Search Results (18)

Background/Objectives: There is a growing need for efficient prostate MRI protocols due to their increasing use in managing prostate cancer (PCa) and potential inclusion in screening. Deep learning reconstruction (DLR) may enhance MR acquisitions and improve image quality compared to conventional acceleration techniques. This systematic review examines DLR approaches to prostate MRI. Methods: A search of PubMed, Web of Science, and Google Scholar identified eligible studies comparing DLR to conventional reconstruction for prostate imaging. A narrative synthesis was performed to summarize the impact of DLR on acquisition time, image quality, and diagnostic performance. Results: Thirty-three studies showed that DLR can reduce acquisition times for T₂w and DWI imaging while maintaining or improving image quality. It did not significantly affect clinical tasks, such as biopsy decisions, and performed comparably to human readers in PI-RADS scoring and the detection of extraprostatic extension. However, AI models trained on conventional data might be less accurate with DLR images. The heterogeneity in image quality metrics among the studies prevented quantitative synthesis. Discussion: DLR has the potential to achieve substantial time savings in prostate MRI while maintaining image quality, which is especially relevant because of increased MRI demands. Future research should address the effect of DLR on clinically relevant downstream tasks, including AI algorithms’ performances and biopsy decisions, and explore task-specific accelerated protocols for screening, image-guided biopsy, and treatment. Full article

Background: T1 mapping has become a valuable technique in cardiac magnetic resonance imaging (CMR) for evaluating myocardial tissue properties. However, its quantitative accuracy remains limited by noise-related variability. Super-resolution deep learning-based reconstruction (SR-DLR) has shown potential in enhancing image quality across various MRI applications, yet its effectiveness in myocardial T1 mapping has not been thoroughly investigated. This study aimed to evaluate the impact of SR-DLR on noise reduction and measurement consistency in myocardial T1 mapping. Methods: This single-center retrospective observational study included 36 patients who underwent CMR between July and December 2023. T1 mapping was performed using a modified Look-Locker inversion recovery (MOLLI) sequence before and after contrast administration. Images were reconstructed with and without SR-DLR using identical scan data. Phantom studies using seven homemade phantoms with different Gd-DOTA dilution ratios were also conducted. Quantitative evaluation included mean T1 values, standard deviation (SD), and coefficient of variation (CV). Intraclass correlation coefficients (ICCs) were calculated to assess inter-observer agreement. Results: SR-DLR had no significant effect on mean native or post-contrast T1 values but significantly reduced SD and CV in both patient and phantom studies. SD decreased from 44.0 to 31.8 ms (native) and 20.0 to 14.1 ms (post-contrast), and CV also improved. ICCs indicated excellent inter-observer reproducibility (native: 0.822; post-contrast: 0.955). Conclusions: SR-DLR effectively reduces measurement variability while preserving T1 accuracy, enhancing the reliability of myocardial T1 mapping in both clinical and research settings. Full article

Objectives: We evaluated the noise reduction effects of deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) in brain computed tomography (CT). Methods: CT images of a 16 cm dosimetry phantom, a head phantom, and the brains of 11 patients were reconstructed using filtered backprojection (FBP) and various levels of DLR and HIR. The slice thickness was 5, 2.5, 1.25, and 0.625 mm. Phantom imaging was also conducted at various tube currents. The noise reduction ratio was calculated using FBP as the reference. For patient imaging, overall image quality was visually compared between DLR and HIR images that exhibited similar noise reduction ratios. Results: The noise reduction ratio increased with increasing levels of DLR and HIR in phantom and patient imaging. For DLR, noise reduction was more pronounced with decreasing slice thickness, while such thickness dependence was less evident for HIR. Although the noise reduction effects of DLR were similar between the head phantom and patients, they differed for the dosimetry phantom. Variations between imaging objects were small for HIR. The noise reduction ratio was low at low tube currents for the dosimetry phantom using DLR; otherwise, the influence of the tube current was small. In terms of visual image quality, DLR outperformed HIR in 1.25 mm thick images but not in thicker images. Conclusions: The degree of noise reduction using DLR depends on the slice thickness, tube current, and imaging object in addition to the level of DLR, which should be considered in the clinical use of DLR. DLR may be particularly beneficial for thin-slice imaging. Full article

