limited number of training data from a target scanner, was directly applied to unseen testing data from new scanners. The performance of Mask-ViT was compared with state-of-the-art DL methods including U-Net and C-Gan taking the full-time PET images as the reference. Statistical analysis on image quality metrics were carried out with Wilcoxon signed-rank test. For clinical evaluation, two readers scored image quality on a 5-point scale (5 = excellent) and provided a binary assessment for diagnostic quality evaluation. The U2BH PET images denoised by Mask-ViT showed statistically significant improvement over U-Net and C-Gan on image quality metrics (p < 0.05). For clinical evaluation, Mask-ViT exhibited a lesion detection accuracy of 91.3%, 90.4% and 91.7%, when it was evaluated on three different scanners. Mask-ViT can effectively enhance the quality of the U2BH PET images in a data-efficient generalization setup. The denoised images meet clinical diagnostic requirements of lesion detectability.

Myocardial computed tomography (CT) late enhancement (LE) allows assessment of myocardial scarring. Super-resolution deep learning image reconstruction (SR-DLR) trained on data acquired from ultra-high-resolution CT may improve image quality for CT-LE. Therefore, this study investigated image noise and image quality with SR-DLR compared with conventional DLR (C-DLR) and hybrid iterative reconstruction (hybrid IR). We retrospectively analyzed 30 patients who underwent CT-LE using 320-row CT. The CT protocol comprised stress dynamic CT perfusion, coronary CT angiography, and CT-LE. CT-LE images were reconstructed using three different algorithms: SR-DLR, C-DLR, and hybrid IR. Image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and qualitative image quality scores are in terms of noise reduction, sharpness, visibility of scar and myocardial boarder, and overall image quality. Inter-observer differences in myocardial scar sizing in CT-LE by the three algorithms were also compared. SR-DLR significantly decreased image noise by 35% compared to C-DLR (median 6.2 HU, interquartile range [IQR] 5.6-7.2 HU vs 9.6 HU, IQR 8.4-10.7 HU; p < 0.001) and by 37% compared to hybrid IR (9.8 HU, IQR 8.5-12.0 HU; p < 0.001). SNR and CNR of CT-LE reconstructed using SR-DLR were significantly higher than with C-DLR (both p < 0.001) and hybrid IR (both p < 0.05). All qualitative image quality scores were higher with SR-DLR than those with C-DLR and hybrid IR (all p < 0.001). The inter-observer differences in scar sizing were reduced with SR-DLR and C-DLR compared with hybrid IR (both p = 0.02). SR-DLR reduces image noise and improves image quality of myocardial CT-LE compared with C-DLR and hybrid IR techniques and improves inter-observer reproducibility of scar sizing compared to hybrid IR. The SR-DLR approach has the potential to improve the assessment of myocardial scar by CT late enhancement.

[Objective] In single-photon emission computed tomography (SPECT) image reconstruction, limited-angle conditions lead to a loss of frequency components, which distort the reconstructed tomographic image along directions corresponding to the non-collected projection angle range. Although conventional iterative image reconstruction methods have been used to improve the reconstructed images in limited-angle conditions, the image quality is still unsuitable for clinical use. We propose a limited-angle SPECT image reconstruction method that uses an end-to-end deep image prior (DIP) framework to improve reconstructed image quality.&#xD;[Approach] The proposed limited-angle SPECT image reconstruction is an end-to-end DIP framework which incorporates a forward projection model into the loss function to optimise the neural network. By also incorporating a binary mask that indicates whether each data point in the measured projection data has been collected, the proposed method restores the non-collected projection data and reconstructs a less distorted image.&#xD;[Main results] The proposed method was evaluated using 20 numerical phantoms and clinical patient data. In numerical simulations, the proposed method outperformed existing back-projection-based methods in terms of peak signal-to-noise ratio and structural similarity index measure. We analysed the reconstructed tomographic images in the frequency domain using an object-specific modulation transfer function, in simulations and on clinical patient data, to evaluate the response of the reconstruction method to different frequencies of the object. The proposed method significantly improved the response to almost all spatial frequencies, even in the non-collected projection angle range. The results demonstrate that the proposed method reconstructs a less distorted tomographic image.&#xD;[Significance] The proposed end-to-end DIP-based reconstruction method restores lost frequency components and mitigates image distortion under limited-angle conditions by incorporating a binary mask into the loss function.

