Koichiro Yasaka
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Koichiro Yasaka has a total of 218 co-authors. Here are the top co-authors by number of shared publications:
Osamu Abe
The University of Tokyo, Tokyo, Japan
33 shared publications- Osamu Abe
Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
23 shared publications - Shigeru Kiryu
International University of Health and Welfare
15 shared publications - Hiroyuki Akai
Department of Radiology, Institute of Medical Science, The University of Tokyo, Tokyo, Japan
11 shared publications Jun Kanzawa
Department of Radiology, The University of Tokyo, Tokyo, Japan
11 shared publicationsKuni Ohtomo
11 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Wiley in Journal of Magnetic Resonance Imaging
Simplifying CT / MRI LI ‐ RADS v2018 Maintains Diagnostic Performance: An Individual Participant Data Meta‐Analysis
Background: The Liver Imaging Reporting and Data System (LI‐RADS) diagnostic algorithm assesses hepatocellular carcinoma (HCC) probability of liver observations in high‐risk individuals, but complexity may limit its adoption. Purpose: To evaluate whether LI‐RADS v2018 can be simplified without impairing diagnostic performance by removing threshold growth (TG) and reducing size cut‐offs. Study Type: Retrospective meta‐analysis. Population: Eight thousand five hundred eighty‐two patients (mean age: 59 ± 11 years; 6610 male) at risk for HCC with CT/MRI (986 CT, 6554 MRI, and 1042 CT/MRI). Field Strength/Sequence: Field strength: 1.5T and 3.0T; sequences varied by institution per LI‐RADS technical requirements. Assessment: LI‐RADS v2018 using major features only was compared with seven simplifications removing TG and/or applying single size cut‐offs (≥ 10, ≥ 15, and ≥ 20 mm) in individual participant data (IPD) of 64 studies (29 institutions, 11 countries) from the LI‐RADS Living Systematic Review and IPD Meta‐analysis Project. Risk of bias was assessed with QUADAS‐2. Statistical Tests: Summary receiver operating characteristic curves estimated area under the curve (AUC) across LR‐3 to LR‐5; LR‐5 sensitivity, specificity, and positive predictive value (PPV) were estimated using a one‐step bivariate mixed‐effects model. Differences were assessed by cluster bootstrap. p < 0.05 indicated significance, uncorrected for multiple comparisons. Results: Nine thousand four hundred six observations were included. Excluding TG with a 10‐mm cut‐off showed AUC similar to LI‐RADS v2018 (0.80 vs. 0.81, p = 0.44) and significantly higher LR‐5 sensitivity (73.8% vs. 71.8%) with similar specificity (72.5% vs. 73.7%, p = 0.13) and PPV (97.8% vs. 97.8%, p = 0.73). Removing TG with 15‐mm and 20‐mm cut‐offs had significantly lower AUC than v2018 (−0.03 [95% CI: −0.041, −0.019]; −0.043 [−0.054, −0.032], respectively) and sensitivity (−13.2% [95% CI: −14.5%, −12.0%]; −30.1% [−31.7%, −28.5%], respectively). Of the 64 studies, 17 had low‐risk of bias, and 56 had low applicability concerns. Conclusion: Simplifying LI‐RADS v2018 by removing TG and using a 10‐mm size cut‐off preserved diagnostic table AUC while improving LR‐5 sensitivity without loss of specificity or PPV. Protocol Registration: Open Science Framework ( https://osf.io/cjwgp ). Evidence Level: 3. Technical Efficiency: Stage 2.
- 2 November 2026
- Published by Wiley in Journal of Magnetic Resonance Imaging
Open AccessSimplifying CT / MRI LI ‐ RADS v2018 Maintains Diagnostic Performance: An Individual Participant Data Meta‐Analysis
Background: The Liver Imaging Reporting and Data System (LI‐RADS) diagnostic algorithm assesses hepatocellular carcinoma (HCC) probability of liver observations in high‐risk individuals, but complexity may limit its adoption. Purpose: To evaluate whether LI‐RADS v2018 can be simplified without impairing diagnostic performance by removing threshold growth (TG) and reducing size cut‐offs. Study Type: Retrospective meta‐analysis. Population: Eight thousand five hundred eighty‐two patients (mean age: 59 ± 11 years; 6610 male) at risk for HCC with CT/MRI (986 CT, 6554 MRI, and 1042 CT/MRI). Field Strength/Sequence: Field strength: 1.5T and 3.0T; sequences varied by institution per LI‐RADS technical requirements. Assessment: LI‐RADS v2018 using major features only was compared with seven simplifications removing TG and/or applying single size cut‐offs (≥ 10, ≥ 15, and ≥ 20 mm) in individual participant data (IPD) of 64 studies (29 institutions, 11 countries) from the LI‐RADS Living Systematic Review and IPD Meta‐analysis Project. Risk of bias was assessed with QUADAS‐2. Statistical Tests: Summary receiver operating characteristic curves estimated area under the curve (AUC) across LR‐3 to LR‐5; LR‐5 sensitivity, specificity, and positive predictive value (PPV) were estimated using a one‐step bivariate mixed‐effects model. Differences were assessed by cluster bootstrap. p < 0.05 indicated significance, uncorrected for multiple comparisons. Results: Nine thousand four hundred six observations were included. Excluding TG with a 10‐mm cut‐off showed AUC similar to LI‐RADS v2018 (0.80 vs. 0.81, p = 0.44) and significantly higher LR‐5 sensitivity (73.8% vs. 71.8%) with similar specificity (72.5% vs. 73.7%, p = 0.13) and PPV (97.8% vs. 97.8%, p = 0.73). Removing TG with 15‐mm and 20‐mm cut‐offs had significantly lower AUC than v2018 (−0.03 [95% CI: −0.041, −0.019]; −0.043 [−0.054, −0.032], respectively) and sensitivity (−13.2% [95% CI: −14.5%, −12.0%]; −30.1% [−31.7%, −28.5%], respectively). Of the 64 studies, 17 had low‐risk of bias, and 56 had low applicability concerns. Conclusion: Simplifying LI‐RADS v2018 by removing TG and using a 10‐mm size cut‐off preserved diagnostic table AUC while improving LR‐5 sensitivity without loss of specificity or PPV. Protocol Registration: Open Science Framework ( https://osf.io/cjwgp ). Evidence Level: 3. Technical Efficiency: Stage 2.
