Accelerated single-shot T2-weighted fat-suppressed (FS) MRI of the liver with deep learning-based image reconstruction: qualitative and quantitative comparison of image quality with conventional T2-weighted FS sequence

Application of deep learning techniques for breath-hold, high-precision T2-weighted magnetic resonance imaging of the abdomen

PURPOSE

To evaluate the feasibility of a high-precision single-shot fast spin-echo (SS-FSE) sequence using the deep learning-based Precise IQ Engine (PIQE) algorithm in comparison with standard SS-FSE for T2-weighted MR imaging of the abdomen, and to compare the image quality with a multi-shot (MS)-FSE sequence using the PIQE algorithm.

METHODS

This retrospective study included 105 patients who underwent abdominal MR including T2-weighted sequences using the PIQE reconstruction algorithm. The image quality, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) in high-precision SS-FSE sequences using PIQE were compared to those in standard SS-FSE without PIQE and MS-FSE sequences using PIQE.

RESULTS

The scores for all qualitative parameters were significantly higher in high-precision SS-FSE sequence using PIQE than in standard SS-FSE sequence without PIQE (all p < 0.001). In the comparison between two high-precision sequences using PIQE, the SS-FSE sequence showed significantly better scores for the blurring, ghosts or motion/flow artifacts, conspicuity of intrahepatic structures, focal nonsolid hepatic and pancreatic cystic lesions, and overall image quality, in comparison to the MS-FSE sequence (all p < 0.001). Additionally, the SS-FSE sequence using PIQE showed significantly higher SNR of the liver and CNR of nonsolid hepatic lesions than the MS-FSE sequence using PIQE (p < 0.001).

CONCLUSIONS

A high-precision SS-FSE sequence using the PIQE algorithm is a feasible alternative to the standard FSE sequence in T2-weighted MR imaging of the abdomen. It can improve image quality, the SNR of the liver, and the ability to visualize nonsolid focal liver lesions and pancreatic cystic lesions in comparison to a high-precision MS-FSE sequence using PIQE although this study was limited by single-center design and lack of pathological confirmation.

Deep learning reconstruction of diffusion-weighted imaging with single-shot echo-planar imaging in endometrial cancer: a comparison with multi-shot echo-planar imaging

PURPOSE

To evaluate the efficacy of deep learning reconstruction (DLR) in diffusion-weighted imaging (DWI) with single-shot echo-planar imaging (SSEPI) for endometrial cancer, compared to multiplexed sensitivity-encoding (MUSE) DWI.

METHODS

We retrospectively reviewed 31 women with surgically confirmed endometrial cancer who underwent preoperative pelvic magnetic resonance imaging (MRI) including DWI. Qualitative analysis including overall image quality, susceptibility artifacts, sharpness of the uterine edge, and lesion conspicuity were compared among conventional SSEPI (SSEPI-C), SSEPI with DLR (SSEPI-DL), and MUSE using the Friedman's test. Quantitative analysis including the apparent diffusion coefficient (ADC) values, noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were also compared among three DWI sequences using the Friedman's test. In addition, the diagnostic accuracy for deep myometrial invasion was compared to three DWI sequences using Cochran's Q test.

RESULTS

The scores of overall image quality, sharpness of the uterine edge, and lesion conspicuity in SSEPI-DL were higher than SSEPI-C (p < 0.001) with no significant difference compared to MUSE (p > 0.05). Noise in SSEPI-DL was lower than SSEPI-C (p < 0.001), with no significant difference compared to MUSE (p > 0.05). SNR and CNR in SSEPI-DL were also superior to SSEPI-C (p < 0.001), and comparable to MUSE (p > 0.05). The diagnostic accuracy for detecting deep myometrial invasion showed no significant difference among SSEPI-C, SSEPI-DL and MUSE (p > 0.05).

CONCLUSION

DLR improves the image quality of DWI in endometrial cancer, demonstrating image quality equivalent to that of SSEPI-DL and MUSE. SSEPI-DL can be an alternative to MUSE in female pelvic MRI, with the benefit of significantly shortened scan time.

Multiparametric MR Urography: State of the Art

MR urography (MRU) is an imaging technique that provides comprehensive evaluation of the kidneys, pelvicalyceal system, ureters, and urinary bladder. Although CT urography (CTU) remains the first-line imaging modality for the urinary tract, incremental improvements in MRU have allowed simultaneous imaging of the kidneys, collecting system, and urinary bladder with superior contrast resolution and tissue characterization, equivalent visualization of the upper tracts, and similar specificity for detection of noncalculous diseases of the collecting system compared with that of CTU. MRU has evolved into an alternative to CTU in the broader patient population and a first-line examination in specific patient populations for which CTU is less preferred. This subgroup includes pediatric patients, pregnant patients, patients needing recurring studies, and patients with poor renal function or severe allergies to iodinated contrast material. The most common techniques encompassing a conventional MRU examination include static-fluid T2-weighted imaging and gadolinium-enhanced urothelial and excretory phase imaging. The addition of dynamic contrast-enhanced MRI and diffusion-weighted imaging results in multiparametric MRU that increases diagnostic accuracy. Newer techniques, such as parallel imaging, compressed sensing, radial k-space sampling, and deep learning-based image reconstruction, can shorten examination times and improve image quality and patient compliance. Successful MRU interpretation relies on technique optimization, knowledge of various urinary tract pathologic conditions, and familiarity with different sequences, potential interpretive pitfalls, and artifacts. ©RSNA, 2025 Supplemental material is available for this article.

Deep Learning-Accelerated Non-Contrast Abbreviated Liver MRI for Detecting Malignant Focal Hepatic Lesions: Dual-Center Validation

OBJECTIVE

To compare a deep learning (DL)-accelerated non-enhanced abbreviated MRI (AMRIDL) protocol with standard AMRI (AMRISTD) of the liver in terms of image quality and malignant focal lesion detection.

MATERIALS AND METHODS

This retrospective study included 155 consecutive patients (110 male; mean age 62.4 ± 11 years) from two sites who underwent standard liver MRI and additional AMRIDL sequences, specifically DL-accelerated single-shot fast-spin echo (SSFSEDL) and DL-accelerated diffusion-weighted imaging (DWIDL). Additional MRI phantom experiments assessed signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and apparent diffusion coefficient (ADC) values. Three reviewers evaluated AMRIDL and AMRISTD protocols for image quality using a five-point Likert scale and identified malignant hepatic lesions. Image quality scores and per-lesion sensitivities were compared between AMRIDL and AMRISTD using the Wilcoxon signed-rank test and logistic regression with generalized estimating equations, respectively.

RESULTS

Phantom experiments demonstrated comparable SNR and higher CNR for SSFSEDL compared to SSFSESTD, with similar ADC values for DWIDL and DWISTD. Among the 155 patients, 130 (83.9%) had chronic liver disease or a history of intra- or extrahepatic malignancy. Of 104 malignant focal lesions in 64 patients, 58 (55.8%) were hepatocellular carcinomas (HCCs), 38 (36.5%) were metastases, four (3.8%) were cholangiocarcinomas, and four (3.8%) were lymphomas. The pooled per-lesion sensitivity across three readers was 97.6% for AMRIDL, comparable to 97.6% for AMRISTD. Compared with AMRISTD, AMRIDL demonstrated superior image quality regarding structural sharpness, artifacts, and noise (all P < 0.001) and reduced the average scan time by approximately 50% (2 min 29 sec vs. 4 min 11 sec). In patients with chronic liver disease, AMRIDL achieved a 96.6% per-lesion sensitivity for HCC detection, similar to 96.5% for AMRISTD (P > 0.05).