Motion artifacts are common for knee MRI, which usually lead to rescanning. Effective removal of motion artifacts would be clinically useful. To construct an effective deep learning-based model to remove motion artifacts for knee MRI using real-world data. Retrospective. Model construction: 90 consecutive patients (1997 2D slices) who had knee MRI images with motion artifacts paired with immediately rescanned images without artifacts served as ground truth. Internal test dataset: 25 patients (795 slices) from another period; external test dataset: 39 patients (813 slices) from another hospital. 3-T/1.5-T knee MRI with T1-weighted imaging, T2-weighted imaging, and proton-weighted imaging. A deep learning-based supervised conditional diffusion model was constructed. Objective metrics (root mean square error [RMSE], peak signal-to-noise ratio [PSNR], structural similarity [SSIM]) and subjective ratings were used for image quality assessment, which were compared with three other algorithms (enhanced super-resolution [ESR], enhanced deep super-resolution, and ESR using a generative adversarial network). Diagnostic performance of the output images was compared with the rescanned images. The Kappa Test, Pearson chi-square test, Fredman's rank-sum test, and the marginal homogeneity test. A p value < 0.05 was considered statistically significant. Subjective ratings showed significant improvements in the output images compared to the input, with no significant difference from the ground truth. The constructed method demonstrated the smallest RMSE (11.44  <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mo>±</mo></mrow> <annotation>$$ \pm $$</annotation></semantics> </math>  5.47 in the validation cohort; 13.95  <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mo>±</mo></mrow> <annotation>$$ \pm $$</annotation></semantics> </math>  4.32 in the external test cohort), the largest PSNR (27.61  <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mo>±</mo></mrow> <annotation>$$ \pm $$</annotation></semantics> </math>  3.20 in the validation cohort; 25.64  <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mo>±</mo></mrow> <annotation>$$ \pm $$</annotation></semantics> </math>  2.67 in the external test cohort) and SSIM (0.97  <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mo>±</mo></mrow> <annotation>$$ \pm $$</annotation></semantics> </math>  0.04 in the validation cohort; 0.94  <math xmlns="http://www.w3.org/1998/Math/MathML"> <semantics><mrow><mo>±</mo></mrow> <annotation>$$ \pm $$</annotation></semantics> </math>  0.04 in the external test cohort) compared to the other three algorithms. The output images achieved comparable diagnostic capability as the ground truth for multiple anatomical structures. The constructed model exhibited feasibility and effectiveness, and outperformed multiple other algorithms for removing motion artifacts in knee MRI. Level 3. Stage 2.

We evaluated a dedicated dose-reduced UHR-CT for head and neck imaging, combined with a novel deep learning reconstruction algorithm to assess its impact on image quality and radiation exposure. Retrospective analysis of ninety-eight consecutive patients examined using a new body weight-adapted protocol. Images were reconstructed using adaptive iterative dose reduction and advanced intelligent Clear-IQ engine with an already established (DL-1) and a newly implemented reconstruction algorithm (DL-2). Additional thirty patients were scanned without body-weight-adapted dose reduction (DL-1-SD). Three readers evaluated subjective image quality regarding image quality and assessment of several anatomic regions. For objective image quality, signal-to-noise ratio and contrast-to-noise ratio were calculated for temporalis and masseteric muscle and the floor of the mouth. Radiation dose was evaluated by comparing the computed tomography dose index (CTDIvol) values. Deep learning-based reconstruction algorithms significantly improved subjective image quality (diagnostic acceptability: DL‑1 vs AIDR OR of 25.16 [6.30;38.85], p < 0.001 and DL‑2 vs AIDR 720.15 [410.14;> 999.99], p < 0.001). Although higher doses (DL-1-SD) resulted in significantly enhanced image quality, DL‑2 demonstrated significant superiority over all other techniques across all defined parameters (p < 0.001). Similar results were demonstrated for objective image quality, e.g. image noise (DL‑1 vs AIDR OR of 19.0 [11.56;31.24], p < 0.001 and DL‑2 vs AIDR > 999.9 [825.81;> 999.99], p < 0.001). Using weight-adapted kV reduction, very low radiation doses could be achieved (CTDIvol: 7.4 ± 4.2 mGy). AI-based reconstruction algorithms in ultra-high resolution head and neck imaging provide excellent image quality while achieving very low radiation exposure.

