1
|
Sato Y, Ohkuma K. Verification of image quality improvement by deep learning reconstruction to 1.5 T MRI in T2-weighted images of the prostate gland. Radiol Phys Technol 2024:10.1007/s12194-024-00819-5. [PMID: 38850389 DOI: 10.1007/s12194-024-00819-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2024] [Revised: 05/16/2024] [Accepted: 06/04/2024] [Indexed: 06/10/2024]
Abstract
This study aimed to evaluate whether the image quality of 1.5 T magnetic resonance imaging (MRI) of the prostate is equal to or higher than that of 3 T MRI by applying deep learning reconstruction (DLR). To objectively analyze the images from the 13 healthy volunteers, we measured the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the images obtained by the 1.5 T scanner with and without DLR, as well as for images obtained by the 3 T scanner. In the subjective, T2W images of the prostate were visually evaluated by two board-certified radiologists. The SNRs and CNRs in 1.5 T images with DLR were higher than that in 3 T images. Subjective image scores were better for 1.5 T images with DLR than 3 T images. The use of the DLR technique in 1.5 T MRI substantially improved the SNR and image quality of T2W images of the prostate gland, as compared to 3 T MRI.
Collapse
Affiliation(s)
- Yoshiomi Sato
- Department of Radiology, Saitama City Hospital, Mimuro 2460, Saitama, 336-8522, Japan.
| | - Kiyoshi Ohkuma
- Department of Diagnostic Radiology, Saitama City Hospital, Mimuro 2460, Saitama, 336-8522, Japan
| |
Collapse
|
2
|
Akai H, Yasaka K, Sugawara H, Furuta T, Tajima T, Kato S, Yamaguchi H, Ohtomo K, Abe O, Kiryu S. Faster acquisition of magnetic resonance imaging sequences of the knee via deep learning reconstruction: a volunteer study. Clin Radiol 2024; 79:453-459. [PMID: 38614869 DOI: 10.1016/j.crad.2024.03.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Revised: 12/29/2023] [Accepted: 03/02/2024] [Indexed: 04/15/2024]
Abstract
AIM To evaluate whether deep learning reconstruction (DLR) can accelerate the acquisition of magnetic resonance imaging (MRI) sequences of the knee for clinical use. MATERIALS AND METHODS Using a 1.5-T MRI scanner, sagittal fat-suppressed T2-weighted imaging (fs-T2WI), coronal proton density-weighted imaging (PDWI), and coronal T1-weighted imaging (T1WI) were performed. DLR was applied to images with a number of signal averages (NSA) of 1 to obtain 1DLR images. Then 1NSA, 1DLR, and 4NSA images were compared subjectively, and by noise (standard deviation of intra-articular water or medial meniscus) and contrast-to-noise ratio between two anatomical structures or between an anatomical structure and intra-articular water. RESULTS Twenty-seven healthy volunteers (age: 40.6 ± 11.9 years) were enrolled. Three 1DLR image sequences were obtained within 200 s (approximately 12 minutes for 4NSA image). According to objective evaluations, PDWI 1DLR images showed the smallest noise and significantly higher contrast than 1NSA and 4NSA images. For fs-T2WI, smaller noise and higher contrast were observed in the order of 4NSA, 1DLR, and 1NSA images. According to the subjective analysis, structure visibility, image noise, and overall image quality were significantly better for PDWI 1DLR than 1NSA images; moreover, the visibility of the meniscus and bone, image noise, and overall image quality were significantly better for 1DLR than 4NSA images. Fs-T2WI and T1WI 1DLR images showed no difference between 1DLR and 4NSA images. CONCLUSION Compared to PDWI 4NSA images, PDWI 1DLR images were of higher quality, while the quality of fs-T2WI and T1WI 1DLR images was similar to that of 4NSA images.
