Faculty Bibliography

PURPOSE:To describe and evaluate a new segmentation method using deep convolutional neural network (CNN), 3D fully connected conditional random field (CRF), and 3D simplex deformable modeling to improve the efficiency and accuracy of knee joint tissue segmentation. METHODS:A segmentation pipeline was built by combining a semantic segmentation CNN, 3D fully connected CRF, and 3D simplex deformable modeling. A convolutional encoder-decoder network was designed as the core of the segmentation method to perform high resolution pixel-wise multi-class tissue classification for 12 different joint structures. The 3D fully connected CRF was applied to regularize contextual relationship among voxels within the same tissue class and between different classes. The 3D simplex deformable modeling refined the output from 3D CRF to preserve the overall shape and maintain a desirable smooth surface for joint structures. The method was evaluated on 3D fast spin-echo (3D-FSE) MR image data sets. Quantitative morphological metrics were used to evaluate the accuracy and robustness of the method in comparison to the ground truth data. RESULTS:The proposed segmentation method provided good performance for segmenting all knee joint structures. There were 4 tissue types with high mean Dice coefficient above 0.9 including the femur, tibia, muscle, and other non-specified tissues. There were 7 tissue types with mean Dice coefficient between 0.8 and 0.9 including the femoral cartilage, tibial cartilage, patella, patellar cartilage, meniscus, quadriceps and patellar tendon, and infrapatellar fat pad. There was 1 tissue type with mean Dice coefficient between 0.7 and 0.8 for joint effusion and Baker's cyst. Most musculoskeletal tissues had a mean value of average symmetric surface distance below 1 mm. CONCLUSION:The combined CNN, 3D fully connected CRF, and 3D deformable modeling approach was well-suited for performing rapid and accurate comprehensive tissue segmentation of the knee joint. The deep learning-based segmentation method has promising potential applications in musculoskeletal imaging.

BACKGROUND:F-FDG) PET images. A deep convolutional encoder-decoder network was trained to identify tissue contrast in volumetric uncorrected PET images co-registered to CT data. A set of 100 retrospective 3D FDG PET head images was used to train the model. The model was evaluated in another 28 patients by comparing the generated pseudo-CT to the acquired CT using Dice coefficient and mean absolute error (MAE) and finally by comparing reconstructed PET images using the pseudo-CT and acquired CT for attenuation correction. Paired-sample t tests were used for statistical analysis to compare PET reconstruction error using deepAC with CT-based attenuation correction. RESULTS:F-FDG PET results with average errors of less than 1% in most brain regions. CONCLUSIONS:F-FDG non-attenuation-corrected (NAC) PET image and evaluated it in PET/CT brain imaging.

Purpose To determine the feasibility of using a deep learning approach to detect cartilage lesions (including cartilage softening, fibrillation, fissuring, focal defects, diffuse thinning due to cartilage degeneration, and acute cartilage injury) within the knee joint on MR images. Materials and Methods A fully automated deep learning-based cartilage lesion detection system was developed by using segmentation and classification convolutional neural networks (CNNs). Fat-suppressed T2-weighted fast spin-echo MRI data sets of the knee of 175 patients with knee pain were retrospectively analyzed by using the deep learning method. The reference standard for training the CNN classification was the interpretation provided by a fellowship-trained musculoskeletal radiologist of the presence or absence of a cartilage lesion within 17 395 small image patches placed on the articular surfaces of the femur and tibia. Receiver operating curve (ROC) analysis and the κ statistic were used to assess diagnostic performance and intraobserver agreement for detecting cartilage lesions for two individual evaluations performed by the cartilage lesion detection system. Results The sensitivity and specificity of the cartilage lesion detection system at the optimal threshold according to the Youden index were 84.1% and 85.2%, respectively, for evaluation 1 and 80.5% and 87.9%, respectively, for evaluation 2. Areas under the ROC curve were 0.917 and 0.914 for evaluations 1 and 2, respectively, indicating high overall diagnostic accuracy for detecting cartilage lesions. There was good intraobserver agreement between the two individual evaluations, with a κ of 0.76. Conclusion This study demonstrated the feasibility of using a fully automated deep learning-based cartilage lesion detection system to evaluate the articular cartilage of the knee joint with high diagnostic performance and good intraobserver agreement for detecting cartilage degeneration and acute cartilage injury. © RSNA, 2018 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 determine whether a T2 mapping sequence could depict early changes in the composition and microstructure of cartilage overlying stable lesions of the medial femoral condyle in patients with juvenile osteochondritis dissecans (JOCD). Materials and Methods This retrospective study analyzed a sagittal T2 mapping sequence performed between September 1, 2015, and March 31, 2017, on 16 patients (10 boys and six girls; median age, 11.5 years) with 18 stable medial femoral condyle JOCD lesions and 18 age-, sex-, and skeletal maturation-matched control participants (11 boys and seven girls; median age, 11.5 years). Cartilage T2 values were quantitatively measured within regions of interest placed around the cartilage within and overlying the JOCD lesion in patients with JOCD and around the cartilage on the weight-bearing medial femoral condyle in patients with JOCD and controls. Wilcoxon signed rank and Wilcoxon rank sum tests were used to compare T2 values. Results T2 values were significantly higher (P < .001) for cartilage within the JOCD lesion than for cartilage overlying the JOCD lesion in patients with JOCD. However, there were no significant differences in T2 values between cartilage overlying the JOCD lesion and cartilage on the weight-bearing medial femoral condyle in patients with JOCD (P = .67) or in T2 values of the cartilage on the weight-bearing medial femoral condyle between patients with JOCD and controls (P = .30). Conclusion There were no significant quantifiable differences in T2 values of cartilage overlying stable JOCD lesions and normal cartilage on the medial femoral condyle, suggesting no substantial changes in cartilage composition and microstructure.

