Faculty Bibliography

PURPOSE:To describe and evaluate a new fully automated musculoskeletal tissue segmentation method using deep convolutional neural network (CNN) and three-dimensional (3D) simplex deformable modeling to improve the accuracy and efficiency of cartilage and bone segmentation within the knee joint. METHODS:A fully automated segmentation pipeline was built by combining a semantic segmentation CNN and 3D simplex deformable modeling. A CNN technique called SegNet was applied as the core of the segmentation method to perform high resolution pixel-wise multi-class tissue classification. The 3D simplex deformable modeling refined the output from SegNet to preserve the overall shape and maintain a desirable smooth surface for musculoskeletal structure. The fully automated segmentation method was tested using a publicly available knee image data set to compare with currently used state-of-the-art segmentation methods. The fully automated method was also evaluated on two different data sets, which include morphological and quantitative MR images with different tissue contrasts. RESULTS:The proposed fully automated segmentation method provided good segmentation performance with segmentation accuracy superior to most of state-of-the-art methods in the publicly available knee image data set. The method also demonstrated versatile segmentation performance on both morphological and quantitative musculoskeletal MR images with different tissue contrasts and spatial resolutions. CONCLUSION:The study demonstrates that the combined CNN and 3D deformable modeling approach is useful for performing rapid and accurate cartilage and bone segmentation within the knee joint. The CNN has promising potential applications in musculoskeletal imaging. Magn Reson Med 79:2379-2391, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Purpose To develop and evaluate the feasibility of deep learning approaches for magnetic resonance (MR) imaging-based attenuation correction (AC) (termed deep MRAC) in brain positron emission tomography (PET)/MR imaging. Materials and Methods A PET/MR imaging AC pipeline was built by using a deep learning approach to generate pseudo computed tomographic (CT) scans from MR images. A deep convolutional auto-encoder network was trained to identify air, bone, and soft tissue in volumetric head MR images coregistered to CT data for training. A set of 30 retrospective three-dimensional T1-weighted head images was used to train the model, which was then evaluated in 10 patients by comparing the generated pseudo CT scan to an acquired CT scan. A prospective study was carried out for utilizing simultaneous PET/MR imaging for five subjects by using the proposed approach. Analysis of covariance and paired-sample t tests were used for statistical analysis to compare PET reconstruction error with deep MRAC and two existing MR imaging-based AC approaches with CT-based AC. Results Deep MRAC provides an accurate pseudo CT scan with a mean Dice coefficient of 0.971 ± 0.005 for air, 0.936 ± 0.011 for soft tissue, and 0.803 ± 0.021 for bone. Furthermore, deep MRAC provides good PET results, with average errors of less than 1% in most brain regions. Significantly lower PET reconstruction errors were realized with deep MRAC (-0.7% ± 1.1) compared with Dixon-based soft-tissue and air segmentation (-5.8% ± 3.1) and anatomic CT-based template registration (-4.8% ± 2.2). Conclusion The authors developed an automated approach that allows generation of discrete-valued pseudo CT scans (soft tissue, bone, and air) from a single high-spatial-resolution diagnostic-quality three-dimensional MR image and evaluated it in brain PET/MR imaging. This deep learning approach for MR imaging-based AC provided reduced PET reconstruction error relative to a CT-based standard within the brain compared with current MR imaging-based AC approaches. ^© RSNA, 2017 Online supplemental material is available for this article.

Purpose To determine the diagnostic performance of three-dimensional (3D) MRI for the depiction and characterization of cartilage defects within the knee joint by using arthroscopy and/or open surgery as the standard of reference. Materials and Methods A systematic literature search was performed to extract diagnostic studies published between January 1985 and October 2017. Two independent investigators assessed the methodologic quality of each study by using Quality Assessment of Diagnostic Accuracy Studies 2. Bivariate random-effects model was used to compare the diagnostic odds ratio (DOR) of 3D and two-dimensional (2D) MRI for helping to detect knee cartilage defects and to assess the effect of relevant covariates on diagnostic performance of 3D MRI. Meta-regression analysis was performed to assess DOR of 3D MRI during the last 3 decades. Results Twenty-seven studies (composed of 1710 MRI examinations) were included. Of those, 16 (59%) studies compared the diagnostic performance of 3D and 2D MRI. The diagnostic performance of 3D MRI statistically significantly improved over the last 3 decades (P = .003). Three-dimensional MRI obtained by using 3.0-T field strength had higher DOR relative to 1.5-T or lower field strength (relative DOR, 4.05; P = .01). Three-dimensional multiplanar reformation was associated with higher specificity (P = .001) compared with conventional axial, sagittal, and coronal 2D MRI planes. Three-dimensional fast-spin-echo sequences provided higher sensitivity and specificity (P < .05) than did 2D MRI. Conclusion Three-dimensional MRI currently provides comparable diagnostic performance to two-dimensional MRI, with improvement in diagnostic performance achieved by using 3.0-T field strength, three-dimensional fast-spin-echo sequences, and multiplanar reformation. © RSNA, 2018 Online supplemental material is available for this article.

