Deep learning image reconstruction of diffusion-weighted imaging in evaluation of prostate cancer focusing on its clinical implications.

Background: Image-based assessment of prostate cancer (PCa) is increasingly emphasized in the diagnostic workflow for selecting biopsy targets and possibly predicting clinically significant prostate cancer (csPCa). Assessment is based on Prostate Imaging-Reporting and Data System (PI-RADS) which is largely dependent on T2-weighted image (T2WI) and diffusion weighted image (DWI). This study aims to determine whether deep learning reconstruction (DLR) can improve the image quality of DWI and affect the assessment of PI-RADS ≥4 in patients with PCa. Methods: In this retrospective study, 3.0T post-biopsy prostate magnetic resonance imaging (MRI) of 70 patients with PCa in Korea University Ansan Hospital from November 2021 to July 2022 was reconstructed with and without using DLR. Four DWI image sets were made: (I) conventional DWI (CDWI): DWI with acceleration factor 2 and conventional parallel imaging reconstruction, (II) DL1: DWI with acceleration factor 2 using DLR, (III) DL2: DWI with acceleration factor 3 using DLR, and (IV) DL3: DWI with acceleration factor 3 and half average b-value using DLR. Apparent diffusion coefficient (ADC) value, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured by one reviewer, while two reviewers independently assessed overall image quality, noise, and lesion conspicuity using a four-point visual scoring system from each DWI image set. Two reviewers also performed PI-RADSv2.1 scoring on lesions suspected of malignancy. Results: A total of 70 patients (mean age, 70.8±9.7 years) were analyzed. The image acquisition time was 4:46 min for CDWI and DL1, 3:40 min for DL2, and 2:00 min for DL3. DL1 and DL2 images resulted in better lesion conspicuity compared to CDWI images assessed by both readers (P<0.05). DLR resulted in a significant increase in SNR, from 38.4±14.7 in CDWI to 56.9±21.0 in DL1. CNR increased from 25.1±11.5 in CDWI to 43.1±17.8 in DL1 (P<0.001). PI-RADS v2.1 scoring for PCa lesions was more agreeable with the DL1 reconstruction method than with CDWI (κ value CDWI, DL1; 0.40, 0.61, respectively). A statistically significant number of lesions were upgraded from PI-RADS <4 in CDWI image to PI-RADS ≥4 in DL1 images for both readers (P<0.05). Most of the PI-RADS upgraded lesions were from higher than unfavorable intermediate-risk groups according to the 2023 National Comprehensive Cancer Network guidelines with statistically significant difference of marginal probability in DL1 and DL2 for both readers (P<0.05). Conclusions: DLR in DWI for PCa can provide options for improving image quality with a significant impact on PI-RADS evaluation or about a 23% reduction in acquisition time without compromising image quality.

Accelerated Diffusion-Weighted Magnetic Resonance Imaging of the Liver at 1.5 T With Deep Learning-Based Image Reconstruction: Impact on Image Quality and Lesion Detection.

OBJECTIVE: To perform image quality comparison between deep learning-based multiband diffusion-weighted sequence (DL-mb-DWI), accelerated multiband diffusion-weighted sequence (accelerated mb-DWI), and conventional multiband diffusion-weighted sequence (conventional mb-DWI) in patients undergoing clinical liver magnetic resonance imaging (MRI). METHODS: Fifty consecutive patients who underwent clinical MRI of the liver at a 1.5-T scanner, between September 1, 2021, and January 31, 2022, were included in this study. Three radiologists independently reviewed images using a 5-point Likert scale for artifacts and image quality factors, in addition to assessing the presence of liver lesions and lesion conspicuity. RESULTS: DL-mb-DWI acquisition time was 65.0 ± 2.4 seconds, significantly (P < 0.001) shorter than conventional mb-DWI (147.5 ± 19.2 seconds) and accelerated mb-DWI (94.3 ± 1.8 seconds). DL-mb-DWI received significantly higher scores than conventional mb-DWI for conspicuity of the left lobe (P < 0.001), sharpness of intrahepatic vessel margin (P < 0.001), sharpness of the pancreatic contour (P < 0.001), in-plane motion artifact (P = 0.002), and overall image quality (P = 0.005) by reader 2. DL-mb-DWI received significantly higher scores for conspicuity of the left lobe (P = 0.006), sharpness of the pancreatic contour (P = 0.020), and in-plane motion artifact (P = 0.042) by reader 3. DL-mb-DWI received significantly higher scores for strength of fat suppression (P = 0.004) and sharpness of the pancreatic contour (P = 0.038) by reader 1. The remaining quality parameters did not reach statistical significance for reader 1. CONCLUSIONS: Novel diffusion-weighted MRI sequence with deep learning-based image reconstruction demonstrated significantly decreased acquisition times compared with conventional and accelerated mb-DWI sequences, while maintaining or improving image quality for routine abdominal MRI. DL-mb-DWI offers a potential alternative to conventional mb-DWI in routine clinical liver MRI.

