OBJECTIVES:To evaluate whether an artificial intelligence-based denoising (AID) algorithm can effectively attenuate body mass index (BMI)-related noise degradation in cardiac photon-counting detector CT (PCD-CT) while maintaining strict quantitative diagnostic equivalence and clinical interchangeability compared with quantum iterative reconstruction (QIR). MATERIALS AND METHODS:This retrospective study included 100 patients undergoing non-contrast coronary artery calcium (CAC) scoring and contrast-enhanced coronary CT angiography (CCTA) on a dual-source PCD-CT. Images were reconstructed using standard QIR and a PCD-CT-weighted AID algorithm. Subjective image quality was assessed by four blinded raters. Objective metrics included noise magnitude (noise power spectrum) and spatial resolution (edge rise distance). Frequentist generalized estimating equations (GEE) evaluated reconstruction effects and BMI interactions. Clinical interchangeability (Agatston scoring, coronary age, CAD-RADS, and plaque characterization) was assessed using Bayesian regions of practical equivalence (ROPE). RESULTS:AID significantly improved subjective image quality and reduced overall noise magnitude by approximately 64 % in CAC and 78 % in CCTA (p<0.001). GEE models revealed that AID robustly attenuated BMI-driven noise escalation by 44 % (CAC) and 78 % (CCTA, p<0.001 for interactions in both). Noise texture was stable in CCTA datasets, but revealed smoothening in CAC datasets. However, spatial resolution was preserved and remained stable across varying patient habitus. ROPE analysis proved strict diagnostic equivalence between QIR and AID, yielding near-certain probabilities (>0.999) of practical equivalence for continuous Agatston scores, categorical CAD-RADS severity classification, and specific coronary plaque composition. CONCLUSIONS:The PCD-CT-weighted AID algorithm improves subjective and objective image quality in both CAC and CCTA, while maintaining diagnostic equivalence and workflow efficiency compared to QIR.

To compare the diagnostic performance of portal-venous (PV) blended CT images alone vs PV blended images supplemented with spectral reconstructions for detecting acute bowel ischemia, stratified by scanner platform (dual-energy CT [DECT] vs photon-counting CT [PCCT]). This retrospective single-center, multireader, crossover diagnostic accuracy study compared PV blended images alone (image set A) with PV blended images supplemented by spectral reconstructions (image set B: 40-keV virtual monoenergetic images, iodine maps, and virtual non-contrast images) acquired on DECT and PCCT. The reference standard was a prespecified composite derived from surgical and index-hospitalization documentation. Diagnostic performance was analyzed using mixed-effects logistic models for accuracy, sensitivity, and specificity, cumulative link mixed models for 7-point suspicion scores, and ROC analyses using a multireader multicase framework. A total of 378 patients (mean age, 68.1 years ± 7.4, 206 men) were evaluated. 150/378 (39.7

Multidisciplinary tumor boards (MDTs) are critical for the personalized management of soft tissue sarcomas (STS), but they are limited by time, costs, and resource demands. With recent advances in large language models (LLMs) like ChatGPT, there is growing interest in evaluating their potential role in augmenting MDT workflows. This study aimed to assess the clinical performance of ChatGPT-4o in real-world STS cases using predefined evaluation criteria, comparing its treatment suggestions with expert MDT decisions. This retrospective study included 152 patients presented to the multidisciplinary sarcoma tumor board. ChatGPT-4o was prompted to generate guideline-based treatment recommendations based on anonymized tumor board registration letters. Outputs were scored by blinded expert reviewers using a five-domain framework: diagnostic modalities, therapeutic modalities, treatment sequencing/timing, chemotherapy regimen, and clinical contextualization. Descriptive statistics and non-parametric ANOVA with post hoc tests assessed performance, including subgroup analysis by sarcoma subtype. ChatGPT-4o scores were significantly lower than the maximum achievable value of 1.0 across all five criteria (all p < 0.0001). Among individual domains, clinical contextualization significantly outperformed all other criteria in pairwise comparisons (all p < 0.05). No significant performance differences were observed across sarcoma subtypes (H = 19.74, p = 0.138). ChatGPT-4o demonstrated substantial expert-rated performance in generating tumor board recommendations for soft tissue sarcoma cases, particularly excelling in personalized contextualization. Discrepancies in treatment sequencing and chemotherapy selection highlight the need for expert oversight. These findings support the feasibility of LLM integration into oncology workflows, warranting further refinement toward safe, supportive clinical use.

