Deep learning reconstruction accelerated reduced field-of-view DWI in rectal cancer: mucosa-submucosa-muscularis visualization and T staging

This study compared the imaging quality, diagnostic accuracy, and apparent diffusion coefficient (ADC) values of reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) and full field-of-view (fFOV) single-shot echo-planar imaging with regard to patients with nonmuscle-invasive or muscle-invasive bladder cancer.Thirty-nine patients with 60 bladder tumors underwent rFOV and fFOV DWI in this internal review board-approved study. Pathologic and histologic grades were determined for all tumors. Two observers rated DWI image quality using a 4-point scale. Two radiologists who were blinded to the pathology findings reviewed 3 image sets (T2-weighted alone, T2-weighted plus fFOV DWI, and T2-weighted plus rFOV DWI) and assigned T stages and confidence levels for tumors of stage T2 or higher. The image quality scores for the 2 DWI sequences were assessed using the Wilcoxon signed-rank test. Differences in the diagnostic accuracy, sensitivity, and specificity for each image set were evaluated using the McNemar test. Differences in performance were analyzed by comparing the areas under the receiver-operating characteristic curves (ie, the Az values). A Mann–Whitney U test was used to compare the mean ADCs and the relationship between tumor stage and histologic grade.Image quality scores were significantly higher for rFOV (mean = 3.62) than for fFOV DWI (2.98; P < 0.001). The pooled diagnostic accuracies were 57%, 70%, and 78% for the T2-weighted alone images, the T2-weighted plus fFOV DWI images, and the T2-weighted plus rFOV DWI images, respectively. The overall accuracy, specificity, and Az for diagnosing T2 or higher stages were significantly improved by adding rFOV DWI (P < 0.05). The mean ADC values of the muscle-invasive and G3 grade bladder cancers were significantly lower than those of the nonmuscle-invasive tumors and G1 grade cancers, regardless of DWI sequence (P < 0.01).rFOV DWI is superior to fFOV DWI with respect to image quality and diagnostic accuracy. ADC values might be useful for distinguishing nonmuscle-invasive from muscle-invasive cancers, and G1 from G3 grade lesions.

ObjectivesTo investigate whether reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) with deep learning reconstruction (DLR) can improve the accuracy of evaluating muscle invasion using VI-RADS.MethodsEighty-six bladder cancer participants who were evaluated by conventional full field-of-view (fFOV) DWI, standard rFOV (rFOVSTA) DWI, and fast rFOV with DLR (rFOVDLR) DWI were included in this prospective study. Tumors were categorized according to the vesical imaging reporting and data system (VI-RADS). Qualitative image quality scoring, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and ADC value were evaluated. Friedman test with post hoc test revealed the difference across the three DWIs. Receiver operating characteristic analysis was performed to calculate the areas under the curve (AUCs).ResultsThe AUC of the rFOVSTA DWI and rFOVDLR DWI were higher than that of fFOV DWI. rFOVDLR DWI reduced the acquisition time from 5:02 min to 3:25 min, and showed higher scores in overall image quality with higher CNR and SNR, compared to rFOVSTA DWI (p < 0.05). The mean ADC of all cases of rFOVSTA DWI and rFOVDLR DWI was significantly lower than that of fFOV DWI (all p < 0.05). There was no difference in mean ADC value and the AUC for evaluating muscle invasion between rFOVSTA DWI and rFOVDLR DWI (p > 0.05).ConclusionsrFOV DWI with DLR can improve the diagnostic accuracy of fFOV DWI for evaluating muscle invasion. Applying DLR to rFOV DWI reduced the acquisition time and improved overall image quality while maintaining ADC value and diagnostic accuracy.Critical relevance statementThe diagnostic performance and image quality of full field-of-view DWI, reduced field-of-view (rFOV) DWI with and without DLR were compared. DLR would benefit the wide clinical application of rFOV DWI by reducing the acquisition time and improving the image quality.Key PointsDeep learning reconstruction (DLR) can reduce scan time and improve image quality.Reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) with DLR showed better diagnostic performances than full field-of-view DWI.There was no difference of diagnostic accuracy between rFOV DWI with DLR and standard rFOV DWI.Graphical