- Open Access
- 13 June 2026
- Published by Springer Nature in Abdominal Radiology
- Vol. 51 (12) , 6561-6571
Super-resolution deep learning reconstruction improves the depiction of peripancreatic arteries and image quality in pancreatic cancer CT
Purpose: Accurate identification of peripancreatic arteries in pancreatic ductal adenocarcinoma (PDAC) is essential for determining surgical strategy and prognosis. This study compared super-resolution deep learning reconstruction (SR-DLR) with normal-resolution deep learning reconstruction (NR-DLR) and hybrid iterative reconstruction (HIR) in the depiction of peripancreatic arteries in patients with PDAC undergoing pancreatic dynamic CT. Methods: This retrospective study included 40 patients (mean age, 70.8 ± 9.3 years) with pathologically confirmed PDAC who underwent pancreatic dynamic CT. Images were reconstructed using SR-DLR, NR-DLR, and HIR. In quantitative image analyses, CT attenuation, image noise, contrast-to-noise ratio (CNR), edge rise slope (ERS), and edge rise distance (ERD) were assessed. In qualitative image analyses, five radiologists independently evaluated arterial depiction of major arteries and small peripancreatic arteries, tumor–vessel interface, image noise, image sharpness, diagnostic acceptability, and tumor conspicuity. Statistical analyses were performed using paired t -tests and the Wilcoxon signed-rank test with Bonferroni correction. Results: SR-DLR showed higher CT attenuation, lower image noise, and higher CNR than NR-DLR and HIR (all p < 0.001). For both the superior mesenteric artery and pancreatic parenchyma, ERS was higher with SR-DLR than with NR-DLR and HIR (all p ≤ 0.002), whereas ERD was lower than with NR-DLR and HIR (all p ≤ 0.001). In qualitative image analyses, SR-DLR achieved the highest scores for small peripancreatic arteries and all qualitative items except for the depiction of major peripancreatic arteries ( p < 0.001). Conclusion: SR-DLR improved quantitative image quality and enhanced the qualitative depiction of small peripancreatic arteries and the tumor–vessel interface in pancreatic dynamic CT for patients with PDAC.
- 13 June 2026
- Published by Springer Nature in Abdominal Radiology
- Vol. 51 (12) , 6561-6571
Open AccessSuper-resolution deep learning reconstruction improves the depiction of peripancreatic arteries and image quality in pancreatic cancer CT
Purpose: Accurate identification of peripancreatic arteries in pancreatic ductal adenocarcinoma (PDAC) is essential for determining surgical strategy and prognosis. This study compared super-resolution deep learning reconstruction (SR-DLR) with normal-resolution deep learning reconstruction (NR-DLR) and hybrid iterative reconstruction (HIR) in the depiction of peripancreatic arteries in patients with PDAC undergoing pancreatic dynamic CT. Methods: This retrospective study included 40 patients (mean age, 70.8 ± 9.3 years) with pathologically confirmed PDAC who underwent pancreatic dynamic CT. Images were reconstructed using SR-DLR, NR-DLR, and HIR. In quantitative image analyses, CT attenuation, image noise, contrast-to-noise ratio (CNR), edge rise slope (ERS), and edge rise distance (ERD) were assessed. In qualitative image analyses, five radiologists independently evaluated arterial depiction of major arteries and small peripancreatic arteries, tumor–vessel interface, image noise, image sharpness, diagnostic acceptability, and tumor conspicuity. Statistical analyses were performed using paired t -tests and the Wilcoxon signed-rank test with Bonferroni correction. Results: SR-DLR showed higher CT attenuation, lower image noise, and higher CNR than NR-DLR and HIR (all p < 0.001). For both the superior mesenteric artery and pancreatic parenchyma, ERS was higher with SR-DLR than with NR-DLR and HIR (all p ≤ 0.002), whereas ERD was lower than with NR-DLR and HIR (all p ≤ 0.001). In qualitative image analyses, SR-DLR achieved the highest scores for small peripancreatic arteries and all qualitative items except for the depiction of major peripancreatic arteries ( p < 0.001). Conclusion: SR-DLR improved quantitative image quality and enhanced the qualitative depiction of small peripancreatic arteries and the tumor–vessel interface in pancreatic dynamic CT for patients with PDAC.
