Want to use deep learning for image analysis but lack the coding skills? We introduce DELiVR, a game-changer in brain-wide cell analysis. No coding required, our Fiji Plug-in does the magic. Hats off to Doris Kaltenecker, Rami, @moritz_negwer! 🧵👇🏼 1/n

2. What makes DELiVR stand out? It's a robust deep-learning pipeline for mapping cFos+ cells in whole brains. Combining tissue clearing, light-sheet microscopy, VR annotation & deep learning, it comes in an easy-to-use FIJI plugin and docker container!

3. Understanding the status quo: Tissue clearing and fluorescent imaging techniques have revolutionized protein expression analysis in whole specimens. By immunostaining for immediate early genes like c-Fos, we get a comprehensive view of neuronal activity.

4. But there are challenges: Current methods often lack sensitivity and specificity, and while deep learning offers solutions, it requires a lot of training data. Moreover, many of the existing deep learning methods aren't user-friendly for biologists.

5. Introducing DELiVR - our answer to these challenges: a deep learning solution for brain-wide cell analysis, it uses a more accurate and faster VR-based annotation and comes with a user-friendly FIJI plugin.

6. The VR advantage: The bottleneck for training a powerful deep learning solution is often the amount of annotated data. Traditional 2D annotation methods are time-consuming, so we turned to VR for a faster and more reliable approach.

7. The results? Our VR approach improved annotation accuracy and sped up the process by 7X on average! We fully annotated our training data in VR, revolutionizing the ground truth data generation process.

8. Comparing DELiVR to existing solutions: Our method outperforms filter and threshold-based segmentation techniques. With 79.18% instance Dice (+38.66% increase) and 84.70% instance sensitivity (+57.79% increase), it clearly stands out.

9. Next level with Allen Brain Atlas: DELiVR produces whole-brain segmentation output in the original image and atlas space. Cells are assigned values matching the Area ID of Allen Brain Atlas, enabling brain region-based color-coding. Dive into syGlass video for a closer look!

10. At your fingertips: With a docker and Fiji plugin, DELiVR can run on anything from PCs to clusters, creating a seamless workflow for researchers. Just plug in your raw data and output location - voila! Docker & Plugin: Github:

11. Real-world impact: Using DELiVR, we explored brain activity in tumor-bearing mice with stable weight and those with cancer-associated weight loss. The results? Fascinating insights into neurophysiological phenotypes related to weight control in cancer.

12. Findings: We found an increase in neuronal activity in weight-stable cancer mice, a pattern absent in mice experiencing weight loss. This highlights a previously unknown neurophysiological phenotype in cancer-related weight control.

13. Location matters: Many hyperactive areas were located in the cortex. We also saw an increase in c-Fos+ cells in various hypothalamic nuclei, including the lateral hypothalamic nucleus, known for its role in feeding and metabolism.

14. Validate with ease: DELiVR makes it simple to validate quantifications & confirm c-Fos expression in anatomical sub-areas in the original image stacks. Color map of the segmentation output allows easy highlighting of cells in the area of interest using standard Fiji tools.

15. In summary, DELiVR is a VR trained, deep learning pipeline for analyzing neuronal activity markers in mouse brains, in health and disease. Plus, it's user-friendly with an easy-to-launch FIJI plugin.

16. Beyond neuroscience: DELiVR is more than a tool for neuroscientists. It provides a blueprint for integrating VR into the annotation of training data for AI across various fields, revolutionizing this critical step in machine learning.

17. Explore DELiVR: Preprint: Docker & Plugin & Test Dataset: Github: All videos: