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.

Preliminary Experience with Virtual Monoenergetic Imaging and Iodine Mapping in the Primary Staging of Endometrial Cancer.

This study investigated whether virtual monoenergetic images (VMIs) and iodine mapping based on dual-energy CT (DECT) provide advantages in the assessment of endometrial cancer. A dual-source DECT was performed for primary staging of histologically proven endometrioid adenocarcinoma in 21 women (66.8 ± 12.0 years). In addition to iodine maps, VMIs at 40, 50, 60, 70, and 80 keV were reconstructed from polyenergetic images (PEIs). Objective analysis comprised the measurement of tumor contrast, contrast-to-noise ratio, and normalized iodine concentration (NIC). In addition, three radiologists independently rated tumor conspicuity. The highest tumor contrast (106.6 ± 45.0 HU) and contrast-to-noise ratio (4.4 ± 2.0) was established for VMIs at 40 keV. Tumor contrast in all VMIs ≤ 60 keV was higher than in PEIs (p < 0.001). The NIC of malignant tissue measured in iodine maps was substantially lower compared with a healthy myometrium (0.3 ± 0.1 versus 0.6 ± 0.1 mg/mL; p < 0.001). Tumor conspicuity was highest in 40 keV datasets, whereas no difference was found among PEIs and VMIs at 60 and 70 keV (p ≥ 0.334). Interobserver agreement was good, indicated by an intraclass correlation coefficient of 0.824 (0.772-0.876; p < 0.001). In conclusion, computation of VMIs at 40 keV and color-coded iodine maps aids the assessment of endometroid adenocarcinoma in primary staging.

Breast lesion morphology assessment with high and standard b values in diffusion-weighted imaging at 3 Tesla.

INTRODUCTION: With increasing spatial resolution, diffusion-weighted imaging (DWI) may be suitable for morphologic lesion characterization in breast MRI - an area that has traditionally been occupied by dynamic contrast-enhanced imaging (DCE). This investigation compared DWI with b values of 800 and 1600 s/mm2 to DCE for lesion morphology assessment in high-resolution breast MRI at 3 Tesla. MATERIAL AND METHODS: Multiparametric breast MRI was performed in 91 patients with 93 histopathologically proven lesions (31 benign, 62 malignant). Two radiologists independently evaluated three datasets per patient (DWIb800; DWIb1600; DCE) and assessed lesion visibility and BIRADS morphology criteria. Diagnostic accuracy was compared among readers and datasets using Cochran's Q test and pairwise post-hoc McNemar tests. Bland-Altman analyses were conducted for lesion size comparisons. RESULTS: Discrimination of carcinomas was superior compared to benign findings in both DWIb800 and DWIb1600 (p < 0.001) with no b value-dependent difference. Similarly, assessability of mass lesions was better than of non-mass lesions, irrespective of b value (p < 0.001). Intra-reader reliability for the analysis of morphologic BIRADS criteria among DCE and DWI datasets was at least moderate (Fleiss κ≥0.557), while at least substantial inter-reader agreement was ascertained over all assessed categories (κ≥0.776). In pairwise Bland-Altman analyses, the measurement bias between DCE and DWIb800 was 0.7 mm, whereas the difference between DCE and DWIb1600 was 2.8 mm. DWIb1600 allowed for higher specificity than DCE (p = 0.007/0.062). CONCLUSIONS: DWI can be employed for reliable morphologic lesion characterization in high-resolution breast MRI. High b values increase diagnostic specificity, while lesion size assessment is more precise with standard 800 s/mm2 images.

Tin-filtered 100 kV Ultra-low-dose Abdominal CT for Calculi Detection in the Urinary Tract: A Comparative Study of 510 Cases.

OBJECTIVES: For detection of urinary calculi, unenhanced low-dose computed tomography is the method of choice, outperforming radiography and ultrasound. This retrospective monocentric study aims to compare a clinically established, dedicated low-dose imaging protocol for detection of urinary calculi with an ultra-low-dose protocol employing tin prefiltration at a standardized tube voltage of 100 kVp. METHODS: Two study arms included a total of 510 cases. The "low-dose group" was comprised of 290 individuals (96 women; age 49 ± 16 years; BMI 27.23 ± 5.60 kg/m2). The "ultra-low-dose group" with Sn100 kVp consisted of 220 patients (84 women; age 47 ± 17 years; BMI 26.82 ± 5.62 kg/m2). No significant difference was ascertained for comparison of age (p = 0.132) and BMI (p = 0.207) between cohorts. For quantitative assessment of image quality, image noise was assessed. RESULTS: No significant difference regarding frequency of calculi detection was found between groups (p = 0.596). Compared to the low-dose protocol (3.08 mSv; IQR 2.22-4.02 mSv), effective dose was reduced by 62.35% with the ultra-low-dose protocol employing spectral shaping (1.16 mSv; IQR 0.89-1.54 mSv). Image noise was calculated at 18.90 (IQR 17.39-21.20) for the low-dose protocol and at 18.69 (IQR 17.30-21.62) for the ultra-low-dose spectral shaping protocol. No significant difference was ascertained for comparison between groups (p = 0.793). CONCLUSION: For urinary calculi detection, ultra-low-dose scans utilizing spectral shaping by means of tin prefiltration at 100 kVp allow for considerable dose reduction of up to 62% over conventional low-dose CT without compromising image quality.