- Open Access
- 1 June 2026
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 19 (3) , 988-997
Evaluation of super-resolution deep learning reconstruction on three-dimensional constructive interference in steady state for enhanced visualization of vestibular schwannomas
We evaluated whether, compared with conventional deep learning reconstruction (DLR) and zero-filling interpolation (ZIP), super-resolution DLR (SR-DLR) enhances the visualization of vestibular schwannomas and cranial nerves in three-dimensional constructive interference in steady state (3D-CISS) magnetic resonance (MR) imaging. This retrospective study analyzed 39 patients with vestibular schwannomas who underwent 3T MR imaging with 3D-CISS. Axial images were reconstructed using SR-DLR, DLR, and ZIP. Three readers independently evaluated tumor depiction, depiction of facial and vestibulocochlear nerves, sharpness, noise, artifacts, and diagnostic acceptability. Quantitative indicators included edge rise distance (ERD) and edge rise slope (ERS) measured along a linear region of interest (ROI) drawn perpendicularly across the tumor–cistern cerebrospinal fluid (CSF) boundary, and signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and contrast ratio (CR) calculated from circular ROIs (3–5 mm) placed in the tumor and prepontine CSF. SR-DLR significantly improved visualization of vestibular schwannoma and facial and vestibulocochlear nerves compared with ZIP ( p < 0.001). Nerve depiction ratings varied between readers when comparing SR-DLR and DLR. SR-DLR yielded significantly better sharpness, lower ERD and higher ERS than both DLR and ZIP ( p < 0.001). Artifacts showed no significant differences. No clear deterioration in noise was noted. Objectively, SR-DLR showed significantly higher CR than DLR ( p = 0.023) and ZIP ( p < 0.001). SNR and CNR were significantly higher with SR-DLR than ZIP, but comparable to DLR. SR-DLR improves sharpness and lesion conspicuity on 3D-CISS imaging without a clear increase in artifacts or noise compared with ZIP.
- 1 June 2026
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 19 (3) , 988-997
Open AccessEvaluation of super-resolution deep learning reconstruction on three-dimensional constructive interference in steady state for enhanced visualization of vestibular schwannomas
We evaluated whether, compared with conventional deep learning reconstruction (DLR) and zero-filling interpolation (ZIP), super-resolution DLR (SR-DLR) enhances the visualization of vestibular schwannomas and cranial nerves in three-dimensional constructive interference in steady state (3D-CISS) magnetic resonance (MR) imaging. This retrospective study analyzed 39 patients with vestibular schwannomas who underwent 3T MR imaging with 3D-CISS. Axial images were reconstructed using SR-DLR, DLR, and ZIP. Three readers independently evaluated tumor depiction, depiction of facial and vestibulocochlear nerves, sharpness, noise, artifacts, and diagnostic acceptability. Quantitative indicators included edge rise distance (ERD) and edge rise slope (ERS) measured along a linear region of interest (ROI) drawn perpendicularly across the tumor–cistern cerebrospinal fluid (CSF) boundary, and signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and contrast ratio (CR) calculated from circular ROIs (3–5 mm) placed in the tumor and prepontine CSF. SR-DLR significantly improved visualization of vestibular schwannoma and facial and vestibulocochlear nerves compared with ZIP ( p < 0.001). Nerve depiction ratings varied between readers when comparing SR-DLR and DLR. SR-DLR yielded significantly better sharpness, lower ERD and higher ERS than both DLR and ZIP ( p < 0.001). Artifacts showed no significant differences. No clear deterioration in noise was noted. Objectively, SR-DLR showed significantly higher CR than DLR ( p = 0.023) and ZIP ( p < 0.001). SNR and CNR were significantly higher with SR-DLR than ZIP, but comparable to DLR. SR-DLR improves sharpness and lesion conspicuity on 3D-CISS imaging without a clear increase in artifacts or noise compared with ZIP.
