Vertebral Deformity Measurements at MRI, CT, and Radiography Using Deep Learning

Suri, Abhinav; Jones, Brandon C.; Ng, Grace; Anabaraonye, Nancy; Beyrer, Patrick; Domi, Albi; Choi, Grace; Tang, Sisi; Terry, Ashley; Leichner, Thomas; Fathali, Iman; Bastin, Nikita; Chesnais, Helene; Taratuta, Elena; Kneeland, J. Bruce; Rajapakse, Chamith S.

doi:10.1148/ryai.2021210015

Cited by 13 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study is one of the first to assess the reliability of deep learning–based measurements of vertebral bodies on MRI. Recently, Suri et al showed the potential of a deep learning model to accurately measure vertebral body deformity on MRI, CT, and radiography with measurement errors around 2% [ 37 ]. Similarly, the DCNN in our study showed excellent agreement with each radiologist for measuring the anterior and posterior vertebral body height, and the vertebral angle, which was similar to the interobserver reliability between both radiologists.…”

Section: Discussionmentioning

confidence: 99%

“…Recent studies applied a DCNN to distinguish between benign and malignant fractures and between fresh and old osteoporotic fractures on lumbar spine MRI datasets, indicating high diagnostic accuracies [32][33][34]. Regarding AIbased lumbar spine measurements, several studies have been published [14,[35][36][37]. However, to our knowledge, the potential of a DL architecture for quantitative vertebral body assessment together with insufficiency fracture detection on MRI has not been investigated thus far.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection

Germann

Meyer²,

Staib³

et al. 2022

Eur Radiol

View full text Add to dashboard Cite

Objectives The aim is to validate the performance of a deep convolutional neural network (DCNN) for vertebral body measurements and insufficiency fracture detection on lumbar spine MRI. Methods This retrospective analysis included 1000 vertebral bodies in 200 patients (age 75.2 ± 9.8 years) who underwent lumbar spine MRI at multiple institutions. 160/200 patients had ≥ one vertebral body insufficiency fracture, 40/200 had no fracture. The performance of the DCNN and that of two fellowship-trained musculoskeletal radiologists in vertebral body measurements (anterior/posterior height, extent of endplate concavity, vertebral angle) and evaluation for insufficiency fractures were compared. Statistics included (a) interobserver reliability metrics using intraclass correlation coefficient (ICC), kappa statistics, and Bland-Altman analysis, and (b) diagnostic performance metrics (sensitivity, specificity, accuracy). A statistically significant difference was accepted if the 95% confidence intervals did not overlap. Results The inter-reader agreement between radiologists and the DCNN was excellent for vertebral body measurements, with ICC values of > 0.94 for anterior and posterior vertebral height and vertebral angle, and good to excellent for superior and inferior endplate concavity with ICC values of 0.79–0.85. The performance of the DCNN in fracture detection yielded a sensitivity of 0.941 (0.903–0.968), specificity of 0.969 (0.954–0.980), and accuracy of 0.962 (0.948–0.973). The diagnostic performance of the DCNN was independent of the radiological institution (accuracy 0.964 vs. 0.960), type of MRI scanner (accuracy 0.957 vs. 0.964), and magnetic field strength (accuracy 0.966 vs. 0.957). Conclusions A DCNN can achieve high diagnostic performance in vertebral body measurements and insufficiency fracture detection on heterogeneous lumbar spine MRI. Key Points • A DCNN has the potential for high diagnostic performance in measuring vertebral bodies and detecting insufficiency fractures of the lumbar spine.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection

Germann

Meyer²,

Staib³

et al. 2022

Eur Radiol

View full text Add to dashboard Cite

show abstract

“…We also compared our proposed model with other researchers. Our proposed methodology uses YOLOv5 for the localization and HED U-Net for the edge based segmentation, Masood et al used Resnet-UNet for the segmentation of lumbar vertebrae, Suri et al [64] used three neural networks, each network for each modality of image to compute the LLA, while Cho et al [65] used semantic segmentation by using the model UNet We obtained very small mean error of LLA and LSA as compared to [41,64,65]. The first two techniques are applied on Composite Lumbar Spine MRI Dataset [41].…”

