ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist

被引:197
作者
Jamaludin, Amir [1 ]
Lootus, Meelis [1 ]
Kadir, Timor [2 ]
Zisserman, Andrew [1 ]
Urban, Jill [5 ]
Battie, Michele C. [8 ]
Fairbank, Jeremy [6 ,7 ,9 ]
McCall, Iain [3 ,4 ]
机构
[1] Univ Oxford, Dept Engn Sci, Oxford, England
[2] Mirada Med, Oxford, England
[3] RJAH Orthopaed Hosp Fdn Trust, Spinal Studies, Oswestry, Shrops, England
[4] Keele Univ, ISTM, Oswestry, Shrops, England
[5] Univ Oxford, Dept Physiol Anat & Genet, Oxford, England
[6] Univ Oxford, Nuffield Dept Orthopaed Rheumatol & Musculoskelet, Botnar Inst Musculoskeletal Sci, Oxford, England
[7] Oxford Univ Hosp NHS Trust, Nuffield Orthopaed Ctr, Oxford, England
[8] Univ Alberta, Fac Rehabil Med, Edmonton, AB, Canada
[9] St Lukes Hosp, Latimer Rd, Oxford OX3 7PF, England
基金
英国工程与自然科学研究理事会;
关键词
Automated grading; Pfirrmann grading; Modic changes; Disc herniation; Disc bulge; Spondylolisthesis; Disc classification; Disc detection; Disc analysis; Vertebrae analysis; Deep learning; LOW-BACK-PAIN; DISC DEGENERATION; CLASSIFICATION; SYSTEM; KAPPA;
D O I
10.1007/s00586-017-4956-3
中图分类号
R74 [神经病学与精神病学];
学科分类号
100204 [神经病学];
摘要
Investigation of the automation of radiological features from magnetic resonance images (MRIs) of the lumbar spine. To automate the process of grading lumbar intervertebral discs and vertebral bodies from MRIs. MR imaging is the most common imaging technique used in investigating low back pain (LBP). Various features of degradation, based on MRIs, are commonly recorded and graded, e.g., Modic change and Pfirrmann grading of intervertebral discs. Consistent scoring and grading is important for developing robust clinical systems and research. Automation facilitates this consistency and reduces the time of radiological analysis considerably and hence the expense. 12,018 intervertebral discs, from 2009 patients, were graded by a radiologist and were then used to train: (1) a system to detect and label vertebrae and discs in a given scan, and (2) a convolutional neural network (CNN) model that predicts several radiological gradings. The performance of the model, in terms of class average accuracy, was compared with the intra-observer class average accuracy of the radiologist. The detection system achieved 95.6% accuracy in terms of disc detection and labeling. The model is able to produce predictions of multiple pathological gradings that consistently matched those of the radiologist. The model identifies 'Evidence Hotspots' that are the voxels that most contribute to the degradation scores. Automation of radiological grading is now on par with human performance. The system can be beneficial in aiding clinical diagnoses in terms of objectivity of gradings and the speed of analysis. It can also draw the attention of a radiologist to regions of degradation. This objectivity and speed is an important stepping stone in the investigation of the relationship between MRIs and clinical diagnoses of back pain in large cohorts. Level of Evidence: Level 3.
引用
收藏
页码:1374 / 1383
页数:10
相关论文
共 22 条
[1]
[Anonymous], 2014, LNCV B, DOI DOI 10.1007/978-3-319-07269-2
[2]
[Anonymous], 2013, Fine-grained visual classification of aircraft
[3]
Systematic Literature Review of Imaging Features of Spinal Degeneration in Asymptomatic Populations [J].
Brinjikji, W. ;
Luetmer, P. H. ;
Comstock, B. ;
Bresnahan, B. W. ;
Chen, L. E. ;
Deyo, R. A. ;
Halabi, S. ;
Turner, J. A. ;
Avins, A. L. ;
James, K. ;
Wald, J. T. ;
Kallmes, D. F. ;
Jarvik, J. G. .
AMERICAN JOURNAL OF NEURORADIOLOGY, 2015, 36 (04) :811-816
[4]
Intervertebral disc classification by its degree of degeneration from T2-weighted magnetic resonance images [J].
Castro-Mateos, Isaac ;
Hua, Rui ;
Pozo, Jose M. ;
Lazary, Aron ;
Frangi, Alejandro F. .
EUROPEAN SPINE JOURNAL, 2016, 25 (09) :2721-2727
[5]
The relationship between disc degeneration, low back pain, and human pain genetics [J].
Cheung, Kenneth M. C. .
SPINE JOURNAL, 2010, 10 (11) :958-960
[7]
The Association Between Lumbar Disc Degeneration and Low Back Pain The Influence of Age, Gender, and Individual Radiographic Features [J].
de Schepper, Evelien I. T. ;
Damen, Jurgen ;
van Meurs, Joyce B. J. ;
Ginai, Abida Z. ;
Popham, Maria ;
Hofman, Albert ;
Koes, Bart W. ;
Bierma-Zeinstra, Sita M. .
SPINE, 2010, 35 (05) :531-536
[8]
Primary care - Low back pain [J].
Deyo, RA ;
Weinstein, JN .
NEW ENGLAND JOURNAL OF MEDICINE, 2001, 344 (05) :363-370
[9]
Modified Pfirrmann grading system for lumbar intervertebral disc degeneration [J].
Griffith, James F. ;
Wang, Yi-Xiang J. ;
Antonio, Gregory E. ;
Choi, Kai Chow ;
Yu, Alfred ;
Ahuja, Anil T. ;
Leung, Ping Chung .
SPINE, 2007, 32 (24) :E708-E712
[10]
Jamaludin Amir, 2016, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 19th International Conference. Proceedings: LNCS 9901, P166, DOI 10.1007/978-3-319-46723-8_20