Spatial profiling of in vivo diffusion-weighted MRI parameters in the healthy human kidney.

OBJECTIVE: Diffusion-weighted MRI is a technique that can infer microstructural and microcirculatory features from biological tissue, with particular application to renal tissue. There is extensive literature on diffusion tensor imaging (DTI) of anisotropy in the renal medulla, intravoxel incoherent motion (IVIM) measurements separating microstructural from microcirculation effects, and combinations of the two. However, interpretation of these features and adaptation of more specific models remains an ongoing challenge. One input to this process is a whole organ distillation of corticomedullary contrast of diffusion metrics, as has been explored for other renal biomarkers. MATERIALS AND METHODS: In this work, we probe the spatial dependence of diffusion MRI metrics with concentrically layered segmentation in 11 healthy kidneys at 3 T. The metrics include those from DTI, IVIM, a combined approach titled "REnal Flow and Microstructure AnisotroPy (REFMAP)", and a multiply encoded model titled "FC-IVIM" providing estimates of fluid velocity and branching length. RESULTS: Fractional anisotropy decreased from the inner kidney to the outer kidney with the strongest layer correlation in both parenchyma (including cortex and medulla) and medulla with Spearman correlation coefficients and p-values (r, p) of (0.42, <0.001) and (0.37, <0.001), respectively. Also, dynamic parameters derived from the three models significantly decreased with a high correlation from the inner to the outer parenchyma or medulla with (r, p) ranges of (0.46-0.55, <0.001). CONCLUSIONS: These spatial trends might find implications for indirect assessments of kidney physiology and microstructure using diffusion MRI.

Deep Learning Accelerated Brain Diffusion-Weighted MRI with Super Resolution Processing.

OBJECTIVES: To investigate the clinical feasibility and image quality of accelerated brain diffusion-weighted imaging (DWI) with deep learning image reconstruction and super resolution. METHODS: 85 consecutive patients with clinically indicated MRI at a 3 T scanner were prospectively included. Conventional diffusion-weighted data (c-DWI) with four averages were obtained. Reconstructions of one and two averages, as well as deep learning diffusion-weighted imaging (DL-DWI), were accomplished. Three experienced readers evaluated the acquired data using a 5-point Likert scale regarding overall image quality, overall contrast, diagnostic confidence, occurrence of artefacts and evaluation of the central region, basal ganglia, brainstem, and cerebellum. To assess interrater agreement, Fleiss' kappa (Ï°) was determined. Signal intensity (SI) levels for basal ganglia and the central region were estimated via automated segmentation, and SI values of detected pathologies were measured. RESULTS: Intracranial pathologies were identified in 35 patients. DL-DWI was significantly superior for all defined parameters, independently from applied averages (p-value <0.001). Optimum image quality was achieved with DL-DWI by utilizing a single average (p-value <0.001), demonstrating very good (80.9%) to excellent image quality (14.5%) in nearly all cases, compared to 12.5% with very good and 0% with excellent image quality for c-MRI (p-value <0.001). Comparable results could be shown for diagnostic confidence. Inter-rater Fleiss' Kappa demonstrated moderate to substantial agreement for virtually all defined parameters, with good accordance, particularly for the assessment of pathologies (p = 0.74). Regarding SI values, no significant difference was found. CONCLUSION: Ultra-fast diffusion-weighted imaging with super resolution is feasible, resulting in highly accelerated brain imaging while increasing diagnostic image quality.

Shortening Acquisition Time and Improving Image Quality for Pelvic MRI Using Deep Learning Reconstruction for Diffusion-Weighted Imaging at 1.5 T.

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/mm2) 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/mm2, b = 800 s/mm2, 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/mm2, b = 800 s/mm2, 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.

Semiautomated Segmentation and Analysis of Airway Lumen in Pediatric Patients Using Ultra Short Echo Time MRI.

RATIONALE AND OBJECTIVES: Ultra short echo time (UTE) magnetic resonance imaging (MRI) pulse sequences have shown promise for airway assessment, but the feasibility and repeatability in the pediatric lung are unknown. The purpose of this work was to develop a semiautomated UTE MRI airway segmentation pipeline from the trachea-to-tertiary airways in pediatric participants and assess repeatability and lumen diameter correlations to lung function. MATERIALS AND METHODS: A total of 29 participants (n = 7 healthy, n = 11 cystic fibrosis, n = 6 asthma, and n = 5 ex-preterm), aged 7-18 years, were imaged using a 3D stack-of-spirals UTE examination at 3 T. Two independent observers performed airway segmentations using a pipeline developed in-house; observer 1 repeated segmentations 1 month later. Segmentations were extracted using region-growing with leak detection, then manually edited if required. The airway trees were skeletonized, pruned, and labeled. Airway lumen diameter measurements were extracted using ray casting. Intra- and interobserver variability was assessed using the Sørensen-Dice coefficient (DSC) and intra-class correlation coefficient (ICC). Correlations between lumen diameter and pulmonary function were assessed using Spearman's correlation coefficient. RESULTS: For airway segmentations and lumen diameter, intra- and interobserver DSCs were 0.88 and 0.80, while ICCs were 0.95 and 0.89, respectively. The variability increased from the trachea-to-tertiary airways for intra- (DSC: 0.91-0.64; ICC: 0.91-0.49) and interobserver (DSC: 0.84-0.51; ICC: 0.89-0.21) measurements. Lumen diameter was significantly correlated with forced expiratory volume in 1 second and forced vital capacity (P < .05). CONCLUSION: UTE MRI airway segmentation from the trachea-to-tertiary airways in pediatric participants across a range of diseases is feasible. The UTE MRI-derived lumen measurements were repeatable and correlated with lung function.

