Deep Learning Reconstruction Research Articles

Does Deep Learning Reconstruction Improve Ureteral Stone Detection and Subjective Image Quality in the CT Images of Patients with Metal Hardware?

Introduction: Diagnosing ureteral stones with low-dose CT in patients with metal hardware can be challenging because of image noise. The purpose of this study was to compare ureteral stone detection and image quality of low-dose and conventional CT scans with and without deep learning reconstruction (DLR) and metal artifact reduction (MAR) in the presence of metal hip prostheses. Methods: Ten urinary system combinations with 4 to 6 mm ureteral stones were implanted into a cadaver with bilateral hip prostheses. Each set was scanned under two different radiation doses (conventional dose [CD] = 115 mAs and ultra-low dose [ULD] = 6.0 mAs). Two scans were obtained for each dose as follows: one with and another without DLR and MAR. Two blinded radiologists ranked each image in terms of artifact, image noise, image sharpness, overall quality, and diagnostic confidence. Stone detection accuracy at each setting was calculated. Results: ULD with DLR and MAR improved subjective image quality in all five domains (p < 0.05) compared with ULD. In addition, the subjective image quality for ULD with DLR and MAR was greater than the subjective image quality for CD in all five domains (p < 0.05). Stone detection accuracy of ULD improved with the application of DLR and MAR (p < 0.05). Stone detection accuracy of ULD with DLR and MAR was similar to CD (p > 0.25). Conclusions: DLR with MAR may allow the application of low-dose CT protocols in patients with hip prostheses. Application of DLR and MAR to ULD provided a stone detection accuracy comparable with CD, reduced radiation exposure by 94.8%, and improved subjective image quality.

Deep Learning Reconstruction Combined With Conventional Acceleration Improves Image Quality of 3 T Brain MRI and Does Not Impact Quantitative Diffusion Metrics.

Deep learning reconstruction of magnetic resonance imaging (MRI) allows to either improve image quality of accelerated sequences or to generate high-resolution data. We evaluated the interaction of conventional acceleration and Deep Resolve Boost (DRB)-based reconstruction techniques of a single-shot echo-planar imaging (ssEPI) diffusion-weighted imaging (DWI) on image quality features in cerebral 3 T brain MRI and compared it with a state-of-the-art DWI sequence. In this prospective study, 24 patients received a standard of care ssEPI DWI and 5 additional adapted ssEPI DWI sequences, 3 of those with DRB reconstruction. Qualitative analysis encompassed rating of image quality, noise, sharpness, and artifacts. Quantitative analysis compared apparent diffusion coefficient (ADC) values region-wise between the different DWI sequences. Intraclass correlations, paired sampled t test, Wilcoxon signed rank test, and weighted Cohen κ were used. Compared with the reference standard, the acquisition time was significantly improved in accelerated DWI from 75 seconds up to 50% (39 seconds; P < 0.001). All tested DRB-reconstructed sequences showed significantly improved image quality, sharpness, and reduced noise (P < 0.001). Highest image quality was observed for the combination of conventional acceleration and DL reconstruction. In singular slices, more artifacts were observed for DRB-reconstructed sequences (P < 0.001). While in general high consistency was found between ADC values, increasing differences in ADC values were noted with increasing acceleration and application of DRB. Falsely pathological ADCs were rarely observed near frontal poles and optic chiasm attributable to susceptibility-related artifacts due to adjacent sinuses. In this comparative study, we found that the combination of conventional acceleration and DRB reconstruction improves image quality and enables faster acquisition of ssEPI DWI. Nevertheless, a tradeoff between increased acceleration with risk of stronger artifacts and high-resolution with longer acquisition time needs to be considered, especially for application in cerebral MRI.

High-resolution deep learning reconstruction for coronary CTA: compared efficacy of stenosis evaluation with other methods at in vitro and in vivo studies.