Diffusion-weighted imaging (DWI) of the head and neck is essential for various clinical applications but is often hampered by artifacts and reduced image quality. Deep learning (DL) reconstruction has the potential to enhance the quality of head and neck DWI. This study aims to evaluate the performance of an accelerated, DL-reconstructed DWI (DWIDL) in terms of image quality and diagnostic confidence. This retrospective study included patients who underwent clinically indicated head and neck DWI at 1.5 T and 3 T between August 2023 and January 2024 at a tertiary care center. Imaging was performed at low b‑values (0 or 50 sec/mm2) and high b‑values (800 sec/mm2), and apparent diffusion coefficient (ADC) maps were computed. After acquiring standard single-shot echoplanar imaging DWI sequences, the raw MR datasets underwent simulated acceleration by reducing the number of signal averages. These accelerated exams were then reconstructed using a novel DL-based algorithm that combined DL-based k‑space to image reconstruction with DL-based super-resolution processing (DWIDL). Three readers analyzed the images using a visual Likert score to evaluate image sharpness, artifacts, noise, overall image quality, and diagnostic confidence. Comparisons were made using the Wilcoxon signed-rank test. A quantitative analysis of signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and apparent diffusion coefficient values (ADC) was also performed. The study included 30 patients (mean age, 55 ± 19 years; range, 24–84; 18 men) with various pathologies. Scan times were reduced by 67

Objectives:Diagnosis and surgical therapy planning for prostate cancer patients are often hindered by fragmented workflows and a lack of integrated, data-driven analysis - barriers that specifically impede the effective deployment of machine learning (ML)-based risk stratification and clinical decision support. The aim of this exploratory study was to clinically implement and prospectively validate a platform-based multimodal data analysis pipeline within a radiological-urological collaboration. Materials and methods:In this single center analysis, a total of 249 patients (176 retrospectively, 73 prospectively) undergoing radical prostatectomy were included. Multimodal datasets, including preoperative multiparametric MRI, clinical, laboratory, and pathological data, were harmonized and imported into the International Radiomics Platform (IRP). Radiomics features were extracted and machine learning models were constructed to predict extracapsular extension (ECE), nerve-sparing approach decision, and positive surgical margin (PSM) risk. Results are reported as area under the curve (AUC) values including 95% confidence intervals. Results:A cloud-based software prototype was implemented based on the IRP, integrating prediction models for clinical decision support. Using a step-wise modeling approach, prediction of extracapsular extension (ECE) improved substantially when imaging-derived parameters (e.g. PI-RADS scores, tumor-capsule contact length) were added to conventional clinical parameters (AUC 0.90, 95% CI: 0.86-0.94 vs. 0.71, 95% CI: 0.63-0.77). In contrast, the addition of imaging-derived features provided no meaningful incremental value for predicting positive surgical margins (PSM; AUC 0.60, 95% CI: 0.52-0.68) or nerve-sparing approach decisions (AUC 0.79, 95% CI: 0.73-0.83), which were also unchanged by the further inclusion of quantitative radiomics features. Performance was consistent across internal cross-validation and prospective external validation. Conclusion:This exploratory study demonstrates the feasibility of a platform-based, multimodal data analysis workflow for prostate cancer surgical planning. Integration of imaging-derived parameters meaningfully enhanced ECE prediction, while radiomics offered no additional benefit beyond standard imaging. These findings highlight both the potential and current limitations of AI-driven workflow integration in routine clinical practice.