CONCLUSION

The AMRIDL protocol offers comparable sensitivity for detecting malignant focal lesions, including HCC while significantly enhancing image quality and reducing scan time by approximately 50% compared to AMRISTD.

Deep-Learning-Based Reconstruction of Single-Breath-Hold 3 mm HASTE Improves Abdominal Image Quality and Reduces Acquisition Time: A Quantitative Analysis

Purpose: Breath-hold T2-weighted half-Fourier acquisition single-shot turbo spin echo (HASTE) magnetic resonance imaging (MRI) of the upper abdomen with a slice thickness below 5 mm suffers from high image noise and blurring. The purpose of this prospective study was to improve image quality and accelerate imaging acquisition by using single-breath-hold T2-weighted HASTE with deep learning (DL) reconstruction (DL-HASTE) with a 3 mm slice thickness. Method: MRI of the upper abdomen with DL-HASTE was performed in 35 participants (5 healthy volunteers and 30 patients) at 3 Tesla. In a subgroup of five healthy participants, signal-to-noise ratio (SNR) analysis was used after DL reconstruction to identify the smallest possible layer thickness (1, 2, 3, 4, 5 mm). DL-HASTE was acquired with a 3 mm slice thickness (DL-HASTE-3 mm) in 30 patients and compared with 5 mm DL-HASTE (DL-HASTE-5 mm) and with standard HASTE (standard-HASTE-5 mm). Image quality and motion artifacts were assessed quantitatively using Laplacian variance and semi-quantitatively by two radiologists using five-point Likert scales. Results: In the five healthy participants, DL-HASTE-3 mm was identified as the optimal slice (SNR 23.227 ± 3.901). Both DL-HASTE-3 mm and DL-HASTE-5 mm were assigned significantly higher overall image quality scores than standard-HASTE-5 mm (Laplacian variance, both p < 0.001; Likert scale, p < 0.001). Compared with DL-HASTE-5 mm (1.10 × 10-5 ± 6.93 × 10-6), DL-HASTE-3 mm (1.56 × 10-5 ± 8.69 × 10-6) provided a significantly higher SNR Laplacian variance (p < 0.001) and sharpness sub-scores for the intestinal tract, adrenal glands, and small anatomic structures (bile ducts, pancreatic ducts, and vessels; p < 0.05). Lesion detectability was rated excellent for both DL-HASTE-3 mm and DL-HASTE-5 mm (both: 5 [IQR4-5]) and was assigned higher scores than standard-HASTE-5 mm (4 [IQR4-5]; p < 0.001). DL-HASTE reduced the acquisition time by 63-69% compared with standard-HASTE-5 mm (p < 0.001). Conclusions: DL-HASTE is a robust abdominal MRI technique that improves image quality while at the same time reducing acquisition time compared with the routine clinical HASTE sequence. Using ultra-thin DL-HASTE-3 mm results in an even greater improvement with a similar SNR.

Accelerated T2-weighted MRI of the Bowel at 3T Using a Single-shot Technique with Deep Learning-based Image Reconstruction: Impact on Image Quality and Disease Detection

RATIONALE AND OBJECTIVE

A single-shot T2-weighted deep-learning-based image reconstruction (DL-HASTE) has been recently developed allowing for shorter acquisition time than conventional half-Fourier acquisition single-shot turbo-spin echo (HASTE). The purpose of this study was to compare image quality of conventional 6 mm HASTE with DL-HASTE at 4 mm and 6 mm slice thickness.

MATERIALS AND METHODS

91 patients (51 female; mean±SD age: 44±10years) who underwent 3T MR enterography from 5/15/2023-7/15/2023 including pelvic conventional HASTE and DL-HASTE were included. Patients either had 4 mm-DL-HASTE or 6 mm-DL-HASTE. Four abdominal radiologists, blinded to sequence type, independently evaluated overall image quality, artifacts over bowel, bowel wall sharpness, and confidence for the presence/absence of bowel abnormalities on 5-point Likert scales. Readers recorded the presence/absence of ileal wall thickening, ileal inflammation, stricture, and penetrating disease on each sequence. Wilcoxon signed-rank test with continuity correction was used for paired comparisons and Wilcoxon rank sum test was used for unpaired ordinal comparisons. A p < .05 indicated statistical significance.

RESULTS

Acquisition times for 6 mm HASTE, 4 mm-DL-HASTE, and 6 mm-DL-HASTE were 64 s, 51 s, and 49 s, respectively. Overall image quality and bowel sharpness were significantly improved for 4 mm-DL-HASTE versus HASTE for 3/4 readers (all p < .05) and similar for the 4th reader (p > .05). Diagnostic confidence was similar for all readers (p > .05). 6 mm-DL-HASTE was similar to HASTE for bowel sharpness, image quality, and confidence for 3/4 readers (all p > .05). The presence of ileal thickening, ileal inflammation, stricture, and penetrating disease were similar for all readers for HASTE, 4 mm-DL-HASTE, and 6 mm-DL-HASTE (all p > .05).

CONCLUSION

4 mm-DL-HASTE had superior image quality than conventional HASTE at shorter acquisition time.

Development of respiratory motion-resolved hepatobiliary phase cine-magnetic resonance imaging for stereotactic body radiotherapy in liver tumor

Cine-magnetic resonance imaging (MRI) has been used to track respiratory-induced motion of the liver and tumor and assist in the accurate delineation of tumor volume. Recent developments in compressed sensitivity encoding (SENSE; CS) have accelerated temporal resolution while maintaining contrast resolution. This study aimed to develop and assess hepatobiliary phase (HBP) cine-MRI scans using CS. Phantom was imaged using cine-MRI and signal intensity (SI) and contrast ratio (CR) measured to determine the optimal flip-angle turbo field echo (TFE) prepulse delay. We performed cine-MRI in 20 patients for one minute, with images taken every 0.5 s after administration of gadoxetic acid contrast agent. Acquired images had three different acceleration factors (SENSE, CS without denoising [CS-no], and CS with strong denoising [CS-strong]). The image quality of the HBP cine MRI was quantitatively and qualitatively analyzed. In the phantom study, a flip angle of 30 °and TFE prepulse delay of 150 ms were optimal for clinical imaging. In a clinical study, CS-strong showed the highest signal-to-noise ratio and comparable contrast ratio among the three sequences. The CS-strong group showed a significantly higher image quality (P < 0.01), except for motion smoothness (P = 0.11). CS with denoising improved the tumor-to-liver contrast and image quality in high-temporal-resolution HBP cine MRI.

Image quality assessment and white matter hyperintensity quantification in two accelerated high-resolution 3D FLAIR techniques: Wave-CAIPI and deep learning-based SPACE

AIM

To compare the image quality obtained using two accelerated high-resolution 3D fluid-attenuated inversion recovery (FLAIR) techniques for the brain-deep learning-reconstruction SPACE (DL-SPACE) and Wave-CAIPI FLAIR.

MATERIALS AND METHODS

A total of 123 participants who underwent DL-SPACE and Wave-CAIPI FLAIR brain imaging were retrospectively reviewed. In a qualitative analysis, two radiologists rated the quality of each image, including the overall image quality, artifacts, sharpness, fine-structure conspicuity, and lesion conspicuity based on Likert scales. In a quantitative analysis, the signal-to-noise ratio (SNR) for the normal-appearing white matter (NAWM) and lesion and the contrast-to-noise ratio (CNR) for a lesion were calculated and compared. Moreover, the volumes of white matter hyperintensities (WMHs) obtained with the two techniques were automatically quantified and compared.