To directly compare coronary arterial stenosis evaluations by hybrid-type iterative reconstruction (IR), model-based IR (MBIR), deep learning reconstruction (DLR), and high-resolution deep learning reconstruction (HR-DLR) on coronary computed tomography angiography (CCTA) in both in vitro and in vivo studies. For the in vitro study, a total of three-vessel tube phantoms with diameters of 3 mm, 4 mm, and 5 mm and with simulated non-calcified stepped stenosis plaques with degrees of 0%, 25%, 50%, and 75% stenosis were scanned with area-detector CT (ADCT) and ultra-high-resolution CT (UHR-CT). Then, ADCT data were reconstructed using all methods, although UHR-CT data were reconstructed with hybrid-type IR, MBIR, and DLR. For the in vivo study, patients who had undergone CCTA at ADCT were retrospectively selected, and each CCTA data set was reconstructed with all methods. To compare the image noise and measurement accuracy at each of the stenosis levels, image noise, and inner diameter were evaluated and statistically compared. To determine the effect of HR-DLR on CAD-RADS evaluation accuracy, the accuracy of CAD-RADS categorization of all CCTAs was compared by using McNemar's test. The image noise of HR-DLR was significantly lower than that of others on ADCT and UHR-CT (p < 0.0001). At a 50% and 75% stenosis level for each phantom, hybrid-type IR showed a significantly larger mean difference on ADCT than did others (p < 0.05). At in vivo study, 31 patients were included. Accuracy on HR-DLR was significantly higher than that on hybrid-type IR, MBIR, or DLR (p < 0.0001). HR-DLR is potentially superior for coronary arterial stenosis evaluations to hybrid-type IR, MBIR, or DLR shown on CCTA. Question How do coronary arterial stenosis evaluations by hybrid-type IR, MBIR, DLR, and HR-DLR compare to coronary CT angiography? Findings HR-DLR showed significantly lower image noise and more accurate coronary artery disease reporting and data system (CAD-RADS) evaluation than others. Clinical relevance HR-DLR is potentially superior to other reconstruction methods for coronary arterial stenosis evaluations, as demonstrated by coronary CT angiography results on ADCT and as shown in both in vitro and in vivo studies.

Evaluating the Efficacy of Deep Learning Reconstruction in Reducing Radiation Dose for Computer-Aided Volumetry for Liver Tumor: A Phantom Study.

The purpose of this study was to compare radiation dose reduction capability for accurate liver tumor measurements of a computer-aided volumetry (CAD v ) software for filtered back projection (FBP), hybrid-type iterative reconstruction (IR), mode-based iterative reconstruction (MBIR), and deep learning reconstruction (DLR) at a phantom study. A commercially available anthropomorphic abdominal phantom was scanned five times with a 320-detector row CT at 600 mA, 400 mA, 200 mA, and 100 mA and reconstructed by four methods. Signal-to-noise ratios (SNRs) of all lesions within the arterial and portal-venous phase inserts were calculated, and SNR of the lesion phantom was compared with that of all reconstruction methods by means of Tukey's honestly significant difference (HSD) test. Then, tumor volume ( V ) of each nodule was automatically measured using commercially available CAD v software. To compare dose reduction capability for each reconstruction method at both phases, mean differences between measured V and standard references were compared by Tukey's honestly significant difference test among the four different reconstruction methods on CT obtained at each of the four tube currents. With each of the tube currents, SNRs for MBIR and DLR were significantly higher than those for FBP and hybrid-type IR ( p < 0.05). At the arterial phase, the mean difference in V for the CT protocol obtained at 600 or 100 mA and reconstructed with DLR was significantly smaller than that for others ( p < 0.05). At the portal-venous phase, the mean differences in V for the CT protocol obtained at 100 mA and reconstructed with hybrid-type IR, MBIR, and DLR were significantly smaller than that for FBP ( p < 0.05). Findings of our phantom study show that reconstruction method had influence on CAD v merits for abdominal CT with not only standard but also reduced dose examinations and that DLR can potentially yield better image quality and CAD v measurements than FBP, hybrid-type IR, or MBIR in this setting.

Diagnostic value of deep learning reconstruction-based subtraction CT-FFR in patients with calcified-related stenosis or stent implantation.

The application of coronary computed tomography angiography-derived fractional flow reserve (CT-FFR) is limited due to severe coronary calcium burden or stent implantation. This study aimed to explore the diagnostic value of subtraction CT-FFR with deep learning reconstruction (DLR) or hybrid iterative reconstruction (HIR) in detecting calcified-related hemodynamically significant stenosis, and the feasibility in the application of coronary stents. Between March 2020 and January 2022, consecutive patients with calcified-related stenosis or previous stent treatment who had undergone subtraction coronary computed tomography angiography (CTA) and invasive fractional flow reserve (FFR) were included in this prospective study. CT image data were reconstructed using HIR and DLR. The diagnostic performance of CT-FFR, and subtraction CT-FFR were evaluated. An FFR value of 0.8 or less was considered hemodynamically significant. A total of 30 patients with 52 calcified-related lesions and 14 coronary stents were included in this study. Subtraction CT-FFR outperformed the corresponding CT-FFR in detecting calcified-related hemodynamically significant stenosis and in the application of coronary stents, while there was no significant difference when subtraction CT-FFRDLR was compared with subtraction CT-FFRHIR (P>0.05). Lesion-based analysis showed the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy for subtraction CT-FFRDLR were 100.0%, 71.4%, 63.0%, 100% and 80.8%, respectively in detecting calcified-related hemodynamically significant stenosis, and were 100.0%, 83.3%, 88.9%, 100% and 92.9%, respectively in the application of coronary stents. Subtraction CT-FFR yielded optimal diagnostic performance for hemodynamically significant calcified-related stenosis, and the application of subtraction CT-FFR in the evaluation of coronary stents was feasible. The diagnostic performance of subtraction CT-FFRDLR was better than that of subtraction CT-FFRHIR, but there was no significant difference.