Abstract Objectives Gastrointestinal stromal tumors (GISTs) are molecularly heterogeneous neoplasms whose management depends on individualized, multidisciplinary decision-making. While multidisciplinary tumor boards (MTBs) represent the standard of care, access remains limited in many clinical settings. This study evaluates the performance of two large language models in generating GIST MTB recommendations and assesses their agreement with expert MTB decisions using predefined clinical evaluation criteria. Materials and methods This retrospective single-center study included 99 GIST cases discussed at an institutional MTB. A structured prompt was developed to extract clinical variables and generate treatment recommendations. ChatGPT-5 and Qwen3 were independently evaluated across five predefined domains: diagnostic recommendations, therapeutic modalities, treatment sequence and timing, systemic therapy regimen selection, and clinical contextualization. Two expert reviewers scored all outputs in a blinded fashion. Normalized scores, inter-model comparisons, perfect-case rates, and inter-rater agreement were analyzed. Results Both models demonstrated high concordance with expert MTB recommendations, with mean total normalized scores of 0.901 for ChatGPT-5 and 0.875 for Qwen3, without a significant difference between models ( p > 0.05). Perfect agreement was observed in 52.5% of ChatGPT-5 cases and 48.5% of Qwen3 cases ( p > 0.05). Diagnostic recommendations scored significantly lower than all other domains in both models (all adjusted p < 0.05). Overall inter-rater agreement was almost perfect (weighted Cohen’s kappa=0.978). Conclusions Both models demonstrated high agreement with expert GIST MTB recommendations, with no significant performance difference between them. Diagnostic reasoning represented the weakest domain, reflecting the challenge of reconstructing context-dependent workup decisions from tumor board documentation. These findings support a potential assistive role for LLMs in GIST MTB workflows, while underscoring the continued necessity of expert oversight.

RATIONALE AND OBJECTIVES:Photon Counting CT (PCCT) offers advanced imaging capabilities with potential for substantial radiation dose reduction; however, achieving this without compromising image quality remains a challenge due to increased noise at lower doses. This study aims to evaluate the effectiveness of a deep learning (DL)-based denoising algorithm in maintaining diagnostic image quality in whole-body PCCT imaging at reduced radiation levels, using real intraindividual cadaveric scans. MATERIALS AND METHODS:Twenty-four cadaveric human bodies underwent whole-body CT scans on a PCCT scanner (NAEOTOM Alpha, Siemens Healthineers) at four different dose levels (100%, 50%, 25%, and 10% mAs). Each scan was reconstructed using both QIR level 2 and a DL algorithm (ClariCT.AI, ClariPi Inc.), resulting in 192 datasets. Objective image quality was assessed by measuring CT value stability, image noise, and contrast-to-noise ratio (CNR) across consistent regions of interest (ROIs) in the liver parenchyma. Two radiologists independently evaluated subjective image quality based on overall image clarity, sharpness, and contrast. Inter-rater agreement was determined using Spearman's correlation coefficient, and statistical analysis included mixed-effects modeling to assess objective and subjective image quality. RESULTS:Objective analysis showed that the DL denoising algorithm did not significantly alter CT values (p ≥ 0.9975). Noise levels were consistently lower in denoised datasets compared to the Original (p < 0.0001). No significant differences were observed between the 25% mAs denoised and the 100% mAs original datasets in terms of noise and CNR (p ≥ 0.7870). Subjective analysis revealed strong inter-rater agreement (r ≥ 0.78), with the 50% mAs denoised datasets rated superior to the 100% mAs original datasets (p < 0.0001) and no significant differences detected between the 25% mAs denoised and 100% mAs original datasets (p ≥ 0.9436). CONCLUSION:The DL denoising algorithm maintains image quality in PCCT imaging while enabling up to a 75% reduction in radiation dose. This approach offers a promising method for reducing radiation exposure in clinical PCCT without compromising diagnostic quality.