- Open Access
- 18 May 2026
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 19 (3) , 950-960
Improved delineation of the cystic artery using super-resolution deep learning reconstruction in contrast-enhanced abdominal computed tomography
This study aimed to evaluate the image quality and delineation of the cystic artery and related abdominal vessels using Super-Resolution Deep Learning Reconstruction (SR-DLR) on contrast-enhanced computed tomography (CT), compared with standard Deep Learning Reconstruction (DLR). This retrospective study included 60 patients who underwent contrast-enhanced abdominal CT with an arterial phase between April and June 2025. Images were reconstructed using both SR-DLR and DLR algorithms. Quantitative evaluation included CT attenuation values, image noise, contrast-to-noise ratio (CNR), full width at half maximum (FWHM), and edge rise distance and edge rise slope (ERD/ERS) for the superior mesenteric artery (SMA) and proper hepatic artery (PHA). Three radiologists independently performed qualitative assessments of cystic artery, PHA, SMA, and cystic duct delineation, as well as image noise, sharpness, and artifacts. SR-DLR showed significantly lower image noise and higher CT attenuation values and CNR than DLR ( p < 0.001). SR-DLR yielded higher ERS and lower ERD for the PHA and SMA compared to DLR ( p ≤ 0.006). Qualitative analysis demonstrated that all three readers rated cystic artery delineation as significantly better with SR-DLR than with DLR ( p ≤ 0.018). SR-DLR also achieved higher scores for image sharpness and diagnostic acceptability ( p ≤ 0.001). SR-DLR significantly improves the delineation and image quality of the cystic artery and adjacent vascular anatomy compared with DLR. While no significant improvement in cystic artery detection was observed, the enhanced image quality may better support clinical confidence in preoperative planning for cholecystectomy and interventional radiology procedures.
- 18 May 2026
- Published by Springer Nature in Radiological Physics and Technology
- Vol. 19 (3) , 950-960
Open AccessImproved delineation of the cystic artery using super-resolution deep learning reconstruction in contrast-enhanced abdominal computed tomography
This study aimed to evaluate the image quality and delineation of the cystic artery and related abdominal vessels using Super-Resolution Deep Learning Reconstruction (SR-DLR) on contrast-enhanced computed tomography (CT), compared with standard Deep Learning Reconstruction (DLR). This retrospective study included 60 patients who underwent contrast-enhanced abdominal CT with an arterial phase between April and June 2025. Images were reconstructed using both SR-DLR and DLR algorithms. Quantitative evaluation included CT attenuation values, image noise, contrast-to-noise ratio (CNR), full width at half maximum (FWHM), and edge rise distance and edge rise slope (ERD/ERS) for the superior mesenteric artery (SMA) and proper hepatic artery (PHA). Three radiologists independently performed qualitative assessments of cystic artery, PHA, SMA, and cystic duct delineation, as well as image noise, sharpness, and artifacts. SR-DLR showed significantly lower image noise and higher CT attenuation values and CNR than DLR ( p < 0.001). SR-DLR yielded higher ERS and lower ERD for the PHA and SMA compared to DLR ( p ≤ 0.006). Qualitative analysis demonstrated that all three readers rated cystic artery delineation as significantly better with SR-DLR than with DLR ( p ≤ 0.018). SR-DLR also achieved higher scores for image sharpness and diagnostic acceptability ( p ≤ 0.001). SR-DLR significantly improves the delineation and image quality of the cystic artery and adjacent vascular anatomy compared with DLR. While no significant improvement in cystic artery detection was observed, the enhanced image quality may better support clinical confidence in preoperative planning for cholecystectomy and interventional radiology procedures.
- Open Access
- 14 March 2026
- Published by Springer Nature in Neuroradiology
- Vol. 68 (4) , 1007-1016
Super-resolution deep learning reconstruction enhances visualization of cerebral aneurysms on magnetic resonance angiography
Purpose To evaluate the depiction of cerebral aneurysms on magnetic resonance angiography (MRA) reconstructed using super-resolution deep learning reconstruction (SR-DLR). Methods We retrospectively reviewed the MRA images of 79 patients (49 with cerebral aneurysms and 30 without). The MRA images were subjected to SR-DLR and compared with the original images using both quantitative (signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) for the basilar artery (BA) and aneurysms; full width at half maximum (FWHM), edge rise distance (ERD), and edge rise slope (ERS) for the BA) and qualitative metrics (depiction of aneurysms and BA, image sharpness, noise, artifacts, and overall image quality performed by three radiologists). Statistical comparisons were performed using a paired t-test for quantitative metrics and the Wilcoxon signed-rank test for qualitative metrics. Results SR-DLR significantly improved SNR, CNR, and ERD compared with the original images. ERS values showed a trend toward improvement with SR-DLR, whereas FWHM showed no significant difference. Depiction of the vasculature, image sharpness, noise, and overall image quality were rated as significantly better for SR-DLR by all readers. Most readers rated that the depiction of aneurysms was improved with SR-DLR, particularly for aneurysms < 5 mm. The assessment of artifacts varied among readers. Conclusion SR-DLR significantly improves the image quality of MRA and enhances the visualization of cerebral aneurysms, with greater improvements in the depiction of smaller aneurysms.
