File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.eclinm.2021.101220
- Scopus: eid_2-s2.0-85120333629
- PMID: 34901796
- WOS: WOS:000740923500005
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit
Title | Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit |
---|---|
Authors | |
Keywords | Adolescent idiopathic scoliosis Curve progression Radiomics Deep learning Scoliosis screening |
Issue Date | 2021 |
Publisher | Elsevier: Creative Commons Licenses. The Journal's web site is located at https://www.journals.elsevier.com/eclinicalmedicine |
Citation | EClinicalMedicine, 2021, v. 42, article no. 101220 How to Cite? |
Abstract | Background:
Prediction of curve progression risk in adolescent idiopathic scoliosis (AIS) remains elusive. Prior studies have revealed the potential for three-dimensional (3D) morphological parameters to prognosticate progression, but these require specialized biplanar imaging equipment and labor-intensive software reconstruction. This study aimed to formulate a deep learning model with standing posteroanterior (PA) X-rays at first clinic visit to differentiate between progressive (P) and non-progressive (NP) curves.
Methods:
For this retrospective cohort study, we identified patients presenting with AIS between October 2015 to April 2020 at our tertiary referral centre. Patients with mild curvatures (11 – 30o) who were skeletally immature (Risser sign of ≤2) were recruited. Patients receiving biplanar X-ray radiographs (EOS™) were divided between a training-cross-validation cohort (328 patients) and independent testing cohort (110 patients). Another 52 patients receiving standard PA spinal X-rays were recruited for cross-platform validation. Following 3D reconstruction, we designated the major curve apex upon PA X-rays as the region of interest (ROI) for machine learning. A self-attentive capsule network was constructed to differentiate between curves manifesting P and NP trajectories. A two-stage transfer learning strategy was introduced to pre-train and fine-tune the model. Model performance (accuracy, sensitivity, specificity) was compared to that of traditional convolutional neural networks (CNNs) and a clinical parameter-based logistic regression model.
Findings:
3D reconstruction identified that apical rotation of the major curve and torsion were significantly different between P and NP curve trajectories. Our predictive model utilizing an ROI centered on the major curve apex achieved an accuracy of 76.6%, a sensitivity of 75.2% and a specificity of 80.2% upon independent testing. Cross-platform performance upon standard standing PA X-rays yielded an accuracy of 77.1%, a sensitivity of 73.5% and a specificity of 81.0%. Errors in prediction occurred when the degree of apical rotation / torsion was discrepant from that of the subsequent curve trajectory but could be rectified by considering serial X-rays. Performance was superior to that of traditional CNNs as well as clinical parameter-based regression models.
Interpretation:
This is the first report of automated prediction of AIS curve progression based on radiomics and deep learning, towards directing treatment strategy at first visit. Patients predicted to be at-risk of progression may be counselled to receive early bracing with enforcement of treatment compliance. Over-treatment may be avoided in curves deemed to be non-progressive. Results need to be consolidated in larger sample populations of different ethnicities.
Funding:
The Society for the Relief of Disabled Children (SRDC). |
Persistent Identifier | http://hdl.handle.net/10722/309334 |
ISSN | 2023 Impact Factor: 9.6 2023 SCImago Journal Rankings: 3.522 |
PubMed Central ID | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, H | - |
dc.contributor.author | Zhang, T | - |
dc.contributor.author | Cheung, KMC | - |
dc.contributor.author | Shea, GKH | - |
dc.date.accessioned | 2021-12-29T02:13:37Z | - |
dc.date.available | 2021-12-29T02:13:37Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | EClinicalMedicine, 2021, v. 42, article no. 101220 | - |
dc.identifier.issn | 2589-5370 | - |
dc.identifier.uri | http://hdl.handle.net/10722/309334 | - |
dc.description.abstract | Background: Prediction of curve progression risk in adolescent idiopathic scoliosis (AIS) remains elusive. Prior studies have revealed the potential for three-dimensional (3D) morphological parameters to prognosticate progression, but these require specialized biplanar imaging equipment and labor-intensive software reconstruction. This study aimed to formulate a deep learning model with standing posteroanterior (PA) X-rays at first clinic visit to differentiate between progressive (P) and non-progressive (NP) curves. Methods: For this retrospective cohort study, we identified patients presenting with AIS between October 2015 to April 2020 at our tertiary referral centre. Patients with mild curvatures (11 – 30o) who were skeletally immature (Risser sign of ≤2) were recruited. Patients receiving biplanar X-ray radiographs (EOS™) were divided between a training-cross-validation cohort (328 patients) and independent testing cohort (110 patients). Another 52 patients receiving standard PA spinal X-rays were recruited for cross-platform validation. Following 3D reconstruction, we designated the major curve apex upon PA X-rays as the region of interest (ROI) for machine learning. A self-attentive capsule network was constructed to differentiate between curves manifesting P and NP trajectories. A two-stage transfer learning strategy was introduced to pre-train and fine-tune the model. Model performance (accuracy, sensitivity, specificity) was compared to that of traditional convolutional neural networks (CNNs) and a clinical parameter-based logistic regression model. Findings: 3D reconstruction identified that apical rotation of the major curve and torsion were significantly different between P and NP curve trajectories. Our predictive model utilizing an ROI centered on the major curve apex achieved an accuracy of 76.6%, a sensitivity of 75.2% and a specificity of 80.2% upon independent testing. Cross-platform performance upon standard standing PA X-rays yielded an accuracy of 77.1%, a sensitivity of 73.5% and a specificity of 81.0%. Errors in prediction occurred when the degree of apical rotation / torsion was discrepant from that of the subsequent curve trajectory but could be rectified by considering serial X-rays. Performance was superior to that of traditional CNNs as well as clinical parameter-based regression models. Interpretation: This is the first report of automated prediction of AIS curve progression based on radiomics and deep learning, towards directing treatment strategy at first visit. Patients predicted to be at-risk of progression may be counselled to receive early bracing with enforcement of treatment compliance. Over-treatment may be avoided in curves deemed to be non-progressive. Results need to be consolidated in larger sample populations of different ethnicities. Funding: The Society for the Relief of Disabled Children (SRDC). | - |
dc.language | eng | - |
dc.publisher | Elsevier: Creative Commons Licenses. The Journal's web site is located at https://www.journals.elsevier.com/eclinicalmedicine | - |
dc.relation.ispartof | EClinicalMedicine | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | Adolescent idiopathic scoliosis | - |
dc.subject | Curve progression | - |
dc.subject | Radiomics | - |
dc.subject | Deep learning | - |
dc.subject | Scoliosis screening | - |
dc.title | Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit | - |
dc.type | Article | - |
dc.identifier.email | Zhang, T: tgzhang@hku.hk | - |
dc.identifier.email | Cheung, KMC: cheungmc@hku.hk | - |
dc.identifier.email | Shea, GKH: gkshea@hku.hk | - |
dc.identifier.authority | Zhang, T=rp02821 | - |
dc.identifier.authority | Cheung, KMC=rp00387 | - |
dc.identifier.authority | Shea, GKH=rp01781 | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.1016/j.eclinm.2021.101220 | - |
dc.identifier.pmid | 34901796 | - |
dc.identifier.pmcid | PMC8639418 | - |
dc.identifier.scopus | eid_2-s2.0-85120333629 | - |
dc.identifier.hkuros | 331231 | - |
dc.identifier.volume | 42 | - |
dc.identifier.spage | article no. 101220 | - |
dc.identifier.epage | article no. 101220 | - |
dc.identifier.isi | WOS:000740923500005 | - |
dc.publisher.place | United Kingdom | - |