Computer Vision for Segmenting & Analyzing Subcellular Components in Cryo-Electron Tomography

Computer Vision for Segmenting & Analyzing Subcellular Components in Cryo-Electron Tomography

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

Intro

1 of 28

1 of 28

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Computer Vision for Segmenting & Analyzing Subcellular Components in Cryo-Electron Tomography

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 CryoET data analysis offers many opportunities... but also present significant challenges
  3. 3 Quantifying mitochondrial granules in HD neurons
  4. 4 HD Patient iPSC-Derived Neurons on CryoEM Grids
  5. 5 Objective: Automated Quantification of Mito Granules
  6. 6 Training a 3D Segmentation Model
  7. 7 Quantitative Characterization of Mitochondrial Granules in Neurites of HD Neurons
  8. 8 Ongoing and Future Directions
  9. 9 Further reducing annotation needs for training computer vision algorithms
  10. 10 Unsupervised learning methods for segmentation
  11. 11 Motivations for our work in unsupervised segmentation
  12. 12 Hyperbolic space
  13. 13 Poincare ball model
  14. 14 Gyrovector operations bring linear algebra to the Poincare ball
  15. 15 Our work: reconstructing visual hierarchy as a pretext task
  16. 16 Self-supervised hierarchical triplet loss
  17. 17 Hyperbolic clustering
  18. 18 Experimental validation
  19. 19 BraTS Dataset (Menze et al 2015)
  20. 20 Cryogenic electron tomography
  21. 21 Summary
  22. 22 Domain adaptive unsupervised instance segmentation for biomedical images
  23. 23 DARCNN: Domain Adaptive Region-based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical Images
  24. 24 Background: Mask R-CNN instance segmentation architecture
  25. 25 DARCNN model: feature-level adaptation
  26. 26 DARCNN model: pseudo-labelling
  27. 27 Potential unsupervised discovery applications in Cryo-ET
  28. 28 Developing Computer Vision Methods for Segmenting and Analyzing Subcellular Components in Cryo-ET

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.