- 14 March 2026
- Published by Springer Nature in Neuroradiology
- Vol. 68 (4) , 1007-1016
Open AccessSuper-resolution deep learning reconstruction enhances visualization of cerebral aneurysms on magnetic resonance angiography
Purpose To evaluate the depiction of cerebral aneurysms on magnetic resonance angiography (MRA) reconstructed using super-resolution deep learning reconstruction (SR-DLR). Methods We retrospectively reviewed the MRA images of 79 patients (49 with cerebral aneurysms and 30 without). The MRA images were subjected to SR-DLR and compared with the original images using both quantitative (signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) for the basilar artery (BA) and aneurysms; full width at half maximum (FWHM), edge rise distance (ERD), and edge rise slope (ERS) for the BA) and qualitative metrics (depiction of aneurysms and BA, image sharpness, noise, artifacts, and overall image quality performed by three radiologists). Statistical comparisons were performed using a paired t-test for quantitative metrics and the Wilcoxon signed-rank test for qualitative metrics. Results SR-DLR significantly improved SNR, CNR, and ERD compared with the original images. ERS values showed a trend toward improvement with SR-DLR, whereas FWHM showed no significant difference. Depiction of the vasculature, image sharpness, noise, and overall image quality were rated as significantly better for SR-DLR by all readers. Most readers rated that the depiction of aneurysms was improved with SR-DLR, particularly for aneurysms < 5 mm. The assessment of artifacts varied among readers. Conclusion SR-DLR significantly improves the image quality of MRA and enhances the visualization of cerebral aneurysms, with greater improvements in the depiction of smaller aneurysms.
- Open Access
- 3 February 2026
- Published by Springer Nature in Cureus
- Vol. 18 (2)
Clinical Value of Bronchiectasis and Airspace Enlargement Depicted on Iodine Map in Patients With Interstitial Lung Disease: A Pilot Study
Objectives To investigate the degree and clinical meaning of bronchiectasis and airspace enlargement depicted on the iodine map in dual-energy CT pulmonary angiography of patients with interstitial lung disease, as a pilot study. Methods This retrospective study included 25 patients with interstitial lung disease who underwent dual-energy CT pulmonary angiography from November 2019 to February 2023. The iodine map and the 70 keV monochromatic image were reconstructed. Three readers independently evaluated the degree of bronchiectasis and airspace enlargement in the iodine map and monochromatic image. The time course of bronchiectasis and airspace enlargement was evaluated by comparing monochromatic images and follow-up conventional CT images for patients with follow-up CT examinations (n = 20). Results Bronchiectasis and airspace enlargement in the iodine map were significantly more prominent compared to monochromatic images for all readers (p ≤ 0.030). Patients with histopathologically proven usual interstitial pneumonia and those with rheumatoid arthritis showed image findings progressed in regions where bronchiectasis and airspace enlargement were rated as more prominent compared to monochromatic images by most readers. On the contrary, image finding was ameliorated in those regions in patients with dermatomyositis. Conclusions Bronchiectasis and airspace enlargement in the iodine map are depicted more prominently compared to the monochromatic image in dual-energy CT pulmonary angiography and have various time courses based on interstitial lung disease subtypes.
- 3 February 2026
- Published by Springer Nature in Cureus
- Vol. 18 (2)
Open AccessClinical Value of Bronchiectasis and Airspace Enlargement Depicted on Iodine Map in Patients With Interstitial Lung Disease: A Pilot Study
Objectives To investigate the degree and clinical meaning of bronchiectasis and airspace enlargement depicted on the iodine map in dual-energy CT pulmonary angiography of patients with interstitial lung disease, as a pilot study. Methods This retrospective study included 25 patients with interstitial lung disease who underwent dual-energy CT pulmonary angiography from November 2019 to February 2023. The iodine map and the 70 keV monochromatic image were reconstructed. Three readers independently evaluated the degree of bronchiectasis and airspace enlargement in the iodine map and monochromatic image. The time course of bronchiectasis and airspace enlargement was evaluated by comparing monochromatic images and follow-up conventional CT images for patients with follow-up CT examinations (n = 20). Results Bronchiectasis and airspace enlargement in the iodine map were significantly more prominent compared to monochromatic images for all readers (p ≤ 0.030). Patients with histopathologically proven usual interstitial pneumonia and those with rheumatoid arthritis showed image findings progressed in regions where bronchiectasis and airspace enlargement were rated as more prominent compared to monochromatic images by most readers. On the contrary, image finding was ameliorated in those regions in patients with dermatomyositis. Conclusions Bronchiectasis and airspace enlargement in the iodine map are depicted more prominently compared to the monochromatic image in dual-energy CT pulmonary angiography and have various time courses based on interstitial lung disease subtypes.
