Wesley M Durand1, Renaud Lafage2, D Kojo Hamilton3, Peter G Passias4, Han Jo Kim2, Themistocles Protopsaltis4, Virginie Lafage2, Justin S Smith5, Christopher Shaffrey6, Munish Gupta7, Michael P Kelly7, Eric O Klineberg8, Frank Schwab2, Jeffrey L Gum9, Gregory Mundis10, Robert Eastlack10, Khaled Kebaish11, Alex Soroceanu12, Richard A Hostin13, Doug Burton14, Shay Bess15, Christopher Ames16, Robert A Hart17, Alan H Daniels18. 1. Department of Orthopaedic Surgery, Warren Alpert Medical School of Brown University, Alpert Medical School, Providence, Rhode Island, 1 Kettle Point Avenue, East Providence, RI, 02914, USA. 2. Hospital for Special Surgery, Newyork city, NY, USA. 3. University of Pittsburgh Medical Center, Pittsburgh, PA, USA. 4. Langone Medical Center, New York University, New York City, NY, USA. 5. University of Virginia Health System, Charlottesville, VA, USA. 6. Department of Neurosurgery, Duke University Medical Center, Durham, NC, USA. 7. Washington University, St. Louis, MO, USA. 8. University of California, UC Davis Medical Center, Sacramento, CA, USA. 9. Leatherman Spine Center, Louisville, KY, USA. 10. San Diego Spine, La Jolla, San Diego, CA, USA. 11. Johns Hopkins University School of Medicine, Baltimore, MD, USA. 12. University of Calgary, Calgary, AB, Canada. 13. Southwest Scoliosis Institute, Plano, TX, USA. 14. Medical Center, University of Kansas, Kansas City, KS, USA. 15. Denver International Spine Center, Denver, CO, USA. 16. University of California, San Francisco, San Diego, CA, USA. 17. Swedish Neuroscience Institute, Swedish Medical Center, Seattle, WA, USA. 18. Department of Orthopaedic Surgery, Warren Alpert Medical School of Brown University, Alpert Medical School, Providence, Rhode Island, 1 Kettle Point Avenue, East Providence, RI, 02914, USA. alandanielsmd@gmail.com.
Abstract
PURPOSE: AI algorithms have shown promise in medical image analysis. Previous studies of ASD clusters have analyzed alignment metrics-this study sought to complement these efforts by analyzing images of sagittal anatomical spinopelvic landmarks. We hypothesized that an AI algorithm would cluster preoperative lateral radiographs into groups with distinct morphology. METHODS: This was a retrospective review of a multicenter, prospectively collected database of adult spinal deformity. A total of 915 patients with adult spinal deformity and preoperative lateral radiographs were included. A 2 × 3, self-organizing map-a form of artificial neural network frequently employed in unsupervised classification tasks-was developed. The mean spine shape was plotted for each of the six clusters. Alignment, surgical characteristics, and outcomes were compared. RESULTS: Qualitatively, clusters C and D exhibited only mild sagittal plane deformity. Clusters B, E, and F, however, exhibited marked positive sagittal balance and loss of lumbar lordosis. Cluster A had mixed characteristics, likely representing compensated deformity. Patients in clusters B, E, and F disproportionately underwent 3-CO. PJK and PJF were particularly prevalent among clusters A and E. Among clusters B and F, patients who experienced PJK had significantly greater positive sagittal balance than those who did not. CONCLUSIONS: This study clustered preoperative lateral radiographs of ASD patients into groups with highly distinct overall spinal morphology and association with sagittal alignment parameters, baseline HRQOL, and surgical characteristics. The relationship between SVA and PJK differed by cluster. This study represents significant progress toward incorporation of computer vision into clinically relevant classification systems in adult spinal deformity. LEVEL OF EVIDENCE IV: Diagnostic: individual cross-sectional studies with the consistently applied reference standard and blinding.
PURPOSE: AI algorithms have shown promise in medical image analysis. Previous studies of ASD clusters have analyzed alignment metrics-this study sought to complement these efforts by analyzing images of sagittal anatomical spinopelvic landmarks. We hypothesized that an AI algorithm would cluster preoperative lateral radiographs into groups with distinct morphology. METHODS: This was a retrospective review of a multicenter, prospectively collected database of adult spinal deformity. A total of 915 patients with adult spinal deformity and preoperative lateral radiographs were included. A 2 × 3, self-organizing map-a form of artificial neural network frequently employed in unsupervised classification tasks-was developed. The mean spine shape was plotted for each of the six clusters. Alignment, surgical characteristics, and outcomes were compared. RESULTS: Qualitatively, clusters C and D exhibited only mild sagittal plane deformity. Clusters B, E, and F, however, exhibited marked positive sagittal balance and loss of lumbar lordosis. Cluster A had mixed characteristics, likely representing compensated deformity. Patients in clusters B, E, and F disproportionately underwent 3-CO. PJK and PJF were particularly prevalent among clusters A and E. Among clusters B and F, patients who experienced PJK had significantly greater positive sagittal balance than those who did not. CONCLUSIONS: This study clustered preoperative lateral radiographs of ASDpatients into groups with highly distinct overall spinal morphology and association with sagittal alignment parameters, baseline HRQOL, and surgical characteristics. The relationship between SVA and PJK differed by cluster. This study represents significant progress toward incorporation of computer vision into clinically relevant classification systems in adult spinal deformity. LEVEL OF EVIDENCE IV: Diagnostic: individual cross-sectional studies with the consistently applied reference standard and blinding.
Entities:
Keywords:
Adult spinal deformity; Computer vision; Medical image analysis
Authors: Jacob L Jaremko; Philippe Poncet; Janet Ronsky; James Harder; Jean Dansereau; Hubert Labelle; Ronald F Zernicke Journal: J Biomech Eng Date: 2002-10 Impact factor: 2.097
Authors: André Wirries; Florian Geiger; Ahmed Hammad; Martin Bäumlein; Julia Nadine Schmeller; Ingmar Blümcke; Samir Jabari Journal: Biomedicines Date: 2022-06-04
Authors: Rafael De la Garza Ramos; Mousa K Hamad; Jessica Ryvlin; Oscar Krol; Peter G Passias; Mitchell S Fourman; John H Shin; Vijay Yanamadala; Yaroslav Gelfand; Saikiran Murthy; Reza Yassari Journal: J Clin Med Date: 2022-07-29 Impact factor: 4.964