To compare image quality (IQ) of reduced field-of-view (rFOV) and full FOV (fFOV) diffusion-weighted imaging (DWI) sequences at 3T, with histological T staging of rectal cancer as a reference standard. In all, 81 patients with rectal cancer received magnetic resonance (MR) scans (3.0T), including both rFOV and fFOV DWI sequences. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were quantitatively evaluated using the paired t-test. Two radiologists independently assessed subjective IQ parameters, including image sharpness, distortion, artifacts, lesion conspicuity, and overall subjective IQ of both sequences. The Wilcoxon signed rank test was used to compare subjective IQ scores and tumor apparent diffusion coefficients (ADCs) between DWI sequences. Spearman correlation analysis was used to correlate ADC values and corresponding T staging of rectal cancer. CNR was significantly higher in rFOV DWI than in fFOV DWI (7.15 ± 2.77 vs. 5.39 ± 2.08, P < 0.001). SNR was significantly higher in rFOV DWI than in fFOV DWI (44.17 ± 11.01 vs. 34.76 ± 13.30, P < 0.001). The subjective IQ parameters of rFOV DWI sequence were rated superior to those of fFOV DWI sequence by both readers (P < 0.001). No significant differences between mean tumor ADC values of both sequences (0.991 ± 0.121 vs. 0.100 ± 0.126 × 10-3 mm2 /s, P = 0.617) were noted. Apart from T1 stage, T staging of rectal cancer was inversely correlated with ADC values of rFOV DWI (r = -0.688, P < 0.001) and fFOV DWI sequences (r = -0.641, P < 0.001). The rFOV DWI sequence provided significantly better IQ and lesion conspicuity than the fFOV DWI sequence. In addition, rFOV and fFOV DWI sequences can be used in evaluation of histological T staging of rectal cancer. 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:967-975.

The goals of the meticulous selection of patients withhepatocellular carcinoma (HCC) for liver transplanta-tion (LT) are to minimize the incidence of tumor recur-rence after transplantation and to improve patients’survival. Tumor invasion into vascular structures is aknown risk factor for tumor recurrence after LT. Mac-rovascular invasion, which is defined as the presenceof a tumor thrombus in a hepatic or portal vein, canbe detected on preoperative cross-sectional imaging. Itis considered an absolute contraindication to LT. Con-versely, microvascular invasion (MVI) by definitioncan be definitively diagnosed only by histopathology.Several studies have shown that MVI is associatedwith HCC recurrence within 1 year of transplanta-tion.

Cervical cancer (CC) is the second most common cancer in women worldwide. Diffusion-weighted imaging (DWI) plays an important role in the diagnosis of CC, but the conventional techniques are affected by many factors. To compare reduced-field-of-view (r-FOV) and full-field-of-view (f-FOV) DWI in the diagnosis of CC. Preoperative magnetic resonance imaging (MRI) with r-FOV and f-FOV DWI images were collected. Two radiologists reviewed the images using a subjective 4-point scale for anatomical features, magnetic susceptibility artifacts, visual distortion, and overall diagnostic confidence for r-FOV and f-FOV DWI. The objective features included the region of interest (ROI) signal intensity of the cervical lesion (SIlesion) and gluteus maximus muscle (SIgluteus), standard deviation of the background noise (SDbackground), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). The differences of measured apparent diffusion coefficient (ADC) values between the two examinations in pathological grades and FIGO tumor stages were compared. A total of 200 patients were included (170 with squamous cell carcinoma and 30 with adenocarcinoma). The scores of anatomical features, magnetic susceptibility artifacts, visual distortion, and overall diagnostic confidence for r-FOV DWI were significantly higher than those for f-FOV DWI. There was no difference in SNR and CNR between r-FOV DWI and f-FOV DWI. There were significant differences in ADC values between the two groups in all comparisons (P < 0.05). Compared with f-FOV DWI, r-FOV DWI might provide clearer imaging, fewer artifacts, less distortion, and higher image quality for the diagnosis of CC and might assist in the detection of CC.

Application of bi-planar reduced field-of-view DWI (rFOV DWI) in the assessment of muscle-invasiveness of bladder cancer

PurposeTo compare image quality and diagnostic performance among SS-EPI diffusion weighted imaging (DWI), multi-shot (MS) EPI DWI, and reduced field-of-view (rFOV) DWI for muscle-invasive bladder cancer (MIBC).Materials and methodsThis retrospective study included 73 patients with bladder cancer who underwent multiparametric MRI in our referral center between August 2020 and February 2023. Qualitative image assessment was performed in 73; and quantitative assessment was performed in 66 patients with maximum lesion diameter > 10 mm. The diagnostic performance of the imaging finding of muscle invasion was evaluated in 47 patients with pathological confirmation of MIBC. T2-weighted imaging, SS-EPI DWI, MS-EPI DWI, rFOV DWI, and dynamic contrast-enhanced imaging were acquired with 3 T-MRI. Qualitative image assessment was performed by three readers who rated anatomical distortion, clarity of bladder wall, and lesion conspicuity using a four-point scale. Quantitative assessment included calculation of SNR and CNR, and grading of the presence of muscle layer invasion according to the VI-RADS diagnostic criteria. Wilcoxon matched pairs signed rank test was used to compare qualitative and quantitative image quality. McNemar test and receiver-operating characteristic analysis were used to compare diagnostic performance.ResultsAnatomical distortion was less in MS-EPI DWI, rFOV DWI, and SS-EPI DWI, in that order with significant difference. Clarity of bladder wall was greater for MS-EPI DWI, SS-EPI DWI, and rFOV DWI, in that order. There were significant differences between any two combinations of the three DWI types, except between SS-EPI DWI and MS-EPI in Reader 1. Lesion conspicuity, diagnostic performance, SNR and CNR were not significantly different among the three DWI types.ConclusionsAmong the three DWI sequences evaluated, MS-EPI DWI showed the least anatomical distortion and superior bladder wall delineation but no improvement in diagnostic performance for MIBC. MS-EPI DWI may be considered for additional imaging if SS-EPI DWI is of poor quality.

To explore the stability and repeatability of diffusion-weighted imaging (DWI) of normal pancreas with different field of views (FOV) on 5.0 T magnetic resonance imaging (MRI) system. Twenty healthy subjects underwent two sessions of large FOV (lFOV) and reduced FOV (rFOV) DWI sequence scanning. Two radiologists measured the apparent diffusion coefficient (ADC) values and the signal-to-noise ratio (SNR) of the pancreatic head, body, and tail on DWI images, simultaneously, using a 5-point scale, evaluate the artifacts and image quality. One radiologist re-measured the ADC on DWI images again after a 4-week interval. The test-retest repeatability of two scan sessions were also evaluated. Intra-observer and inter-observer at lFOV and rFOV, the ADC values were not significantly different (P > 0.05), intraclass correlation coefficients (ICCs) and coefficient of variations were excellence (ICCs 0.85–0.99, CVs < 8.0%). The ADC values were lower with rFOV than lFOV DWI for the head, body, tail, and overall pancreas. The consistency of the two scan sessions were high. The high stability and repeatability of pancreas DWI has been confirmed at 5.0 T. Scan durations are reduced while resolution and image quality are improved with rFOV DWI, which is more preferable than lFOV for routine pancreas imaging.

Comparison of reduced field-of-view diffusion-weighted imaging (DWI) and conventional DWI techniques in the assessment of Cervical carcinoma at 3.0T: Image quality and FIGO staging

Deep learning reconstruction (DLR) to improve imaging quality has already been introduced, but no studies have evaluated the effect of DLR on diffusion-weighted imaging (DWI) or intravoxel incoherent motion (IVIM) in in vitro or in vivo studies. The purpose of this study was to determine the effect of DLR for magnetic resonance imaging (MRI) in terms of image quality improvement, apparent diffusion coefficient (ADC) assessment, and IVIM index evaluation on DWI through in vitro and in vivo studies. For the in vitro study, a phantom recommended by the Quantitative Imaging Biomarkers Alliance was scanned and reconstructed with and without DLR, and 15 patients with brain tumors with normal-appearing gray and white matter examined using IVIM and reconstructed with and without DLR were included in the in vivo study. The ADCs of all phantoms for DWI with and without DLR, as well as the coefficient of variation percentage (CV%), and ADCs and IVIM indexes for each participant, were evaluated based on DWI with and without DLR by means of region-of-interest measurements. For the in vitro study, using the mean ADCs for all phantoms, a t-test was adopted to compare DWI with and without DLR. For the in vivo study, a Wilcoxon signed-rank test was used to compare the CV% between the two types of DWI. In addition, the Wilcoxon signed-rank test was used to compare the ADC, true diffusion coefficient (D), pseudodiffusion coefficient (D*), and percentage of water molecules in micro perfusion within 1 voxel (f) with and without DLR; the limits of agreement of each parameter were determined through a Bland-Altman analysis. The in vitro study identified no significant differences between the ADC values for DWI with and without DLR (P > 0.05), and the CV% was significantly different for DWI with and without DLR (P < 0.05) when b values ≥250 s/mm2 were used. The in vivo study revealed that D* and f with and without DLR were significantly different (P < 0.001). The limits of agreement of the ADC, D, and D* values for DWI with and without DLR were determined as 0.00 ± 0.51 × 10-3, 0.00 ± 0.06 × 10-3, and 1.13 ± 4.04 × 10-3 mm2/s, respectively. The limits of agreement of the f values for DWI with and without DLR were determined as -0.01 ± 0.07. Deep learning reconstruction for MRI has the potential to significantly improve DWI quality at higher b values. It has some effect on D* and f values in the IVIM index evaluation, but ADC and D values are less affected by DLR.