AcceleratedMulti-b-Value DWI Using Deep Learning Reconstruction: Image Quality Improvement and Microvascular Invasion Prediction in BCLC Stage A Hepatocellular Carcinoma.

AcceleratedMulti-b-Value DWI Using Deep Learning Reconstruction: Image Quality Improvement and Microvascular Invasion Prediction in BCLC Stage A Hepatocellular Carcinoma.

Calorie detection in dishes based on deep learning and 3D reconstruction

Calorie detection in dishes based on deep learning and 3D reconstruction

Unsupervised reconstruction of accelerated cardiac cine MRI using neural fields.

Unsupervised reconstruction of accelerated cardiac cine MRI using neural fields.

Laser ultrasonic reconstruction model for additive manufacturing based on compressed sensing theory

Laser ultrasonic reconstruction model for additive manufacturing based on compressed sensing theory

Ultra-low-dose coronary CT angiography via super-resolution deep learning reconstruction: impact on image quality, coronary plaque, and stenosis analysis.

To exploit the capability of super-resolution deep learning reconstruction (SR-DLR) to save radiation exposure from coronary CT angiography (CCTA) and assess its impact on image quality, coronary plaque quantification and characterization, and stenosis severity analysis. This prospective study included 50 patients who underwent low-dose (LD) and subsequent ultra-low-dose (ULD) CCTA scans. LD CCTA images were reconstructed with hybrid iterative reconstruction (HIR) and ULD CCTA images were reconstructed with HIR and SR-DLR. The objective parameters and subjective scores were compared. Coronary plaques were classified into three components: necrotic, fibrous or calcified content, with absolute volumes (mm3) recorded, and further characterized by percentage of calcified content. The four main coronary arteries were evaluated for the presence of stenosis. Moreover, 48 coronary segments in 9 patients were evaluated for the presence of significant stenosis, with invasive coronary angiography as a reference. Effective dose decreased by 60% from LD to ULD CCTA scans (2.01 ± 0.84 mSv vs. 0.80 ± 0.34 mSv, p < 0.001). ULD SR-DLR was non-inferior or even superior to LD HIR in terms of image quality and showed excellent agreements with LD HIR on the plaque volumes, characterization, and stenosis analysis (ICCs > 0.8). Moreover, there was no evidence of a difference in detecting significant coronary stenosis between the LD HIR and ULD SR-DLR (AUC: 0.90 vs. 0.89; p = 1.0). SR-DLR led to significant radiation dose savings from CCTA while ensuring high image quality and excellent performance in coronary plaque and stenosis analysis. Question How can radiation dose for coronary CT angiography be reduced without compromising image quality or affecting clinical decisions? Finding Super-resolution deep learning reconstruction (SR-DLR) algorithm allows for 60% dose reduction while ensuring high image quality and excellent performance in coronary plaque and stenosis analysis. Clinical relevance Dose optimization via SR-DLR has no detrimental effect on image quality, coronary plaque quantification and characterization, and stenosis severity analysis, which paves the way for its implementation in clinical practice.