This study aimed to compare a conventional three-dimensional (3-D) magnetic resonance cholangiopancreatography (MRCP) sequence with a deep learning (DL)-accelerated MRCP sequence (hereafter, MRCPDL) regarding acquisition time and image quality. We conducted a prospective study of consecutive patients referred for MRCP between November 2023 and April 2024 at a single tertiary center. Each participant underwent 1.5T 3-D T2-weighted turbo spin echo MRCP using both a conventional sequence (threefold acceleration) and MRCPDL (eightfold acceleration). Three blinded readers independently evaluated image quality, including background signal suppression, bile and pancreatic duct visibility, artifact level, and diagnostic confidence on an ordinal four-point scale. Acquisition times were compared using a paired t-test. Image quality parameters were assessed with repeated measures ANOVA. Interreader agreement was analyzed using Fleiss' κ. Out of 419 consecutive patients, 30 participants were evaluated (mean age, 63 ± 15 years; 16 men, 14 women). The mean acquisition time was 10:30 ± 03:04 min for conventional MRCP and 3:57 ± 01:13 min for MRCPDL, P < 0.001. MRCPDL reduced acquisition time by 62.4

Purpose:Deep-learning (DL)-based image reconstruction (DLR) is a key technique for reducing acquisition time (TA) and increasing morphologic resolution in abdominal magnetic resonance imaging (MRI). We aim to compare the performance of a standard ( VIBE Std ) gradient echo (GRE) sequence with Dixon fat separation versus an accelerated ultra-fast ( VIBE UF ) and high-resolution ( VIBE HR ) T1-weighted GRE sequence with Dixon fat separation and DLR. Approach:A total of 50 patients with an abdominal 1.5T MRI, with a mean age of 59 ± 11 years, were prospectively included from January to July 2023. Each examination protocol included VIBE Std , VIBE UF , and VIBE HR . Both DL sequences use more aggressive parallel imaging and partial Fourier sampling to reduce TA (slice thickness VIBE Std and VIBE UF 3 mm, VIBE HR 2 mm). Evaluation of each contrast-enhanced datasets for noise, artifacts, sharpness/contrast, overall image quality, and diagnostic confidence was performed independently by four radiologists using a Likert scale of 1 to 5 (5 = best). Results:VIBE UF significantly reduced TA (mean 7.3 s versus 15.0 s ( VIBE Std ) and 14.5 s ( VIBE HR ); p < 0.001 ). Both DL sequences provided significantly better sharpness/contrast for all organs compared with VIBE Std (median 5 versus 4; p < 0.001 ). VIBE UF showed less noise than VIBE Std (median 5 versus 4; p < 0.001 ), but VIBE Std was less artifact-affected than both DL sequences (median 5 versus 4; p < 0.001 ). Overall image quality was superior in both DL sequences compared with VIBE Std (median 5 versus 4; p < 0.001 ). Diagnostic confidence and lesion detectability were not significantly different ( p > 0.05 ). Conclusion:DL-based image reconstruction significantly improves overall image quality for VIBE UF and VIBE HR , with VIBE UF reducing TA by ∼ 50 % .