RESULTS

The DL-SPACE FLAIR technique demonstrated a significantly higher fine-structure conspicuity (P < 0.001), lower degree of artifacts (P < 0.001) and higher overall image quality (P = 0.001). The mean SNR values were significantly higher with the DL-SPACE FLAIR technique (NAWM, 43.95 vs. 31.6; lesion, 31.35 vs. 21.28; all, P < 0.001). Additionally, the mean CNR of the WMH was significantly higher with the DL-SPACE FLAIR technique (11.34 vs. 8.22; P < 0.001). The periventricular and deep WMH volumes were significantly larger with the DL-SPACE FLAIR technique (1.91 ± 4.69 vs. 1.54 ± 4.18; P < 0.001 and 0.26 ± 0.42 vs. 0.23 ± 0.38; P = 0.002, respectively).

CONCLUSION

The DL-SPACE FLAIR technique produced images with superior quality, SNR and CNR compared with the Wave-CAIPI FLAIR technique with the same acquisition time.

Enhancing gadoxetic acid-enhanced liver MRI: a synergistic approach with deep learning CAIPIRINHA-VIBE and optimized fat suppression techniques

OBJECTIVE

To investigate whether a deep learning (DL) controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA)-volumetric interpolated breath-hold examination (VIBE) technique can improve image quality, lesion conspicuity, and lesion detection compared to a standard CAIPIRINHA-VIBE technique in gadoxetic acid-enhanced liver MRI.

METHODS

This retrospective single-center study included 168 patients who underwent gadoxetic acid-enhanced liver MRI at 3 T using both standard CAIPIRINHA-VIBE and DL CAIPIRINHA-VIBE techniques on pre-contrast and hepatobiliary phase (HBP) images. Additionally, high-resolution (HR) DL CAIPIRINHA-VIBE was obtained with 1-mm slice thickness on the HBP. Three abdominal radiologists independently assessed the image quality and lesion conspicuity of pre-contrast and HBP images. Statistical analyses involved the Wilcoxon signed-rank test for image quality assessment and the generalized estimation equation for lesion conspicuity and detection evaluation.

RESULTS

DL and HR-DL CAIPIRINHA-VIBE demonstrated significantly improved overall image quality and reduced artifacts on pre-contrast and HBP images compared to standard CAIPIRINHA-VIBE (p < 0.001), with a shorter acquisition time (DL vs standard, 11 s vs 17 s). However, the former presented a more synthetic appearance (both p < 0.05). HR-DL CAIPIRINHA-VIBE showed superior lesion conspicuity to standard and DL CAIPIRINHA-VIBE on HBP images (p < 0.001). Moreover, HR-DL CAIPIRINHA-VIBE exhibited a significantly higher detection rate of small (< 2 cm) solid focal liver lesions (FLLs) on HBP images compared to standard CAIPIRINHA-VIBE (92.5% vs 87.4%; odds ratio = 1.83; p = 0.036).

CONCLUSION

DL and HR-DL CAIPIRINHA-VIBE achieved superior image quality compared to standard CAIPIRINHA-VIBE. Additionally, HR-DL CAIPIRINHA-VIBE improved the lesion conspicuity and detection of small solid FLLs. DL and HR-DL CAIPIRINHA-VIBE hold the potential clinical utility for gadoxetic acid-enhanced liver MRI.

CLINICAL RELEVANCE STATEMENT

DL and HR-DL CAIPIRINHA-VIBE hold promise as potential alternatives to standard CAIPIRINHA-VIBE in routine clinical liver MRI, improving the image quality and lesion conspicuity, enhancing the detection of small (< 2 cm) solid focal liver lesions, and reducing the acquisition time.

KEY POINTS

• DL and HR-DL CAIPIRINHA-VIBE demonstrated improved overall image quality and reduced artifacts on pre-contrast and HBP images compared to standard CAIPIRINHA-VIBE, in addition to a shorter acquisition time. • DL and HR-DL CAIPIRINHA-VIBE yielded a more synthetic appearance than standard CAIPIRINHA-VIBE. • HR-DL CAIPIRINHA-VIBE showed improved lesion conspicuity than standard CAIPIRINHA-VIBE on HBP images, with a higher detection of small (< 2 cm) solid focal liver lesions.

Advanced MRI techniques in abdominal imaging

Magnetic resonance imaging (MRI) is a crucial modality for abdominal imaging evaluation of focal lesions and tissue properties. However, several obstacles, such as prolonged scan times, limitations in patients' breath-hold capacity, and contrast agent-associated artifacts, remain in abdominal MR images. Recent techniques, including parallel imaging, three-dimensional acquisition, compressed sensing, and deep learning, have been developed to reduce the scan time while ensuring acceptable image quality or to achieve higher resolution without extending the scan duration. Quantitative measurements using MRI techniques enable the noninvasive evaluation of specific materials. A comprehensive understanding of these advanced techniques is essential for accurate interpretation of MRI sequences. Herein, we therefore review advanced abdominal MRI techniques.

Utility of Thin-slice Fat-suppressed Single-shot T2-weighted MR Imaging with Deep Learning Image Reconstruction as a Protocol for Evaluating the Pancreas

PURPOSE

To compare the utility of thin-slice fat-suppressed single-shot T2-weighted imaging (T2WI) with deep learning image reconstruction (DLIR) and conventional fast spin-echo T2WI with DLIR for evaluating pancreatic protocol.

METHODS

This retrospective study included 42 patients (mean age, 70.2 years) with pancreatic cancer who underwent gadoxetic acid-enhanced MRI. Three fat-suppressed T2WI, including conventional fast-spin echo with 6 mm thickness (FSE 6 mm), single-shot fast-spin echo with 6 mm and 3 mm thickness (SSFSE 6 mm and SSFSE 3 mm), were acquired for each patient. For quantitative analysis, the SNRs of the upper abdominal organs were calculated between images with and without DLIR. The pancreas-to-lesion contrast on DLIR images was also calculated. For qualitative analysis, two abdominal radiologists independently scored the image quality on a 5-point scale in the FSE 6 mm, SSFSE 6 mm, and SSFSE 3 mm with DLIR.

RESULTS

The SNRs significantly improved among the three T2-weighted images with DLIR compared to those without DLIR in all patients (P < 0.001). The pancreas-to-lesion contrast of SSFSE 3 mm was higher than those of the FSE 6 mm (P < 0.001) and tended to be higher than SSFSE 6 mm (P = 0.07). SSFSE 3 mm had the highest image qualities regarding pancreas edge sharpness, pancreatic duct clarity, and overall image quality, followed by SSFSE 6 mm and FSE 6 mm (P < 0.0001).

CONCLUSION

SSFSE 3 mm with DLIR demonstrated significant improvements in SNRs of the pancreas, pancreas-to-lesion contrast, and image quality more efficiently than did SSFSE 6 mm and FSE 6 mm. Thin-slice fat-suppressed single-shot T2WI with DLIR can be easily implemented for pancreatic MR protocol.

Reduced field-of-view DWI based on deep learning reconstruction improving diagnostic accuracy of VI-RADS for evaluating muscle invasion

OBJECTIVES

To 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.

METHODS

Eighty-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).

RESULTS

The 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).

CONCLUSIONS

rFOV 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 STATEMENT

The 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 POINTS

Deep 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.

[Reduction of Motion Artifacts in Liver MRI Using Deep Learning with High-pass Filtering]

PURPOSE

To investigate whether deep learning with high-pass filtering can be used to effectively reduce motion artifacts in magnetic resonance (MR) images of the liver.

METHODS

The subjects were 69 patients who underwent liver MR examination at our hospital. Simulated motion artifact images (SMAIs) were created from non-artifact images (NAIs) and used for deep learning. Structural similarity index measure (SSIM) and contrast ratio (CR) were used to verify the effect of reducing motion artifacts in motion artifact reduction image (MARI) output from the obtained deep learning model. In the visual assessment, reduction of motion artifacts and image sharpness were evaluated between motion artifact images (MAIs) and MARIs.

