spine recognition from medical image analysis to image
play

Spine Recognition: From Medical Image Analysis to Image- Guided - PowerPoint PPT Presentation

Spine Recognition: From Medical Image Analysis to Image- Guided Interventions : Yunliang Cai Background Spine structure: Contain 24 bones (vertebra)


  1. Spine Recognition: From Medical Image Analysis to Image- Guided Interventions 脊柱骨骼识别 : 从医学图像分析到图像引导介入治疗 Yunliang Cai

  2. Background 头椎 • Spine structure: • Contain 24 bones (vertebra) 胸椎 • Strong but highly deformable • Combined w/ bone, soft tissue, nerve … 脊髓 椎体 腰椎 棘突 橫突

  3. Background • Some common spine problems • Spondylolysis 腰椎脱离 • Fractures 椎体骨折 • Deformity 畸形 • Degenerative disc 椎间盘退化 • Some spinal surgeries Spine Fusion • Spine fusion 融合手术 • Discectomy 椎间盘切除 • Laminectomy 椎弓切除

  4. Background • How to automate diagnosis? • How to automate surgery?

  5. Computational Spine Model 脊骨计算模型

  6. Computational Spine Model • Our Approach --- Computational Anatomy Multi-Modality/View/Subject For Diagnosis Parameterized Optimal Computation Geometric Model Parameters Deform Extract & Match For Surgery Guidance

  7. Computational Spine Model • Hierarchical Model Design

  8. Computational Spine Model • Spine Image Analysis: Basic Workflow Y. Cai et al, TMI 2015

  9. Spine Image Analysis 脊骨图像分析

  10. Spine Image Analysis Cross Modality • Local Appearance Module • Use Multi-Modal Deep Net for Cross-Modality Detection

  11. Spine Image Analysis Spine Shape Analysis • Global Geometry Module • Use universal 3D CAD model for spine shape analysis • Register by point registration method (Coherent Point Drift, Myronenko et al PAMI 2010)

  12. Spine Image Analysis Vertebra Pose • Local Geometry Module • Use Lie-Group-based Congealing for vertebra pose estimation ( Y. Cai et al TIP 2013 ) • Use tri-planar estimation for 3D pose

  13. Spine Image Analysis • Multi-view, multi-modal, and whole spine recognition • For diagnosis of spondylolysis, deformity, …

  14. Image-Guided Spinal Surgery 图像引导脊骨手术

  15. Image-Guided Spinal Surgery • Why need it? • Precision !! • How to? • Patient Registration: Pre-Operative Images ( 手术前 ) register with Intra-Operative Structure ( 手术进行时 ) ? Surgery on going… Pre-Operative CT

  16. Image-Guided Spinal Surgery • Pre-Operative Modalities: • CT, MR • Intra-Operative Modalities: • Ultrasound 超声 , Fluoroscopy 透视 , Cone Beam CT 锥束 CT • …

  17. Image-Guided Spinal Surgery • Our Pre-Op Images: CT Stealth Station 立体视觉 ( 实时跟踪用 ) • Our Intra-Op Images: Stereovision(SV) Radiation Free Microscopy ( 拍摄用 ) SV images SV surface CT Pre-Op CT S. Ji et al , TBME 2015

  18. Image-Guided Spinal Surgery • Our method: Rectify the spine to a “deformation-free” pose CT Inverse Flattening NLPCA NLPCA Non-linear PCA: Auto-associate Network (Auto-Encoder Network) M. Scholz et al LNCS 2007 SV Inverse NLPCA Flattening NLPCA

  19. Image-Guided Spinal Surgery • 2D image reg. (faster!) • Dense point-point correspondence (more accurate) Y. Cai et al, SPIE 2016

  20. Demo Accuracy Test: Err < 1.5 mm ! Image-Guided Drilling

  21. Future Directions: Spine Image Analysis • Explore on Soft Tissue PET/CT SPECT/CT PET/MR Analysis for: Cancer Infectious Disease Trauma … • Explore on Spinal Cord Analysis for: Neural Trauma Vascular Function … Diffusion Tensor Imaging CT Angiography

  22. Future Directions: Image- Guided Interventions • Multimodality Integration CT + Ultrasound + SV + ….? • Towards Robotic Surgery 微创手术机器人 Surgical Robot Assistant ( 第三军医大学新桥医院 AQRate Robotic System Mazor Robotics (Technion) (Wright State Univ.) 中科院渖阳自动化研究所 ) (EPFL)

  23. Conclusions • Spine Image Analysis • Computational spinal model • Cross-modality vertebra detection • Spine shape analysis • Vertebra pose estimation • Image guidance spinal surgery • CT-SV image guidance system • Geometric rectification for deformed spines • Image-guided spinal fusion surgery • Future work • Towards hybrid modality analysis • Towards robotic spinal surgery

  24. Acknowledgment • Research led by PI: Prof. Shuo LI PI: Prof. Songbai JI • Surgical team Dr. Scott S. Lollis, MD (Primary Surgeon) • Projects funded by R21 NS078607

  25. Thank You! • Q & A

Recommend


More recommend