PURPOSE:To investigate the feasibility of using compressed sensing (CS) to accelerate three-dimensional fast spin-echo (3D-FSE) imaging of the knee. MATERIALS AND METHODS:A 3D-FSE sequence was performed at 3T with CS (CUBE-CS with 3:16-minute scan time) and without CS (CUBE with 4:44-minute scan time) twice on the knees of 10 healthy volunteers to assess signal-to-noise ratio (SNR) using the addition-subtraction method and once on the knees of 50 symptomatic patients to assess diagnostic performance. SNR of cartilage, muscle, synovial fluid, and bone marrow on CUBE and CUBE-CS images were measured in the 10 healthy volunteers. The CUBE and CUBE-CS sequences of all 50 symptomatic patients were independently reviewed twice by two musculoskeletal radiologists. The radiologists used CUBE and CUBE-CS during each individual review to determine the presence or absence of knee joint pathology. Student's t-tests were used to compare SNR values between sequences, while the kappa statistic was used to determine agreement between sequences for detecting knee joint pathology. Sensitivity and specificity of CUBE and CUBE-CS for detecting knee joint pathology was also calculated in the 18 symptomatic patients who underwent subsequent arthroscopic knee surgery. RESULTS:CUBE and CUBE-CS had similar SNR (P = 0.15-0.67) of cartilage, muscle, synovial fluid, and bone marrow. There was near-perfect to perfect agreement between CUBE and CUBE-CS for both radiologists for detecting cartilage and bone marrow edema lesions, medial and lateral meniscus tears, anterior cruciate ligament tears, effusions, and intra-articular bodies. CUBE and CUBE-CS had similar sensitivity (75.0-100%) and specificity (87.5-100%) for detecting 60 cartilage lesions, 20 meniscus tears, four anterior cruciate ligament tears, and four intra-articular bodies confirmed at surgery. CONCLUSION:CS provided a 30% reduction in scan time for 3D-FSE imaging of the knee without a corresponding decrease in SNR or diagnostic performance. LEVEL OF EVIDENCE:1 J. MAGN. RESON. IMAGING 2017;45:1712-1722.

We present MRiLab, a new comprehensive simulator for large-scale realistic MRI simulations on a regular PC equipped with a modern graphical processing unit (GPU). MRiLab combines realistic tissue modeling with numerical virtualization of an MRI system and scanning experiment to enable assessment of a broad range of MRI approaches including advanced quantitative MRI methods inferring microstructure on a sub-voxel level. A flexible representation of tissue microstructure is achieved in MRiLab by employing the generalized tissue model with multiple exchanging water and macromolecular proton pools rather than a system of independent proton isochromats typically used in previous simulators. The computational power needed for simulation of the biologically relevant tissue models in large 3D objects is gained using parallelized execution on GPU. Three simulated and one actual MRI experiments were performed to demonstrate the ability of the new simulator to accommodate a wide variety of voxel composition scenarios and demonstrate detrimental effects of simplified treatment of tissue micro-organization adapted in previous simulators. GPU execution allowed  ∼ 200× improvement in computational speed over standard CPU. As a cross-platform, open-source, extensible environment for customizing virtual MRI experiments, MRiLab streamlines the development of new MRI methods, especially those aiming to infer quantitatively tissue composition and microstructure.

BACKGROUND:Although knees that have undergone anterior cruciate ligament reconstruction (ACLR) often exhibit normal laxity on clinical examination, abnormal kinematic patterns have been observed when the joint is dynamically loaded during whole body activity. This study investigated whether abnormal knee kinematics arise with loading under isolated dynamic movements. HYPOTHESIS/OBJECTIVE:Tibiofemoral and patellofemoral kinematics of ACLR knees will be similar to those of the contralateral uninjured control knee during passive flexion-extension, with bilateral differences emerging when an inertial load is applied. STUDY DESIGN/METHODS:Controlled laboratory study. METHODS:The bilateral knees of 18 subjects who had undergone unilateral ACLR within the past 4 years were imaged by use of magnetic resonance imaging (MRI). Their knees were cyclically (0.5 Hz) flexed passively. Subjects then actively flexed and extended their knees against an inertial load that induced stretch-shortening quadriceps contractions, as seen during the load acceptance phase of gait. A dynamic, volumetric, MRI sequence was used to track tibiofemoral and patellofemoral kinematics through 6 degrees of freedom. A repeated-measures analysis of variance was used to compare secondary tibiofemoral and patellofemoral kinematics between ACLR and healthy contralateral knees during the passive and active extension phases of the cyclic motion. RESULTS:Relative to the passive motion, inertial loading induced significant shifts in anterior and superior tibial translation, internal tibial rotation, and all patellofemoral degrees of freedom. As hypothesized, tibiofemoral and patellofemoral kinematics were bilaterally symmetric during the passive condition. However, inertial loading induced bilateral differences, with the ACLR knees exhibiting a significant shift toward external tibial rotation. A trend toward greater medial and anterior tibial translation was seen in the ACLR knees. CONCLUSION/CONCLUSIONS:This study demonstrates that abnormal knee kinematic patterns in ACLR knees emerge during a simple, active knee flexion-extension task that can be performed in an MRI scanner. CLINICAL RELEVANCE/CONCLUSIONS:It is hypothesized that abnormal knee kinematics may alter cartilage loading patterns and thereby contribute to increased risk for osteoarthritis. Recent advances in quantitative MRI can be used to detect early cartilage degeneration in ACLR knees. This study demonstrates the feasibility of identifying abnormal ACLR kinematics by use of dynamic MRI, supporting the combined use of dynamic and quantitative MRI to investigate the proposed link between knee motion, cartilage contact, and early biomarkers of cartilage degeneration.

