Spinal Stenosis Grading in Magnetic Resonance Imaging Using Deep Convolutional Neural Networks

Abstract

Study Design. Retrospective magnetic resonance imaging grading with comparison between experts and deep convolutional neural networks (CNNs). Objective. This study aims to verify the feasibility of a computer-assisted spine stenosis grading system by comparing the diagnostic agreement between two experts and the agreement between the experts and trained artificial CNN classifiers. Summary of Background Data. Spinal stenosis grading is important; however, it is tedious job to check the MR images slide by slide to classify patient grades often having different opinions regarding the final diagnosis. Methods. For 542 L4-5 axial MR images, two experts independently localized the center position of the spine canal and graded the status. Two CNN classifiers each trained with the grading label made by the two experts were validated using 10-fold cross-validation. Each classifier consisted of a CNN detection model responsible for the localization of patches near the canal and a classification CNN model to predict the spinal stenosis status in the localized patches. Faster R-CNN was used for the detection model whereas VGG network was used for the classification model. A comparison in grading agreement was carried out between the two experts as well as that of the experts and the prediction results generated by the CNN models. Results. Grading agreement between the experts was 77.5% and 75% in terms of accuracy and F1 scores. The agreement between the first expert and the model trained with the labels of the first expert was 83% and 75.4%, respectively. The agreement between the second expert and the model trained with the labels of the second expert was 77.9% and 74.9%. The differences between the two experts were significant, whereas the differences between each expert and the trained models were not significant. Conclusion. We indeed confirmed that automatic diagnosis using deep learning may be feasible for spinal stenosis grading. Level of Evidence: 4

Study on Automatic Multi-Classification of Spine Based on Deep Learning and Postoperative Infection Screening

“…Traditional machine learning algorithms mainly include two steps: feature extraction and classification. In the part of feature extraction, this study selects five most advanced global algorithms for texture representation, namely local binary patterns (LBPs) [ 2 ], local phase quantization (LPQ) [ 12 ], gray-level co-occurrence matrix (GLCM) [ 3 ], histogram of oriented gradient (HOG), and oriented fast and rotated brief (ORB) [ 4 ]. The feature dimensions of the five feature descriptors are shown in Table 3 .…”

“…Opioids are common analgesics. Although they have certain analgesic effects, the use of opioids alone in large doses is easy to produce drug tolerance, accompanied by many adverse reactions, resulting in low pain control effect and control satisfaction [ 2 ]. The application and development of multimodal analgesia nursing provide an effective guarantee for clinical analgesia nursing.…”

Detection of Degenerative Changes on MR Images of the Lumbar Spine with a Convolutional Neural Network: A Feasibility Study

“…To our knowledge, our study is the first to externally validate a comprehensive software solution that focuses on the diagnosis of clinically relevant degenerative changes such as disc herniation and nerve root compression, in addition to the sole graduation of single degenerative changes. Our approach differs from most preliminary studies since it can process both axial and sagittal slices of lumbar MRIs, leading to markedly enhanced detection rates of spinal pathologies compared to the aforementioned study by Jamaludin et al and a recent study by Won et al (e.g., in case of spinal canal stenosis, our accuracy was 98% vs. 95% vs. 83%, respectively) [ 37 ], even though direct comparison of the methods on different data sets is methodologically difficult.…”

A deep learning algorithm to identify cervical ossification of posterior longitudinal ligaments on radiography

“…A strength of this study was its clear establishment of the ground truth by the presence or absence of cervical OPLL on CT. To create the deep learning algorithm, determination of the ground truth is a critical issue. For example, Won et al created a convolution neural network (CNN) to classify lumbar canal stenosis severity into four grades 11 . Although their study was informative, the study methodology and results were complex; two radiologists assessed lumbar canal stenosis on magnetic resonance imaging independently, and two types of CNNs were investigated using the radiological findings determined by the radiologists.…”