PurposeThis study evaluates the impact of high-resolution T2-weighted imaging (T2HR) combined with deep learning image reconstruction (DLR) on image quality, lesion delineation, and extraprostatic extension (EPE) assessment in prostate multiparametric MRI (mpMRI).Materials and methodsThis retrospective study included 69 patients who underwent mpMRI of the prostate on a 3 T scanner with DLR between April 2023 and March 2024. Routine mpMRI protocols adhering to the Prostate Imaging Reporting and Data System (PI-RADS) v2.1 were used, including an additional T2HR sequence [2 mm slice thickness, 4:31 min vs. 4:12 min for standard T2 (T2S)]. The image datasets were evaluated by two radiologists using a Likert scale ranging from 1 to 5, with 5 being the best for sharpness, lesion contours, motion artifacts, prostate border delineation, overall image quality, and diagnostic confidence. PI-RADS scoring and EPE suspicion were analyzed. The statistical methods used included the Wilcoxon signed-rank test and Cohen's kappa for inter-reader agreement.ResultsT2HR significantly improved lesion contours (medians of 5 vs. 4, p < 0.001), prostate border delineation (medians of 5 vs. 4, p < 0.001), and overall image quality (medians of 5 vs. 4, p < 0.001) compared to T2S. However, motion artifacts were significantly worse in T2HR. Substantial inter-reader agreement was observed in the PI-RADS scoring. EPE detection marginally increased with T2HR, though histopathological validation was limited.ConclusionT2HR imaging with DLR enhances image quality, lesion delineation, and diagnostic confidence without significantly prolonged acquisition time. It shows potential for improving EPE assessment in prostate cancer but requires further validation in larger studies.

Objective Deep learning (DL)–enabled magnetic resonance imaging (MRI) reconstructions can enable shortening of breath-hold examinations and improve image quality by reducing motion artifacts. Prospective studies with DL reconstructions of accelerated MRI of the upper abdomen in the context of pancreatic pathologies are lacking. In a clinical setting, the purpose of this study is to investigate the performance of a novel DL-based reconstruction algorithm in T1-weighted volumetric interpolated breath-hold examinations with partial Fourier sampling and Dixon fat suppression (hereafter, VIBE-DixonDL). The objective is to analyze its impact on acquisition time, image sharpness and quality, diagnostic confidence, pancreatic lesion conspicuity, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Methods This prospective single-center study included participants with various pancreatic pathologies who gave written consent from January 2023 to September 2023. During the same session, each participant underwent 2 MRI acquisitions using a 1.5 T scanner: conventional precontrast and postcontrast T1-weighted VIBE acquisitions with Dixon fat suppression (VIBE-Dixon, reference standard) using 4-fold parallel imaging acceleration and 6-fold accelerated VIBE-Dixon acquisitions with partial Fourier sampling utilizing a novel DL reconstruction tailored to the acquisition. A qualitative image analysis was performed by 4 readers. Acquisition time, image sharpness, overall image quality, image noise and artifacts, diagnostic confidence, as well as pancreatic lesion conspicuity and size were compared. Furthermore, a quantitative analysis of SNR and CNR was performed. Results Thirty-two participants were evaluated (mean age ± SD, 62 ± 19 years; 20 men). The VIBE-DixonDL method enabled up to 52% reduction in average breath-hold time (7 seconds for VIBE-DixonDL vs 15 seconds for VIBE-Dixon, P < 0.001). A significant improvement of image sharpness, overall image quality, diagnostic confidence, and pancreatic lesion conspicuity was observed in the images recorded using VIBE-DixonDL (P < 0.001). Furthermore, a significant reduction of image noise and motion artifacts was noted in the images recorded using the VIBE-DixonDL technique (P < 0.001). In addition, for all readers, there was no evidence of a difference in lesion size measurement between VIBE-Dixon and VIBE-DixonDL. Interreader agreement between VIBE-Dixon and VIBE-DixonDL regarding lesion size was excellent (intraclass correlation coefficient, >90). Finally, a statistically significant increase of pancreatic SNR in VIBE-DIXONDL was observed in both the precontrast (P = 0.025) and postcontrast images (P < 0.001). Also, an increase of splenic SNR in VIBE-DIXONDL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images (P = 0.34 and P = 0.003, respectively). Similarly, an increase of pancreas CNR in VIBE-DIXONDL was observed in both the precontrast and postcontrast images, but only reaching statistical significance in the postcontrast images (P = 0.557 and P = 0.026, respectively). Conclusions The prospectively accelerated, DL-enhanced VIBE with Dixon fat suppression was clinically feasible. It enabled a 52% reduction in breath-hold time and provided superior image quality, diagnostic confidence, and pancreatic lesion conspicuity. This technique might be especially useful for patients with limited breath-hold capacity.