PURPOSE/OBJECTIVE:) relaxation time analysis of human patellar tendon. METHODS:parameter estimation in tendon at different signal-to-noise ratios (SNR) levels. RESULTS:analysis of tendon agreed well with numerical simulations. CONCLUSION/CONCLUSIONS:analysis especially at lower SNR. LEVEL OF EVIDENCE/METHODS:IV.

PURPOSE:To compare bicomponent ultrashort echo time (UTE) T2* parameters of patellar tendon between healthy volunteers and patients with patellar tendinopathy. MATERIALS AND METHODS:) of patellar tendon were measured in all subjects. Wilcoxon rank-sum tests were used to compare UTE- T2* parameters between healthy volunteers and patients with patellar tendinopathy. RESULTS:(P = 0.007) but not T2*S (P = 0.10) of the patellar tendon. CONCLUSION:of patellar tendon than healthy volunteers, which suggests that bicomponent UTE- T2* parameters can detect changes in the composition and microstructure of degenerative tendon. LEVEL OF EVIDENCE:1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:1441-1447.

OBJECTIVE:To compare magnetic resonance imaging (MRI) characteristics of torn and untorn post-operative menisci. METHODS:The study group consisted of 140 patients with 148 partially resected menisci who were evaluated with a repeat knee MRI examination and subsequent repeat arthroscopic knee surgery. Two musculoskeletal radiologists retrospectively assessed the following MRI characteristics of the post-operative meniscus: contour (smooth or irregular), T2 line through the meniscus (no line, intermediate signal line, intermediate-to-high signal line, and high fluid-like signal line), displaced meniscus fragment, and change in signal pattern through the meniscus compared with baseline MRI. Positive predictive values (PPV) and negative predictive values (NPV) were calculated using arthroscopy as the reference standard. RESULTS:All 36 post-operative menisci with no T2 line were untorn at surgery (100% NPV), whereas 46 of the 79 post-operative menisci with intermediate T2 line, 16 of the 18 post-operative menisci with intermediate-to-high T2 line, and 14 of the 15 post-operative menisci with high T2 line were torn at surgery (58.2%, 88.9%, and 93.3% PPV respectively). Additional MRI characteristics associated with torn post-operative meniscus at surgery were irregular meniscus contour (PPV 85.7%), displaced meniscus fragment (PPV 100%), and change in signal pattern through the meniscus (PPV 99.4%). CONCLUSIONS:Post-operative menisci with no T2 signal line were untorn at surgery. The most useful MRI characteristics for predicting torn post-operative menisci at surgery were change in signal pattern through the meniscus compared with baseline MRI, and displaced meniscus fragment followed by high T2 line through the meniscus, intermediate-to-high T2 line through the meniscus, and irregular meniscus contour.

PURPOSE/OBJECTIVE:To study the effects of magnetization transfer (MT) on multicomponent T2 parameters obtained using mcDESPOT in macromolecule-rich tissues and to propose a new method called mcRISE to correct MT-induced biases. METHODS:The two-pool mcDESPOT model was modified by the addition of an exchanging macromolecule proton pool to model the MT effect in cartilage. The mcRISE acquisition scheme was developed to provide sensitivity to all pools. An incremental fitting was applied to estimate MT and relaxometry parameters with minimized coupling. The interaction between MT and relaxometry parameters, efficacy of MT correction, and feasibility of mcRISE in vivo were investigated in simulations and in healthy volunteers. RESULTS:The MT effect caused significant errors in multicomponent T1/T2 values and in fast-relaxing water fraction fF , which is consistent with previous experimental observations. fF increased significantly with macromolecule content if MT was ignored. mcRISE resulted in a multifold reduction of MT biases and yielded decoupled multicomponent T1/T2 relaxometry and quantitative MT parameters. CONCLUSION/CONCLUSIONS:mcRISE is an efficient approach for correcting MT biases in multicomponent relaxometry based on steady state sequences. Improved specificity of mcRISE may help to elucidate the sources of the previously described high sensitivity of noncorrected mcDESPOT parameters to disease-related changes in cartilage and the brain.