Background: The utility of synthetic ECV, which does not require hematocrit values, has been reported; however, high-quality CT images are essential for accurate quantification. Second-generation Deep Learning Reconstruction (DLR) enables low-noise and high-resolution cardiac CT images. The aim of this study is to compare the differences among four reconstruction methods (hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), DLR, and second-generation DLR) in the quantification of synthetic ECV. Methods: We retrospectively analyzed 80 patients who underwent cardiac CT scans, including late contrast-enhanced CT (derivation cohort: n = 40, age 71 ± 12 years, 24 males; validation cohort: n = 40, age 67 ± 11 years, 25 males). In the derivation cohort, a linear regression analysis was performed between the hematocrit values from blood tests and the CT values of the right atrial blood pool on non-contrast CT. In the validation cohort, synthetic hematocrit values were calculated using the linear regression equation and the right atrial CT values from non-contrast CT. The correlation and mean difference between synthetic ECV and laboratory ECV calculated from actual blood tests were assessed. Results: Synthetic ECV and laboratory ECV showed a high correlation across all four reconstruction methods (R ≥ 0.95, p < 0.001). The bias and limit of agreement (LOA) in the Bland–Altman plot were lowest with the second-generation DLR (hybrid IR: bias = −0.21, LOA: 3.16; MBIR: bias = −0.79, LOA: 2.81; DLR: bias = −1.87, LOA: 2.90; second-generation DLR: bias = −0.20, LOA: 2.35). Conclusions: Synthetic ECV using second-generation DLR demonstrated the lowest bias and LOA compared to laboratory ECV among the four reconstruction methods, suggesting that second-generation DLR enables more accurate quantification. Full article

Background: Computed tomography (CT) is the preferred imaging modality for bone evaluation of the knee, while MRI of the bone is actively being developed. We present three techniques using short-interval delta ultrashort echo time (δUTE), field echo (FE), and FE with high resolution–deep learning reconstruction (HR–DLR) for direct bone MRI. Methods: Knees of healthy volunteers (n = 5, 3 females, 38 ± 17.2 years old) were imaged. CT-like images were generated by averaging images from multiple echoes and inverting. The bone signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were determined. Results: The δUTE depicted a cortical bone with high signal intensity but could not resolve trabeculae. In contrast, both the FE and FE HR–DLR images depicted cortical and trabecular bone with high signal. Quantitatively, while δUTE had a good bone SNR of ~100 and CNR of ~40 for the cortical bone, the SNR for the FE HR–DLR was significantly higher (p < 0.05), at over 400, and CNR at over 200. Conclusions: For 3D rendering of the bone surfaces, the δUTE provided better image contrast and separation of bone from ligaments and tendons than the FE sequences. While there still is no MRI technique that provides a perfect CT-like contrast, continued advancement of MRI techniques may provide benefits for specific use cases. Full article