Background: The increase in multiparametric magnetic resonance imaging (mpMRI) examinations as a fundamental tool in prostate cancer (PCa) diagnostics raises the need for supportive computer-aided imaging analysis. Therefore, we evaluated the performance of a commercially available AI-based algorithm for prostate cancer detection and classification in a multi-center setting. Methods: Representative patients with 3T mpMRI between 2017 and 2022 at three different university hospitals were selected. Exams were read according to the PI-RADSv2.1 protocol and then assessed by an AI algorithm. Diagnostic accuracy for PCa of both human and AI readings were calculated using MR-guided ultrasound fusion biopsy as the gold standard. Results: Analysis of 91 patients resulted in 138 target lesions. Median patient age was 67 years (range: 49–82), median PSA at the time of the MRI exam was 8.4 ng/mL (range: 1.47–73.7). Sensitivity and specificity for clinically significant prostate cancer (csPCa, defined as ISUP ≥ 2) were 92%/64% for radiologists vs. 91%/57% for AI detection on patient level and 90%/70% vs. 81%/78% on lesion level, respectively (cut-off PI-RADS ≥ 4). Two cases of csPCa were missed by the AI on patient-level, resulting in a negative predictive value (NPV) of 0.88 at a cut-off of PI-RADS ≥ 3. Conclusions: AI-augmented lesion detection and scoring proved to be a robust tool in a multi-center setting with sensitivity comparable to the radiologists, even outperforming human reader specificity on both patient and lesion levels at a threshold of PI-RADS ≥3 and a threshold of PI-RADS ≥ 4 on lesion level. In anticipation of refinements of the algorithm and upon further validation, AI-detection could be implemented in the clinical workflow prior to human reading to exclude PCa, thereby drastically improving reading efficiency.

Purpose: The purpose of this study was to compare a conventional T1-weighted volumetric interpolated breath-hold examination (VIBE) sequence with a DL-reconstructed accelerated high-resolution VIBE sequence (HR-VIBEDL) in terms of image quality, lesion conspicuity, and lesion detection. Materials and methods: Consecutive patients referred for upper abdominal MRI between December 2023 and March 2024 at a single tertiary center were prospectively enrolled. Participants underwent 1.5 T upper abdominal MRI with acquisition of spectrally fat-saturated unenhanced and gadobutrol-enhanced conventional VIBE (fourfold acceleration, 3.0 mm slice thickness, 72 axial slices) and HR-VIBEDL (sixfold acceleration, 2.0 mm, 108 slices). Both sequences had an identical acquisition time of 16 s. Image analysis was performed by three readers in a blinded and randomized fashion, with respect to image quality, lesion conspicuity, and lesion detection in liver, pancreas, spleen, lymph nodes and adrenal glands. Image quality parameters were compared using repeated measures analysis of variance. Lesion detection rates were compared using Fisher exact test. Inter-reader agreement was assessed using Fleiss kappa test. Results: Among 744 consecutive patients, 50 participants were evaluated. There were 30 men and 20 women, with a mean age of 60 +/- 15 (standard deviation [SD]) years (age range: 18-88 years). HR-VIBEDL images demonstrated superior signal-to-noise ration and edge sharpness by comparison with conventional VIBE images (P < 0.001 for both), with substantial interreader agreement (kappa: 0.70-0.90). Lesion conspicuity was higher with for HR-VIBEDL images (3.50 +/- 0.83 [SD]) by comparison with conventional VIBE images (3.21 +/- 0.98 [SD]) (P = 0.005). There were 171 upper abdominal lesions, yielding a total of 513 for all three readers. HR-VIBEDL images yielded higher lesion detection rate (97.5 %; 500/513) compared to conventional VIBE images (93.2 %; 478/513) (P = 0.002). Conclusion: HR-VIBEDL images of the upper abdomen result in superior image quality, better lesion conspicuity, and improved lesion detection without time penalty by comparsion with conventional VIBE images.

