Skip to Main content Skip to Navigation
Journal articles

Self-learning computers for surgical planning and prediction of postoperative alignment

Abstract : Computer-assisted methods for the prediction of postoperative alignment consist of a three step analysis: identification of anatomical landmark, definition of alignment objectives, and simulation of surgery. Recently, complex rules for the prediction of alignment have been proposed. Even though this kind of work leads to more personalized objectives, the number of parameters involved renders it difficult for clinical use, stressing the importance of developing computer-assisted tools. The evolution of our current technology, including machine learning and other types of advanced algorithms, will provide powerful tools that could be useful in improving surgical outcomes and alignment prediction. These tools can combine different types of advanced technologies, such as image recognition and shape modeling, and using this technique, computer-assisted methods are able to predict spinal shape. The development of powerful computer-assisted methods involves the integration of several sources of information such as radiographic parameters (X-rays, MRI, CT scan, etc.), demographic information, and unusual non-osseous parameters (muscle quality, proprioception, gait analysis data). In using a larger set of data, these methods will aim to mimic what is actually done by spine surgeons, leading to real tailor-made solutions. Integrating newer technology can change the current way of planning/simulating surgery. The use of powerful computer-assisted tools that are able to integrate several parameters and learn from experience can change the traditional way of selecting treatment pathways and counseling patients. However, there is still much work to be done to reach a desired level as noted in other orthopedic fields, such as hip surgery. Many of these tools already exist in non-medical fields and their adaptation to spine surgery is of considerable interest.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-01960516
Contributor : Eric Berton <>
Submitted on : Wednesday, December 19, 2018 - 2:24:33 PM
Last modification on : Tuesday, March 30, 2021 - 3:15:11 AM

Identifiers

Collections

Citation

Renaud Lafage, Sebastien Pesenti, Virginie Lafage, Frank J. Schwab. Self-learning computers for surgical planning and prediction of postoperative alignment. European Spine Journal, Springer Verlag, 2018, 27 (1), pp.S123-S128. ⟨10.1007/s00586-018-5497-0⟩. ⟨hal-01960516⟩

Share

Metrics

Record views

57