Dataset Information

Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study.

ABSTRACT: BACKGROUND:MRI scanning has revolutionized the clinical diagnosis of lumbar spinal stenosis (LSS). However, there is currently no consensus as to how best to classify MRI findings which has hampered the development of robust longitudinal epidemiological studies of the condition. We developed and tested an automated system for grading lumbar spine MRI scans for central LSS for use in epidemiological research. METHODS:Using MRI scans from the large population-based cohort study (the Wakayama Spine Study), all graded by a spinal surgeon, we trained an automated system to grade central LSS in four gradings of the bone and soft tissue margins: none, mild, moderate, severe. Subsequently, we tested the automated grading against the independent readings of our observer in a test set to investigate reliability and agreement. RESULTS:Complete axial views were available for 4855 lumbar intervertebral levels from 971 participants. The machine used 4365 axial views to learn (training set) and graded the remaining 490 axial views (testing set). The agreement rate for gradings was 65.7% (322/490) and the reliability (Lin's correlation coefficient) was 0.73. In 2.2% of scans (11/490) there was a difference in classification of 2 and in only 0.2% (1/490) was there a difference of 3. When classified into 2 groups as 'severe' vs 'no/mild/moderate'. The agreement rate was 94.1% (461/490) with a kappa of 0.75. CONCLUSIONS:This study showed that an automated system can "learn" to grade central LSS with excellent performance against the reference standard. Thus SpineNet offers potential to grade LSS in large-scale epidemiological studies involving a high volume of MRI spine data with a high level of consistency and objectivity.

SUBMITTER: Ishimoto Y

PROVIDER: S-EPMC7066833 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study.

Ishimoto Yuyu Y Jamaludin Amir A Cooper Cyrus C Walker-Bone Karen K Yamada Hiroshi H Hashizume Hiroshi H Oka Hiroyuki H Tanaka Sakae S Yoshimura Noriko N Yoshida Munehito M Urban Jill J Kadir Timor T Fairbank Jeremy J

BMC musculoskeletal disorders 20200312 1

<h4>Background</h4>MRI scanning has revolutionized the clinical diagnosis of lumbar spinal stenosis (LSS). However, there is currently no consensus as to how best to classify MRI findings which has hampered the development of robust longitudinal epidemiological studies of the condition. We developed and tested an automated system for grading lumbar spine MRI scans for central LSS for use in epidemiological research.<h4>Methods</h4>Using MRI scans from the large population-based cohort study (the ...[more]

PMID: 32164627

Similar Datasets

Project description:Purpose:To develop a self-administered diagnostic screening questionnaire for lumbar spinal stenosis (LSS) consisting of items with high content validity and to investigate the diagnostic value of the questionnaire and the items. Patients and Methods:A self-reported diagnostic LSS screening questionnaire was developed based on items from the existing literature describing key symptoms of LSS. The screening questionnaire (index test) was to be tested in a cohort of patients with persistent lumbar and/or leg pain recruited from a Danish publicly funded outpatient secondary care spine clinic with clinicians performing the reference test. However, to avoid unnecessary collection of data if the screening questionnaire proved to be of limited value, a case-control design was incorporated into the cohort design including an interim analysis. Additional cases for the case-control study were recruited at two Danish publicly funded spine surgery departments. Prevalence, sensitivity, specificity and diagnostic odds ratio (OR) were calculated for each individual item, and AUC (area under the curve) was calculated to examine the performance of the full questionnaire. Results:A 13-item Danish questionnaire was developed and tested in 153 cases and 230 controls. The interim analysis was not in favour of continuing the cohort study, and therefore, only results from the case-control study are reported. There was a positive association for all items except the presence of back pain. However, the association was only moderate with ORs up to 3.3. When testing the performance of the whole questionnaire, an AUC of 0.72 was reached with a specificity of 20% for a fixed sensitivity of 95%. Conclusion:The items were associated with LSS and therefore have some potential to identify LSS patients. However, the association was not strong enough to provide sufficient accuracy for a diagnostic tool. Additional dimensions of symptoms of LSS need identification to obtain a reliable questionnaire for screening purposes.

Project description:Lumbar Spinal Stenosis causes low back pain through pressures exerted on the spinal nerves. This can be verified by measuring the anteroposterior diameter and foraminal widths of the patient's lumbar spine. Our goal is to develop a novel strategy for assessing the extent of Lumbar Spinal Stenosis by automatically calculating these distances from the patient's lumbar spine MRI. Our method starts with a semantic segmentation of T1- and T2-weighted composite axial MRI images using SegNet that partitions the image into six regions of interest. They consist of three main regions-of-interest, namely the Intervertebral Disc, Posterior Element, and Thecal Sac, and three auxiliary regions-of-interest that includes the Area between Anterior and Posterior elements. A novel contour evolution algorithm is then applied to improve the accuracy of the segmentation results along important region boundaries. Nine anatomical landmarks on the image are located by delineating the region boundaries found in the segmented image before the anteroposterior diameter and foraminal widths can be measured. The performance of the proposed algorithm was evaluated through a set of experiments on the Lumbar Spine MRI dataset containing MRI studies of 515 patients. These experiments compare the performance of our contour evolution algorithm with the Geodesic Active Contour and Chan-Vese methods over 22 different setups. We found that our method works best when our contour evolution algorithm is applied to improve the accuracy of both the label images used to train the SegNet model and the automatically segmented image. The average error of the calculated right and left foraminal distances relative to their expert-measured distances are 0.28 mm (p = 0.92) and 0.29 mm (p = 0.97), respectively. The average error of the calculated anteroposterior diameter relative to their expert-measured diameter is 0.90 mm (p = 0.92). The method also achieves 96.7% agreement with an expert opinion on determining the severity of the Intervertebral Disc herniations.

Project description:To improve our understanding of patients' perspectives regarding: (1) the decision-making and prehabilitation before lumbar spinal stenosis (LSS) surgery and (2) their postoperative experiences. Qualitative research with semi-structured interviews. General community. Individuals who received (N=10) and who did not receive (N=15) prehabilitation before LSS surgery were recruited at the 6-month postoperative follow-up (8 females; average age: 67.7±6.7 years) by purposive sampling. Additionally, 1 participant invited her daughter to accompany her in an interview. Not applicable. Concerns and experiences of patients with LSS regarding prehabilitation and recovery after spine surgery. Thematic analysis was conducted to identify 4 themes inductively: (1) sources of information about LSS surgery; (2) factors affecting the surgical decision-making; (3) attitudes toward prehabilitation; and (4) postoperative recovery. All participants desired to have more preoperative education to inform their surgical decision-making. There were mixed opinions regarding the perceived benefits of prehabilitation because some individuals hesitated to participate in prehabilitation because of their symptoms, or the cost or time of traveling. Many participants expected some or even complete relief of LSS-related symptoms after surgery. However, not all participants experienced the expected postoperative improvements. Some participants only experienced temporary symptomatic relief, while others experienced new postoperative symptoms. Patients generally found that postoperative exercises taught by physiotherapists were useful although their compliance decreased over time. Our study highlights the need for better preoperative LSS education. Because face-to-face prehabilitation or postoperative rehabilitation may not be feasible for all patients, future studies should explore whether online-based prehabilitation or postoperative rehabilitation may benefit certain patient subgroups.

Dataset Information

Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study.

Publications

Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets