Deep Learning Application in Spinal Implant Identification

Abstract

Study Design. Retrospective observational study. Objective. To demonstrate the clinical usefulness of deep learning by identifying previous spinal implants through application of deep learning. Summary of Background Data. Deep learning has recently been actively applied to medical images. However, despite many attempts to apply deep learning to medical images, the application has rarely been successful. We aimed to demonstrate the effectiveness and usefulness of deep learning in the medical field. The goal of this study was to demonstrate the clinical usefulness of deep learning by identifying previous spinal implants through application of deep learning. Methods. For deep learning algorithm development, radiographs were retrospectively obtained from clinical cases in which the patients had lumbar spine one-segment instrument surgery. A total of 2894 lumbar spine anteroposterior (AP: 1446 cases) and lateral (1448 cases) radiographs were collected. Labeling work was conducted for five different implants. We conducted experiments using three deep learning algorithms. The traditional deep neural network model built by coding the transfer learning algorithm, Google AutoML, and Apple Create ML. Recall (sensitivity) and precision (specificity) were measured after training. Results. Overall, each model performed well in identifying each pedicle screw implant. In conventional transfer learning, AP radiography showed 97.0% precision and 96.7% recall. Lateral radiography showed 98.7% precision and 98.2% recall. In Google AutoML, AP radiography showed 91.4% precision and 87.4% recall; lateral radiography showed 97.9% precision and 98.4% recall. In Apple Create ML, AP radiography showed 76.0% precision and 73.0% recall; lateral radiography showed 89.0% precision and 87.0% recall. In all deep learning algorithms, precision and recall were higher in lateral than in AP radiography. Conclusion. The deep learning application is effective for spinal implant identification. This demonstrates that clinicians can use ML-based deep learning applications to improve clinical practice and patient care. Level of Evidence: 3

Exploring the Learning Psychology Mobilization of Music Majors Through Innovative Teaching Methods Under the Background of New Curriculum Reform

“…Scholars worldwide have developed multiple genres of understanding of deep learning. Here, the view of the genre of ternary theory (Panagakis et al, 2021) is quoted, which is represented by Nelsonlarid et al (2020) Particularly, the ternary theory has put forward the scale of deep learning (Yang et al, 2021), and deep learning is defined from three specific dimensions (Zaidi and Naqa, 2021). The first dimension is higher-order thinking, which uses the learning process to promote the construction of meaning and a more comprehensive understanding.…”

A computer vision approach to identifying the manufacturer of posterior thoracolumbar instrumentation systems

“…16 Recently, three studies have applied computer vision techniques for hardware identification for the planning of revision surgery. 9,10,17 Two of the studies used computer vision SVMs and deep learning to develop classifiers to identify anterior cervical discectomy and fusion hardware, showing good results. 10,17 The third study, similar to our study, aimed to identify thoracolumbar screw-and-rod systems; however, they utilized deep learning, demonstrating classifier accuracy ranging from 73% to 98% for fivelevel classification.…”

“…This approach was selected over other traditional computer vision techniques such as convoluted neural networks because the data sets were sparse. 5,9 A KAZE feature extractor identified relevant radiographic features from training images. This algorithm was chosen because it is scale and rotation invariant and uses nonlinear scale-spaces to preserve important features while eliminating noise in the image.…”

“…The goal of that study was to demonstrate the clinical utility specifically of deep learning, with the example being thoracolumbar spinal implants. 9 The authors used AutoML via Google and Apple neural network platforms to achieve respectable results but at the price of "black box" mechanics, that is, poorly understood pathways from input to output.…”

Evaluation of Deep Learning-Based Automated Detection of Primary Spine Tumors on MRI Using the Turing Test

“…Deep learning (DL)-a class of artificial intelligence (AI) -is now prevalent in computer vision tasks. For spine imaging, especially MRI, DL, and other AI systems are being applied as diagnostic imaging technologies (1)(2)(3)(4)(5). Hallinan 9) developed the DL-based automated detection of spinal schwannomas in MRI.…”