RESULTS

The SSIM values were 0.882 on the MARIs and 0.869 on the SMAIs. There was no statistically significant difference in CR between NAIs and MARIs. The visual assessment showed that MARIs had reduced motion artifacts and improved sharpness compared to MAIs.

CONCLUSION

The learning model in this study is indicated to be reduced motion artifacts without decreasing the sharpness of liver MR images.

Bladder MRI with deep learning-based reconstruction: a prospective evaluation of muscle invasiveness using VI-RADS

PURPOSE

To investigate the influence of deep learning reconstruction (DLR) on bladder MRI, specifically examination time, image quality, and diagnostic performance of vesical imaging reporting and data system (VI-RADS) within a prospective clinical cohort.

METHODS

Seventy participants with bladder cancer who underwent MRI between August 2022 and February 2023 with a protocol containing standard T2-weighted imaging (T2WIS), standard diffusion-weighted imaging (DWIS), fast T2WI with DLR (T2WIDL), and fast DWI with DLR (DWIDL) were enrolled in this prospective study. Imaging quality was evaluated by measuring signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and qualitative image quality scoring. Additionally, the apparent diffusion coefficient (ADC) of bladder lesions derived from DWIS and DWIDL was measured and VI-RADS scoring was performed. Paired t-test or paired Wilcoxon signed-rank test were performed to compare image quality score, SNR, CNR, and ADC between standard sequences and fast sequences with DLR. The diagnostic performance for VI-RADS was assessed using the area under the receiver operating characteristic curve (AUC).

RESULTS

Compared to T2WIS and DWIS, T2WIDL and DWIDL reduced the acquisition time from 5:57 min to 3:13 min and showed significantly higher SNR, CNR, qualitative image quality score of overall image quality, image sharpness, and lesion conspicuity. There were no significant differences in ADC and AUC of VI-RADS between standard sequences and fast sequences with DLR.

CONCLUSIONS

The application of DLR to T2WI and DWI reduced examination time and significantly improved image quality, maintaining ADC and the diagnostic performance of VI-RADS for evaluating muscle invasion in bladder cancer.

Deep learning-accelerated T2-weighted imaging versus conventional T2-weighted imaging in the female pelvic cavity: image quality and diagnostic performance

BACKGROUND

The deep learning (DL)-based reconstruction algorithm reduces noise in magnetic resonance imaging (MRI), thereby enabling faster MRI acquisition.

PURPOSE

To compare the image quality and diagnostic performance of conventional turbo spin-echo (TSE) T2-weighted (T2W) imaging with DL-accelerated sagittal T2W imaging in the female pelvic cavity.

METHODS

This study evaluated 149 consecutive female pelvic MRI examinations, including conventional T2W imaging with TSE (acquisition time = 2:59) and DL-accelerated T2W imaging with breath hold (DL-BH) (1:05 [0:14 × 3 breath-holds]) in the sagittal plane. In 294 randomly ordered sagittal T2W images, two radiologists independently assessed image quality (sharpness, subjective noise, artifacts, and overall image quality), made a diagnosis for uterine leiomyomas, and scored diagnostic confidence. For the uterus and piriformis muscle, quantitative imaging analysis was also performed. Wilcoxon signed rank tests were used to compare the two sets of T2W images.

RESULTS

In the qualitative analysis, DL-BH showed similar or significantly higher scores for all features than conventional T2W imaging (P <0.05). In the quantitative analysis, the noise in the uterus was lower in DL-BH, but the noise in the muscle was lower in conventional T2W imaging. In the uterus and muscle, the signal-to-noise ratio was significantly lower in DL-BH than in conventional T2W imaging (P <0.001). The diagnostic performance of the two sets of T2W images was not different for uterine leiomyoma.

CONCLUSIONS

DL-accelerated sagittal T2W imaging obtained with three breath-holds demonstrated superior or comparable image quality to conventional T2W imaging with no significant difference in diagnostic performance for uterine leiomyomas.

Effect of Deep Learning Reconstruction on Respiratory-triggered T2-weighted MR Imaging of the Liver: A Comparison between the Single-shot Fast Spin-echo and Fast Spin-echo Sequences

PURPOSE

To compare the effects of deep learning reconstruction (DLR) on respiratory-triggered T2-weighted MRI of the liver between single-shot fast spin-echo (SSFSE) and fast spin-echo (FSE) sequences.

METHODS

Respiratory-triggered fat-suppressed liver T2-weighted MRI was obtained with the FSE and SSFSE sequences at the same spatial resolution in 55 patients. Conventional reconstruction (CR) and DLR were applied to each sequence, and the SNR and liver-to-lesion contrast were measured on FSE-CR, FSE-DLR, SSFSE-CR, and SSFSE-DLR images. Image quality was independently assessed by three radiologists. The results of the qualitative and quantitative analyses were compared among the four types of images using repeated-measures analysis of variance or Friedman's test for normally and non-normally distributed data, respectively, and a visual grading characteristics (VGC) analysis was performed to evaluate the image quality improvement by DLR on the FSE and SSFSE sequences.

RESULTS

The liver SNR was lowest on SSFSE-CR and highest on FSE-DLR and SSFSE-DLR (P < 0.01). The liver-to-lesion contrast did not differ significantly among the four types of images. Qualitatively, noise scores were worst on SSFSE-CR but best on SSFSE-DLR because DLR significantly reduced noise (P < 0.01). In contrast, artifact scores were worst both on FSE-CR and FSE-DLR (P < 0.01) because DLR did not reduce the artifacts. Lesion conspicuity was significantly improved by DLR compared with CR in the SSFSE (P < 0.01) but not in FSE sequences for all readers. Overall image quality was significantly improved by DLR compared with CR for all readers in the SSFSE (P < 0.01) but only one reader in the FSE (P < 0.01). The mean area under the VGC curve values for the FSE-DLR and SSFSE-DLR sequences were 0.65 and 0.94, respectively.

CONCLUSION

In liver T2-weighted MRI, DLR produced more marked improvements in image quality in SSFSE than in FSE.

Dynamic recurrent inference machines for accelerated MRI-guided radiotherapy of the liver

Recurrent inference machines (RIM), a deep learning model that learns an iterative scheme for reconstructing sparsely sampled MRI, has been shown able to perform well on accelerated 2D and 3D MRI scans, learn from small datasets and generalize well to unseen types of data. Here we propose the dynamic recurrent inference machine (DRIM) for reconstructing sparsely sampled 4D MRI by exploiting correlations between respiratory states. The DRIM was applied to a 4D protocol for MR-guided radiotherapy of liver lesions based on repetitive interleaved coronal 2D multi-slice T2-weighted acquisitions. We demonstrate with an ablation study that the DRIM outperforms the RIM, increasing the SSIM score from about 0.89 to 0.95. The DRIM allowed for an approximately 2.7 times faster scan time than the current clinical protocol with only a slight loss in image sharpness. Correlations between slice locations can also be used, but were found to be of less importance, as were a majority of tested variations in network architecture, as long as the respiratory states are processed by the network. Through cross-validation, the DRIM is also shown to be robust in terms of training data. We further demonstrate a good performance across a large range of subsampling factors, and conclude through an evaluation by a radiation oncologist that reconstructed images of the liver contour and inner structures are of a clinically acceptable standard at acceleration factors 10x and 8x, respectively. Finally, we show that binning the data with respect to respiratory states prior to reconstruction comes at a slight cost to reconstruction quality, but at greater speed of the overall protocol.

