This prospective study aimed to assess the feasibility of a half-Fourier single-shot turbo spin echo sequence (HASTE) with deep learning (DL) reconstruction for ultrafast imaging of the bladder with reduced susceptibility to motion artifacts. 50 patients underwent pelvic T2w imaging at 3 Tesla using the following MR sequences in sagittal orientation without antiperistaltic premedication: T2-TSE (time of acquisition [TA]: 2.03-4.00 min), standard HASTE (TA: 0.65-1.10 min), and DL-HASTE (TA: 0.25-0.47 min), with a slice thickness of 3 mm and a varying number of slices (25-45). Three radiologists evaluated the image quality of the three sequences quantitatively and qualitatively. Overall image quality of DL-HASTE (average score: 5) was superior to HASTE and T2-TSE (p < .001). DL-HASTE provided the clearest bladder wall delineation, especially in the apical part of the bladder (p < .001). SNR (36.3 ± 6.3) and CNR (50.3 ± 19.7) were the highest on DL-HASTE, followed by T2-TSE (33.1 ± 6.3 and 44.3 ± 21.0, respectively; p < .05) and HASTE (21.7 ± 5.4 and 35.8 ± 17.5, respectively; p < .01). A limitation of DL-HASTE and HASTE was the susceptibility to urine flow artifact within the bladder, which was absent or only minimal on T2-TSE. Diagnostic confidence in assessment of the bladder was highest with the combination of DL-HASTE and T2-TSE (p < .05). DL-HASTE allows for ultrafast imaging of the bladder with high image quality and is a promising addition to T2-TSE.

High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for precise clinical diagnosis and advancing our understanding of fetal brain development. This necessitates reliable slice-to-volume registration (SVR) for motion correction and super-resolution reconstruction (SRR) techniques. Traditional approaches have their limitations, but deep learning (DL) offers the potential in enhancing SVR and SRR. However, most of DL methods require large-scale external 3D high-resolution (HR) training datasets, which is challenging in clinical fetal MRI. To address this issue, we propose an unsupervised iterative joint SVR and SRR DL framework for 3D isotropic HR volume reconstruction. Specifically, our method conceptualizes SVR as a function that maps a 2D slice and a 3D target volume to a rigid transformation matrix, aligning the slice to the underlying location within the target volume. This function is parameterized by a convolutional neural network, which is trained by minimizing the difference between the volume slicing at the predicted position and the actual input slice. For SRR, a decoding network embedded within a deep image prior framework, coupled with a comprehensive image degradation model, is used to produce the HR volume. The deep image prior framework offers a local consistency prior to guide the reconstruction of HR volumes. By performing a forward degradation model, the HR volume is optimized by minimizing the loss between the predicted slices and the acquired slices. Experiments on both large-magnitude motion-corrupted simulation data and clinical data have shown that our proposed method outperforms current state-of-the-art fetal brain reconstruction methods. The source code is available at https://github.com/DeepBMI/SUFFICIENT.

Transformers have revolutionized medical image restoration, but the quadratic complexity still poses limitations for their application to high-resolution medical images. The recent advent of the Receptance Weighted Key Value (RWKV) model in the natural language processing field has attracted much attention due to its ability to process long sequences efficiently. To leverage its advanced design, we propose Restore-RWKV, the first RWKV-based model for medical image restoration. Since the original RWKV model is designed for 1D sequences, we make two necessary modifications for modeling spatial relations in 2D medical images. First, we present a recurrent WKV (Re-WKV) attention mechanism that captures global dependencies with linear computational complexity. Re-WKV incorporates bidirectional attention as basic for a global 16 receptive field and recurrent attention to effectively model 2D dependencies from various scan directions. Second, we develop an omnidirectional token shift (Omni-Shift) layer that enhances local dependencies by shifting tokens from all directions and across a wide context range. These adaptations make the proposed Restore-RWKV an efficient and effective model for medical image restoration. Even a lightweight variant of Restore-RWKV, with only 1.16 million parameters, achieves comparable or even superior results compared to existing state-of-the-art (SOTA) methods. Extensive experiments demonstrate that the resulting Restore-RWKV achieves SOTA performance across a range of medical image restoration tasks, including PET image synthesis, CT image denoising, MRI image superresolution, and all-in-one medical image restoration. Code is available at: https://github.com/Yaziwel/Restore-RWKV.