Advanced and traditional chest MRI sequence for the clinical assessment of systemic sclerosis related interstitial lung disease, compared to CT: disease extent analysis and correlations with pulmonary function tests.

BACKGROUND: MRI is a radiation-free emerging alternative to CT in systemic sclerosis related interstitial lung disease (SSc-ILD) assessment. We aimed to compare a T2 radial TSE and a PD UTE MRI sequence with CT in SSc-ILD extent evaluation and correlations with pulmonary function tests (PFT). MATERIAL AND METHODS: 29 SSc-ILD patients underwent CT, MRI and PFT. ILD extent was visually assessed. Lin's concordance correlation coefficients (CCC) and Kruskal Wallis test (p-value < 0.05) were computed for inter-method comparison. Patients were divided in limited and extended disease, defining extended ILD with two methods: (A) ILD>30% or 10%20% or 20% with FVC%<70%. MRI Sensitivity, Specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV) and Accuracy were assessed. Pearson correlation coefficients r (p-value<0.025) were computed between ILD extents and PFT (FVC% and DLCO%). RESULTS: Median ILD extents were 11%, 11%, 10% on CT, radial TSE and UTE, respectively. CCC between CT and MRI was 0.95 for both sequences (Kruskal-Wallis p-value=0.64). Sensitivity, Specificity, PPV, NPV and Accuracy in identifying extended disease were: (A) 87.5 %, 100 %, 100 %, 95.5 and 96.6 % with radial TSE and 87.5 %, 95.2 %, 87.5 %, 95.2 and 93.1 % with UTE; (B) 86.7 %, 86.4 %, 66.7 %, 95.0 % and 86.2 % for both sequences. Pearson r of CT, radial TSE and UTE ILD extents with FVC were -0.66, -0.60 and -0.68 with FVC, -0.59, -0.56 and -0.57 with DLCO, respectively (p<0.002). CONCLUSIONS: MRI sequences may have similar accuracy to CT to determine SSc-ILD extent and severity, with analogous correlations with PFT.

Deep learning-based k-space-to-image reconstruction and super resolution for diffusion-weighted imaging in whole-spine MRI.

PURPOSE: To assess the feasibility of deep learning (DL)-based k-space-to-image reconstruction and super resolution for whole-spine diffusion-weighted imaging (DWI). METHOD: This retrospective study included 97 consecutive patients with hematologic and/or oncologic diseases who underwent DL-processed whole-spine MRI from July 2022 to March 2023. For each patient, conventional (CONV) axial single-shot echo-planar DWI (b = 50, 800 s/mm2) was performed, followed by DL reconstruction and super resolution processing. The presence of malignant lesions and qualitative (overall image quality and diagnostic confidence) and quantitative (nonuniformity [NU], lesion contrast, signal-to-noise ratio [SNR], contrast-to-noise ratio [CNR], and ADC values) parameters were assessed for DL and CONV DWI. RESULTS: Ultimately, 67 patients (mean age, 63.0 years; 35 females) were analyzed. The proportions of vertebrae with malignant lesions for both protocols were not significantly different (P: [0.55-0.99]). The overall image quality and diagnostic confidence scores were higher for DL DWI (all P ≤ 0.002) than CONV DWI. The NU, lesion contrast, SNR, and CNR of each vertebral segment (P ≤ 0.04) but not the NU of the sacral segment (P = 0.51) showed significant differences between protocols. For DL DWI, the NU was lower, and lesion contrast, SNR, and CNR were higher than those of CONV DWI (median values of all segments; 19.8 vs. 22.2, 5.4 vs. 4.3, 7.3 vs. 5.5, and 0.8 vs. 0.7). Mean ADC values of the lesions did not significantly differ between the protocols (P: [0.16-0.89]). CONCLUSIONS: DL reconstruction can improve the image quality of whole-spine diffusion imaging.

Deep Learning k-Space-to-Image Reconstruction Facilitates High Spatial Resolution and Scan Time Reduction in Diffusion-Weighted Imaging Breast MRI.

