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.

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 .

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.

To investigate the feasibility of using a deep learning-based approach to detect an anterior cruciate ligament (ACL) tear within the knee joint at MRI by using arthroscopy as the reference standard. Materials and Methods: A fully automated deep learning-based diagnosis system was developed by using two deep convolutional neural networks (CNNs) to isolate the ACL on MR images followed by a classification CNN to detect structural abnormalities within the isolated ligament. With institutional review board approval, sagittal proton density-weighted and fat-suppressed T2-weighted fast spinecho MR images of the knee in 175 subjects with a full-thickness ACL tear (98 male subjects and 77 female subjects; average age, 27.5 years) and 175 subjects with an intact ACL (100 male subjects and 75 female subjects; average age, 39.4 years) were retrospectively analyzed by using the deep learning approach. Sensitivity and specificity of the ACL tear detection system and five clinical radiologists for detecting an ACL tear were determined by using arthroscopic results as the reference standard. Receiver operating characteristic (ROC) analysis and two-sided exact binomial tests were used to further assess diagnostic performance. Results: The sensitivity and specificity of the ACL tear detection system at the optimal threshold were 0.96 and 0.96, respectively. In comparison, the sensitivity of the clinical radiologists ranged between 0.96 and 0.98, while the specificity ranged between 0.90 and 0.98. There was no statistically significant difference in diagnostic performance between the ACL tear detection system and clinical radiologists at P < .05. The area under the ROC curve for the ACL tear detection system was 0.98, indicating high overall diagnostic accuracy. Conclusion: There was no significant difference between the diagnostic performance of the ACL tear detection system and clinical radiologists for determining the presence or absence of an ACL tear at MRI.

A new Cardiac Electrical Sparse Imaging (CESI) technique is proposed to image cardiac activation throughout the three-dimensional myocardium from body surface electrocardiogram (ECG) with the aid of individualized heart-torso geometry. The sparse property of cardiac electrical activity in the time domain is utilized in the temporal sparse promoting inverse solution, one formulated to achieve higher spatial-temporal resolution, stronger robustness and thus enhanced capability in imaging cardiac electrical activity. Computer simulations were carried out to evaluate the performance of this imaging method under various circumstances. A total of 12 single site pacing and 7 dual sites pacing simulations with artificial and the hospital recorded sensor noise were used to evaluate the accuracy and stability of the proposed method. Simulations with modeling error on heart-torso geometry and electrode-torso registration were also performed to evaluate the robustness of the technique. In addition to the computer simulations, the CESI algorithm was further evaluated using experimental data in an animal model where the noninvasively imaged activation sequences were compared with those measured with simultaneous intracardiac mapping. All of the CESI results were compared with conventional weighted minimum norm solutions. The present results show that CESI can image with better accuracy, stability and stronger robustness in both simulated and experimental circumstances. In sum, we have proposed a novel method for cardiac activation imaging, and our results suggest that the CESI has enhanced performance, and offers the potential to image the cardiac activation and to assist in the clinical management of ventricular arrhythmias.

Background Imaging myocardial activation from noninvasive body surface potentials promises to aid in both cardiovascular research and clinical medicine. Objective This study investigates the ability of a noninvasive 3-dimensional cardiac electrical imaging (3DCEI) technique for characterizing the activation patterns of dynamically changing ventricular arrhythmias during drug-induced QT prolongation in rabbit. Methods Simultaneous body surface potential mapping and 3-dimensional intra-cardiac mapping were performed in a closed-chest condition in eight rabbits. Data analysis was performed on premature ventricular complexes, couplets, and torsades de pointes (TdP) induced during i.v. administration of clofilium and phenylephrine with combinations of various infusion rates. Results The drug infusion led to significant increase of QT interval (175±7ms to 274±31ms) and rate-corrected QT interval (183±5ms to 262±21ms) during the first dose cycle. All the ectopic beats initiated by a focal activation pattern. The initial beat of TdPs arose at focal site, whereas the subsequent beats were due to focal activity from different sites or two competing focal sites. The imaged results captured the dynamic shift of activation patterns and were in good correlation with the simultaneous measurements with a correlation coefficient of 0.65±0.02 averaged over 111 ectopic beats. Sites of initial activation were localized to be ~5mm. Conclusion The 3DCEI technique could localize the origin of activation and image activation sequence of TdP during QT prolongation induced by clofilium and phenylephrine in rabbit. It offers the potential to non-invasively investigate the proarrhythmic effects of drug infusion and assess the mechanisms of arrhythmias on a beat-to-beat basis.