Low-dose computed tomography (LDCT) reduces radiation exposure but suffers from image artifacts and loss of detail due to quantum and electronic noise, potentially impacting diagnostic accuracy. Transformer combined with diffusion models has been a promising approach for image generation. Nevertheless, existing methods exhibit limitations in preserving finegrained image details. To address this issue, frequency domain-directed diffusion transformer (FD-DiT) is proposed for LDCT reconstruction. FD-DiT centers on a diffusion strategy that progressively introduces noise until the distribution statistically aligns with that of LDCT data, followed by denoising processing. Furthermore, we employ a frequency decoupling technique to concentrate noise primarily in high-frequency domain, thereby facilitating effective capture of essential anatomical structures and fine details. A hybrid denoising network is then utilized to optimize the overall data reconstruction process. To enhance the capability in recognizing high-frequency noise, we incorporate sliding sparse local attention to leverage the sparsity and locality of shallow-layer information, propagating them via skip connections for improving feature representation. Finally, we propose a learnable dynamic fusion strategy for optimal component integration. Experimental results demonstrate that at identical dose levels, LDCT images reconstructed by FD-DiT exhibit superior noise and artifact suppression compared to state-of-the-art methods.

To evaluate the efficacy of thin-slice T₂-weighted imaging (T₂WI) and super-resolution reconstruction (SRR) for preoperative assessment of vascular invasion in pancreatic ductal adenocarcinoma (PDAC). Ninety-five PDACs with preoperative MRI were retrospectively enrolled as a training set, with non-reconstructed T₂WI (NRT₂) in different slice thicknesses (NRT₂-3, 3 mm; NRT₂-5, ≥ 5 mm). A prospective test set was collected with NRT₂-5 (n = 125) only. A deep-learning network was employed to generate reconstructed super-resolution T₂WI (SRT₂) in different slice thicknesses (SRT₂-3, 3 mm; SRT₂-5, ≥ 5 mm). Image quality was assessed, including the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and signal-intensity ratio (SIR_t/p, tumor/pancreas; SIR_t/b, tumor/background). Diagnostic efficacy for vascular invasion was evaluated using the area under the curve (AUC) and compared across different slice thicknesses before and after reconstruction. SRT₂-5 demonstrated higher SNR and SIR_t/p compared to NRT₂-5 (74.18 vs 72.46; 1.42 vs 1.30; p < 0.05). SRT₂-3 showed increased SIR_t/p and SIR_t/b over NRT₂-3 (1.35 vs 1.31; 2.73 vs 2.58; p < 0.05). SRT₂-5 showed higher CNR, SIR_t/p and SIR_t/b than NRT₂-3 (p < 0.05). NRT₂-3 outperformed NRT₂-5 in evaluating venous invasion (AUC: 0.732 vs 0.597, p = 0.021). SRR improved venous assessment (AUC: NRT₂-3, 0.927 vs 0.732; NRT₂-5, 0.823 vs 0.597; p < 0.05), and SRT₂-5 exhibits comparable efficacy to NRT₂-3 in venous assessment (AUC: 0.823 vs 0.732, p = 0.162). Thin-slice T₂WI and SRR effectively improve the image quality and diagnostic efficacy for assessing venous invasion in PDAC. Thick-slice T₂WI with SRR is a potential alternative to thin-slice T₂WI. Both thin-slice T₂-WI and SRR effectively improve image quality and diagnostic performance, providing valuable options for optimizing preoperative vascular assessment in PDAC. Non-invasive and accurate assessment of vascular invasion supports treatment planning and avoids futile surgery. Vascular invasion evaluation is critical for the surgical eligibility of PDAC. SRR improved image quality and vascular assessment in T₂WI. Utilizing thin-slice T₂WI and SRR aids in clinical decision making for PDAC.

Magnetic Resonance Imaging (MRI) reconstruction is essential in medical diagnostics. As the latest generative models, diffusion models (DMs) have struggled to produce high-fidelity images due to their stochastic nature in image domains. Latent diffusion models (LDMs) yield both compact and detailed prior knowledge in latent domains, which could effectively guide the model towards more effective learning of the original data distribution. Inspired by this, we propose Multi-domain Diffusion Prior Guidance (MDPG) provided by pre-trained LDMs to enhance data consistency in MRI reconstruction tasks. Specifically, we first construct a Visual-Mamba-based backbone, which enables efficient encoding and reconstruction of under-sampled images. Then pre-trained LDMs are integrated to provide conditional priors in both latent and image domains. A novel Latent Guided Attention (LGA) is proposed for efficient fusion in multi-level latent domains. Simultaneously, to effectively utilize a prior in both the k-space and image domain, under-sampled images are fused with generated full-sampled images by the Dual-domain Fusion Branch (DFB) for self-adaption guidance. Lastly, to further enhance the data consistency, we propose a k-space regularization strategy based on the non-auto-calibration signal (NACS) set. Extensive experiments on two public MRI datasets fully demonstrate the effectiveness of the proposed methodology. The code is available at https://github.com/Zolento/MDPG.