Deep learning HASTE sequence compared with T2-weighted BLADE sequence for liver MRI at 3 Tesla: a qualitative and quantitative prospective study

OBJECTIVES

To qualitatively and quantitatively compare a single breath-hold fast half-Fourier single-shot turbo spin echo sequence with deep learning reconstruction (DL HASTE) with T2-weighted BLADE sequence for liver MRI at 3 T.

METHODS

From December 2020 to January 2021, patients with liver MRI were prospectively included. For qualitative analysis, sequence quality, presence of artifacts, conspicuity, and presumed nature of the smallest lesion were assessed using the chi-squared and McNemar tests. For quantitative analysis, number of liver lesions, size of the smallest lesion, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) in both sequences were assessed using the paired Wilcoxon signed-rank test. Intraclass correlation coefficients (ICCs) and kappa coefficients were used to assess agreement between the two readers.

RESULTS

One hundred and twelve patients were evaluated. Overall image quality (p = .006), artifacts (p < .001), and conspicuity of the smallest lesion (p = .001) were significantly better for the DL HASTE sequence than for the T2-weighted BLADE sequence. Significantly more liver lesions were detected with the DL HASTE sequence (356 lesions) than with the T2-weighted BLADE sequence (320 lesions; p < .001). CNR was significantly higher for the DL HASTE sequence (p < .001). SNR was higher for the T2-weighted BLADE sequence (p < .001). Interreader agreement was moderate to excellent depending on the sequence. Of the 41 supernumerary lesions visible only on the DL HASTE sequence, 38 (93%) were true-positives.

CONCLUSION

The DL HASTE sequence can be used to improve image quality and contrast and reduces artifacts, allowing the detection of more liver lesions than with the T2-weighted BLADE sequence.

CLINICAL RELEVANCE STATEMENT

The DL HASTE sequence is superior to the T2-weighted BLADE sequence for the detection of focal liver lesions and can be used in daily practice as a standard sequence.

KEY POINTS

• The half-Fourier acquisition single-shot turbo spin echo sequence with deep learning reconstruction (DL HASTE sequence) has better overall image quality, reduced artifacts (particularly motion artifacts), and improved contrast, allowing the detection of more liver lesions than with the T2-weighted BLADE sequence. • The acquisition time of the DL HASTE sequence is at least eight times faster (21 s) than that of the T2-weighted BLADE sequence (3-5 min). • The DL HASTE sequence could replace the conventional T2-weighted BLADE sequence to meet the growing indication for hepatic MRI in clinical practice, given its diagnostic and time-saving performance.

Deep Learning Convolutional Neural Network Reconstruction and Radial k-Space Acquisition MR Technique for Enhanced Detection of Retropatellar Cartilage Lesions of the Knee Joint

OBJECTIVES

To assess diagnostic performance of standard radial k-space (PROPELLER) MRI sequences and compare with accelerated acquisitions combined with a deep learning-based convolutional neural network (DL-CNN) reconstruction for evaluation of the knee joint.

METHODS

Thirty-five patients undergoing MR imaging of the knee at 1.5 T were prospectively included. Two readers evaluated image quality and diagnostic confidence of standard and DL-CNN accelerated PROPELLER MR sequences using a four-point Likert scale. Pathological findings of bone, cartilage, cruciate and collateral ligaments, menisci, and joint space were analyzed. Inter-reader agreement (IRA) for image quality and diagnostic confidence was assessed using intraclass coefficients (ICC). Cohen's Kappa method was used for evaluation of IRA and consensus between sequences in assessing different structures. In addition, image quality was quantitatively evaluated by signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) measurements.

RESULTS

Mean acquisition time of standard vs. DL-CNN sequences was 10 min 3 s vs. 4 min 45 s. DL-CNN sequences showed significantly superior image quality and diagnostic confidence compared to standard MR sequences. There was moderate and good IRA for assessment of image quality in standard and DL-CNN sequences with ICC of 0.524 and 0.830, respectively. Pathological findings of the knee joint could be equally well detected in both sequences (κ-value of 0.8). Retropatellar cartilage could be significantly better assessed on DL-CNN sequences. SNR and CNR was significantly higher for DL-CNN sequences (both p < 0.05).

CONCLUSIONS

In MR imaging of the knee, DL-CNN sequences showed significantly higher image quality and diagnostic confidence compared to standard PROPELLER sequences, while reducing acquisition time substantially. Both sequences perform comparably in the detection of knee-joint pathologies, while DL-CNN sequences are superior for evaluation of retropatellar cartilage lesions.

Usefulness of Breath-Hold Fat-Suppressed T2-Weighted Images With Deep Learning-Based Reconstruction of the Liver: Comparison to Conventional Free-Breathing Turbo Spin Echo

OBJECTIVES

The aim of this study was to evaluate the usefulness of breath-hold turbo spin echo with deep learning-based reconstruction (BH-DL-TSE) in acquiring fat-suppressed T2-weighted images (FS-T2WI) of the liver by comparing this method with conventional free-breathing turbo spin echo (FB-TSE) and breath-hold half Fourier single-shot turbo spin echo with deep learning-based reconstruction (BH-DL-HASTE).

MATERIALS AND METHODS

The study cohort comprised 111 patients with suspected liver disease who underwent 3 T magnetic resonance imaging. Fifty-eight focal solid liver lesions ≥10 mm were also evaluated. Three sets of FS-T2WI were acquired using FB-TSE, prototypical BH-DL-TSE, and prototypical BH-DL-HASTE, respectively. In the qualitative analysis, 2 radiologists evaluated the image quality using a 5-point scale. In the quantitative analysis, we calculated the lesion-to-liver signal intensity ratio (LEL-SIR). Friedman test and Dunn multiple comparison test were performed to assess differences among 3 types of FS-T2WI with respect to image quality and LEL-SIR.

RESULTS

The mean acquisition time was 4 minutes and 43 seconds ± 1 minute and 21 seconds (95% confidence interval, 4 minutes and 28 seconds to 4 minutes and 58 seconds) for FB-TSE, 40 seconds for BH-DL-TSE, and 20 seconds for BH-DL-HASTE. In the qualitative analysis, BH-DL-HASTE resulted in the fewest respiratory motion artifacts ( P < 0.0001). BH-DL-TSE and FB-TSE exhibited significantly less motion-related signal loss and clearer intrahepatic vessels than BH-DL-HASTE ( P < 0.0001). Regarding the edge sharpness of the left lobe, BH-DL-HASTE scored the highest ( P < 0.0001), and BH-DL-TSE scored higher than FB-TSE ( P = 0.0290). There were no significant differences among 3 types of FS-T2WI with respect to the edge sharpness of the right lobe ( P = 0.1290), lesion conspicuity ( P = 0.5292), and LEL-SIR ( P = 0.6026).

CONCLUSIONS

BH-DL-TSE provides a shorter acquisition time and comparable or better image quality than FB-TSE, and could replace FB-TSE in acquiring FS-T2WI of the liver. BH-DL-TSE and BH-DL-HASTE have their own advantages and may be used complementarily.

High-Resolution Single-Shot Fast Spin-Echo MR Imaging with Deep Learning Reconstruction Algorithm Can Improve Repeatability and Reproducibility of Follicle Counting

OBJECTIVE

To investigate the diagnostic performance of high-resolution single-shot fast spin-echo (SSFSE) imaging with deep learning (DL) reconstruction algorithm on follicle counting and compare it with original SSFSE images and conventional fast spin-echo (FSE) images.

