Deep Spine: Automated Lumbar Vertebral Segmentation, Disc-Level Designation, and Spinal Stenosis Grading using Deep Learning

Jen-Tang Lu, Stefano Pedemonte, Bernardo Bizzo, Sean Doyle, Katherine P. Andriole, Mark H. Michalski, R. Gilberto Gonzalez, Stuart R. Pomerantz
; Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:403-419, 2018.

Abstract

The high prevalence of spinal stenosis results in a large volume of MRI imaging, yet interpretation can be time-consuming with high inter-reader variability even among the most specialized radiologists. In this paper, we develop an efficient methodology to leverage the subject-matter-expertise stored in large-scale archival reporting and image data for a deep-learning approach to fully-automated lumbar spinal stenosis grading. Specifically, we introduce three major contributions: (1) a natural-language-processing scheme to extract level-by-level ground-truth labels from free-text radiology reports for the various types and grades of spinal stenosis (2) accurate vertebral segmentation and disc-level localization using a U-Net architecture combined with a spine-curve fitting method, and (3) a multi-input, multi-task, and multi-class convolutional neural network to perform central canal and foraminal stenosis grading on both axial and sagittal imaging series inputs with the extracted report-derived labels applied to corresponding imaging level segments. This study uses a large dataset of 22796 disc-levels extracted from 4075 patients. We achieve state-of-the-art performance on lumbar spinal stenosis classification and expect the technique will increase both radiology workflow efficiency and the perceived value of radiology reports for referring clinicians and patients.

Cite this Paper


BibTeX
@InProceedings{pmlr-v85-lu18a, title = {Deep Spine: Automated Lumbar Vertebral Segmentation, Disc-Level Designation, and Spinal Stenosis Grading using Deep Learning}, author = {Lu, Jen-Tang and Pedemonte, Stefano and Bizzo, Bernardo and Doyle, Sean and Andriole, Katherine P. and Michalski, Mark H. and Gonzalez, R. Gilberto and Pomerantz, Stuart R.}, booktitle = {Proceedings of the 3rd Machine Learning for Healthcare Conference}, pages = {403--419}, year = {2018}, editor = {Finale Doshi-Velez and Jim Fackler and Ken Jung and David Kale and Rajesh Ranganath and Byron Wallace and Jenna Wiens}, volume = {85}, series = {Proceedings of Machine Learning Research}, address = {Palo Alto, California}, month = {17--18 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v85/lu18a/lu18a.pdf}, url = {http://proceedings.mlr.press/v85/lu18a.html}, abstract = {The high prevalence of spinal stenosis results in a large volume of MRI imaging, yet interpretation can be time-consuming with high inter-reader variability even among the most specialized radiologists. In this paper, we develop an efficient methodology to leverage the subject-matter-expertise stored in large-scale archival reporting and image data for a deep-learning approach to fully-automated lumbar spinal stenosis grading. Specifically, we introduce three major contributions: (1) a natural-language-processing scheme to extract level-by-level ground-truth labels from free-text radiology reports for the various types and grades of spinal stenosis (2) accurate vertebral segmentation and disc-level localization using a U-Net architecture combined with a spine-curve fitting method, and (3) a multi-input, multi-task, and multi-class convolutional neural network to perform central canal and foraminal stenosis grading on both axial and sagittal imaging series inputs with the extracted report-derived labels applied to corresponding imaging level segments. This study uses a large dataset of 22796 disc-levels extracted from 4075 patients. We achieve state-of-the-art performance on lumbar spinal stenosis classification and expect the technique will increase both radiology workflow efficiency and the perceived value of radiology reports for referring clinicians and patients.} }
Endnote
%0 Conference Paper %T Deep Spine: Automated Lumbar Vertebral Segmentation, Disc-Level Designation, and Spinal Stenosis Grading using Deep Learning %A Jen-Tang Lu %A Stefano Pedemonte %A Bernardo Bizzo %A Sean Doyle %A Katherine P. Andriole %A Mark H. Michalski %A R. Gilberto Gonzalez %A Stuart R. Pomerantz %B Proceedings of the 3rd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2018 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v85-lu18a %I PMLR %J Proceedings of Machine Learning Research %P 403--419 %U http://proceedings.mlr.press %V 85 %W PMLR %X The high prevalence of spinal stenosis results in a large volume of MRI imaging, yet interpretation can be time-consuming with high inter-reader variability even among the most specialized radiologists. In this paper, we develop an efficient methodology to leverage the subject-matter-expertise stored in large-scale archival reporting and image data for a deep-learning approach to fully-automated lumbar spinal stenosis grading. Specifically, we introduce three major contributions: (1) a natural-language-processing scheme to extract level-by-level ground-truth labels from free-text radiology reports for the various types and grades of spinal stenosis (2) accurate vertebral segmentation and disc-level localization using a U-Net architecture combined with a spine-curve fitting method, and (3) a multi-input, multi-task, and multi-class convolutional neural network to perform central canal and foraminal stenosis grading on both axial and sagittal imaging series inputs with the extracted report-derived labels applied to corresponding imaging level segments. This study uses a large dataset of 22796 disc-levels extracted from 4075 patients. We achieve state-of-the-art performance on lumbar spinal stenosis classification and expect the technique will increase both radiology workflow efficiency and the perceived value of radiology reports for referring clinicians and patients.
APA
Lu, J., Pedemonte, S., Bizzo, B., Doyle, S., Andriole, K.P., Michalski, M.H., Gonzalez, R.G. & Pomerantz, S.R.. (2018). Deep Spine: Automated Lumbar Vertebral Segmentation, Disc-Level Designation, and Spinal Stenosis Grading using Deep Learning. Proceedings of the 3rd Machine Learning for Healthcare Conference, in PMLR 85:403-419

Related Material