BACKGROUND: For time-consuming diffusion-weighted imaging (DWI) of the breast, deep learning-based imaging acceleration appears particularly promising. PURPOSE: To investigate a combined k-space-to-image reconstruction approach for scan time reduction and improved spatial resolution in breast DWI. STUDY TYPE: Retrospective. POPULATION: 133 women (age 49.7 ± 12.1 years) underwent multiparametric breast MRI. FIELD STRENGTH/SEQUENCE: 3.0T/T2 turbo spin echo, T1 3D gradient echo, DWI (800 and 1600 sec/mm2 ). ASSESSMENT: DWI data were retrospectively processed using deep learning-based k-space-to-image reconstruction (DL-DWI) and an additional super-resolution algorithm (SRDL-DWI). In addition to signal-to-noise ratio and apparent diffusion coefficient (ADC) comparisons among standard, DL- and SRDL-DWI, a range of quantitative similarity (e.g., structural similarity index [SSIM]) and error metrics (e.g., normalized root mean square error [NRMSE], symmetric mean absolute percent error [SMAPE], log accuracy error [LOGAC]) was calculated to analyze structural variations. Subjective image evaluation was performed independently by three radiologists on a seven-point rating scale. STATISTICAL TESTS: Friedman's rank-based analysis of variance with Bonferroni-corrected pairwise post-hoc tests. P < 0.05 was considered significant. RESULTS: Both DL- and SRDL-DWI allowed for a 39% reduction in simulated scan time over standard DWI (5 vs. 3 minutes). The highest image quality ratings were assigned to SRDL-DWI with good interreader agreement (ICC 0.834; 95% confidence interval 0.818-0.848). Irrespective of b-value, both standard and DL-DWI produced superior SNR compared to SRDL-DWI. ADC values were slightly higher in SRDL-DWI (+0.5%) and DL-DWI (+3.4%) than in standard DWI. Structural similarity was excellent between DL-/SRDL-DWI and standard DWI for either b value (SSIM ≥ 0.86). Calculation of error metrics (NRMSE ≤ 0.05, SMAPE ≤ 0.02, and LOGAC ≤ 0.04) supported the assumption of low voxel-wise error. DATA CONCLUSION: Deep learning-based k-space-to-image reconstruction reduces simulated scan time of breast DWI by 39% without influencing structural similarity. Additionally, super-resolution interpolation allows for substantial improvement of subjective image quality. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 1.

Longitudinal Evaluation of Bronchial Changes in Cystic Fibrosis Patients Undergoing Elexacaftor/Tezacaftor/Ivacaftor Therapy Using Lung MRI With Ultrashort Echo-Times.

BACKGROUND: Lung magnetic resonance imaging (MRI) with ultrashort echo-times (UTE-MRI) allows high-resolution and radiation-free imaging of the lung structure in cystic fibrosis (CF). In addition, the combination of elexacaftor/tezacaftor/ivacaftor (ETI) has improved CF clinical outcomes such as need for hospitalization. However, the effect on structural disease still needs longitudinal evaluation at high resolution. PURPOSE: To analyze the effects of ETI on lung structural alterations using UTE-MRI, with a focus on bronchiectasis reversibility. STUDY TYPE: Retrospective. POPULATION: Fifty CF patients (mean age 24.3 ± 9.2; 23 males). FIELD STRENGTH/SEQUENCE: 1.5 T, UTE-MRI. ASSESSMENT: All subjects completed both UTE-MRI and pulmonary function tests (PFTs) during two annual visits (M0 and M12), and 30 of them completed a CT scan. They initiated ETI treatment after M0 within a maximum of 3 months from the annual examinations. Three observers scored a clinical MRI Bhalla score on UTE-MRI. Bronchiectasis reversibility was defined as a reduction in both outer and inner bronchial dimensions. Correlations were searched between the Bhalla score and PFT such as the forced expiratory volume in 1 second percentage predicted (FEV1%p). STATISTICAL TESTS: Comparison was assessed using the paired t-test, correlation using the Spearman correlation test with a significance level of 0.05. Concordance and reproducibility were assessed using intraclass correlation coefficient (ICC). RESULTS: There was a significant improvement in MRI Bhalla score after ETI treatment. UTE-MRI demonstrated bronchiectasis reversibility in a subgroup of 18 out of 50 CF patients (36%). These patients with bronchiectasis reversibility were significantly younger, with lower severity of wall thickening but no difference in mucus plugging extent (P = 0.39) was found. The reproducibility of UTE-MRI evaluations was excellent (ICC ≥ 0.95), was concordant with CT scan (N = 30; ICC ≥ 0.90) and significantly correlated to FEV1% at PFT at M0 (N = 50; r = 0.71) and M12 (N = 50; r = 0.72). DATA CONCLUSION: UTE-MRI is a reproducible tool for the longitudinal follow-up of CF patients, allowing to quantify the response to ETI and demonstrating the reversibility of some structural alterations such as bronchiectasis in a substantial fraction of this study population. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 2.

Impact on the image quality of modified reduced field-of-view diffusion-weighted magnetic resonance imaging of pancreatic adenocarcinoma using spatially tailored two-dimensional radiofrequency pulses with a tilted excitation plane: A comparison with conventional field-of-view imaging.