METHODS

This study included 20 participants (40 ovaries) with clinically confirmed polycystic ovary syndrome (PCOS) who underwent high-resolution ovary MRI, including three-plane T2-weighted FSE sequences and slice-matched T2-weighted SSFSE sequences. A DL reconstruction algorithm was applied to the SSFSE sequences to generate SSFSE-DL images, and the original SSFSE images were also saved. Subjective evaluations such as the blurring artifacts, subjective noise, and clarity of the follicles on the SSFSE-DL, SSFSE, and conventional FSE images were independently conducted by two observers. Intra-class correlation coefficients and Bland-Altman plots were used to present the repeatability and reproducibility of the follicle number per ovary (FNPO) based on the three types of images.

RESULTS

SSFSE-DL images showed less blurring artifact, subjective noise, and better clarity of the follicles than SSFSE and FSE (p < 0.05). For the repeatability of the FNPO, SSFSE-DL showed the highest intra-observer (ICC = 0.930; 95% CI: 0.878-0.962) and inter-observer (ICC = 0.914; 95% CI: 0.843-0.953) agreements. The inter-observer 95% limits of agreement (LOA) for SSFSE-DL, SSFSE, and FSE ranged from -3.7 to 4.5, -4.4 to 7.0, and -7.1 to 7.6, respectively. The intra-observer 95% LOA for SSFSE-DL, SSFSE, and FSE ranged from -3.5 to 4.0, -5.1 to 6.1, and -5.7 to 4.2, respectively. The absolute values of intra-observer and inter-observer differences for SSFSE-DL were significantly lower than those for SSFSE and FSE (p < 0.05).

CONCLUSIONS

Compared with the original SSFSE images and the conventional FSE images, high-resolution SSFSE images with DL reconstruction algorithm can better display follicles, thus improving FNPO assessment.

Differentiation of benign versus malignant indistinguishable vertebral compression fractures by different machine learning with MRI-based radiomic features

OBJECTIVES

To explore an optimal machine learning (ML) model trained on MRI-based radiomic features to differentiate benign from malignant indistinguishable vertebral compression fractures (VCFs).

METHODS

This retrospective study included patients within 6 weeks of back pain (non-traumatic) who underwent MRI and were diagnosed with benign and malignant indistinguishable VCFs. The two cohorts were retrospectively recruited from the Affiliated Hospital of Qingdao University (QUH) and Qinghai Red Cross Hospital (QRCH). Three hundred seventy-six participants from QUH were divided into the training (n = 263) and validation (n = 113) cohort based on the date of MRI examination. One hundred three participants from QRCH were used to evaluate the external generalizability of our prediction models. A total of 1045 radiomic features were extracted from each region of interest (ROI) and used to establish the models. The prediction models were established based on 7 different classifiers.

RESULTS

These models showed favorable efficacy in differentiating benign from malignant indistinguishable VCFs. However, our Gaussian naïve Bayes (GNB) model attained higher AUC and accuracy (0.86, 87.61%) than the other classifiers in validation cohort. It also remains the high accuracy and sensitivity for the external test cohort.

CONCLUSIONS

Our GNB model performed better than the other models in the present study, suggesting that it may be more useful for differentiating indistinguishable benign form malignant VCFs.

KEY POINTS

• The differential diagnosis of benign and malignant indistinguishable VCFs based on MRI is rather difficult for spine surgeons or radiologists. • Our ML models facilitate the differential diagnosis of benign and malignant indistinguishable VCFs with improved diagnostic efficacy. • Our GNB model had the high accuracy and sensitivity for clinical application.

Application of deep learning-based image reconstruction in MR imaging of the shoulder joint to improve image quality and reduce scan time

OBJECTIVES

To compare the image quality and diagnostic performance of conventional motion-corrected periodically rotated overlapping parallel line with enhanced reconstruction (PROPELLER) MRI sequences with post-processed PROPELLER MRI sequences using deep learning-based (DL) reconstructions.

METHODS

In this prospective study of 30 patients, conventional (19 min 18 s) and accelerated MRI sequences (7 min 16 s) using the PROPELLER technique were acquired. Accelerated sequences were post-processed using DL. The image quality and diagnostic confidence were qualitatively assessed by 2 readers using a 5-point Likert scale. Analysis of the pathological findings of cartilage, rotator cuff tendons and muscles, glenoid labrum and subacromial bursa was performed. Inter-reader agreement was calculated using Cohen's kappa statistic. Quantitative evaluation of image quality was measured using the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR).

RESULTS

Mean image quality and diagnostic confidence in evaluation of all shoulder structures were higher in DL sequences (p value = 0.01). Inter-reader agreement ranged between kappa values of 0.155 (assessment of the bursa) and 0.947 (assessment of the rotator cuff muscles). In 17 cases, thickening of the subacromial bursa of more than 2 mm was only visible in DL sequences. The pathologies of the other structures could be properly evaluated by conventional and DL sequences. Mean SNR (p value = 0.01) and CNR (p value = 0.02) were significantly higher for DL sequences.

CONCLUSIONS

The accelerated PROPELLER sequences with DL post-processing showed superior image quality and higher diagnostic confidence compared to the conventional PROPELLER sequences. Subacromial bursa can be thoroughly assessed in DL sequences, while the other structures of the shoulder joint can be assessed in conventional and DL sequences with a good agreement between sequences.

KEY POINTS

• MRI of the shoulder requires long scan times and can be hampered by motion artifacts. • Deep learning-based convolutional neural networks are used to reduce image noise and scan time while maintaining optimal image quality. The radial k-space acquisition technique (PROPELLER) can reduce the scan time and has potential to reduce motion artifacts. • DL sequences show a higher diagnostic confidence than conventional sequences and therefore are preferred for assessment of the subacromial bursa, while conventional and DL sequences show comparable performance in the evaluation of the shoulder joint.

Accelerated T2-weighted MRI of the liver at 3 T using a single-shot technique with deep learning-based image reconstruction: impact on the image quality and lesion detection

PURPOSE

Fat-suppressed T2-weighted imaging (T2-FS) requires a long scan time and can be wrought with motion artifacts, urging the development of a shorter and more motion robust sequence. We compare the image quality of a single-shot T2-weighted MRI prototype with deep-learning-based image reconstruction (DL HASTE-FS) with a standard T2-FS sequence for 3 T liver MRI.

METHODS

41 consecutive patients with 3 T abdominal MRI examinations including standard T2-FS and DL HASTE-FS, between 5/6/2020 and 11/23/2020, comprised the study cohort. Three radiologists independently reviewed images using a 5-point Likert scale for artifact and image quality measures, while also assessing for liver lesions.

RESULTS

DL HASTE-FS acquisition time was 54.93 ± 16.69, significantly (p < .001) shorter than standard T2-FS (114.00 ± 32.98 s). DL HASTE-FS received significantly higher scores for sharpness of liver margin (4.3 vs 3.3; p < .001), hepatic vessel margin (4.2 vs 3.3; p < .001), pancreatic duct margin (4.0 vs 1.9; p < .001); in-plane (4.0 vs 3.2; p < .001) and through-plane (3.9 vs 3.4; p < .001) motion artifacts; other ghosting artifacts (4.3 vs 2.9; p < .001); and overall image quality (4.0 vs 2.9; p < .001), in addition to receiving a higher score for homogeneity of fat suppression (3.7 vs 3.4; p = .04) and liver-fat contrast (p = .03). For liver lesions, DL HASTE-FS received significantly higher scores for sharpness of lesion margin (4.4 vs 3.7; p = .03).

CONCLUSION

Novel single-shot T2-weighted MRI with deep-learning-based image reconstruction demonstrated superior image quality compared with the standard T2-FS sequence for 3 T liver MRI, while being acquired in less than half the time.

Respiratory Motion Management in Abdominal MRI: Radiology In Training

A 96-year-old woman had a suboptimal evaluation of liver observations at abdominal MRI due to significant respiratory motion. State-of-the-art strategies to minimize respiratory motion during clinical abdominal MRI are discussed.