- Open Access
- 10 December 2025
- Published by Springer Nature in Japanese Journal of Radiology
- Vol. 44 (4) , 641-649
Super-resolution deep learning reconstruction improves brain MRI quality and detection of metastases
Purpose: Accurate identification of brain metastases is critical for determining prognosis and guiding treatment. Deep learning reconstruction (DLR) enhances MRI quality by reducing noise, while super-resolution DLR (SR-DLR) may further improve spatial resolution and lesion detectability. To evaluate SR-DLR versus conventional DLR in detecting and visualizing brain metastases on postcontrast T1-weighted brain MRI. Materials and methods: This retrospective study included 47 consecutive patients who underwent postcontrast 3D whole-brain T1-weighted MRI between July and December 2024. Images were reconstructed using both SR-DLR and DLR. Three independent readers evaluated metastatic lesion detection and rated image quality. Subjective assessments included lesion visibility, visibility of normal structures, sharpness, noise, and overall image quality. Objective metrics—full width at half maximum (FWHM), edge rise distance (ERD), edge rise slope (ERS), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR)—were also measured. Statistical tests included jackknife alternative free-response receiver operating characteristic (JAFROC) analysis, Wilcoxon signed-rank test, McNemar’s test, and paired t -tests, with significance threshold of p < 0.050. Results: A total of 117 brain metastases were detected in 47 patients (mean age, 59 years ± 18; 27 men). SR-DLR demonstrated significantly better lesion detection performance than DLR (mean figure of merit = 0.842 vs. 0.797; p = 0.042). Subjective image quality ratings favored SR-DLR for lesion and structure visibility, sharpness, noise, and overall quality in most cases. Objectively, SR-DLR yielded lower FWHM (1.2 mm vs. 1.9 mm; p < 0.001), higher ERS (791.3 mm − 1 vs. 645.3 mm − 1 ; p = 0.013) indicating enhanced sharpness as well as improved CNR (27.5 vs. 24.9; p < 0.001) compared to DLR. Conclusion: Compared to DLR, SR-DLR significantly enhances brain MRI quality and improves detection of metastatic lesions.
- 10 December 2025
- Published by Springer Nature in Japanese Journal of Radiology
- Vol. 44 (4) , 641-649
Open AccessSuper-resolution deep learning reconstruction improves brain MRI quality and detection of metastases
Purpose: Accurate identification of brain metastases is critical for determining prognosis and guiding treatment. Deep learning reconstruction (DLR) enhances MRI quality by reducing noise, while super-resolution DLR (SR-DLR) may further improve spatial resolution and lesion detectability. To evaluate SR-DLR versus conventional DLR in detecting and visualizing brain metastases on postcontrast T1-weighted brain MRI. Materials and methods: This retrospective study included 47 consecutive patients who underwent postcontrast 3D whole-brain T1-weighted MRI between July and December 2024. Images were reconstructed using both SR-DLR and DLR. Three independent readers evaluated metastatic lesion detection and rated image quality. Subjective assessments included lesion visibility, visibility of normal structures, sharpness, noise, and overall image quality. Objective metrics—full width at half maximum (FWHM), edge rise distance (ERD), edge rise slope (ERS), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR)—were also measured. Statistical tests included jackknife alternative free-response receiver operating characteristic (JAFROC) analysis, Wilcoxon signed-rank test, McNemar’s test, and paired t -tests, with significance threshold of p < 0.050. Results: A total of 117 brain metastases were detected in 47 patients (mean age, 59 years ± 18; 27 men). SR-DLR demonstrated significantly better lesion detection performance than DLR (mean figure of merit = 0.842 vs. 0.797; p = 0.042). Subjective image quality ratings favored SR-DLR for lesion and structure visibility, sharpness, noise, and overall quality in most cases. Objectively, SR-DLR yielded lower FWHM (1.2 mm vs. 1.9 mm; p < 0.001), higher ERS (791.3 mm − 1 vs. 645.3 mm − 1 ; p = 0.013) indicating enhanced sharpness as well as improved CNR (27.5 vs. 24.9; p < 0.001) compared to DLR. Conclusion: Compared to DLR, SR-DLR significantly enhances brain MRI quality and improves detection of metastatic lesions.
- Open Access
- 15 November 2025
- Published by Springer Nature in Skeletal Radiology
- Vol. 55 (4) , 757-765
Diagnostic value of a second-generation super-resolution deep learning–based reconstruction combined with a metal artifact reduction algorithm for pelvic CT
Objective: To evaluate the impact of combining a second-generation super-resolution deep learning–based reconstruction (DLR2) with a metal artifact reduction (MAR) algorithm in CT images of patients with metal hip implants by assessing both quantitative metrics and qualitative reader ratings. Materials and methods: This retrospective study included 40 patients (30 females; age range, 54–93 years) with metal hip implants. Images were reconstructed using DLR2, a first-generation DLR (DLR1), and a conventional hybrid iterative reconstruction (HIR), each combined with MAR. Images without MAR were also reconstructed using DLR2 (DLR2-only). Standard deviations (SDs) of attenuation in the regions of interest (ROI) over the bladder, gluteus maximus muscle, and gluteal fat were recorded. Artifact indices for muscle (AI muscle ) and fat (AI fat ) were also calculated. Three radiologists independently assessed the depiction of pelvic structures (femoral artery, bladder, rectum, uterus/prostate), artifact reduction, and diagnostic usability with 5-point scores. For statistical analysis, the Wilcoxon signed-rank test was used with the Holm correction for multiple comparisons. Results: DLR2 + MAR showed significantly lower SDs than DLR1 + MAR, HIR + MAR, and DLR2-only across all three ROIs ( p < 0.01–0.02). For both AI muscle and AI fat , DLR2 + MAR had the lowest values, though differences with DLR1 + MAR were not significant ( p = 0.80, 0.11). DLR2 + MAR showed significantly higher scores for the depiction of the femoral artery and rectum compared with other + MAR reconstruction methods ( p < 0.01–0.04), with no significant differences in the remaining categories ( p = 0.08–0.91). Inter-rater agreement ranged from 0.67 to 0.77, indicating substantial agreement. Conclusion: Combining DLR2 and MAR improves image quality and visualization of pelvic structures.
