Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit
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-in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-12-01
|
| Series: | EClinicalMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589537021005010 |
| _version_ | 1819022287889760256 |
|---|---|
| author | Hongfei Wang Teng Zhang Kenneth Man-Chee Cheung Graham Ka-Hon Shea |
| author_facet | Hongfei Wang Teng Zhang Kenneth Man-Chee Cheung Graham Ka-Hon Shea |
| author_sort | Hongfei Wang |
| collection | DOAJ |
| description | 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). |
| first_indexed | 2024-12-21T04:20:36Z |
| format | Article |
| id | doaj.art-05560692eab0409ca7a6a2c547cac91d |
| institution | Directory Open Access Journal |
| issn | 2589-5370 |
| language | English |
| last_indexed | 2024-12-21T04:20:36Z |
| publishDate | 2021-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EClinicalMedicine |
| spelling | doaj.art-05560692eab0409ca7a6a2c547cac91d2022-12-21T19:16:10ZengElsevierEClinicalMedicine2589-53702021-12-0142101220Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visitHongfei Wang0Teng Zhang1Kenneth Man-Chee Cheung2Graham Ka-Hon Shea3Department of Orthopaedics and Traumatology, The University of Hong Kong, Hong KongDepartment of Orthopaedics and Traumatology, The University of Hong Kong, Hong KongDepartment of Orthopaedics and Traumatology, The University of Hong Kong, Hong KongDepartment of Orthopaedics and Traumatology, The University of Hong Kong, Hong Kong; Correspondence to: Dr Graham Ka-Hon Shea, MBBS, PhD, FRCSEd (Orthopaedics and Traumatology), Department of Orthopaedics and Traumatology, The University of Hong Kong, Hong KongBackground: 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).http://www.sciencedirect.com/science/article/pii/S2589537021005010Adolescent idiopathic scoliosiscurve progressionradiomicsdeep learningscoliosis screening |
| spellingShingle | Hongfei Wang Teng Zhang Kenneth Man-Chee Cheung Graham Ka-Hon Shea Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit EClinicalMedicine Adolescent idiopathic scoliosis curve progression radiomics deep learning scoliosis screening |
| title | Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit |
| title_full | Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit |
| title_fullStr | Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit |
| title_full_unstemmed | Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit |
| title_short | Application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit |
| title_sort | application of deep learning upon spinal radiographs to predict progression in adolescent idiopathic scoliosis at first clinic visit |
| topic | Adolescent idiopathic scoliosis curve progression radiomics deep learning scoliosis screening |
| url | http://www.sciencedirect.com/science/article/pii/S2589537021005010 |
| work_keys_str_mv | AT hongfeiwang applicationofdeeplearninguponspinalradiographstopredictprogressioninadolescentidiopathicscoliosisatfirstclinicvisit AT tengzhang applicationofdeeplearninguponspinalradiographstopredictprogressioninadolescentidiopathicscoliosisatfirstclinicvisit AT kennethmancheecheung applicationofdeeplearninguponspinalradiographstopredictprogressioninadolescentidiopathicscoliosisatfirstclinicvisit AT grahamkahonshea applicationofdeeplearninguponspinalradiographstopredictprogressioninadolescentidiopathicscoliosisatfirstclinicvisit |