Artificial intelligence and machine learning in cancer imaging

An increasing array of tools is being developed using artificial intelligence (AI) and machine learning (ML) for cancer imaging. The development of an optimal tool requires multidisciplinary engagement to ensure that the appropriate use case is met, as well as to undertake robust development and testing prior to its adoption into healthcare systems. This multidisciplinary review highlights key developments in the field. We discuss the challenges and opportunities of AI and ML in cancer imaging; considerations for the development of algorithms into tools that can be widely used and disseminated; and the development of the ecosystem needed to promote growth of AI and ML in cancer imaging.

Improved Single Breath-Hold SSFSE Sequence for Liver MRI Based on Compressed Sensing: Evaluation of Image Quality Compared with Conventional T2-Weighted Sequences

The purpose of this study was to evaluate the image quality of compressed-sensing accelerated single-shot fast spin-echo (SSFSECS) sequences acquired within a single breath-hold in comparison with conventional SSFSE (SSFSECONV) and multishot TSE (mTSE). A total of 101 patients who underwent liver MRI at 3 T, including SSFSECONV (acquisition time (TA) = 58−62 s), mTSE (TA = 108 s), and SSFSECS (TA = 18 s), were included in this retrospective study. Two radiologists assessed the three sequences with respect to artifacts, organ sharpness, small structure visibility, overall image quality, and conspicuity of main lesions of liver and pancreas using a five-point evaluation scale system. Descriptive statistics and the Wilcoxon signed-rank test were used for statistical analysis. SSFSECS was significantly better than SSFSECONV and mTSE for artifacts, small structure visibility, overall image quality, and conspicuity of main lesions (p < 0.005). Regarding organ sharpness, mTSE and SSFSECS did not significantly differ (p = 0.554). Conspicuity of liver lesion did not significantly differ between SSFSECONV and mTSE (p = 0.404). SSFSECS showed superior image quality compared with SSFSECONV and mTSE despite a more than three-fold reduction in TA, suggesting a remarkable potential for saving time in liver imaging.

Potential of a Non-Contrast-Enhanced Abbreviated MRI Screening Protocol (NC-AMRI) in High-Risk Patients under Surveillance for HCC

PURPOSE

To evaluate NC-AMRI for the detection of HCC in high-risk patients.

METHODS

Patients who underwent yearly contrast-enhanced MRI (i.e., full MRI protocol) of the liver were included retrospectively. For all patients, the sequences that constitute the NC-AMRI protocol, namely diffusion-weighted imaging (DWI), T2-weighted (T2W) imaging with fat saturation, and T1-weighted (T1W) in-phase and opposed-phase imaging, were extracted, anonymized, and uploaded to a separate research server and reviewed independently by three radiologists with different levels of experience. Reader I and III held a mutual training session. Levels of suspicion of HCC per patient were compared and the sensitivity, specificity, and area under the curve (AUC) using the Mann-Whitney U test were calculated. The reference standard was a final diagnosis based on full liver MRI and clinical follow-up information.

RESULTS

Two-hundred-and-fifteen patients were included, 36 (16.7%) had HCC and 179 (83.3%) did not. The level of agreement between readers was reasonable to good and concordant with the level of expertise and participation in a mutual training session. Receiver operating characteristics (ROC) analysis showed relatively high AUC values (range 0.89-0.94). Double reading showed increased sensitivity of 97.2% and specificity of 87.2% compared with individual results (sensitivity 80.1%-91.7%-97.2%; specificity 91.1%-72.1%-82.1%). Only one HCC (2.8%) was missed by all readers.

CONCLUSION

NC-AMRI presents a good potential surveillance imaging tool for the detection of HCC in high-risk patients. The best results are achieved with two observers after a mutual training session.

Reduction in Acquisition Time and Improvement in Image Quality in T2-Weighted MR Imaging of Musculoskeletal Tumors of the Extremities Using a Novel Deep Learning-Based Reconstruction Technique in a Turbo Spin Echo (TSE) Sequence

Background: The aim of this study was to assess the technical feasibility and the impact on image quality and acquisition time of a deep learning-accelerated fat-saturated T2-weighted turbo spin echo sequence in musculoskeletal imaging of the extremities. Methods: Twenty-three patients who underwent MRI of the extremities were prospectively included. Standard T2w turbo inversion recovery magnitude (TIRMStd) imaging was compared to a deep learning-accelerated T2w TSE (TSEDL) sequence. Image analysis of 23 patients with a mean age of 60 years (range 30−86) was performed regarding image quality, noise, sharpness, contrast, artifacts, lesion detectability and diagnostic confidence. Pathological findings were documented measuring the maximum diameter. Results: The analysis showed a significant improvement for the T2 TSEDL with regard to image quality, noise, contrast, sharpness, lesion detectability, and diagnostic confidence, as compared to T2 TIRMStd (each p < 0.001). There were no differences in the number of detected lesions. The time of acquisition (TA) could be reduced by 52−59%. Interrater agreement was almost perfect (κ = 0.886). Conclusion: Accelerated T2 TSEDL was technically feasible and superior to conventionally applied T2 TIRMStd. Concurrently, TA could be reduced by 52−59%. Therefore, deep learning-accelerated MR imaging is a promising and applicable method in musculoskeletal imaging.

Fast T2-weighted liver MRI: Image quality and solid focal lesions conspicuity using a deep learning accelerated single breath-hold HASTE fat-suppressed sequence

PURPOSE

Acceleration of MRI acquisitions and especially of T2-weighted sequences is essential to reduce the duration of MRI examinations but also kinetic artifacts in liver imaging. The purpose of this study was to compare the acquisition time and the image quality of a single-shot fat-suppressed turbo spin-echo (TSE) T2-weighted sequence with deep learning reconstruction (HASTE_DL) with that of a fat-suppressed T2-weighted BLADE TSE sequence in patients with focal liver lesions.

MATERIALS AND METHODS

Ninety-five patients (52 men, 43 women; mean age: 61 ± 14 [SD]; age range: 28-87 years) with 42 focal liver lesions (17 hepatocellular carcinomas, 10 sarcoidosis lesions, 9 myeloma lesions, 3 liver metastases and 3 focal nodular hyperplasias) who underwent liver MRI at 1.5 T including HASTE_DL and BLADE sequences were retrospectively included. Overall image quality, noise level in the liver, lesion conspicuity and sharpness of liver lesion contours were assessed by two independent readers. Liver signal-to-noise ratio (SNR) and lesion contrast-to-noise ratio (CNR) were measured and compared between the two sequences, as well as the mean duration of the sequences (Student t-test or Wilcoxon test for paired data).

RESULTS

Median overall quality on HASTE_DL images (3; IQR: 3, 3) was significantly greater than that on BLADE images (2; IQR: 1, 3) (P < 0.001). Median noise level in the liver on HASTE_DL images (0; IQR: 0, 0.5) was significantly lower than that on BLADE images (1; IQR: 1, 2) (P < 0.001). On HASTE_DL images, mean liver SNR (107.3 ± 39.7 [SD]) and mean focal liver lesion CNR (87.0 ± 76.6 [SD]) were significantly greater than those on BLADE images (67.1 ± 23.8 [SD], P < 0.001 and 48.6 ± 43.9 [SD], P = 0.027, respectively). Acquisition time was significantly shorter with the HASTE_DL sequence (18 ± [0] s; range: 18-18 s) compared to BLADE sequence (152 ± 47 [SD] s; range: 87-263 s) (P < 0.001).

CONCLUSION

By comparison with the BLADE sequence, HASTE_DL sequence significantly reduces acquisition time while improving image quality, liver SNR and focal liver lesions CNR.

