Segmenting Epithelial Cells in High-Throughput RNAi Screens (MIAAB 2011)
0 likes890 views
This document details a proposed two-step watershed segmentation method for accurately analyzing epithelial cell structures, particularly regarding junctions associated with e-cadherin and actin. The method aims to improve the localization and quantification of these cellular structures, addressing challenges in current segmentation techniques. It includes a comparison with Voronoi-based segmentation and outlines limitations as well as future work suggestions.
Segmenting Epithelial Cells in High-Throughput RNAi Screens (MIAAB 2011)
- 1. Two-Step Watershed Segmentation of Epithelial Cells Kevin Keraudren, Martin Spitaler, Vania M.M. Braga, Daniel Rueckert, Luis Pizarro Department of Computing, National Heart & Lung Institute, Imperial College London, UK 6th International Workshop on Microscopic Image Analysis with Applications in Biology Heidelberg, September 2nd, 2011
- 2. Introduction Segmentation Feature analysis Conclusion 1 Introduction Biological background Challenges 2 Segmentation Proposed method Comparison with Voronoi-based segmentation 3 Feature analysis 4 Conclusion Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 2 / 44
- 3. Introduction Segmentation Feature analysis Conclusion 1 Introduction Biological background Challenges 2 Segmentation 3 Feature analysis 4 Conclusion Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 3 / 44
- 4. Introduction Segmentation Feature analysis Conclusion Biological background Biological background Cells junctions essential for life of multi-cellular organisms E-cadherin: master cell-cell adhesion receptor frequently disrupted in different pathologies and cancer Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 4 / 44
- 5. Introduction Segmentation Feature analysis Conclusion Biological background Biological background During malignancy different oncogenes disassemble junctions to enable cell invasion Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 5 / 44
- 6. Introduction Segmentation Feature analysis Conclusion Biological background High-Throughput RNAi Screens Studying the stability of junctions for Cancer Research E-cadherin Actin Nuclei Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 6 / 44
- 7. Introduction Segmentation Feature analysis Conclusion Biological background Junctions phenotypes Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 7 / 44
- 8. Introduction Segmentation Feature analysis Conclusion Biological background Challenges Accurate cell segmentation for per cell measurements: E-cadherin & Actin localization/quantification Shape of junctions: straight, wavy, fragmented =⇒ Nuclei Cytoplasm Junctions Cell-cell contact Background Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 8 / 44
- 9. Introduction Segmentation Feature analysis Conclusion Biological background Challenges Accurate cell segmentation for per cell measurements: E-cadherin & Actin localization/quantification Shape of junctions: straight, wavy, fragmented =⇒ Nuclei Cytoplasm Junctions Cell-cell contact Background No current method Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 8 / 44
- 10. Introduction Segmentation Feature analysis Conclusion Challenges Challenges Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 9 / 44
- 11. Introduction Segmentation Feature analysis Conclusion Challenges Challenges Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 10 / 44
- 12. Introduction Segmentation Feature analysis Conclusion 1 Introduction 2 Segmentation Proposed method Comparison with Voronoi-based segmentation 3 Feature analysis 4 Conclusion Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 11 / 44
- 13. Introduction Segmentation Feature analysis Conclusion Proposed method Segmentation pipeline overview 1 Preprocessing 2 Nuclei segmentation 3 Background thresholding 4 Edge map 5 Two-step watershed Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 12 / 44
- 14. Introduction Segmentation Feature analysis Conclusion Proposed method Junctions image Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 13 / 44
- 15. Introduction Segmentation Feature analysis Conclusion Proposed method Block-matching filtering (BM3D, Dabov et al., 2007) Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 14 / 44
- 16. Introduction Segmentation Feature analysis Conclusion Proposed method Block-matching filtering (BM3D, Dabov et al., 2007) Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 15 / 44
- 17. Introduction Segmentation Feature analysis Conclusion Proposed method Coherence enhancing diffusion (CED, Weickert, 1999) Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 16 / 44
- 18. Introduction Segmentation Feature analysis Conclusion Proposed method Background tresholding on Actin Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 17 / 44
- 19. Introduction Segmentation Feature analysis Conclusion Proposed method Background tresholding on Actin Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 18 / 44
- 20. Introduction Segmentation Feature analysis Conclusion Proposed method Adaptive thresholding + filling holes on Nuclei Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 19 / 44
- 21. Introduction Segmentation Feature analysis Conclusion Proposed method Sobel filter + morphological closing on Junctions Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 20 / 44
- 22. Introduction Segmentation Feature analysis Conclusion Proposed method Sobel filter + morphological closing on Junctions Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 21 / 44