Collapse
Affiliation(s)
- H Akai
- Department of Radiology, Institute of Medical Science, University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo, 108-8639, Japan; Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan
| | - K Yasaka
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan; Department of Radiology, Graduate School of Medicine, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - H Sugawara
- Department of Diagnostic Radiology, McGill University, 1650 Cedar Avenue, Montreal, Quebec, H3G 1A4, Canada
| | - T Furuta
- Department of Radiology, Institute of Medical Science, University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo, 108-8639, Japan
| | - T Tajima
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan; Department of Radiology, International University of Health and Welfare Mita Hospital, 1-4-3 Mita, Minato-ku, Tokyo, 108-8329, Japan
| | - S Kato
- Department of Radiology, Institute of Medical Science, University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo, 108-8639, Japan
| | - H Yamaguchi
- Department of Radiology, Institute of Medical Science, University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo, 108-8639, Japan
| | - K Ohtomo
- International University of Health and Welfare, 2600-1 Kiakanemaru, Ohtawara, Tochigi, 324-8501, Japan
| | - O Abe
- Department of Radiology, Graduate School of Medicine, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - S Kiryu
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan.
| |
Collapse
|
3
|
Singh SB, Sarrami AH, Gatidis S, Varniab ZS, Chaudhari A, Daldrup-Link HE. Applications of Artificial Intelligence for Pediatric Cancer Imaging. AJR Am J Roentgenol 2024. [PMID: 38809123 DOI: 10.2214/ajr.24.31076] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/30/2024]
Abstract
Artificial intelligence (AI) is transforming medical imaging of adult patients. However, its utilization in pediatric oncology imaging remains constrained, in part due to the inherent data scarcity associated with childhood cancers. Pediatric cancers are rare, and imaging technologies are evolving rapidly, leading to insufficient data of a particular type to effectively train these algorithms. The small market size of pediatrics compared to adults could also contribute to this challenge, as market size is a driver of commercialization. This article provides an overview of the current state of AI applications for pediatric cancer imaging, including applications for medical image acquisition, processing, reconstruction, segmentation, diagnosis, staging, and treatment response monitoring. While current developments are promising, impediments due to diverse anatomies of growing children and nonstandardized imaging protocols have led to limited clinical translation thus far. Opportunities include leveraging reconstruction algorithms to achieve accelerated low-dose imaging and automating the generation of metric-based staging and treatment monitoring scores. Transfer-learning of adult-based AI models to pediatric cancers, multi-institutional data sharing, and ethical data privacy practices for pediatric patients with rare cancers will be keys to unlocking AI's full potential for clinical translation and improved outcomes for these young patients.
Collapse
Affiliation(s)
- Shashi B Singh
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Amir H Sarrami
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Sergios Gatidis
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Zahra S Varniab
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Akshay Chaudhari
- Department of Radiology, Integrative Biomedical Imaging Informatics (IBIIS), Stanford University School of Medicine, Stanford University, Stanford, CA, 94304
- Department of Biomedical Data Science, Stanford University School of Medicine, Stanford University, Stanford, CA, 94304
| | - Heike E Daldrup-Link
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
- Department of Pediatrics, Pediatric Hematology/Oncology, Lucile Packard Children's Hospital, Stanford University, Stanford, CA, 94305
| |
Collapse
|
4
|
Kakigi T, Sakamoto R, Arai R, Yamamoto A, Kuriyama S, Sano Y, Imai R, Numamoto H, Miyake KK, Saga T, Matsuda S, Nakamoto Y. Thin-slice 2D MR Imaging of the Shoulder Joint Using Denoising Deep Learning Reconstruction Provides Higher Image Quality Than 3D MR Imaging. Magn Reson Med Sci 2024:mp.2023-0115. [PMID: 38777762 DOI: 10.2463/mrms.mp.2023-0115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/25/2024] Open
Abstract
PURPOSE This study was conducted to evaluate whether thin-slice 2D fat-saturated proton density-weighted images of the shoulder joint in three imaging planes combined with parallel imaging, partial Fourier technique, and denoising approach with deep learning-based reconstruction (dDLR) are more useful than 3D fat-saturated proton density multi-planar voxel images. METHODS Eighteen patients who underwent MRI of the shoulder joint at 3T were enrolled. The denoising effect of dDLR in 2D was evaluated using coefficient of variation (CV). Qualitative evaluation of anatomical structures, noise, and artifacts in 2D after dDLR and 3D was performed by two radiologists using a five-point Likert scale. All were analyzed statistically. Gwet's agreement coefficients were also calculated. RESULTS The CV of 2D after dDLR was significantly lower than that before dDLR (P < 0.05). Both radiologists rated 2D higher than 3D for all anatomical structures and noise (P < 0.05), except for artifacts. Both Gwet's agreement coefficients of anatomical structures, noise, and artifacts in 2D and 3D produced nearly perfect agreement between the two radiologists. The evaluation of 2D tended to be more reproducible than 3D. CONCLUSION 2D with parallel imaging, partial Fourier technique, and dDLR was proved to be superior to 3D for depicting shoulder joint structures with lower noise.