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 atertiary 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 anovel 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 avisual Likert score to evaluate image sharpness, artifacts, noise, overall image quality, and diagnostic confidence. Comparisons were made using the Wilcoxon signed-rank test. Aquantitative analysis of signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and apparent diffusion coefficient values (ADC) was also performed. The study included 30patients (mean age, 55 ± 19years; range, 24-84; 18men) with various pathologies. Scan times were reduced by 67% at 1.5 T and up to 55% at 3 T. The quantitative analysis revealed aminimal but statistically significant decrease in SNR and CNR in the deep learning-reconstructed images (p = 0.002 and p < 0.001, respectively). However, readers reported no significant differences between DWI and DWIDL regarding image quality parameters or diagnostic confidence for both low and high b‑value images, as well as the ADC (all p > 0.05). DL reconstruction of head and neck DWI is feasible, significantly reducing examination time without compromising image quality or diagnostic confidence. This technique enables accelerated and effective diagnostic DWI of the head and neck.

To investigate the impact of deep learning reconstruction (DLR) on the image quality of diffusion-weighted imaging (DWI) for liver and its ability to differentiate benign from malignant focal liver lesions (FLLs). Consecutive patients with suspected liver disease who underwent liver MRI between January and May 2025 were included. All patients received conventional DWI (DWIC) and an accelerated reconstructed DWI (DWIDLR) in which acquisition time was prospectively halved by reducing signal averages. Image quality was compared qualitatively using Likert scores (e.g., lesion conspicuity, overall quality) and quantitatively by measuring signal-to-noise ratio of the liver (SNRLiver) and lesion (SNRLesion), contrast-to-noise ratio (CNR), and edge rise distance (ERD). Apparent diffusion coefficient (ADC) values and diagnostic performance for differentiating benign from malignant FLLs were assessed. A total of 193 patients (128 males, 65 females; age range, 23-81 years) were included. For quantitative assessment, DWIDLR demonstrated higher SNRLiver, SNRLesion, CNR, and a shorter ERD (all p < 0.05). For qualitative assessment, DWIDLR showed improved lesion conspicuity, liver edge sharpness, and overall image quality (all p < 0.01), with no significant difference in artifacts (p = 0.08). ADC values were lower with DWIDLR for both benign and malignant FLLs (p < 0.001). In differentiating benign from malignant lesions, DWIDLR achieved better diagnostic performance (AUC: 0.921 vs. 0.904, p < 0.05). Deep learning-enhanced DWI enables a 50% reduction in acquisition time while simultaneously improving liver MRI image quality and diagnostic performance in differentiating benign from malignant FLLs. This study demonstrates that deep learning-based reconstruction enables faster, higher-quality liver MRI with improved diagnostic accuracy for focal liver lesions, supporting its integration into routine radiological practice. Diffusion-weighted liver MRI commonly suffers from limited image quality and efficiency. Deep learning reconstruction substantially improves liver MRI quality while enabling significantly shorter acquisition times. Improved lesion differentiation enables more accurate clinical diagnosis of liver lesions.

Diffusion-weighted images (DWI) obtained by echo-planar imaging (EPI) are frequently degraded by susceptibility artifacts. It has been suggested that DWI obtained by fast advanced spin-echo (FASE) or reconstructed with deep learning reconstruction (DLR) could be useful for image quality improvements. The purpose of this investigation using in vitro and in vivo studies was to determine the influence of sequence difference and of DLR for DWI on image quality, apparent diffusion coefficient (ADC) evaluation, and differentiation of malignant from benign head and neck tumors. For the in vitro study, a DWI phantom was scanned by FASE and EPI sequences and reconstructed with and without DLR. Each ADC within the phantom for each DWI was then assessed and correlated for each measured ADC and standard value by Spearman's rank correlation analysis. For the in vivo study, DWIs obtained by EPI and FASE sequences were also obtained for head and neck tumor patients. Signal-to-noise ratio (SNR) and ADC were then determined based on ROI measurements, while SNR of tumors and ADC were compared between all DWI data sets by means of Tukey's Honest Significant Difference test. For the in vitro study, all correlations between measured ADC and standard reference were significant and excellent (0.92 ≤ ρ ≤ 0.99, p < 0.0001). For the in vivo study, the SNR of FASE with DLR was significantly higher than that of FASE without DLR (p = 0.02), while ADC values for benign and malignant tumors showed significant differences between each sequence with and without DLR (p < 0.05). In comparison with EPI sequence, FASE sequence and DLR can improve image quality and distortion of DWIs without significantly influencing ADC measurements or differentiation capability of malignant from benign head and neck tumors.

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. 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. 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). 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.

Conventional vs. reduced field of view diffusion weighted imaging of the prostate: Comparison of image quality, correlation with histology, and inter-reader agreement