The escalating adoption of high-resolution, large-field-of-view imagery amplifies the need for efficient compression methodologies. Conventional techniques frequently fail to preserve critical image details, while data-driven approaches exhibit limited generalizability. Implicit Neural Representations (INRs) present a promising alternative by learning continuous mappings from spatial coordinates to pixel intensities for individual images, thereby storing network weights rather than raw pixels and avoiding the generalization problem. However, INR-based compression of large images faces challenges including slow compression speed and suboptimal compression ratios. To address these limitations, we introduce COLI (Compressor for Large Images), a novel framework leveraging Neural Representations for Videos (NeRV). First, recognizing that INR-based compression constitutes a training process, we accelerate its convergence through a pretraining-finetuning paradigm, mixed-precision training, and reformulation of the sequential loss into a parallelizable objective. Second, capitalizing on INRs' transformation of image storage constraints into weight storage, we implement Hyper-Compression, a novel post-training technique to substantially enhance compression ratios while maintaining minimal output distortion. Evaluations across two medical imaging datasets demonstrate that COLI consistently achieves competitive or superior PSNR and SSIM metrics at significantly reduced bits per pixel (bpp), while accelerating NeRV training by up to 4 times.

Phase-sensitive inversion recovery late gadolinium enhancement (LGE) improves tissue contrast, however it is challenging to combine with a free-breathing acquisition. Deep-learning (DL) algorithms have growing applications in cardiac magnetic resonance imaging (CMR) to improve image quality. We compared a novel combination of a free-breathing single-shot phase-sensitive LGE with respiratory triggering (FB-PS) sequence with DL noise reduction reconstruction algorithm to a conventional segmented phase-sensitive LGE acquired during breath holding (BH-PS). 61 adult subjects (29 male, age 51 ± 15) underwent clinical CMR (1.5 T) with the FB-PS sequence and the conventional BH-PS sequence. DL noise reduction was incorporated into the image reconstruction pipeline. Qualitative metrics included image quality, artifact severity, diagnostic confidence. Quantitative metrics included septal-blood border sharpness, LGE sharpness, blood-myocardium apparent contrast-to-noise ratio (CNR), LGE-myocardium CNR, LGE apparent signal-to-noise ratio (SNR), and LGE burden. The sequences were compared via paired t-tests. 27 subjects had positive LGE. Average time to acquire a slice for FB-PS was 4-12 s versus ~32-38 s for BH-PS (including breath instructions and break time in between breath hold). FB-PS with medium DL noise reduction had better image quality (FB-PS 3.0 ± 0.7 vs. BH-PS 1.5 ± 0.6, p < 0.0001), less artifact (4.8 ± 0.5 vs. 3.4 ± 1.1, p < 0.0001), and higher diagnostic confidence (4.0 ± 0.6 vs. 2.6 ± 0.8, p < 0.0001). Septum sharpness in FB-PS with DL reconstruction versus BH-PS was not significantly different. There was no significant difference in LGE sharpness or LGE burden. FB-PS had superior blood-myocardium CNR (17.2 ± 6.9 vs. 16.4 ± 6.0, p = 0.040), LGE-myocardium CNR (12.1 ± 7.2 vs. 10.4 ± 6.6, p = 0.054), and LGE SNR (59.8 ± 26.8 vs. 31.2 ± 24.1, p < 0.001); these metrics further improved with DL noise reduction. A FB-PS sequence shortens scan time by over 5-fold and reduces motion artifact. Combined with a DL noise reduction algorithm, FB-PS provides better or similar image quality compared to BH-PS. This is a promising solution for patients who cannot hold their breath.

This study aims to evaluate the effectiveness of a deep learning (DL)-enhanced four-fold parallel acquisition technique (P4) in improving prostate MR image quality while optimizing scan efficiency compared to the traditional two-fold parallel acquisition technique (P2). Patients undergoing prostate MRI with DL-enhanced acquisitions were analyzed from January 2024 to July 2024. The participants prospectively received T2-weighted sequences in all imaging planes using both P2 and P4. Three independent readers assessed image quality, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR). Significant differences in contrast and gray-level properties between P2 and P4 were identified through radiomics analysis (p <.05). A total of 51 participants (mean age 69.4 years ± 10.5 years) underwent P2 and P4 imaging. P4 demonstrated higher CNR and SNR values compared to P2 (p <.001). P4 was consistently rated superior to P2, demonstrating enhanced image quality and greater diagnostic precision across all evaluated categories (p <.001). Furthermore, radiomics analysis confirmed that P4 significantly altered structural and textural differentiation in comparison to P2. The P4 protocol reduced T2w scan times by 50.8%, from 11:48 min to 5:48 min (p <.001). In conclusion, P4 imaging enhances diagnostic quality and reduces scan times, improving workflow efficiency, and potentially contributing to a more patient-centered and sustainable radiology practice.