Collapse
Affiliation(s)
- Takahide Kakigi
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Ryo Sakamoto
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
- Department of Real World Data Research and Development, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Ryuzo Arai
- Department of Orthopaedic Surgery, Kyoto Katsura Hospital, Kyoto, Kyoto, Japan
| | - Akira Yamamoto
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
- Center for Medical Education, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Shinichi Kuriyama
- Department of Orthopaedic Surgery, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Yuichiro Sano
- MRI Systems Division, Canon Medical Systems Corporation, Otawara, Tochigi, Japan
| | - Rimika Imai
- MRI Systems Division, Canon Medical Systems Corporation, Otawara, Tochigi, Japan
| | - Hitomi Numamoto
- Division of Clinical Radiology Service, Kyoto University Hospital, Kyoto, Kyoto, Japan
- Department of Advanced Medical Imaging Research, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Kanae Kawai Miyake
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
- Department of Advanced Medical Imaging Research, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Tsuneo Saga
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
- Department of Advanced Medical Imaging Research, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Shuichi Matsuda
- Department of Orthopaedic Surgery, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| | - Yuji Nakamoto
- Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Kyoto, Japan
| |
Collapse
|
5
|
Yasaka K, Uehara S, Kato S, Watanabe Y, Tajima T, Akai H, Yoshioka N, Akahane M, Ohtomo K, Abe O, Kiryu S. Super-resolution Deep Learning Reconstruction Cervical Spine 1.5T MRI: Improved Interobserver Agreement in Evaluations of Neuroforaminal Stenosis Compared to Conventional Deep Learning Reconstruction. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01112-y. [PMID: 38671337 DOI: 10.1007/s10278-024-01112-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/19/2024] [Revised: 03/28/2024] [Accepted: 04/01/2024] [Indexed: 04/28/2024]
Abstract
The aim of this study was to investigate whether super-resolution deep learning reconstruction (SR-DLR) is superior to conventional deep learning reconstruction (DLR) with respect to interobserver agreement in the evaluation of neuroforaminal stenosis using 1.5T cervical spine MRI. This retrospective study included 39 patients who underwent 1.5T cervical spine MRI. T2-weighted sagittal images were reconstructed with SR-DLR and DLR. Three blinded radiologists independently evaluated the images in terms of the degree of neuroforaminal stenosis, depictions of the vertebrae, spinal cord and neural foramina, sharpness, noise, artefacts and diagnostic acceptability. In quantitative image analyses, a fourth radiologist evaluated the signal-to-noise ratio (SNR) by placing a circular or ovoid region of interest on the spinal cord, and the edge slope based on a linear region of interest placed across the surface of the spinal cord. Interobserver agreement in the evaluations of neuroforaminal stenosis using SR-DLR and DLR was 0.422-0.571 and 0.410-0.542, respectively. The kappa values between reader 1 vs. reader 2 and reader 2 vs. reader 3 significantly differed. Two of the three readers rated depictions of the spinal cord, sharpness, and diagnostic acceptability as significantly better with SR-DLR than with DLR. Both SNR and edge slope (/mm) were also significantly better with SR-DLR (12.9 and 6031, respectively) than with DLR (11.5 and 3741, respectively) (p < 0.001 for both). In conclusion, compared to DLR, SR-DLR improved interobserver agreement in the evaluations of neuroforaminal stenosis using 1.5T cervical spine MRI.
Collapse
Affiliation(s)
- Koichiro Yasaka
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan
| | - Shunichi Uehara
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Shimpei Kato
- Department of Radiology, The Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo, 108-8639, Japan
| | - Yusuke Watanabe
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Taku Tajima
- Department of Radiology, International University of Health and Welfare Mita Hospital, 1-4-3 Mita, Minato-ku, Tokyo, 108-8329, Japan
| | - Hiroyuki Akai
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan
- Department of Radiology, The Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, Tokyo, 108-8639, Japan
| | - Naoki Yoshioka
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan
| | - Masaaki Akahane
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan
| | - Kuni Ohtomo
- International University of Health and Welfare, 2600-1 Ktiakanemaru, Ohtawara, Tochigi, 324-8501, Japan
| | - Osamu Abe
- Department of Radiology, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, 113-8655, Japan
| | - Shigeru Kiryu
- Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita, Chiba, 286-0124, Japan.