A fully diagnostic MRI glioma protocol is key to monitoring therapy assessment but is time-consuming and especially challenging in critically ill and uncooperative patients. Artificial intelligence demonstrated promise in reducing scan time and improving image quality simultaneously. The purpose of this study was to investigate the diagnostic performance, the impact on acquisition acceleration, and the image quality of a deep learning optimized glioma protocol of the brain. Thirty-three patients with histologically confirmed glioblastoma underwent standardized brain tumor imaging according to the glioma consensus recommendations on a 3-Tesla MRI scanner. Conventional and deep learning-reconstructed (DLR) fluid-attenuated inversion recovery, and T2- and T1-weighted contrast-enhanced Turbo spin echo images with an improved in-plane resolution, i.e., super-resolution, were acquired. Two experienced neuroradiologists independently evaluated the image datasets for subjective image quality, diagnostic confidence, tumor conspicuity, noise levels, artifacts, and sharpness. In addition, the tumor volume was measured in the image datasets according to Response Assessment in Neuro-Oncology (RANO) 2.0, as well as compared between both imaging techniques, and various clinical–pathological parameters were determined. The average time saving of DLR sequences was 30% per MRI sequence. Simultaneously, DLR sequences showed superior overall image quality (all p < 0.001), improved tumor conspicuity and image sharpness (all p < 0.001, respectively), and less image noise (all p < 0.001), while maintaining diagnostic confidence (all p > 0.05), compared to conventional images. Regarding RANO 2.0, the volume of non-enhancing non-target lesions (p = 0.963), enhancing target lesions (p = 0.993), and enhancing non-target lesions (p = 0.951) did not differ between reconstruction types. The feasibility of the deep learning-optimized glioma protocol was demonstrated with a 30% reduction in acquisition time on average and an increased in-plane resolution. The evaluated DLR sequences improved subjective image quality and maintained diagnostic accuracy in tumor detection and tumor classification according to RANO 2.0. Full article

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

Background: Temporomandibular joint disorder (TMD) is a common medical condition. Cone beam computed tomography (CBCT) is effective in assessing TMD-related bone changes, but image noise may impair diagnosis. Emerging deep learning reconstruction algorithms (DLRs) could minimize noise and improve CBCT image clarity. This study compares standard and deep learning-enhanced CBCT images for image quality in detecting osteoarthritis-related degeneration in TMJs (temporomandibular joints). This study analyzed CBCT images of patients with suspected temporomandibular joint degenerative joint disease (TMJ DJD). Methods: The DLM reconstructions were performed with ClariCT.AI software. Image quality was evaluated objectively via CNR in target areas and subjectively by two experts using a five-point scale. Both readers also assessed TMJ DJD lesions. The study involved 50 patients with a mean age of 28.29 years. Results: Objective analysis revealed a significantly better image quality in DLM reconstructions (CNR levels; p < 0.001). Subjective assessment showed high inter-reader agreement (κ = 0.805) but no significant difference in image quality between the reconstruction types (p = 0.055). Lesion counts were not significantly correlated with the reconstruction type (p > 0.05). Conclusions: The analyzed DLM reconstruction notably enhanced the objective image quality in TMJ CBCT images but did not significantly alter the subjective quality or DJD lesion diagnosis. However, the readers favored DLM images, indicating the potential for better TMD diagnosis with CBCT, meriting more study. Full article

The aim of this study was to compare diagnostic performance for extra-prostatic extension (EPE) and image quality among three image datasets: conventional T2-weighted images (T2WI_conv, slice thickness, 3 mm) and high-resolution thin-slice T2WI (T2WI_HR, 2 mm), with and without deep learning reconstruction (DLR) in patients with prostatic cancer (PCa). A total of 88 consecutive patients (28 EPE-positive and 60 negative) diagnosed with PCa via radical prostatectomy who had undergone 3T-MRI were included. Two independent reviewers performed a crossover review in three sessions, in which each reviewer recorded five-point confidence scores for the presence of EPE and image quality using a five-point Likert scale. Pathologic topographic maps served as the reference standard. For both reviewers, T2WI_conv showed better diagnostic performance than T2WI_HR with and without DLR (AUCs, in order, for reviewer 1, 0.883, 0.806, and 0.772, p = 0.0006; for reviewer 2, 0.803, 0.762, and 0.745, p = 0.022). The image quality was also the best in T2WI_conv, followed by T2WI_{HR with DLR} and T2WI_{HR without DLR} for both reviewers (median, in order, 3, 4, and 5, p < 0.0001). In conclusion, T2WI_conv was optimal in regard to image quality and diagnostic performance for the evaluation of EPE in patients with PCa. Full article

Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity. Full article

Objective: This study aims to evaluate the feasibility of visualizing nasal cartilage using deep-learning-based reconstruction (DLR) fast spin-echo (FSE) imaging in comparison to three-dimensional fast spoiled gradient-echo (3D FSPGR) images. Materials and Methods: This retrospective study included 190 set images of 38 participants, including axial T1- and T2-weighted FSE images using DLR (T1WI_DL and T2WI_DL, belong to FSE_DL) and without using DLR (T1WI_O and T2WI_O, belong to FSE_O) and 3D FSPGR images. Subjective evaluation (overall image quality, noise, contrast, artifacts, and identification of anatomical structures) was independently conducted by two radiologists. Objective evaluation including signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) was conducted using manual region-of-interest (ROI)-based analysis. Coefficient of variation (CV) and Bland–Altman plots were used to demonstrate the intra-rater repeatability of measurements for cartilage thickness on five different images. Results: Both qualitative and quantitative results confirmed superior FSE_DL to 3D FSPGR images (both p < 0.05), improving the diagnosis confidence of the observers. Lower lateral cartilage (LLC), upper lateral cartilage (ULC), and septal cartilage (SP) were relatively well delineated on the T2WI_DL, while 3D FSPGR showed poorly on the septal cartilage. For the repeatability of cartilage thickness measurements, T2WI_DL showed the highest intra-observer (%CV = 8.7% for SP, 9.5% for ULC, and 9.7% for LLC) agreements. In addition, the acquisition time for T1WI_DL and T2WI_DL was respectively reduced by 14.2% to 29% compared to 3D FSPGR (both p < 0.05). Conclusions: Two-dimensional equivalent-thin-slice T1- and T2-weighted images using DLR showed better image quality and shorter scan time than 3D FSPGR and conventional construction images in nasal cartilages. The anatomical details were preserved without losing clinical performance on diagnosis and prognosis, especially for pre-rhinoplasty planning. Full article

Background: In coronary computed tomography angiography (CCTA), the main issue of image quality is noise in obese patients, blooming artifacts due to calcium and stents, high-risk coronary plaques, and radiation exposure to patients. Objective: To compare the CCTA image quality of deep learning-based reconstruction (DLR) with that of filtered back projection (FBP) and iterative reconstruction (IR). Methods: This was a phantom study of 90 patients who underwent CCTA. CCTA images were acquired using FBP, IR, and DLR. In the phantom study, the aortic root and the left main coronary artery in the chest phantom were simulated using a needleless syringe. The patients were classified into three groups according to their body mass index. Noise, the signal-to-noise ratio (SNR), and the contrast-to-noise ratio (CNR) were measured for image quantification. A subjective analysis was also performed for FBP, IR, and DLR. Results: According to the phantom study, DLR reduced noise by 59.8% compared to FBP and increased SNR and CNR by 121.4% and 123.6%, respectively. In a patient study, DLR reduced noise compared to FBP and IR. Furthermore, DLR increased the SNR and CNR more than FBP and IR. In terms of subjective scores, DLR was higher than FBP and IR. Conclusion: In both phantom and patient studies, DLR effectively reduced image noise and improved SNR and CNR. Therefore, the DLR may be useful for CCTA examinations. Full article

The study’s aim was to assess the impact of a deep learning image reconstruction algorithm (Precise Image; DLR) on image quality and liver metastasis conspicuity compared with an iterative reconstruction algorithm (IR). This retrospective study included all consecutive patients with at least one liver metastasis having been diagnosed between December 2021 and February 2022. Images were reconstructed using level 4 of the IR algorithm (i4) and the Standard/Smooth/Smoother levels of the DLR algorithm. Mean attenuation and standard deviation were measured by placing the ROIs in the fat, muscle, healthy liver, and liver tumor. Two radiologists assessed the image noise and image smoothing, overall image quality, and lesion conspicuity using Likert scales. The study included 30 patients (mean age 70.4 ± 9.8 years, 17 men). The mean CTDI_vol was 6.3 ± 2.1 mGy, and the mean dose-length product 314.7 ± 105.7 mGy.cm. Compared with i4, the HU values were similar in the DLR algorithm at all levels for all tissues studied. For each tissue, the image noise significantly decreased with DLR compared with i4 (p < 0.01) and significantly decreased from Standard to Smooth (−26 ± 10%; p < 0.01) and from Smooth to Smoother (−37 ± 8%; p < 0.01). The subjective image assessment confirmed that the image noise significantly decreased between i4 and DLR (p < 0.01) and from the Standard to Smoother levels (p < 0.01), but the opposite occurred for the image smoothing. The highest scores for overall image quality and conspicuity were found for the Smooth and Smoother levels. Full article