PURPOSE: Modified reduced FOV diffusion-weighted imaging (DWI) using spatially-tailored 2D RF pulses with tilted excitation plane (tilted r-DWI) has been developed. The purpose of this study was to evaluate the impact on image quality and quantitative apparent diffusion coefficient (ADC) values of tilted r-DWI for pancreatic ductal adenocarcinomas (PDAC) in comparison to conventional full-FOV DWI (f-DWI). METHODS: This retrospective study included 21 patients (mean 70.7, range 50-85 years old) with pathologically confirmed PDAC. All MR images were obtained using 3 T systems. Two radiologists evaluated presence of blurring or ghost artifacts, susceptibility artifacts, and aliasing artifacts; anatomic visualization of the pancreas; interslice signal homogeneity; overall image quality; and conspicuity of the PDAC. For quantitative analysis, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), signal-intensity ratio (SIR) and ADC values were measured using regions of interest. RESULTS: All image quality scores except aliasing artifacts in tilted r-DWI were significantly higher than those in f-DWI (p < 0.01). The CNR and SIR of PDAC were significantly higher in tilted r-DWI than in f-DWI (6.7 ± 4.4 vs. 4.7 ± 3.9, 2.02 ± 0.72 vs. 1.72 ± 0.60, p < 0.01). Conversely, the SNR of PDAC in tilted r-DWI was significantly lower than that in f-DWI (56.0 ± 33.1 vs. 113.6 ± 67.3, p < 0.01). No significant difference was observed between mean ADC values of the PDAC calculated from tilted r-DWI (tilted r-ADC) and those from f-DWI (f-ADC) (1225 ± 250 vs. 1294 ± 302, p = 0.11). CONCLUSION: The r-DWI using 2D RF techniques with a tilted excitation plane was shown to significantly improve the image quality and CNR and reduce image artifacts compared to f-DWI techniques in MRI evaluations of PDAC without significantly affecting ADC values.

Evaluation of diffusion-weighted magnetic resonance imaging of the rectal cancers: comparison between modified reduced field-of-view single-shot echo-planar imaging with tilted two-dimensional radiofrequency excitation pulses and conventional full field-of-view readout-segmented echo-planar imaging.

PURPOSE: To evaluate the image quality qualitatively and quantitatively, as well as apparent diffusion coefficient (ADC) values of modified reduced field-of-view diffusion-weighted magnetic resonance imaging (MRI) using spatially tailored two-dimensional radiofrequency pulses with tilted excitation plane (tilted r-DWI) based on single-shot echo planar imaging (SS-EPI) compared with full-size field-of-view DWI (f-DWI) using readout segmented (RS)-EPI in patients with rectal cancer. MATERIALS AND METHODS: Twenty-two patients who underwent an MRI for further evaluation of rectal cancer were included in this retrospective study. All MR images were analyzed to compare image quality, lesion conspicuity, and artifacts between f-DWI with RS-EPI and tilted r-DWI with SS-EPI. Signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and ADC values were also compared. The Wilcoxon signed-rank test or paired t test was performed to compare the qualitative and quantitative assessments. RESULTS: All image quality scores, except aliasing artifacts, were significantly higher (p < 0.01 for all) in tilted r-DWI than f-DWI with RS-EPI. CNR in tilted r-DWI was significantly higher than in f-DWI with RS-EPI (p < 0.01), while SNR was not significantly different. Regarding the ADC values, no significant difference was observed between tilted r-DWI and f-DWI with RS-EPI (p = 0.27). CONCLUSION: Tilted r-DWI provides a better image quality with fewer artifacts and higher rectal lesion conspicuity than f-DWI with RS-EPI, indicating the feasibility of this MR sequence in evaluating rectal cancer in clinical practice.

Accelerated diffusion-weighted imaging of the prostate using deep learning image reconstruction: A retrospective comparison with standard diffusion-weighted imaging.

PURPOSE: Routine multiparametric MRI of the prostate reduces overtreatment and increases sensitivity in the diagnosis of the most common solid cancer in men. However, the capacity of MRI systems is limited. Here we investigate the ability of deep learning image reconstruction to accelerate time consuming diffusion-weighted imaging (DWI) acquisition while maintaining diagnostic image quality. METHOD: In this retrospective study, raw data of DWI sequences of consecutive patients undergoing MRI of the prostate at a tertiary care hospital in Germany were reconstructed using standard and deep learning reconstruction. To simulate a shortening of acquisition times by 39 %, one instead of two and six instead of ten averages were used in the reconstruction of b = 0 and 1000 s/mm2 images, respectively. Image quality was assessed by three radiologists and objective image quality metrics. RESULTS: After the application of exclusion criteria, 35 out of 147 patients examined between September 2022 and January 2023 were included in this study. The radiologists perceived less image noise on deep learning reconstructed images at b = 0 s/mm2 images and ADC maps with good inter-reader agreement. Signal-to-noise ratios were similar overall with discretely reduced values in the transitional zone after deep learning reconstruction. CONCLUSIONS: An acquisition time reduction of 39 % without loss in image quality is feasible in DWI of the prostate when using deep learning image reconstruction.