| |
Collapse
|
6
|
Hokamura M, Uetani H, Nakaura T, Matsuo K, Morita K, Nagayama Y, Kidoh M, Yamashita Y, Ueda M, Mukasa A, Hirai T. Exploring the impact of super-resolution deep learning on MR angiography image quality. Neuroradiology 2024; 66:217-226. [PMID: 38148334 DOI: 10.1007/s00234-023-03271-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2023] [Accepted: 12/14/2023] [Indexed: 12/28/2023]
Abstract
PURPOSE The aim of this study is to assess the effect of super-resolution deep learning-based reconstruction (SR-DLR), which uses k-space properties, on image quality of intracranial time-of-flight (TOF) magnetic resonance angiography (MRA) at 3 T. METHODS This retrospective study involved 35 patients who underwent intracranial TOF-MRA using a 3-T MRI system with SR-DLR based on k-space properties in October and November 2022. We reconstructed MRA with SR-DLR (matrix = 1008 × 1008) and MRA without SR-DLR (matrix = 336 × 336). We measured the signal-to-noise ratio (SNR), contrast, and contrast-to-noise ratio (CNR) in the basilar artery (BA) and the anterior cerebral artery (ACA) and the sharpness of the posterior cerebral artery (PCA) using the slope of the signal intensity profile curve at the half-peak points. Two radiologists evaluated image noise, artifacts, contrast, sharpness, and overall image quality of the two image types using a 4-point scale. We compared quantitative and qualitative scores between images with and without SR-DLR using the Wilcoxon signed-rank test. RESULTS The SNRs, contrasts, and CNRs were all significantly higher in images with SR-DLR than those without SR-DLR (p < 0.001). The slope was significantly greater in images with SR-DLR than those without SR-DLR (p < 0.001). The qualitative scores in MRAs with SR-DLR were all significantly higher than MRAs without SR-DLR (p < 0.001). CONCLUSION SR-DLR with k-space properties can offer the benefits of increased spatial resolution without the associated drawbacks of longer scan times and reduced SNR and CNR in intracranial MRA.
Collapse
Affiliation(s)
- Masamichi Hokamura
- Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8556, Japan
| | - Hiroyuki Uetani
- Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8556, Japan
| | - Takeshi Nakaura
- Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8556, Japan.
| | - Kensei Matsuo
- Department of Central Radiology, Kumamoto University Hospital, Honjo 1-1-1, Kumamoto, 860-8556, Japan
| | - Kosuke Morita
- Department of Central Radiology, Kumamoto University Hospital, Honjo 1-1-1, Kumamoto, 860-8556, Japan
| | - Yasunori Nagayama
- Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8556, Japan
| | - Masafumi Kidoh
- Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8556, Japan
| | - Yuichi Yamashita
- Canon Medical Systems Corporation, 70-1, Yanagi-cho, Saiwai-ku, Kawasaki-shi, Kanagawa, 212-0015, Japan
| | - Mitsuharu Ueda
- Department of Neurology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Kumamoto, 860-8556, Japan
| | - Akitake Mukasa
- Department of Neurosurgery, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Kumamoto, 860-8556, Japan
| | - Toshinori Hirai
- Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, Honjo 1-1-1, Chuo-ku, Kumamoto-shi, Kumamoto, 860-8556, Japan
| |
Collapse
|
7
|
Lee J, Jung M, Park J, Kim S, Im Y, Lee N, Song HT, Lee YH. Highly accelerated knee magnetic resonance imaging using deep neural network (DNN)-based reconstruction: prospective, multi-reader, multi-vendor study. Sci Rep 2023; 13:17264. [PMID: 37828048 PMCID: PMC10570285 DOI: 10.1038/s41598-023-44248-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/12/2023] [Accepted: 10/05/2023] [Indexed: 10/14/2023] Open
Abstract
In this prospective, multi-reader, multi-vendor study, we evaluated the performance of a commercially available deep neural network (DNN)-based MR image reconstruction in enabling accelerated 2D fast spin-echo (FSE) knee imaging. Forty-five subjects were prospectively enrolled and randomly divided into three 3T MRIs. Conventional 2D FSE and accelerated 2D FSE sequences were acquired for each subject, and the accelerated FSE images were reconstructed and enhanced with DNN-based reconstruction software (FSE-DNN). Quantitative assessments and diagnostic performances were independently evaluated by three musculoskeletal radiologists. For statistical analyses, paired t-tests, and Pearson's correlation were used for image quality comparison and inter-reader agreements. Accelerated FSE-DNN reduced scan times by 41.0% on average. FSE-DNN showed better SNR and CNR (p < 0.001). Overall image quality of FSE-DNN was comparable (p > 0.05), and diagnostic performances of FSE-DNN showed comparable lesion detection. Two of cartilage lesions were under-graded or over-graded (n = 2) while there was no significant difference in other image sets (n = 43). Overall inter-reader agreement between FSE-conventional and FSE-DNN showed good agreement (R2 = 0.76; p < 0.001). In conclusion, DNN-based reconstruction can be applied to accelerated knee imaging in multi-vendor MRI scanners, with reduced scan time and comparable image quality. This study suggests the potential for DNN-accelerated knee MRI in clinical practice.