- 15 November 2025
- Published by Springer Nature in Skeletal Radiology
- Vol. 55 (4) , 757-765
Open AccessDiagnostic value of a second-generation super-resolution deep learning–based reconstruction combined with a metal artifact reduction algorithm for pelvic CT
Objective: To evaluate the impact of combining a second-generation super-resolution deep learning–based reconstruction (DLR2) with a metal artifact reduction (MAR) algorithm in CT images of patients with metal hip implants by assessing both quantitative metrics and qualitative reader ratings. Materials and methods: This retrospective study included 40 patients (30 females; age range, 54–93 years) with metal hip implants. Images were reconstructed using DLR2, a first-generation DLR (DLR1), and a conventional hybrid iterative reconstruction (HIR), each combined with MAR. Images without MAR were also reconstructed using DLR2 (DLR2-only). Standard deviations (SDs) of attenuation in the regions of interest (ROI) over the bladder, gluteus maximus muscle, and gluteal fat were recorded. Artifact indices for muscle (AI muscle ) and fat (AI fat ) were also calculated. Three radiologists independently assessed the depiction of pelvic structures (femoral artery, bladder, rectum, uterus/prostate), artifact reduction, and diagnostic usability with 5-point scores. For statistical analysis, the Wilcoxon signed-rank test was used with the Holm correction for multiple comparisons. Results: DLR2 + MAR showed significantly lower SDs than DLR1 + MAR, HIR + MAR, and DLR2-only across all three ROIs ( p < 0.01–0.02). For both AI muscle and AI fat , DLR2 + MAR had the lowest values, though differences with DLR1 + MAR were not significant ( p = 0.80, 0.11). DLR2 + MAR showed significantly higher scores for the depiction of the femoral artery and rectum compared with other + MAR reconstruction methods ( p < 0.01–0.04), with no significant differences in the remaining categories ( p = 0.08–0.91). Inter-rater agreement ranged from 0.67 to 0.77, indicating substantial agreement. Conclusion: Combining DLR2 and MAR improves image quality and visualization of pelvic structures.
- Open Access
- 28 October 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (4) , 1-8
Impact of Super-Resolution Deep Learning Reconstruction on Low-Dose CT in Patients with Central Venous Catheter or Central Venous Port
CT imaging is useful for evaluating complications related to central venous catheter insertion; however, it involves exposure to ionizing radiation. This study aimed to evaluate the impact of super-resolution deep learning reconstruction (SR-DLR) on the quality of low-dose CT imaging compared to hybrid iterative reconstruction (HIR) in patients with central venous catheter or central venous port. In this retrospective study, chest CT images were reconstructed using SR-DLR and HIR from source data acquired with a three-dimensional landmark scan during scout imaging. Three readers independently assessed the quality of images in terms of noise, artifacts, depiction of the brachiocephalic vein and superior vena cava, and ease of evaluating hematoma and catheter location. The standard deviation of CT attenuation within a region of interest placed in the right atrium was recorded as quantitative image noise. All readers rated noise, artifacts, and depiction of the brachiocephalic vein as significantly improved in SR-DLR compared to HIR ( p ≤ 0.042). Two out of three readers rated depiction of the superior vena cava, ease of evaluating hematoma, and catheter location as significantly improved in SR-DLR compared to HIR ( p ≤ 0.016). Quantitative image noise in SR-DLR was 10.2 Hounsfield unit, which was significantly reduced compared to HIR (24.0 Hounsfield unit) ( p < 0.001). When sufficient information can be obtained from these images, the main CT scans may be omitted. In conclusion, SR-DLR enhanced the quality of low-dose CT imaging compared to HIR in patients with central venous catheter or central venous port.
