1. Automatic Segmentation and Identification of Spinous Processes on Sagittal X-Rays Based on Random Forest Classification and Dedicated Contextual Features
- Author
-
Shahin Ebrahimi, Elsa D. Angelini, Wafa Skalli, Laurent Gajny, Institut de Biomécanique Humaine Georges Charpak (IBHGC), Université Sorbonne Paris Nord-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM), Laboratoire de biomécanique (LBM), Université Sorbonne Paris Cité (USPC)-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12)-Centre National de la Recherche Scientifique (CNRS)-Université Sorbonne Paris Nord, Imperial College London, Télécom ParisTech, and HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)
- Subjects
Spine X-ray ,Identification ,Computer science ,Radiography ,Spinous process ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] ,Intelligence artificielle [Informatique] ,Segmentation ,medicine ,[INFO.INFO-IM]Computer Science [cs]/Medical Imaging ,Imagerie médicale [Informatique] ,Radiation treatment planning ,Visual features ,business.industry ,Vision par ordinateur et reconnaissance de formes [Informatique] ,ingénierie bio-médicale [Sciences du vivant] ,[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] ,Pattern recognition ,Sagittal plane ,Random forest ,Identification (information) ,medicine.anatomical_structure ,Hausdorff distance ,Multi-class Random Forest ,[SDV.IB]Life Sciences [q-bio]/Bioengineering ,Artificial intelligence ,business - Abstract
International audience; X-ray based quantitative analysis of spine parameters is required in routine diagnosis or treatment planning. Existing tools commonly require manual intervention. Attempts towards automation of the whole procedure have mainly focused on vertebral bodies, whereas other regions such as the posterior arch also bear considerable amount of useful information. In this study, we combine a specific design of contextual visual features with a multi-class Random Forest classifier to perform pixel-wise segmentation and identification of all cervical spine spinous processes, on sagittal radiographs. Segmentations were evaluated on 62 radiographs, comparing to manual tracing. Correct identification was obtained for all subjects, and segmentation returned mean SD values of: Dice coefficient =88 8%; Hausdorff distance =2.1 1.4 mm and; mean surface distance =0.6 0.4 mm. The derived geometric parameters can be used to reduce the amount of manual intervention needed for spine modeling or to measure clinical indices.
- Published
- 2019
- Full Text
- View/download PDF