HYPOTHESIS:Photon-counting detector CT (PCD-CT) with deep learning-supported denoising can significantly reduce the radiation dose for cochlear implant (CI) planning without compromising the accuracy of cochlear duct length (CDL) measurements. BACKGROUND:Optimal electrode placement in CI surgery requires detailed cochlear anatomy from CT scans, but reducing radiation exposure is critical. This study explores PCD-CT with denoising algorithms to lower doses while preserving diagnostic accuracy. METHODS:Four body donors without inner ear malformations were scanned using PCD-CT at 100%, 50%, 25%, 10%, and 5% dose levels. Images were denoised with ClariAce, a deep learning algorithm, and CDL was measured using OTOPLAN software. Neurotologists compared the results to manual segmentations. Statistical analyses evaluated accuracy across dose levels, with Bland-Altman plots assessing systematic errors. RESULTS:Automatic segmentation succeeded across all doses but showed increased failure below 50%. At 100% and 50% doses, CDL measurements closely matched the gold standard, with minor deviations (eg, -0.17 mm at 50%). Below 50%, CDL underestimation increased (-1.25 mm at 25% and -4.0 mm at 5%). Denoising improved segmentation but minimally affected CDL accuracy at low doses, where manual segmentation performed better. CONCLUSIONS:PCD-CT enables significant dose reduction for CI planning, with reliable CDL accuracy down to 50%. Deep learning denoising enhances image quality but is less effective below 50%, necessitating manual segmentation. These findings align with ALARA principles and suggest further refinement of AI algorithms for lower-dose applicability in CI diagnostics.

Comment on: JUNGES FORUM – Kognitive Verzerrung in der RadiologieRofo 2024; 196(06): 535-536DOI: 10.1055/a-2253-1107

Rationale and Objectives: To compare a conventional T1 volumetric interpolated breath-hold examination (VIBE) with SPectral Attenuated Inversion Recovery (SPAIR) fat saturation and a deep learning (DL)-reconstructed accelerated VIBE sequence with SPAIR fat saturation achieving a 50 % reduction in breath-hold duration (hereafter, VIBE-SPAIR(DL)) in terms of image quality and diagnostic confidence. Materials and Methods: This prospective study enrolled consecutive patients referred for upper abdominal MRI from November 2023 to December 2023 at a single tertiary center. Patients underwent upper abdominal MRI with acquisition of non-contrast and gadobutrolenhanced conventional VIBE-SPAIR (fourfold acceleration, acquisition time 16 s) and VIBE-SPAIR(DL) (sixfold acceleration, acquisition time 8 s) on a 1.5 T scanner. Image analysis was performed by four readers, evaluating homogeneity of fat suppression, perceived signal-to-noise ratio (SNR), edge sharpness, artifact level, lesion detectability and diagnostic confidence. A statistical power analysis for patient sample size estimation was performed. Image quality parameters were compared by a repeated measures analysis of variance, and interreader agreement was assessed using Fleiss' kappa. Results: Among 450 consecutive patients, 45 patients were evaluated (mean age, 60 years +/- 15 [SD]; 27 men, 18 women). VIBESPAIRDL acquisition demonstrated superior SNR (P < 0.001), edge sharpness (P < 0.001), and reduced artifacts (P < 0.001) with substantial to almost perfect interreader agreement for non-contrast (kappa: 0.70-0.91) and gadobutrol-enhanced MRI (kappa: 0.68-0.87). No evidence of a difference was found between conventional VIBE-SPAIR and VIBE-SPAIR(DL) regarding homogeneity of fat suppression, lesion detectability, or diagnostic confidence (all P > 0.05). Conclusion: Deep learning reconstruction of VIBE-SPAIR facilitated a reduction of breath-hold duration by half, while reducing artifacts and improving image quality. Summary: Deep learning reconstruction of prospectively accelerated T1 volumetric interpolated breath-hold examination for upper abdominal MRI enabled a 50 % reduction in breath-hold time with superior image quality.