Generating High-Resolution Synthetic CT from Lung MRI with Ultrashort Echo Times: Initial Evaluation in Cystic Fibrosis.

Background Lung MRI with ultrashort echo times (UTEs) enables high-resolution and radiation-free morphologic imaging; however, its image quality is still lower than that of CT. Purpose To assess the image quality and clinical applicability of synthetic CT images generated from UTE MRI by a generative adversarial network (GAN). Materials and Methods This retrospective study included patients with cystic fibrosis (CF) who underwent both UTE MRI and CT on the same day at one of six institutions between January 2018 and December 2022. The two-dimensional GAN algorithm was trained using paired MRI and CT sections and tested, along with an external data set. Image quality was assessed quantitatively by measuring apparent contrast-to-noise ratio, apparent signal-to-noise ratio, and overall noise and qualitatively by using visual scores for features including artifacts. Two readers evaluated CF-related structural abnormalities and used them to determine clinical Bhalla scores. Results The training, test, and external data sets comprised 82 patients with CF (mean age, 21 years ± 11 [SD]; 42 male), 28 patients (mean age, 18 years ± 11; 16 male), and 46 patients (mean age, 20 years ± 11; 24 male), respectively. In the test data set, the contrast-to-noise ratio of synthetic CT images (median, 303 [IQR, 221-382]) was higher than that of UTE MRI scans (median, 9.3 [IQR, 6.6-35]; P < .001). The median signal-to-noise ratio was similar between synthetic and real CT (88 [IQR, 84-92] vs 88 [IQR, 86-91]; P = .96). Synthetic CT had a lower noise level than real CT (median score, 26 [IQR, 22-30] vs 42 [IQR, 32-50]; P < .001) and the lowest level of artifacts (median score, 0 [IQR, 0-0]; P < .001). The concordance between Bhalla scores for synthetic and real CT images was almost perfect (intraclass correlation coefficient, ≥0.92). Conclusion Synthetic CT images showed almost perfect concordance with real CT images for the depiction of CF-related pulmonary alterations and had better image quality than UTE MRI. Clinical trial registration no. NCT03357562 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Schiebler and Glide-Hurst in this issue.

Lung Function in Patients with Cystic Fibrosis before and during CFTR-Modulator Therapy Using 3D Ultrashort Echo Time MRI.

Background The triple combination of the cystic fibrosis transmembrane regulator (CFTR) modulators elexacaftor, tezacaftor, and ivacaftor (hereafter, elexacaftor/tezacaftor/ivacaftor) has a positive effect on lung function in patients with cystic fibrosis (CF). Purpose To compare three-dimensional (3D) ultrashort echo time (UTE) MRI functional lung data to common functional lung parameters in assessing lung function in patients with CF undergoing elexacaftor/tezacaftor/ivacaftor therapy. Materials and Methods In this prospective feasibility study, 16 participants with CF consented to undergo pulmonary MRI with a breath-hold 3D UTE sequence at baseline (April 2018-June 2019) and follow-up (April-July 2021). Eight participants received elexacaftor/tezacaftor/ivacaftor after baseline, and eight participants with unchanged treatment served as the control group. Lung function was assessed with body plethysmography and lung clearance index (LCI). Image-based functional lung parameters, such as ventilation inhomogeneity and ventilation defect percentage (VDP), were calculated from signal intensity change between MRI scans at inspiration and expiration. Metrics at baseline and follow-up were compared within groups (permutation test), correlation was tested (Spearman rank correlation), and 95% CIs were calculated (bootstrapping technique). Results MRI ventilation inhomogeneity correlated with LCI at baseline (r = 0.92, P < .001) and follow-up (r = 0.81, P = .002). Mean MRI ventilation inhomogeneity (baseline, 0.74 ± 0.15 [SD]; follow-up, 0.64 ± 0.11; P = .02) and mean VDP (baseline, 14.1% ± 7.4; follow-up, 8.5% ± 3.3; P = .02) decreased from baseline to follow-up in the treatment group. Lung function was stable over time (mean LCI: 9.3 turnovers ± 4.1 at baseline vs 11.5 turnovers ± 7.4 at follow-up; P = .34) in the control group. In all participants, correlation of forced expiratory volume in 1 second with MRI ventilation inhomogeneity was good at baseline (r = -0.61, P = .01) but poor during follow-up (r = -0.06, P = .82). Conclusion Noncontrast 3D UTE lung MRI functional parameters of ventilation inhomogeneity and VDP can be used to assess lung function over time in patients with CF and can add regional information to established global parameters, such as LCI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Iwasawa in this issue.

Novel deep-learning-based diffusion weighted imaging sequence in 1.5 T breast MRI.

