Multi-modal vertebrae recognition using Transformed Deep Convolution Network. (July 2016)

• Record Type: Journal Article
• Authors: Cai, Yunliang; Landis, Mark; Laidley, David T.; Kornecki, Anat; Lum, Andrea; Li, Shuo
• Is Part Of: Computerized medical imaging and graphics. Volume 51(2016)
• Page Start: 11
• Page End: 19
• Publication Date: 2016-07
• Subjects: Vertebra detection -- Vertebra recognition -- Deep learning -- Convolution network; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2016.02.002
• Languages: English
• ISSNs: 0895-6111

Abstract

Abstract : Highlights: First cross modality 2D vertebra recognition, efficient clinical tool. New Transformed Deep Convolution Network, great potential to many cross modality organ recognition. Above 90% sensitivity. Abstract: Automatic vertebra recognition, including the identification of vertebra locations and naming in multiple image modalities, are highly demanded in spinal clinical diagnoses where large amount of imaging data from various of modalities are frequently and interchangeably used. However, the recognition is challenging due to the variations of MR/CT appearances or shape/pose of the vertebrae. In this paper, we propose a method for multi-modal vertebra recognition using a novel deep learning architecture called Transformed Deep Convolution Network (TDCN). This new architecture can unsupervisely fuse image features from different modalities and automatically rectify the pose of vertebra. The fusion of MR and CT image features improves the discriminativity of feature representation and enhances the invariance of the vertebra pattern, which allows us to automatically process images from different contrast, resolution, protocols, even with different sizes and orientations. The feature fusion and pose rectification are naturally incorporated in a multi-layer deep learning network. Experiment results show that our method outperforms existing detection methods and provides a fully automatic location + naming + pose recognition for routine clinical practice.