High spatial resolution spectral imaging based on amplitude-phase joint modulation metasurfaces using a global optimization algorithm

Conventional spectral imaging techniques relying on dispersive spectrometers are limited by the trade-offs in size, cost, imaging speed, and other factors. Currently, metasurface-based spectral imaging has attracted considerable attention owing to its miniaturization, real-time detection, and low cost. However, introducing randomness in the spectral response function utilizing guided resonance in metasurfaces requires a large number of periodic elements, resulting in reduced spatial resolution in spectral imaging. Here, we propose a compact miniaturized spectrometer based on an aperiodic metasurface. The response function of the metasurface exhibits a rich variety of features based on the amplitude modulation of optical resonances, which is further enhanced by diffraction effects through phase modulation. By employing a genetic algorithm to optimize the layout of the metasurface, one can achieve low correlation coefficients and a small footprint for spectral encoders, marking a significant improvement in spatial resolution compared to previous metasurface-based spectral imaging approaches. Leveraging the deep learning reconstruction algorithm, we can achieve high-precision spectral recovery in the visible range of 400-700 nm with various narrowband and broadband spectra. The proposed method provides a new idea for hyperspectral imaging technology with high spatial resolution, noise robustness, and fast imaging speed.

Deep learning reconstruction of zero-echo time sequences to improve visualization of osseous structures and associated pathologies in MRI of cervical spine

ObjectivesTo determine whether deep learning-based reconstructions of zero-echo-time (ZTE-DL) sequences enhance image quality and bone visualization in cervical spine MRI compared to traditional zero-echo-time (ZTE) techniques, and to assess the added value of ZTE-DL sequences alongside standard cervical spine MRI for comprehensive pathology evaluation.MethodsIn this retrospective study, 52 patients underwent cervical spine MRI using ZTE, ZTE-DL, and T2-weighted 3D sequences on a 1.5-Tesla scanner. ZTE-DL sequences were reconstructed from raw data using the AirReconDL algorithm. Three blinded readers independently evaluated image quality, artifacts, and bone delineation on a 5-point Likert scale. Cervical structures and pathologies, including soft tissue and bone components in spinal canal and neural foraminal stenosis, were analyzed. Image quality was quantitatively assessed by signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR).ResultsMean image quality scores were 2.0 ± 0.7 for ZTE and 3.2 ± 0.6 for ZTE-DL, with ZTE-DL exhibiting fewer artifacts and superior bone delineation. Significant differences were observed between T2-weighted and ZTE-DL sequences for evaluating intervertebral space, anterior osteophytes, spinal canal, and neural foraminal stenosis (p < 0.05), with ZTE-DL providing more accurate assessments. ZTE-DL also showed improved evaluation of the osseous components of neural foraminal stenosis compared to ZTE (p < 0.05).ConclusionsZTE-DL sequences offer superior image quality and bone visualization compared to ZTE sequences and enhance standard cervical spine MRI in assessing bone involvement in spinal canal and neural foraminal stenosis.Critical relevance statementDeep learning-based reconstructions improve zero-echo-time sequences in cervical spine MRI by enhancing image quality and bone visualization. This advancement offers additional insights for assessing bone involvement in spinal canal and neural foraminal stenosis, advancing clinical radiology practice.Key PointsConventional MRI encounters challenges with osseous structures due to low signal-to-noise ratio.Zero-echo-time (ZET) sequences offer CT-like images of the C-spine but with lower quality.Deep learning reconstructions improve image quality of zero-echo-time sequences.ZTE sequences with deep learning reconstructions refine cervical spine osseous pathology assessment.These sequences aid assessment of bone involvement in spinal and foraminal stenosis.Graphical

Intraindividual Comparison of Image Quality Between Low-Dose and Ultra-Low-Dose Abdominal CT With Deep Learning Reconstruction and Standard-Dose Abdominal CT Using Dual-Split Scan.