- 23. Introduction Segmentation Feature analysis Conclusion Proposed method 1st watershed step on Edge map Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 22 / 44
- 24. Introduction Segmentation Feature analysis Conclusion Proposed method 1st watershed step on Edge map Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 23 / 44
- 25. Introduction Segmentation Feature analysis Conclusion Proposed method 1st watershed step on Edge map Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 24 / 44
- 26. Introduction Segmentation Feature analysis Conclusion Proposed method Eroding cells at junctions Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 25 / 44
- 27. Introduction Segmentation Feature analysis Conclusion Proposed method Eroding cells at junctions Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 26 / 44
- 28. Introduction Segmentation Feature analysis Conclusion Proposed method 2nd watershed on raw Junctions Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 27 / 44
- 29. Introduction Segmentation Feature analysis Conclusion Comparison with Voronoi-based segmentation Comparison with Voronoi-based segmentation Voronoi-Based Segmentation (T. Jones et al., 2005) implemented in CellProfiler and Bioconductor (propagate) Pixel distance = Gradient +λ×Euclidean distance 1+λ λ = 0 λ = 1000 Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 28 / 44
- 30. Introduction Segmentation Feature analysis Conclusion Comparison with Voronoi-based segmentation Comparison with Voronoi-based segmentation propagate λ = 10−5 Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 29 / 44
- 31. Introduction Segmentation Feature analysis Conclusion Comparison with Voronoi-based segmentation Comparison with Voronoi-based segmentation Proposed segmentation pipeline Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 30 / 44
- 32. Introduction Segmentation Feature analysis Conclusion 1 Introduction 2 Segmentation 3 Feature analysis 4 Conclusion Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 31 / 44
- 33. Introduction Segmentation Feature analysis Conclusion Feature extraction Junctions region with per cell threshold Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 32 / 44
- 34. Introduction Segmentation Feature analysis Conclusion Feature analysis 0.1 0.2 0.3 0.4 0.5 0.050.100.150.20 Mean HECD1 intensity at junctions Vs non−junction Mean HECD1 intensity at junction (per cell threshold) MeanHECD1intensityincytoplasm(percellthreshold) Cytoplasmic Wavy Fragmented Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 33 / 44
- 35. Introduction Segmentation Feature analysis Conclusion Feature extraction Corner-to-corner contours Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 34 / 44
- 36. Introduction Segmentation Feature analysis Conclusion Feature extraction Corner-to-corner contours Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 35 / 44
- 37. Introduction Segmentation Feature analysis Conclusion Feature extraction q q Cytoplasmic Wavy Fragmented 1.321.341.361.381.401.421.44 Cell perimeter / Corner−to−corner perimeter (mean) Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 36 / 44
- 38. Introduction Segmentation Feature analysis Conclusion Feature extraction Smoothed contours Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 37 / 44
- 39. Introduction Segmentation Feature analysis Conclusion Feature extraction Smoothed contours Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 38 / 44
- 40. Introduction Segmentation Feature analysis Conclusion Feature extraction q q q q Cytoplasmic Wavy Fragmented 1.071.081.091.101.11 Cell perimeter / Smoothed perimeter (mean) Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 39 / 44
- 41. Introduction Segmentation Feature analysis Conclusion 1 Introduction 2 Segmentation 3 Feature analysis 4 Conclusion Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 40 / 44
- 42. Introduction Segmentation Feature analysis Conclusion Main contribution Novel segmentation method for RNAi depleted cells Accurate localization of cell structures Allows precise quantification of E-cadherin & Actin Nuclei Cytoplasm Junctions Cell-cell contact Background Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 41 / 44
- 43. Introduction Segmentation Feature analysis Conclusion Limitations of our method Tailored for specific images: cell-cell junctions Suffers from watershed leaks or local maxima Unable to recognise“no-nucleus”cells Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 42 / 44
- 44. Introduction Segmentation Feature analysis Conclusion Future work Segmentation quality assessment Cell under-segmentation More feature extraction Share code with EBImage authors Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 43 / 44
- 45. Introduction Segmentation Feature analysis Conclusion Thanks! Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 44 / 44
- 46. Introduction Segmentation Feature analysis Conclusion watergrow function Watershed with seed regions Region growing with shape prior Example with a 5x5 box neighbourhood, 6 votes required: 1 1 1 1 1 3 3 2 3 3 3 3 2 3 3 3 1 1 3 3 3 1 1 3 3 2 will not be included 1 1 1 1 1 3 2 2 2 3 3 2 2 2 3 3 1 1 1 3 1 1 1 1 1 2 will be included Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 44 / 44
- 47. Introduction Segmentation Feature analysis Conclusion Feature extraction Junctions region with per cell threshold Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 44 / 44
- 48. Introduction Segmentation Feature analysis Conclusion Feature extraction Junctions region with constant width Keraudren, Spitaler, Braga, Rueckert, Pizarro () Two-Step Watershed Segmentation September 2nd, 2011 44 / 44