Purpose: To investigate the metal artifact suppression potential of combining tin prefiltration and virtual monoenergetic imaging (VMI) for osseous microarchitecture depiction in ultra-high-resolution (UHR) photon-counting CT (PCCT) of the lower extremity.Method: Derived from tin-filtered UHR scans at 140 kVp, polychromatic datasets (T3D) and VMI reconstructions at 70, 110, 150, and 190 keV were compared in 117 patients with lower extremity metal implants (53 female; 62.1 +/- 18.0 years). Three implant groups were investigated (total arthroplasty [n = 48], osteosynthetic material [n = 43], and external fixation [n = 26]). Image quality was assessed with regions of interest placed in the most pronounced artifacts and adjacent soft tissue, measuring the respective attenuation. Additionally, artifact extent, bone-metal interface interpretability and overall image quality were independently evaluated by three radiologists.Results: Artifact reduction was superior with increasing keV level of VMI. While T3D was superior to VMI70keV (p >= 0.117), artifacts were more severe in T3D than in VMI >= 110 keV (all p <= 0.036). Image noise was highest for VMI70keV (all p < 0.001) and lowest for VMI110keV with comparable results for VMI110keV - VMI190keV. Subjective image quality regarding artifacts was superior for VMI >= 110 keV (all p <= 0.042) and comparable for VMI110keV - VMI190keV. Bone-metal interface interpretability was superior for VMI110keV (all p <= 0.001), while T3D, VMI150keV and VMI190keV were comparable. Overall image quality was deemed best for VMI110keV and VMI150keV. Interreader reliability was good in all cases (ICC >= 0.833).Conclusions: Tin-filtered UHR-PCCT scans of the lower extremity combined with VMI reconstructions allow for efficient artifact reduction in the vicinity of bone-metal interfaces.

Rationale and Objectives: To determine the impact on acquisition time reduction and image quality of a deep learning (DL) reconstruction for accelerated diffusion-weighted imaging (DWI) of the pelvis at 1.5 T compared to standard DWI. Materials and Methods: A total of 55 patients (mean age, 61 +/- 13 years; range, 27-89; 20 men, 35 women) were consecutively included in this retrospective, monocentric study between February and November 2022. Inclusion criteria were (1) standard DWI (DWIS) in clinically indicated magnetic resonance imaging (MRI) at 1.5 T and (2) DL-reconstructed DWI (DWIDL). All patients were examined using the institution's standard MRI protocol according to their diagnosis including DWI with two different b-values (0 and 800 s/mm(2)) and calculation of apparent diffusion coefficient (ADC) maps. Image quality was qualitatively assessed by four radiologists using a visual 5-point Likert scale (5 = best) for the following criteria: overall image quality, noise level, extent of artifacts, sharpness, and diagnostic confidence. The qualitative scores for DWIS and DWIDL were compared with the Wilcoxon signed-rank test. Results: The overall image quality was evaluated to be significantly superior in DWIDL compared to DWIS for b = 0 s/mm(2), b = 800 s/mm(2), and ADC maps by all readers (P < .05). The extent of noise was evaluated to be significantly less in DWIDL compared to DWIS for b = 0 s/mm(2), b = 800 s/mm(2), and ADC maps by all readers (P < .001). No significant differences were found regarding artifacts, lesion detectability, sharpness of organs, and diagnostic confidence (P > .05). Acquisition time for DWIS was 2:06 minutes, and simulated acquisition time for DWIDL was 1:12 minutes. Conclusion: DL image reconstruction improves image quality, and simulation results suggest that a reduction in acquisition time for diffusion-weighted MRI of the pelvis at 1.5 T is possible.