BACKGROUND:Abnormal knee mechanics may contribute to early cartilage degeneration following anterior cruciate ligament reconstruction. Anterior cruciate ligament graft geometry has previously been linked to abnormal tibiofemoral kinematics, suggesting this parameter may be important in restoring normative cartilage loading. However, the relationship between graft geometry and cartilage contact is unknown. METHODS:Static MR images were collected and segmented for eighteen subjects to obtain bone, cartilage, and anterior cruciate ligament geometries for their reconstructed and contralateral knees. The footprint locations and orientation of the anterior cruciate ligament were calculated. Volumetric, dynamic MR imaging was also performed to measure tibiofemoral kinematics, cartilage contact location, and contact sliding velocity while subjects performed loaded knee flexion-extension. Multiple linear regression was used to determine the relationship between non-anatomic graft geometry and asymmetric knee mechanics. FINDINGS: = 0.54). INTERPRETATION:This study provides evidence that non-anatomic graft geometry is linked to asymmetric knee mechanics, suggesting that restoring native anterior cruciate ligament geometry may be important to mitigate the risk of early cartilage degeneration in these patients.

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.

OBJECTIVE:The purpose of this study is to determine whether marginal osteophytes in compartments with normal cartilage would be more frequently observed in knees with cartilage lesions and osteophytes in other compartments. MATERIALS AND METHODS/METHODS:This retrospective study reviewed 500 consecutive knee MRI examinations performed within 6 months of arthroscopic knee surgery conducted for 497 patients with symptoms (289 male patients and 208 female patients; age range, 17-74 years; median age, 43 years). The highest grade of cartilage lesion detected at MRI and arthroscopy was recorded. Marginal osteophytes were graded on MRI with use of a standardized scoring system, with grade 0 denoting no osteophyte; grade 1, small osteophyte; grade 2, medium-size osteophyte; and grade 3, large osteophyte). The frequency of false-positive osteophytes, defined as osteophytes present in compartments (the patellofemoral, medial tibiofemoral, and lateral tibiofemoral compartments) with normal cartilage observed on MRI and arthroscopy, was calculated. The Goodman and Kruskal gamma statistic was used to test the association of osteophyte size between compartments. Logistic regression was used to test the association between osteophyte size and the severity of the cartilage lesions. RESULTS:Marginal osteophytes were seen in compartments with normal cartilage on MRI and arthroscopy in 60.5% of knees (75 of 124) with cartilage lesions and osteophytes in other compartments and accounted for all false-positive grade 2 and grade 3 osteophytes. Marginal osteophytes were seen in 12.7% of knees (13 of 102) that had no cartilage lesions in any compartment on MRI or arthroscopy, and all of these were grade 1 osteophytes. The presence of larger sized osteophytes in the compartments with cartilage lesions was associated with the presence of larger sized osteophytes in the compartments with normal cartilage. More severe cartilage lesions were associated with larger osteophyte size. CONCLUSION/CONCLUSIONS:Compartments with marginal osteophytes and normal cartilage are commonly seen in knees that have other compartments with osteophytes and cartilage lesions.

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.

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.