2020
DOI: 10.14444/7131
|View full text |Cite
|
Sign up to set email alerts
|

Feasibility of Deep Learning Algorithms for Reporting in Routine Spine Magnetic Resonance Imaging

Abstract: Background: Artificial intelligence is gaining traction in automated medical imaging analysis. Development of more accurate magnetic resonance imaging (MRI) predictors of successful clinical outcomes is necessary to better define indications for surgery, improve clinical outcomes with targeted minimally invasive and endoscopic procedures, and realize cost savings by avoiding more invasive spine care.Objective: To demonstrate the ability for deep learning neural network models to identify features in MRI DICOM … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
15
0
1

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 34 publications
(17 citation statements)
references
References 81 publications
1
15
0
1
Order By: Relevance
“…This model performed well on the holdout dataset with an AUC of 0.94 and F1-score of 0.82. These performance metrics are similar to the best performing lumbar spine models that have been previously published 39,[41][42][43] . We generated CAMs using example images from the testing dataset that were classified correctly (true positives) and incorrectly (false negatives).…”
Section: Discussionsupporting
confidence: 66%
See 1 more Smart Citation
“…This model performed well on the holdout dataset with an AUC of 0.94 and F1-score of 0.82. These performance metrics are similar to the best performing lumbar spine models that have been previously published 39,[41][42][43] . We generated CAMs using example images from the testing dataset that were classified correctly (true positives) and incorrectly (false negatives).…”
Section: Discussionsupporting
confidence: 66%
“…Image segmentation can potentially allow for automated localization of pathologic findings, which was not possible with the simpler approach that we took. Another study by Lewandrowski et al used a dataset of lumbar spine MRI scans from 3560 patients and developed a model to grade lumbar disc herniation and canal stenosis 42 , 43 . Similar to the DeepSpine framework, their approach consisted of a segmentation step in which intervertebral disks were segmented.…”
Section: Discussionmentioning
confidence: 99%
“…For the imagistic diagnosis, at present, there is used simple X-ray for lumbar spine in two instances (front and profile), CT scan and magnetic resonance imaging (MRI). For now, MRI represents the selection imagistic method due to its advantage of not using ionizing radiations and its good visualization characteristics, especially for the soft tissues [ 25 , 26 , 27 , 28 ].…”
Section: ⧉ Discussionmentioning
confidence: 99%
“…Concerning the spine, it was suggested that AI applied to MR images can yield a fast and accurate diagnosis and prognosis prediction regarding spinal diseases [ 67 , 68 ]. Disc localization; segmentation; and analysis of intensity, shape, and other features of IVDs in spine MRI are usually done by radiologists, with a subjective and time-consuming assessment that depends on individual experience and knowledge [ 69 , 70 ]. The use of AI to assess DDD in MR images has been investigated in several studies in the last decade.…”
Section: New Diagnostic Perspective: Artificial Intelligencementioning
confidence: 99%