Collapse
Affiliation(s)
- Joohee Lee
- Department of Radiology, Research Institute of Radiological Science, and Center for Clinical Imaging Data Science (CCIDS), Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea
| | - Min Jung
- Department of Orthopaedic Surgery, Yonsei University College of Medicine, Seoul, Korea
| | - Jiwoo Park
- Department of Radiology, Research Institute of Radiological Science, and Center for Clinical Imaging Data Science (CCIDS), Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea
| | - Sungjun Kim
- Department of Radiology, Research Institute of Radiological Science, and Center for Clinical Imaging Data Science (CCIDS), Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea
| | - Yunjin Im
- Department of Radiology, Research Institute of Radiological Science, and Center for Clinical Imaging Data Science (CCIDS), Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea
| | - Nim Lee
- Department of Radiology, Research Institute of Radiological Science, and Center for Clinical Imaging Data Science (CCIDS), Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea
| | - Ho-Taek Song
- Department of Radiology, Research Institute of Radiological Science, and Center for Clinical Imaging Data Science (CCIDS), Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea
| | - Young Han Lee
- Department of Radiology, Research Institute of Radiological Science, and Center for Clinical Imaging Data Science (CCIDS), Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 03722, Korea.
| |
Collapse
|
8
|
Kiryu S, Akai H, Yasaka K, Tajima T, Kunimatsu A, Yoshioka N, Akahane M, Abe O, Ohtomo K. Clinical Impact of Deep Learning Reconstruction in MRI. Radiographics 2023; 43:e220133. [PMID: 37200221 DOI: 10.1148/rg.220133] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/20/2023]
Abstract
Deep learning has been recognized as a paradigm-shifting tool in radiology. Deep learning reconstruction (DLR) has recently emerged as a technology used in the image reconstruction process of MRI, which is an essential procedure in generating MR images. Denoising, which is the first DLR application to be realized in commercial MRI scanners, improves signal-to-noise ratio. When applied to lower magnetic field-strength scanners, the signal-to-noise ratio can be increased without extending the imaging time, and image quality is comparable to that of higher-field-strength scanners. Shorter imaging times decrease patient discomfort and reduce MRI scanner running costs. The incorporation of DLR into accelerated acquisition imaging techniques, such as parallel imaging or compressed sensing, shortens the reconstruction time. DLR is based on supervised learning using convolutional layers and is divided into the following three categories: image domain, k-space learning, and direct mapping types. Various studies have reported other derivatives of DLR, and several have shown the feasibility of DLR in clinical practice. Although DLR efficiently reduces Gaussian noise from MR images, denoising makes image artifacts more prominent, and a solution to this problem is desired. Depending on the training of the convolutional neural network, DLR may change the imaging features of lesions and obscure small lesions. Therefore, radiologists may need to adopt the habit of questioning whether any information has been lost on images that appear clean. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.
Collapse
Affiliation(s)
- Shigeru Kiryu
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Hiroyuki Akai
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Koichiro Yasaka
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Taku Tajima
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Akira Kunimatsu
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Naoki Yoshioka
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Masaaki Akahane
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Osamu Abe
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| | - Kuni Ohtomo
- From the Department of Radiology, International University of Health and Welfare Narita Hospital, 852 Hatakeda, Narita 286-0124, Japan (S.K., H.A., K.Y., T.T., A.K., N.Y., M.A.); Department of Radiology, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan (H.A.); Department of Radiology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan (K.Y., O.A.); Department of Radiology, International University of Health and Welfare Mita Hospital, Tokyo, Japan (T.T., A.K.); and International University of Health and Welfare, Otawara, Japan (K.O.)
| |
Collapse
|