Accelerating susceptibility-weighted imaging with deep learning by complex-valued convolutional neural network (ComplexNet): validation in clinical brain imaging

OBJECTIVES

Susceptibility-weighted imaging (SWI) is crucial for the characterization of intracranial hemorrhage and mineralization, but has the drawback of long acquisition times. We aimed to propose a deep learning model to accelerate SWI, and evaluate the clinical feasibility of this approach.

METHODS

A complex-valued convolutional neural network (ComplexNet) was developed to reconstruct high-quality SWI from highly accelerated k-space data. ComplexNet can leverage the inherently complex-valued nature of SWI data and learn richer representations by using complex-valued network. SWI data were acquired from 117 participants who underwent clinical brain MRI examination between 2019 and 2021, including patients with tumor, stroke, hemorrhage, traumatic brain injury, etc. Reconstruction quality was evaluated using quantitative image metrics and image quality scores, including overall image quality, signal-to-noise ratio, sharpness, and artifacts.

RESULTS

The average reconstruction time of ComplexNet was 19 ms per section (1.33 s per participant). ComplexNet achieved significantly improved quantitative image metrics compared to a conventional compressed sensing method and a real-valued network with acceleration rates of 5 and 8 (p < 0.001). Meanwhile, there was no significant difference between fully sampled and ComplexNet approaches in terms of overall image quality and artifacts (p > 0.05) at both acceleration rates. Furthermore, ComplexNet showed comparable diagnostic performance to the fully sampled SWI for visualizing a wide range of pathology, including hemorrhage, cerebral microbleeds, and brain tumor.

CONCLUSIONS

ComplexNet can effectively accelerate SWI while providing superior performance in terms of overall image quality and visualization of pathology for routine clinical brain imaging.

KEY POINTS

• The complex-valued convolutional neural network (ComplexNet) allowed fast and high-quality reconstruction of highly accelerated SWI data, with an average reconstruction time of 19 ms per section. • ComplexNet achieved significantly improved quantitative image metrics compared to a conventional compressed sensing method and a real-valued network with acceleration rates of 5 and 8 (p < 0.001). • ComplexNet showed comparable diagnostic performance to the fully sampled SWI for visualizing a wide range of pathology, including hemorrhage, cerebral microbleeds, and brain tumor.

Impact of Deep Learning Reconstruction Combined With a Sharpening Filter on Single-Shot Fast Spin-Echo T2-Weighted Magnetic Resonance Imaging of the Uterus

OBJECTIVE

This study aimed to evaluate the effects of deep learning (DL) reconstruction and a postprocessing sharpening filter on the image quality of single-shot fast spin-echo (SSFSE) T2-weighted imaging (T2WI) of the uterus.

MATERIALS AND METHODS

Fifty consecutive patients who underwent pelvic magnetic resonance imaging were included. Parasagittal T2WI with a slice thickness of 4 mm was obtained with the periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) and SSFSE sequences (mean scan time, 204 and 22 seconds, respectively). The following 3 types of SSFSE images were reconstructed, and the signal-to-noise ratio (SNR) and tissue contrast were assessed: conventional reconstruction (SSFSE-C), DL reconstruction (SSFSE-DL), and DL with a sharpening filter (SSFSE-DLF). Three radiologists independently assessed image quality, and area under the visual grading characteristics curve (AUCVGC) analysis was performed to compare the SSFSE and PROPELLER images.

RESULTS

Compared with that of the PROPELLER images, the SNR of the SSFSE-C, SSFSE-DL, and SSFSE-DLF images was significantly lower (P < 0.05), significantly higher (P < 0.05), and equivalent, respectively. The SSFSE-DL images exhibited significantly lower contrast between the junctional zone and myometrium than those obtained with the other sequences (P < 0.05). In qualitative comparisons with the PROPELLER images, all 3 SSFSE sequences, SSFSE-DL, and SSFSE-DLF demonstrated significantly higher scores for artifacts, noise, and sharpness, respectively (P < 0.01). The overall image quality of SSFSE-C (mean AUCVGC, 0.03; P < 0.01) and SSFSE-DL (mean AUCVGC, 0.23; P < 0.01) was rated as significantly inferior, whereas that of SSFSE-DLF (mean AUCVGC, 0.69) was equivalent or significantly higher (P < 0.01).

CONCLUSION

Using a combination of DL and a sharpening filter markedly increases the image quality of SSFSE of the uterus to the level of the PROPELLER sequence.

Current Landscape and Future Perspectives of Abbreviated MRI for Hepatocellular Carcinoma Surveillance

While ultrasound (US) is considered an important tool for hepatocellular carcinoma (HCC) surveillance, it has limited sensitivity for detecting early-stage HCC. Abbreviated MRI (AMRI) has recently gained popularity owing to better sensitivity in its detection of early-stage HCC than US, while also minimizing the time and cost in comparison to complete contrast-enhanced MRI, as AMRI includes only a few essential sequences tailored for detecting HCC. Currently, three AMRI protocols exist, namely gadoxetic acid-enhanced hepatobiliary-phase AMRI, dynamic contrast-enhanced AMRI, and non-enhanced AMRI. In this study, we discussed the rationale and technical details of AMRI techniques for achieving optimal surveillance performance. The strengths, weaknesses, and current issues of each AMRI protocol were also elucidated. Moreover, we scrutinized previously performed AMRI studies regarding clinical and technical factors. Reporting and recall strategies were discussed while considering the differences in AMRI protocols. A risk-stratified approach for the target population should be taken to maximize the benefits of AMRI and the cost-effectiveness should be considered. In the era of multiple HCC surveillance tools, patients need to be fully informed about their choices for better adherence to a surveillance program.

Deep learning-accelerated T2-weighted imaging of the prostate: Impact of further acceleration with lower spatial resolution on image quality

PURPOSE

To compare image quality in prostate MRI among standard T2-weighted imaging (T2-std), accelerated T2-weighted imaging (T2WI) with high resolution (T2-HR) and more accelerated T2WI with lower resolution (T2-LR) using both conventional reconstruction (C) and deep learning reconstruction (DL).

MATERIALS AND METHODS

In 46 consecutive patients, T2-std, T2-HR and T2-LR were acquired in 3:32 min, 1:06 min and 0.52 min, respectively. Both reconstruction techniques (C and DL) were applied to T2-HR and T2-LR. Five sets of images (T2-std, T2-HR_C, T2-LR_C, T2-HR_DL, and T2-LR_DL) for each patient were independently evaluated by two radiologists. Quantitative analysis including the signal-to-noise ratio (SNR) and contrast ratio (CR) and qualitative analysis with a 5-point scale for the sharpness of structures, ghosting or other artifacts, noise and overall image quality were performed.

RESULTS

The SNR was not different in either the peripheral zone (PZ) or transition zone (TZ) between T2-LR_DL and T2-std with the median value of 21.7 versus 22.6 in PZ and 16.5 versus 17.3 in TZ, respectively. The CR between the prostate gland and muscle was significantly lower on T2-HR_C and T2-LR_C than on T2-std. Most of the evaluated factors showed significantly lower scores on T2-HR_C and T2-LR_C than on T2-std. Although noise and overall image quality on T2-HR_DL and other artifacts on T2-LR_DL were rated significantly lower than on T2-std (median value 4.0 versus 4.5, P < 0.001; 4.5 versus 5.0, P = 0.001; 4.5 versus 5.0, P = 0.006, respectively), other factors did not differ between T2-std and T2-HR_DL or T2-LR_DL.

CONCLUSION

DL is useful to improve image quality in accelerated T2WI of the prostate gland. Using DL, accelerated T2WI with lower spatial resolution than T2-std can be achieved with similar image quality in much shorter scan time (75.5% reduction in the acquisition time).