Objective Highest dominant-frequency (DF) drivers maintaining atrial fibrillation (AF) activities are effective ablation targets for restoring sinus rhythms in patients. This study aims to investigate whether AF drivers with highest activation rate can be noninvasively localized by means of a frequency-based cardiac electrical imaging (CEI) technique, which may aid in the planning of ablation strategy and the investigation of the underlying mechanisms of AF. Method A total of 7 out of 13 patients were recorded with spontaneous paroxysmal or persistent AF and analyzed. The bi-atrial DF maps were reconstructed by coupling 5-second BSPM with CT-determined patient geometry. The CEI results were compared with ablation sites and DFs found from BSPMs. Results CEI imaged left-to-right maximal frequency gradient (7.42 ± 0.66 Hz vs. 5.85 ± 1.2 Hz, LA vs. RA, p<0.05) in paroxysmal AF patients. Patients with persistent AF were imaged with a loss of the intra-chamber frequency gradient and a dispersion of the fast sources in both chambers. CEI was able to capture the AF behaviors, which were characterized by short-term stability, dynamic transition, and spatial repetition of the highest DF sites. The imaged highest DF sites were consistent with ablation sites in patients studied. Conclusions The frequency-based CEI allows localization of AF drivers with highest DF and characterization of the spatiotemporal frequency behaviors, suggesting the possibility for individualizing treatment strategy and advancing understanding of the underlying AF mechanisms. Significance: The establishment of noninvasive imaging techniques localizing AF drivers would facilitate management of this significant cardiac arrhythmia.

OBJECTIVE. The objective of our study was to use a T2 mapping sequence performed at 3 T to investigate changes in the composition and microstructure of the cartilage and menisci of the pediatric knee joint during maturation. MATERIALS AND METHODS. This retrospective study was performed of MRI examinations of 76 pediatric knees without internal derangement in 72 subjects (29 boys [mean age, 12.5 years] and 43 girls [mean age, 13.0 years]) who were evaluated with a sagittal T2 mapping sequence. T2 relaxation time values were quantitatively measured in eight cartilage subregions and in the medial and lateral menisci. Wilcoxon rank sum and Kruskal-Wallis tests were used to analyze the relationship between cartilage and meniscus T2 relaxation time values and sex and skeletal maturation, respectively. A multivariate linear regression model was used to investigate the independent association between cartilage T2 relaxation time values and age, weight, and body mass index (BMI [weight in kilograms divided by the square of height in meters]). RESULTS. There were no significant sex differences (p = 0.26–0.91) in T2 relaxation time values for cartilage or meniscus. T2 relaxation time values in each individual cartilage subregion significantly decreased (p < 0.001) with progressive maturation. T2 relaxation time values in the lateral meniscus significantly increased (p = 0.001) with maturation, whereas T2 relaxation time values in the medial meniscus did not significantly change (p = 0.82). There was a significant association (p < 0.001) between cartilage T2 relaxation time values and age independent of weight and BMI, but no significant association between cartilage T2 relaxation time values and weight (p = 0.06) and BMI (p = 0.20) independent of age. CONCLUSION. Cartilage T2 relaxation time values significantly decreased in all cartilage subregions and meniscus T2 relaxation time values significantly increased in the lateral meniscus during maturation. These changes in T2 relaxation time values reflect age-related changes in tissue composition and microstructure.