Naveen Subhas1,2, Hongyu Li3, Mingrui Yang1,4, Carl S Winalski1,2, Joshua Polster1,2, Nancy Obuchowski1,2,5, Kenji Mamoto1,4, Ruiying Liu3, Chaoyi Zhang3, Peizhou Huang3, Sunil Kumar Gaire3, Dong Liang6, Bowen Shen7, Xiaojuan Li1,2,4, Leslie Ying3. 1. Program of Advanced Musculoskeletal Imaging (PAMI), Imaging Institute, Cleveland Clinic, Cleveland, OH, USA. 2. Department of Diagnostic Radiology, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA. 3. Department of Biomedical Engineering, Department of Electrical Engineering, University at Buffalo, the State University of New York, Buffalo, NY, USA. 4. Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA. 5. Department of Quantitative Health Sciences, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA. 6. Paul C. Lauterbur Research Center for Biomedical Imaging, Medical AI Research Center, SIAT, CAS, Shenzhen, China. 7. Department of Computer Science, Virginia Tech, Blacksburg, VA, USA.
Abstract
BACKGROUND: MRI acceleration using deep learning (DL) convolutional neural networks (CNNs) is a novel technique with great promise. Increasing the number of convolutional layers may allow for more accurate image reconstruction. Studies on evaluating the diagnostic interchangeability of DL reconstructed knee magnetic resonance (MR) images are scarce. The purpose of this study was to develop a deep CNN (DCNN) with an optimal number of layers for accelerating knee magnetic resonance imaging (MRI) acquisition by 6-fold and to test the diagnostic interchangeability and image quality of nonaccelerated images versus images reconstructed with a 15-layer DCNN or 3-layer CNN. METHODS: For the feasibility portion of this study, 10 patients were randomly selected from the Osteoarthritis Initiative (OAI) cohort. For the interchangeability portion of the study, 40 patients were randomly selected from the OAI cohort. Three readers assessed meniscal and anterior cruciate ligament (ACL) tears and cartilage defects using DCNN, CNN, and nonaccelerated images. Image quality was subjectively graded as nondiagnostic, poor, acceptable, or excellent. Interchangeability was tested by comparing the frequency of agreement when readers used both accelerated and nonaccelerated images to frequency of agreement when readers only used nonaccelerated images. A noninferiority margin of 0.10 was used to ensure type I error ≤5% and power ≥80%. A logistic regression model using generalized estimating equations was used to compare proportions; 95% confidence intervals (CIs) were constructed. RESULTS: DCNN and CNN images were interchangeable with nonaccelerated images for all structures, with excess disagreement values ranging from -2.5% [95% CI: (-6.1, 1.1)] to 3.0% [95% CI: (-0.1, 6.1)]. The quality of DCNN images was graded higher than that of CNN images but less than that of nonaccelerated images [excellent/acceptable quality: DCNN, 95% of cases (114/120); CNN, 60% (72/120); nonaccelerated, 97.5% (117/120)]. CONCLUSIONS: Six-fold accelerated knee images reconstructed with a DL technique are diagnostically interchangeable with nonaccelerated images and have acceptable image quality when using a 15-layer CNN. 2020 Quantitative Imaging in Medicine and Surgery. All rights reserved.
BACKGROUND: MRI acceleration using deep learning (DL) convolutional neural networks (CNNs) is a novel technique with great promise. Increasing the number of convolutional layers may allow for more accurate image reconstruction. Studies on evaluating the diagnostic interchangeability of DL reconstructed knee magnetic resonance (MR) images are scarce. The purpose of this study was to develop a deep CNN (DCNN) with an optimal number of layers for accelerating knee magnetic resonance imaging (MRI) acquisition by 6-fold and to test the diagnostic interchangeability and image quality of nonaccelerated images versus images reconstructed with a 15-layer DCNN or 3-layer CNN. METHODS: For the feasibility portion of this study, 10 patients were randomly selected from the Osteoarthritis Initiative (OAI) cohort. For the interchangeability portion of the study, 40 patients were randomly selected from the OAI cohort. Three readers assessed meniscal and anterior cruciate ligament (ACL) tears and cartilage defects using DCNN, CNN, and nonaccelerated images. Image quality was subjectively graded as nondiagnostic, poor, acceptable, or excellent. Interchangeability was tested by comparing the frequency of agreement when readers used both accelerated and nonaccelerated images to frequency of agreement when readers only used nonaccelerated images. A noninferiority margin of 0.10 was used to ensure type I error ≤5% and power ≥80%. A logistic regression model using generalized estimating equations was used to compare proportions; 95% confidence intervals (CIs) were constructed. RESULTS: DCNN and CNN images were interchangeable with nonaccelerated images for all structures, with excess disagreement values ranging from -2.5% [95% CI: (-6.1, 1.1)] to 3.0% [95% CI: (-0.1, 6.1)]. The quality of DCNN images was graded higher than that of CNN images but less than that of nonaccelerated images [excellent/acceptable quality: DCNN, 95% of cases (114/120); CNN, 60% (72/120); nonaccelerated, 97.5% (117/120)]. CONCLUSIONS: Six-fold accelerated knee images reconstructed with a DL technique are diagnostically interchangeable with nonaccelerated images and have acceptable image quality when using a 15-layer CNN. 2020 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Authors: Faysal F Altahawi; Kevin J Blount; Nicholas P Morley; Esther Raithel; Imran M Omar Journal: Skeletal Radiol Date: 2016-10-15 Impact factor: 2.199
Authors: Erin FitzGerald Alaia; Alex Benedick; Nancy A Obuchowski; Joshua M Polster; Luis S Beltran; Jean Schils; Elisabeth Garwood; Christopher J Burke; I-Yuan Joseph Chang; Soterios Gyftopoulos; Naveen Subhas Journal: Skeletal Radiol Date: 2017-09-26 Impact factor: 2.199
Authors: Florian Knoll; Tullie Murrell; Anuroop Sriram; Nafissa Yakubova; Jure Zbontar; Michael Rabbat; Aaron Defazio; Matthew J Muckley; Daniel K Sodickson; C Lawrence Zitnick; Michael P Recht Journal: Magn Reson Med Date: 2020-06-07 Impact factor: 4.668
Authors: S Sridhar; J Amutharaj; Prajoona Valsalan; B Arthi; S Ramkumar; S Mathupriya; T Rajendran; Yosef Asrat Waji Journal: J Healthc Eng Date: 2022-02-08 Impact factor: 2.682