Background: Children have a potential risk from radiation exposure because they are more sensitive to radiation than adults. Objective: The purpose of this work is to estimate image quality according to tube voltage (kV) and radiation dose in pediatric computed tomography (CT) using deep learning reconstruction (DLR). Methods: Phantom images of children and adults were obtained for kV, radiation dose, and image reconstruction methods. The CT emits a fan beam to the opposite detector, and the geometry of the detector was symmetrical. Phantom images of children and adults were acquired at a volume CT dose index (CTDIvol) from 0.5 to 10.0 mGy for tube voltages at 80, 100, and 120 kV. A DLR was used to reconstruct the phantom image, and filtered back projection (FBP) and iterative reconstruction (IR) were also performed for comparison with the DLR. Image quality was evaluated by measuring the contrast-to-noise ratio (CNR) and noise. Results: Under the same imaging conditions, the DLR images of pediatric and adult phantoms generally provided improved CNR and noise compared with the FBP and IR images. At a similar CNR and noise, the FBP, IR, and DLR of the pediatric images showed a dose reduction compared with the FBP, IR, and DLR of the adult images, respectively. In terms of the effect of tube voltage, the CNR of the 100 kV DLR images was higher than that of the 120 kV DLR images. Conclusion: According to the results, since pediatric CT images maintain the same image quality at lower doses compared with adult CT images, DLR can improve image quality while reducing the radiation dose in children’s abdominal CT scans. Full article

Objective: To compare the image quality of computed tomography angiography of the supra-aortic arteries (CTSA) at different tube voltages in low doses settings with deep learning-based image reconstruction (DLR) vs. hybrid iterative reconstruction (H-IR). Methods: We retrospectively reviewed 102 patients who underwent CTSA systematically reconstructed with both DLR and H-IR. We assessed the image quality both quantitatively and qualitatively at 11 arterial segmental levels and 3 regional levels. Radiation-dose parameters were recorded and the effective dose was calculated. Eighty-six patients were eligible for analysis Of these patients, 27 were imaged with 120 kVp, 30 with 100 kVp, and 29 with 80 kVp. Results: The effective dose in 120 kVp, 100 kVp and 80 kVp was 1.5 ± 0.4 mSv, 1.1 ± 0.3 mSv and 0.68 ± 0.1 mSv, respectively (p < 0.01). Comparing 80 kVp + DLR vs. 120 and 100 kVp + H-IR CT scans, the mean overall arterial attenuation was about 64% and 34% higher (625.9 ± 118.5 HU vs. 382.3 ± 98.6 HU and 468 ± 118.5 HU; p < 0.01) without a significant difference in terms of image noise (17.7 ± 4.9 HU vs. 17.5 ± 5.2; p = 0.7 and 18.1 ± 5.4; p = 0.3) and signal-to-ratio increased by 59% and 33%, respectively (37.9 ± 12.3 vs. 23.8 ± 9.7 and 28.4 ± 12.5). This protocol also provided superior image quality in terms of qualitative parameters, compared to standard-kVp protocols with H-IR. Highest subjective image-quality grades for vascular segments close to the aorta were obtained with the 100 kVp + DLR protocol. Conclusions: DLR significantly reduced image noise and improved the overall image quality of CTSA with both low and standard tube voltages and at all vascular segments. CT that was acquired with 80 kVp and reconstructed with DLR yielded better overall image quality compared to higher kVp values with H-IR, while reducing the radiation dose by half, but it has limitations for arteries that are close to the aortic arch. Full article