Diffusion-weighted Breast MRI at 3 Tesla: Improved Lesion Visibility and Image Quality with a Combination of Water-excitation and Spectral Fat Saturation.

RATIONALE AND OBJECTIVES: In breast MRI with diffusion-weighted imaging (DWI), fat suppression is essential for eliminating the dominant lipid signal. This investigation evaluates a combined water-excitation-spectral-fatsat method (WEXfs) versus standard spectral attenuated inversion recovery (SPAIR) in high-resolution 3-Tesla breast MRI. MATERIALS AND METHODS: Multiparametric breast MRI with 2 echo-planar DWI sequences was performed in 83 patients (50.1 ± 12.6 years) employing either WEXfs or SPAIR for fat signal suppression. Three radiologists assessed overall DWI quality and delineability of 88 focal lesions (28 malignant, 60 benign) on images with b values of 800 and 1600 s/mm2, as well as apparent diffusion coefficient (ADC) maps. For each fat suppression method and b value, the longest lesion diameter was determined in addition to measuring the signal intensity in DWI and ADC value in standardized regions of interest. RESULTS: Regardless of b values, image quality (all p < 0.001) and lesion delineability (all p ≤ 0.003) with WEXfs-DWI were deemed superior compared to SPAIR-DWI in benign and malignant lesions. Irrespective of lesion characterization, WEXfs-DWI provided superior signal-to-noise, contrast-to-noise and signal-intensity ratios with 1600 s/mm2 (all p ≤ 0.05). The lesion size difference between contrast-enhanced T1 subtraction images and DWI was smaller for WEXfs compared to SPAIR fat suppression (all p ≤ 0.007). The mean ADC value in malignant lesions was lower for WEXfs-DWI (p < 0.001), while no significant ADC difference was ascertained between both techniques in benign lesions (p = 0.947). CONCLUSION: WEXfs-DWI provides better subjective and objective image quality than standard SPAIR-DWI, resulting in a more accurate estimation of benign and malignant lesion size.

Artificial-intelligence-enhanced synthetic thick slabs versus standard slices in digital breast tomosynthesis.

OBJECTIVES: Digital breast tomosynthesis (DBT) can provide additional information over mammography, albeit at the cost of prolonged reading time. This study retrospectively investigated the impact of reading enhanced synthetic 6 mm slabs instead of standard 1 mm slices on interpretation time and readers performance in a diagnostic assessment centre. METHODS: Three radiologists (R1-3; 6/4/2 years of breast imaging experience) reviewed 111 diagnostic DBT examinations. Two datasets were interpreted independently for each patient, with one set containing artificial-intelligence-enhanced synthetic 6 mm slabs with 3 mm overlap, while the other set comprised standard 1 mm slices. Blinded to histology and follow-up, readers noted individual BIRADS categories and diagnostic confidence while reading time was recorded. Among the 111 examinations, 70 findings were histopathologically correlated including 56 malignancies. RESULTS: No significant difference was found between BIRADS categories assigned based on 6 mm vs 1 mm datasets (p ≥ 0.317). Diagnostic accuracy was comparable for 6 mm and 1 mm readings (R1: 87.0% vs 87.0%; R2: 86.1% vs 87.0%; R3: 80.0% vs 84.4%; p ≥ 0.125) with high interrater agreement (intraclass correlation coefficient 0.848 vs 0.865). One reader reported higher confidence with 1 mm slices (R1: p = 0.033). Reading time was substantially shorter when interpreting 6 mm slabs compared to 1 mm slices (R1: 33.5 vs 46.2; R2: 49.1 vs 64.8; R3: 39.5 vs 67.2 sec; all p < 0.001). CONCLUSIONS: Artificial-intelligence-enhanced synthetic 6 mm slabs allow for substantial interpretation time reduction in diagnostic DBT without a decrease in reader accuracy. ADVANCES IN KNOWLEDGE: A simplified slab-only protocol instead of 1 mm slices may offset the higher reading time without a loss of diagnosis-relevant image information in first and second readings. Further evaluations are required regarding workflow implications, particularly in screening settings.