- 28 October 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 39 (4) , 1-8
Open AccessImpact of Super-Resolution Deep Learning Reconstruction on Low-Dose CT in Patients with Central Venous Catheter or Central Venous Port
CT imaging is useful for evaluating complications related to central venous catheter insertion; however, it involves exposure to ionizing radiation. This study aimed to evaluate the impact of super-resolution deep learning reconstruction (SR-DLR) on the quality of low-dose CT imaging compared to hybrid iterative reconstruction (HIR) in patients with central venous catheter or central venous port. In this retrospective study, chest CT images were reconstructed using SR-DLR and HIR from source data acquired with a three-dimensional landmark scan during scout imaging. Three readers independently assessed the quality of images in terms of noise, artifacts, depiction of the brachiocephalic vein and superior vena cava, and ease of evaluating hematoma and catheter location. The standard deviation of CT attenuation within a region of interest placed in the right atrium was recorded as quantitative image noise. All readers rated noise, artifacts, and depiction of the brachiocephalic vein as significantly improved in SR-DLR compared to HIR ( p ≤ 0.042). Two out of three readers rated depiction of the superior vena cava, ease of evaluating hematoma, and catheter location as significantly improved in SR-DLR compared to HIR ( p ≤ 0.016). Quantitative image noise in SR-DLR was 10.2 Hounsfield unit, which was significantly reduced compared to HIR (24.0 Hounsfield unit) ( p < 0.001). When sufficient information can be obtained from these images, the main CT scans may be omitted. In conclusion, SR-DLR enhanced the quality of low-dose CT imaging compared to HIR in patients with central venous catheter or central venous port.
- Open Access
- 21 October 2025
- Published by Springer Nature in Neuroradiology
- Vol. 68 (1) , 105-113
Pituitary neuroendocrine tumor: evaluation with super resolution deep learning reconstruction
Purpose: To evaluate the impact of super-resolution deep learning reconstruction (SR-DLR) algorithm on the evaluations of pituitary neuroendocrine tumor (PitNET) and on the image quality of pituitary MRI compared to conventional images with zero-filling interpolation (ZIP) technique. Methods: This retrospective study included 29 patients with PitNET who underwent pituitary MRI imaging. T2-weighted coronal images were reconstructed with SR-DLR and ZIP. Three readers assessed the images in terms of pituitary stalk deviation, noise, sharpness, depiction of PitNET, and diagnostic acceptability. A radiologist placed circular or ovoid regions of interest (ROIs) on the lateral ventricle and the tumor, and signal-to-noise ratio (SNR) and contrast-to-noise ratio were calculated. The radiologist also placed a linear ROI crossing the septum pellucidum perpendicularly. From the signal intensity profile along this ROI, edge rise slope (ERS) and full width at half maximum (FWHM) were calculated. Results: Inter-reader agreement in the evaluations of pituitary stalk deviation in SR-DLR (0.518) tended to be superior to that in ZIP (0.405). Scores in the qualitative image analyses in SR-DLR were significantly better than those in ZIP for all evaluation items ( p < 0.001). SNR and CNR in SR-DLR were significantly higher compared to ZIP ( p < 0.001). Results of ERS (5433/2177 in SR-DLR/ZIP) and FWHM (0.67/1.27 mm in SR-DLR/ZIP) indicated significantly enhanced spatial resolution in SR-DLR compared to ZIP. Conclusion: SR-DLR tended to enhance inter-reader agreement in the evaluations of pituitary stalk deviation and significantly improved quality of pituitary MRI images compared to conventional ZIP images.
- 21 October 2025
- Published by Springer Nature in Neuroradiology
- Vol. 68 (1) , 105-113
Open AccessPituitary neuroendocrine tumor: evaluation with super resolution deep learning reconstruction
Purpose: To evaluate the impact of super-resolution deep learning reconstruction (SR-DLR) algorithm on the evaluations of pituitary neuroendocrine tumor (PitNET) and on the image quality of pituitary MRI compared to conventional images with zero-filling interpolation (ZIP) technique. Methods: This retrospective study included 29 patients with PitNET who underwent pituitary MRI imaging. T2-weighted coronal images were reconstructed with SR-DLR and ZIP. Three readers assessed the images in terms of pituitary stalk deviation, noise, sharpness, depiction of PitNET, and diagnostic acceptability. A radiologist placed circular or ovoid regions of interest (ROIs) on the lateral ventricle and the tumor, and signal-to-noise ratio (SNR) and contrast-to-noise ratio were calculated. The radiologist also placed a linear ROI crossing the septum pellucidum perpendicularly. From the signal intensity profile along this ROI, edge rise slope (ERS) and full width at half maximum (FWHM) were calculated. Results: Inter-reader agreement in the evaluations of pituitary stalk deviation in SR-DLR (0.518) tended to be superior to that in ZIP (0.405). Scores in the qualitative image analyses in SR-DLR were significantly better than those in ZIP for all evaluation items ( p < 0.001). SNR and CNR in SR-DLR were significantly higher compared to ZIP ( p < 0.001). Results of ERS (5433/2177 in SR-DLR/ZIP) and FWHM (0.67/1.27 mm in SR-DLR/ZIP) indicated significantly enhanced spatial resolution in SR-DLR compared to ZIP. Conclusion: SR-DLR tended to enhance inter-reader agreement in the evaluations of pituitary stalk deviation and significantly improved quality of pituitary MRI images compared to conventional ZIP images.