Section: Comparison With Other Researchersmentioning

confidence: 99%

“…The first two techniques are applied on the same dataset. Cho et al[65] and Suri et al[64] have relatively larger LLA mean errors.…”

mentioning

confidence: 93%

Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models

Mushtaq

Akram

Alghamdi

et al. 2022

Sensors

View full text Add to dashboard Cite

The lumbar spine plays a very important role in our load transfer and mobility. Vertebrae localization and segmentation are useful in detecting spinal deformities and fractures. Understanding of automated medical imagery is of main importance to help doctors in handling the time-consuming manual or semi-manual diagnosis. Our paper presents the methods that will help clinicians to grade the severity of the disease with confidence, as the current manual diagnosis by different doctors has dissimilarity and variations in the analysis of diseases. In this paper we discuss the lumbar spine localization and segmentation which help for the analysis of lumbar spine deformities. The lumber spine is localized using YOLOv5 which is the fifth variant of the YOLO family. It is the fastest and the lightest object detector. Mean average precision (mAP) of 0.975 is achieved by YOLOv5. To diagnose the lumbar lordosis, we correlated the angles with region area that is computed from the YOLOv5 centroids and obtained 74.5% accuracy. Cropped images from YOLOv5 bounding boxes are passed through HED U-Net, which is a combination of segmentation and edge detection frameworks, to obtain the segmented vertebrae and its edges. Lumbar lordortic angles (LLAs) and lumbosacral angles (LSAs) are found after detecting the corners of vertebrae using a Harris corner detector with very small mean errors of 0.29 and 0.38, respectively. This paper compares the different object detectors used to localize the vertebrae, the results of two methods used to diagnose the lumbar deformity, and the results with other researchers.

show abstract

“…Previous use of raw imaging in deep learning models for spine surgery has typically been for tissue segmentation and automating radiographic measurements to minimize surgeon workload. 29,30 However, raw imaging deep learning can also be used to drive clinically meaningful predictions and potentially augment spinal surgical workflows.…”

mentioning

confidence: 99%

Artificial Intelligence to Preoperatively Predict Proximal Junction Kyphosis Following Adult Spinal Deformity Surgery: Soft Tissue Imaging May Be Necessary for Accurate Models

Johnson,

Chanbour,

Ali

et al. 2023

Spine

View full text Add to dashboard Cite

Study Design. Retrospective cohort. Objective: In a cohort of patients undergoing adult spinal deformity (ASD) surgery, we used artificial intelligence to compare three models of preoperatively predicting radiographic proximal junction kyphosis (PJK) using: (1) traditional demographics and radiographic measurements, (2) raw preoperative scoliosis radiographs, and (3) raw preoperative thoracic magnetic resonance imaging (MRI). Summary of Background Data. Despite many proposed risk factors, PJK following ASD surgery remains difficult to predict. Materials and Methods. A single-institution, retrospective cohort study was undertaken for patients undergoing ASD surgery from 2009 to 2021. PJK was defined as a sagittal Cobb angle of upper-instrumented vertebra (UIV) and UIV+2>10° and a postoperative change in UIV/UIV+2>10°. For model 1, a support vector machine was used to predict PJK within 2 years postoperatively using clinical and traditional sagittal/coronal radiographic variables and intended levels of instrumentation. Next, for model 2, a convolutional neural network (CNN) was trained on raw preoperative lateral and posterior-anterior scoliosis radiographs. Finally, for model 3, a CNN was trained on raw preoperative thoracic T1 MRIs. Results. A total of 191 patients underwent ASD surgery with at least 2-year follow-up and 89 (46.6%) developed radiographic PJK within 2 years. Model 1: Using clinical variables and traditional radiographic measurements, the model achieved a sensitivity: 57.2% and a specificity: 56.3%. Model 2: a CNN with raw scoliosis x-rays predicted PJK with a sensitivity: 68.2% and specificity: 58.3%. Model 3: a CNN with raw thoracic MRIs predicted PJK with average sensitivity: 73.1% and specificity: 79.5%. Finally, an attention map outlined the imaging features used by model 3 elucidated that soft tissue features predominated all true positive PJK predictions. Conclusions. The use of raw MRIs in an artificial intelligence model improved the accuracy of PJK prediction compared with raw scoliosis radiographs and traditional clinical/radiographic measurements. The improved predictive accuracy using MRI may indicate that PJK is best predicted by soft tissue degeneration and muscle atrophy.

show abstract

Vertebral Deformity Measurements at MRI, CT, and Radiography Using Deep Learning

Cited by 13 publications

References 16 publications

Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection

Performance of a deep convolutional neural network for MRI-based vertebral body measurements and insufficiency fracture detection

Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models

Artificial Intelligence to Preoperatively Predict Proximal Junction Kyphosis Following Adult Spinal Deformity Surgery: Soft Tissue Imaging May Be Necessary for Accurate Models

Contact Info

Product

Resources

About