Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach

Galbusera, Fabio; Niemeyer, Frank; Wilke, Hans–Joachim; Bassani, Tito; Casaroli, Gloria; Anania, Carla Daniela; Costa, Francesco; Brayda-Bruno, Marco; Sconfienza, Luca Maria

doi:10.1007/s00586-019-05944-z

Cited by 112 publications

(91 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The plans were generated by the proposed computer-assisted tool based on parametric modeling of the vertebral and pedicle shape, maximization of the screw fastening strength, and taking into account two important surgical considerations: (a) pedicle screw placement to simulate the straight-forward surgical insertion technique and (b) pedicle screw entry points to follow the spinal curvature. Although the emerging technologies based on state-of-the-art machine learning approaches [43][44][45][46] may represent an alternative for future modeling of the vertebral bodies, pedicles, and pedicle screw size and trajectories, our approach does not require any training but is based on parametric modeling augmented with morphological, structural, and procedural knowledge of vertebral structures and pedicle screw placement. The pedicle screw placement plans, obtained by different versions of the computer-assisted tool from preoperative CT images, were graded to assess their quality.…”

Section: Discussionmentioning

confidence: 99%

Computer‐assisted pedicle screw trajectory planning using CT‐inferred bone density: A demonstration against surgical outcomes

et al. 2019

View full text Add to dashboard Cite

Purpose Image‐guided spine surgery and preoperative computer‐assisted planning provide spine surgeons with tools to improve the safety, accuracy, and reliability of pedicle screw placement. The purpose of this study is to demonstrate a computer‐assisted pedicle screw placement planning tool in comparison to screws as delivered by a spine surgeon. Methods We describe a novel computer‐assisted tool for preoperative pedicle screw placement planning in computed tomography (CT) images, designed with respect to the vertebral shape and structure, and augmented with respect to the considerations of surgical practice. The approach is based on three‐dimensional (3D) modeling of the vertebral body and pedicles, and planning of the pedicle screw size and insertion trajectory by maximizing the screw fastening strength, evaluated through CT‐inferred bone density maps. The approach is augmented by yielding screw plans consistent with the straight‐forward surgical technique of aligning screws parallel to vertebral endplates, and the screw entry points following the spinal curvature to facilitate rod attachment. For a cohort of 25 patients, placement plans were retrospectively obtained for 204 pedicle screws with the computer‐assisted tool from preoperative CT images, while reference trajectories of inserted pedicle screws were reconstructed in 3D from postoperative biplanar radiographs. Results The best performing version of the computer‐assisted tool achieved clinically acceptable preoperative pedicle screw placement plans in 96.6% of the cases, while the comparison to the postoperative reconstructions resulted in 3.4 ± 2.5 mm for the screw entry point location, 2.7 ± 1.6 mm for the screw crossing point location, and 7.4 ± 5.3∘ for the screw sagittal inclination (mean absolute difference ± standard deviation). Conclusion Quantitative comparison revealed that the preoperative placement plans are consistent with the postoperative results, and that the computer‐assisted tool integrating bone density and surgical constraints can successfully incorporate important aspects of pedicle screw placement. The results therefore confirm the accuracy of the tool prior to being integrated in an image‐guidance system.

show abstract

Section: Discussionmentioning

confidence: 99%

Computer‐assisted pedicle screw trajectory planning using CT‐inferred bone density: A demonstration against surgical outcomes

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Zhang et al trained a deep ANN to predict the vertebral slopes on coronal radiographic images and used the slope data to estimate the Cobb angle, achieving absolute errors lower than 3°. Wu et al and Galbusera et al exploited the three‐dimensional information contained in biplanar radiographs to perform a more comprehensive assessment of the pathological curvature. Seeing the problem from another perspective, Thong et al attempted to use an unsupervised clustering method to obtain a novel classification scheme for adolescent idiopathic scoliosis which effectively describes the variability of the curves among the subjects.…”

Section: Applications Of Ai and ML In Spine Researchmentioning

confidence: 99%

Artificial intelligence and machine learning in spine research

2019

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) and machine learning (ML) techniques are revolutionizing several industrial and research fields like computer vision, autonomous driving, natural language processing, and speech recognition. These novel tools are already having a major impact in radiology, diagnostics, and many other fields in which the availability of automated solution may benefit the accuracy and repeatability of the execution of critical tasks. In this narrative review, we first present a brief description of the various techniques that are being developed nowadays, with special focus on those used in spine research. Then, we describe the applications of AI and ML to problems related to the spine which have been published so far, including the localization of vertebrae and discs in radiological images, image segmentation, computer‐aided diagnosis, prediction of clinical outcomes and complications, decision support systems, content‐based image retrieval, biomechanics, and motion analysis. Finally, we briefly discuss major ethical issues related to the use of AI in healthcare, namely, accountability, risk of biased decisions as well as data privacy and security, which are nowadays being debated in the scientific community and by regulatory agencies.

show abstract

“…Poor-quality images such as those with poor image contrast and positioning errors were excluded. Among the collected radiographs, 13% (128) of the images are of children (age < 12), 42% (414) of the images are of young adults (age [13][14][15][16][17][18] and 45% (448) of the images are of adults (age > 18). Overall, 77% (765) of the images do not have an implant, while 23% (225) do.…”

Section: Data Preparationmentioning

confidence: 99%

“…In addition, Wimmer et al [17] used 3D CNN for vertebrae localization. There were also studies on radiographs: for biplanar radiographs, including A-P and lateral view, Gallbusera et al [18] used a database collected using the EOS™ imaging system [19] and trained CNN models for each of the landmarks. For lateral spine radiographs, Al Arif et al [20] applied a UNet model for the localization of cervical vertebral centers.…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence for Automatic Measurement of Sagittal Vertical Axis Using ResUNet Framework

Weng¹,

Wang

Huang

et al. 2019

JCM

View full text Add to dashboard Cite

We present an automated method for measuring the sagittal vertical axis (SVA) from lateral radiography of whole spine using a convolutional neural network for keypoint detection (ResUNet) with our improved localization method. The algorithm is robust to various clinical conditions, such as degenerative changes or deformities. The ResUNet was trained and evaluated on 990 standing lateral radiographs taken at Chang Gung Memorial Hospital, Linkou and performs SVA measurement with median absolute error of 1.183 ± 0.166 mm. The 5-mm detection rate of the C7 body and the sacrum are 91% and 87%, respectively. The SVA calculation takes approximately 0.2 s per image. The intra-class correlation coefficient of the SVA estimates between the algorithm and physicians of different years of experience ranges from 0.946 to 0.993, indicating an excellent consistency. The superior performance of the proposed method and its high consistency with physicians proved its usefulness for automatic measurement of SVA in clinical settings.

show abstract

Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach

Cited by 112 publications

References 22 publications

Computer‐assisted pedicle screw trajectory planning using CT‐inferred bone density: A demonstration against surgical outcomes

Computer‐assisted pedicle screw trajectory planning using CT‐inferred bone density: A demonstration against surgical outcomes

Artificial intelligence and machine learning in spine research

Artificial Intelligence for Automatic Measurement of Sagittal Vertical Axis Using ResUNet Framework

Contact Info

Product

Resources

About