The aim of this study was to intraindividually compare the conspicuity of focal liver lesions (FLLs) between low- and ultra-low-dose computed tomography (CT) with deep learning reconstruction (DLR) and standard-dose CT with model-based iterative reconstruction (MBIR) from a single CT using dual-split scan in patients with suspected liver metastasis via a noninferiority design. This prospective study enrolled participants who met the eligibility criteria at 2 tertiary hospitals in South Korea from June 2022 to January 2023. The criteria included (a) being aged between 20 and 85 years and (b) having suspected or known liver metastases. Dual-source CT scans were conducted, with the standard radiation dose divided in a 2:1 ratio between tubes A and B (67% and 33%, respectively). The voltage settings of 100/120 kVp were selected based on the participant's body mass index (<30 vs ≥30 kg/m2). For image reconstruction, MBIR was utilized for standard-dose (100%) images, whereas DLR was employed for both low-dose (67%) and ultra-low-dose (33%) images. Three radiologists independently evaluated FLL conspicuity, the probability of metastasis, and subjective image quality using a 5-point Likert scale, in addition to quantitative signal-to-noise and contrast-to-noise ratios. The noninferiority margins were set at -0.5 for conspicuity and -0.1 for detection. One hundred thirty-three participants (male = 58, mean body mass index = 23.0 ± 3.4 kg/m2) were included in the analysis. The low- and ultra-low- dose had a lower radiation dose than the standard-dose (median CT dose index volume: 3.75, 1.87 vs 5.62 mGy, respectively, in the arterial phase; 3.89, 1.95 vs 5.84 in the portal venous phase, P < 0.001 for all). Median FLL conspicuity was lower in the low- and ultra-low-dose scans compared with the standard-dose (3.0 [interquartile range, IQR: 2.0, 4.0], 3.0 [IQR: 1.0, 4.0] vs 3.0 [IQR: 2.0, 4.0] in the arterial phase; 4.0 [IQR: 1.0, 5.0], 3.0 [IQR: 1.0, 4.0] vs 4.0 [IQR: 2.0, 5.0] in the portal venous phases), yet within the noninferiority margin (P < 0.001 for all). FLL detection was also lower but remained within the margin (lesion detection rate: 0.772 [95% confidence interval, CI: 0.727, 0.812], 0.754 [0.708, 0.795], respectively) compared with the standard-dose (0.810 [95% CI: 0.770, 0.844]). Sensitivity for liver metastasis differed between the standard- (80.6% [95% CI: 76.0, 84.5]), low-, and ultra-low-doses (75.7% [95% CI: 70.2, 80.5], 73.7 [95% CI: 68.3, 78.5], respectively, P < 0.001 for both), whereas specificity was similar (P > 0.05). Low- and ultra-low-dose CT with DLR showed noninferior FLL conspicuity and detection compared with standard-dose CT with MBIR. Caution is needed due to a potential decrease in sensitivity for metastasis (clinicaltrials.gov/ NCT05324046).

Applications and Challenges of AI in PCB X-ray Inspection: A Comprehensive Study

As printed circuit boards (PCBs) continue to evolve in complexity and miniaturization, the demand for robust and efficient inspection techniques has become paramount in ensuring the quality and reliability of electronic devices. The application of machine learning and deep learning techniques has revolutionized PCB inspection in recent years, enabling the ability to automate and improve numerous elements of the process. In this article, a comprehensive analysis is performed on the applications and challenges of AI, encompassing techniques of deep learning and machine learning, in the domain of PCB X-ray scrutiny. The main focus of this research centers around defect detection, identification of components and layers, deep learning algorithms for image reconstruction, as well as the identification of defects and features in advanced packaging. This study examines the current cutting-edge advancements in each of these areas, closely examining the existing methodologies and technologies employed. Furthermore, it delves into the limitations and challenges inherent in PCB X-ray inspection, such as the unavailability of data, computational demands, and the interpretability of models. In addition, this article offers prospective insights and presents promising avenues like application of generative adversarial networks and deep learning reconstruction methods for future exploration.

Accelerated High-resolution T1- and T2-weighted Breast MRI with Deep Learning Super-resolution Reconstruction.

To assess the performance of an industry-developed deep learning (DL) algorithm to reconstruct low-resolution Cartesian T1-weighted dynamic contrast-enhanced (T1w) and T2-weighted turbo-spin-echo (T2w) sequences and compare them to standard sequences. Female patients with indications for breast MRI were included in this prospective study. The study protocol at 1.5 Tesla MRI included T1w and T2w. Both sequences were acquired in standard resolution (T1S and T2S) and in low-resolution with following DL reconstructions (T1DL and T2DL). For DL reconstruction, two convolutional networks were used: (1) Adaptive-CS-Net for denoising with compressed sensing, and (2) Precise-Image-Net for resolution upscaling of previously downscaled images. Overall image quality was assessed using 5-point-Likert scale (from 1=non-diagnostic to 5=excellent). Apparent signal-to-noise (aSNR) and contrast-to-noise (aCNR) ratios were calculated. Breast Imaging Reporting and Data System (BI-RADS) agreement between different sequence types was assessed. A total of 47 patients were included (mean age, 58±11 years). Acquisition time for T1DL and T2DL were reduced by 51% (44 vs. 90s per dynamic phase) and 46% (102 vs. 192s), respectively. T1DL and T2DL showed higher overall image quality (e.g., 4 [IQR, 4-4] for T1S vs. 5 [IQR, 5-5] for T1DL, P<0.001). Both, T1DL and T2DL revealed higher aSNR and aCNR than T1S and T2S (e.g., aSNR: 32.35±10.23 for T2S vs. 27.88±6.86 for T2DL, P=0.014). Cohen k agreement by BI-RADS assessment was excellent (0.962, P<0.001). DL for denoising and resolution upscaling reduces acquisition time and improves image quality for T1w and T2w breast MRI.