PURPOSE: This study aimed to assess the technical feasibility, the impact on image quality, and the acquisition time (TA) of a new deep-learning-based reconstruction algorithm in diffusion weighted imaging (DWI) of breast magnetic resonance imaging (MRI). METHODS: Retrospective analysis of 55 female patients who underwent breast DWI at 1.5 T. Raw data were reconstructed using a deep-learning (DL) reconstruction algorithm on a subset of the acquired averages, therefore a reduction of TA. Clinically used standard DWI sequence (DWIStd) and the DL-reconstructed images (DWIDL) were compared. Two radiologists rated the image quality of b800 and ADC images, using a Likert-scale from 1 to 5 with 5 being considered perfect image quality. Signal intensities were measured by placing a region of interest (ROI) at the same position in both sequences. RESULTS: TA was reduced by 40 % in DWIDL, compared to DWIStd, DWIDL improved noise and sharpness while maintaining contrast, the level of artifacts, and diagnostic confidence. There were no differences regarding the signal intensity values of the apparent diffusion coefficient (ADC), (p = 0.955), b50-values (p = 0.070) and b800-values (p = 0.415) comparing standard and DL-imaging. Lesion assessment showed no differences regarding the number of lesions in ADC and DWI (both p = 1.000) and regarding the lesion diameter in DWI (p = 0.961;0.972) and ADC (p = 0.961;0.972). CONCLUSIONS: The novel deep-learning-based reconstruction algorithm significantly reduces TA in breast DWI, while improving sharpness, reducing noise, and maintaining a comparable level of image quality, artifacts, contrast, and diagnostic confidence. DWIDL does not influence the quantifiable parameters.

Accelerated Diffusion-Weighted Imaging in 3 T Breast MRI Using a Deep Learning Reconstruction Algorithm With Superresolution Processing: A Prospective Comparative Study.

OBJECTIVES: Diffusion-weighted imaging (DWI) enhances specificity in multiparametric breast MRI but is associated with longer acquisition time. Deep learning (DL) reconstruction may significantly shorten acquisition time and improve spatial resolution. In this prospective study, we evaluated acquisition time and image quality of a DL-accelerated DWI sequence with superresolution processing (DWI DL ) in comparison to standard imaging including analysis of lesion conspicuity and contrast of invasive breast cancers (IBCs), benign lesions (BEs), and cysts. MATERIALS AND METHODS: This institutional review board-approved prospective monocentric study enrolled participants who underwent 3 T breast MRI between August and December 2022. Standard DWI (DWI STD ; single-shot echo-planar DWI combined with reduced field-of-view excitation; b-values: 50 and 800 s/mm 2 ) was followed by DWI DL with similar acquisition parameters and reduced averages. Quantitative image quality was analyzed for region of interest-based signal-to-noise ratio (SNR) on breast tissue. Apparent diffusion coefficient (ADC), SNR, contrast-to-noise ratio, and contrast (C) values were calculated for biopsy-proven IBCs, BEs, and for cysts. Two radiologists independently assessed image quality, artifacts, and lesion conspicuity in a blinded independent manner. Univariate analysis was performed to test differences and interrater reliability. RESULTS: Among 65 participants (54 ± 13 years, 64 women) enrolled in the study, the prevalence of breast cancer was 23%. Average acquisition time was 5:02 minutes for DWI STD and 2:44 minutes for DWI DL ( P < 0.001). Signal-to-noise ratio measured in breast tissue was higher for DWI STD ( P < 0.001). The mean ADC values for IBC were 0.77 × 10 -3 ± 0.13 mm 2 /s in DWI STD and 0.75 × 10 -3 ± 0.12 mm 2 /s in DWI DL without significant difference when sequences were compared ( P = 0.32). Benign lesions presented with mean ADC values of 1.32 × 10 -3 ± 0.48 mm 2 /s in DWI STD and 1.39 × 10 -3 ± 0.54 mm 2 /s in DWI DL ( P = 0.12), and cysts presented with 2.18 × 10 -3 ± 0.49 mm 2 /s in DWI STD and 2.31 × 10 -3 ± 0.43 mm 2 /s in DWI DL . All lesions presented with significantly higher contrast in the DWI DL ( P < 0.001), whereas SNR and contrast-to-noise ratio did not differ significantly between DWI STD and DWI DL regardless of lesion type. Both sequences demonstrated a high subjective image quality (29/65 for DWI STD vs 20/65 for DWI DL ; P < 0.001). The highest lesion conspicuity score was observed more often for DWI DL ( P < 0.001) for all lesion types. Artifacts were scored higher for DWI DL ( P < 0.001). In general, no additional artifacts were noted in DWI DL . Interrater reliability was substantial to excellent (k = 0.68 to 1.0). CONCLUSIONS: DWI DL in breast MRI significantly reduced scan time by nearly one half while improving lesion conspicuity and maintaining overall image quality in a prospective clinical cohort.

Validation of an MR-based multimodal method for molecular composition and proton stopping power ratio determination using ex vivo animal tissues and tissue-mimicking phantoms.