Photoacoustic computed tomography (PACT) is an emerging hybrid imaging modality with potential applications in biomedicine. A major roadblock to the widespread adoption of PACT is the limited number of detectors, which gives rise to spatial aliasing and manifests as streak artifacts in the reconstructed image. A brute-force solution to the problem is to increase the number of detectors, which, however, is often undesirable due to escalated costs. In this study, we present a novel self-supervised learning approach, to overcome this long-standing challenge. We found that small blocks of PACT channel data show similarity at various downsampling rates. Based on this observation, a neural network trained on downsampled data can reliably perform accurate interpolation without requiring densely-sampled ground truth data, which is typically unavailable in real practice. Our method has undergone validation through numerical simulations, controlled phantom experiments, as well as ex vivo and in vivo animal tests, across multiple PACT systems. We have demonstrated that our technique provides an effective and cost-efficient solution to address the under-sampling issue in PACT, thereby enhancing the capabilities of this imaging technology.

The exponential growth of medical imaging has created significant challenges in data storage, transmission, and management for healthcare systems. In this vein, efficient compression becomes increasingly important. Unlike natural image compression, medical image compression prioritizes preserving diagnostic details and structural integrity, imposing stricter quality requirements and demanding fast, memory-efficient algorithms that balance computational complexity with clinically acceptable reconstruction quality. Meanwhile, the medical imaging family includes a plethora of modalities, each possessing different requirements. For example, 2D medical image (e.g., X-rays, histopathological images) compression focuses on exploiting intra-slice spatial redundancy, while volumetric medical image faces require handling intra-slice and inter-slice spatial correlations, and 4D dynamic imaging (e.g., time-series CT/MRI, 4D ultrasound) additionally demands processing temporal correlations between consecutive time frames. Traditional compression methods, grounded in mathematical transforms and information theory principles, provide solid theoretical foundations, predictable performance, and high standardization levels, with extensive validation in clinical environments. In contrast, deep learning-based approaches demonstrate remarkable adaptive learning capabilities and can capture complex statistical characteristics and semantic information within medical images. This comprehensive survey establishes a two-facet taxonomy based on data structure (2D vs 3D/4D) and technical approaches (traditional vs learning-based), thereby systematically presenting the complete technological evolution, analyzing the unique technical challenges, and prospecting future directions in medical image compression.

Magnetic resonance imaging (MRI) is crucial in pediatric radiology; however, the prolonged scan time is a major drawback that often requires sedation. Deep learning reconstruction (DLR) is a promising method for accelerating MRI acquisition. To evaluate the clinical feasibility of accelerated brain MRI with DLR in pediatric neuroimaging, focusing on image quality compared to conventional MRI. In this retrospective study, 116 pediatric participants (mean age 7.9 ± 5.4 years) underwent routine brain MRI with three reconstruction methods: conventional MRI without DLR (C-MRI), conventional MRI with DLR (DLC-MRI), and accelerated MRI with DLR (DLA-MRI). Two pediatric radiologists independently assessed the overall image quality, sharpness, artifacts, noise, and lesion conspicuity. Quantitative image analysis included the measurement of image noise and coefficient of variation (CoV). DLA-MRI reduced the scan time by 43% compared with C-MRI. Compared with C-MRI, DLA-MRI demonstrated higher scores for overall image quality, noise, and artifacts, as well as similar or higher scores for lesion conspicuity, but similar or lower scores for sharpness. DLC-MRI demonstrated the highest scores for all the parameters. Despite variations in image quality and lesion conspicuity, the lesion detection rates were 100% across all three reconstructions. Quantitative analysis revealed lower noise and CoV for DLA-MRI than those for C-MRI. Interobserver agreement was substantial to almost perfect (weighted Cohen's kappa = 0.72-0.97). DLR enabled faster MRI with improved image quality compared with conventional MRI, highlighting its potential to address prolonged MRI scan times in pediatric neuroimaging and optimize clinical workflows.

While data-driven motion correction (DDMC) techniques have proven to enhance the visibility of lesions affected by motion, their impact on overall detectability remains unclear. This study investigates whether DDMC improves lesion detectability in PET-CT using FDG-18F. A moving platform simulated respiratory motion in a NEMA-IEC body phantom with varying amplitudes (0, 7, 10, 20, 30 mm) and target-to-background ratios (2, 5, 10.5). Scans were reconstructed with and without DDMC, and the spherical targets' maximal and mean recovery coefficient (RC) and contrast-to-noise ratio (CNR) were measured. DDMC results in higher RC values in the target spheres. CNR values increase for small, high-motion affected targets but decrease for larger spheres with smaller amplitudes. A sub-analysis shows that DDMC increases the contrast of the sphere along with a 36% increase in background noise. While DDMC significantly enhances contrast (RC), its impact on detectability (CNR) is less profound due to increased background noise. CNR improves for small targets with high motion amplitude, potentially enhancing the detectability of low-uptake lesions. Given that the increased background noise may reduce detectability for targets unaffected by motion, we suggest that DDMC reconstructions are used best in addition to non-DDMC reconstructions.