Characterization of hepatocellular carcinomawith CT with deep learning reconstruction compared with iterative reconstruction and 3-Tesla MRI.

This study compared the characteristics of lesions suspicious for hepatocellular carcinoma (HCC) and their LI-RADS classifications in adaptive statistical iterative reconstruction (ASIR) and deep learning reconstruction (DLR) to those of MR images, along with radiologist confidence. This prospective single-center trial included patients who underwent four-phase liver CT and multiphasic contrast-enhanced MRI within 7 days from February to August 2023. The lesion characteristics, LI-RADS classifications and confidence scores according to two radiologists on the ASIR, DLR and MRI techniques were compared. If the patient had at least one lesion, he was included in the HCC group, otherwise in the non-HCC group. MRI being the technique with the best sensitivity, concordance of lesions characteristics and LI-RADS classifications were calculated by weighted kappa between the ASIR and MRI and between the DLR and MRI. The confidence scores are expressed as the means and standard deviations. Eighty-nine patients were enrolled, 52 in the HCC group (67 years ± 9 [mean ± SD], 46 men) and 37 in the non-HCC group (68 years ± 9, 33 men). The concordance coefficient between the LI-RADS classification by ASIR and MRI was 0.64 [0.52; 0.76], showing good agreement, that by DLR and MRI was 0.83 [0.73; 0.92], showing excellent agreement. The diagnostic confidence in ASIR was 3.31 ± 0.95 (mean ± SD) and 3.0 ± 1.11, that in the DLR was 3.9 ± 0.88 and 4.11 ± 0.75, that in the MRI was 4.46 ± 0.80 and 4.57 ± 0.80. DLR provided excellent LI-RADS classification concordance with MRI, whereas ASIR provided good concordance. The radiologists' confidence was greater in the DLR than in the ASIR but remained highest in the MR group. Question Does the use of deep learning reconstructions (DLR) improve LI-RADS classification of suspicious hepatocellular carcinoma lesions compared to adaptive statistical iterative reconstructions (ASIR)? Findings DLR demonstrated superior concordance of LI-RADS classification with MRI compared to ASIR. It also provided greater diagnostic confidence than ASIR. Clinical relevance The use of DLR enhances radiologists' ability to visualize and characterize lesions suspected of being HCC, as well as their LI-RADS classification. Moreover, it also boosts their confidence in interpreting these images.

Enhancing repeatability of follicle counting with deep learning reconstruction high-resolution MRI in PCOS patients

Follicle count, a pivotal metric in the adjunct diagnosis of polycystic ovary syndrome (PCOS), is often underestimated when assessed via transvaginal ultrasonography compared to MRI. Nevertheless, the repeatability of follicle counting using traditional MR images is still compromised by motion artifacts or inadequate spatial resolution. In this prospective study involving 22 PCOS patients, we employed periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) and single-shot fast spin-echo (SSFSE) T2-weighted sequences to suppress motion artifacts in high-resolution ovarian MRI. Additionally, deep learning (DL) reconstruction was utilized to compensate noise in SSFSE imaging. We compared the performance of DL reconstruction SSFSE (SSFSE-DL) images with conventional reconstruction SSFSE (SSFSE-C) and PROPELLER images in follicle detection, employing qualitative indices (blurring artifacts, subjective noise, and conspicuity of follicles) and the repeatability of follicle number per ovary (FNPO) assessment. Despite similar subjective noise between SSFSE-DL and PROPELLER as assessed by one observer, SSFSE-DL images outperformed SSFSE-C and PROPELLER images across all three qualitative indices, resulting in enhanced repeatability in FNPO assessment. These results highlighted the potential of DL reconstruction high-resolution SSFSE imaging as a more dependable method for identifying polycystic ovary, thus facilitating more accurate diagnosis of PCOS in future clinical practices.

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.

Enhanced image quality and lesion detection in FLAIR MRI of white matter hyperintensity through deep learning-based reconstruction

Enhanced image quality and lesion detection in FLAIR MRI of white matter hyperintensity through deep learning-based reconstruction

ECG-triggered, highly undersampled contrast-enhanced MRA of the thoracic aorta using deep learning reconstruction

ECG-triggered, highly undersampled contrast-enhanced MRA of the thoracic aorta using deep learning reconstruction