Objective. Range uncertainty in proton therapy is an important factor limiting clinical effectiveness. Magnetic resonance imaging (MRI) can measure voxel-wise molecular composition and, when combined with kilovoltage CT (kVCT), accurately determine mean ionization potential (Im), electron density, and stopping power ratio (SPR). We aimed to develop a novel MR-based multimodal method to accurately determine SPR and molecular compositions. This method was evaluated in tissue-mimicking andex vivoporcine phantoms, and in a brain radiotherapy patient.Approach. Four tissue-mimicking phantoms with known compositions, two porcine tissue phantoms, and a brain cancer patient were imaged with kVCT and MRI. Three imaging-based values were determined: SPRCM(CT-based Multimodal), SPRMM(MR-based Multimodal), and SPRstoich(stoichiometric calibration). MRI was used to determine two tissue-specific quantities of the Bethe Bloch equation (Im, electron density) to compute SPRCMand SPRMM. Imaging-based SPRs were compared to measurements for phantoms in a proton beam using a multilayer ionization chamber (SPRMLIC).Main results. Root mean square errors relative to SPRMLICwere 0.0104(0.86%), 0.0046(0.45%), and 0.0142(1.31%) for SPRCM, SPRMM, and SPRstoich, respectively. The largest errors were in bony phantoms, while soft tissue and porcine tissue phantoms had <1% errors across all SPR values. Relative to known physical molecular compositions, imaging-determined compositions differed by approximately ≤10%. In the brain case, the largest differences between SPRstoichand SPRMMwere in bone and high lipids/fat tissue. The magnitudes and trends of these differences matched phantom results.Significance. Our MR-based multimodal method determined molecular compositions and SPR in various tissue-mimicking phantoms with high accuracy, as confirmed with proton beam measurements. This method also revealed significant SPR differences compared to stoichiometric kVCT-only calculation in a clinical case, with the largest differences in bone. These findings support that including MRI in proton therapy treatment planning can improve the accuracy of calculated SPR values and reduce range uncertainties.

Deep Learning-Accelerated Liver Diffusion-Weighted Imaging: Intraindividual Comparison and Additional Phantom Study of Free-Breathing and Respiratory-Triggering Acquisitions.

OBJECTIVES: Deep learning-reconstructed diffusion-weighted imaging (DL-DWI) is an emerging promising time-efficient method for liver evaluation, but analyses regarding different motion compensation strategies are lacking. This study evaluated the qualitative and quantitative features, sensitivity for focal lesion detection, and scan time of free-breathing (FB) DL-DWI and respiratory-triggered (RT) DL-DWI compared with RT conventional DWI (C-DWI) in the liver and a phantom. MATERIALS AND METHODS: Eighty-six patients indicated for liver MRI underwent RT C-DWI, FB DL-DWI, and RT DL-DWI with matching imaging parameters other than the parallel imaging factor and number of averages. Two abdominal radiologists independently assessed qualitative features (structural sharpness, image noise, artifacts, and overall image quality) using a 5-point scale. The signal-to-noise ratio (SNR) along with the apparent diffusion coefficient (ADC) value and its standard deviation (SD) were measured in the liver parenchyma and a dedicated diffusion phantom. For focal lesions, per-lesion sensitivity, conspicuity score, SNR, and ADC value were evaluated. Wilcoxon signed rank test and repeated-measures analysis of variance with post hoc test revealed the difference in DWI sequences. RESULTS: Compared with RT C-DWI, the scan times for FB DL-DWI and RT DL-DWI were reduced by 61.5% and 23.9%, respectively, with statistically significant differences between all 3 pairs (all P 's < 0.001). Respiratory-triggered DL-DWI showed a significantly sharper liver margin, less image noise, and more minor cardiac motion artifact compared with RT C-DWI (all P 's < 0.001), whereas FB DL-DWI showed more blurred liver margins and poorer intrahepatic vessels demarcation than RT C-DWI. Both FB- and RT DL-DWI showed significantly higher SNRs than RT C-DWI in all liver segments (all P 's < 0.001). There was no significant difference in overall ADC values across DWI sequences in the patient or phantom, with the highest value recorded in the left liver dome by RT C-DWI. The overall SD was significantly lower with FB DL-DWI and RT DL-DWI than RT C-DWI (all P 's ≤ 0.003). Respiratory-triggered DL-DWI showed a similar per-lesion sensitivity (0.96; 95% confidence interval, 0.90-0.99) and conspicuity score to those of RT C-DWI and significantly higher SNR and contrast-to-noise ratio values ( P ≤ 0.006). The per-lesion sensitivity of FB DL-DWI (0.91; 95% confidence interval, 0.85-0.95) was significantly lower than that of RT C-DWI ( P = 0.001), with a significantly lower conspicuity score. CONCLUSIONS: Compared with RT C-DWI, RT DL-DWI demonstrated superior SNR, comparable sensitivity for focal hepatic lesions, and reduced acquisition time, making it a suitable alternative to RT C-DWI. Despite FB DL-DWI's weakness in motion-related challenges, further refinement could potentiate FB DL-DWI in the context of abbreviated screening protocols, where time efficiency is a high priority.