Please sign in before starting!!.

This project has been built using the Zooniverse Project Builder but is not yet an official Zooniverse project. Queries and issues relating to this project directed at the Zooniverse Team may not receive any response.

Adipose Tissue Mask Repair for Cancer Biomarker Discovery

Help improve AI-generated tissue masks for biomarker discovery in cancer research.

Learn more
Get Started!

You can do real research by clicking to get started here!

Zooniverse Talk

Chat with the research team and other volunteers!

Join in

Adipose Tissue Mask Repair for Cancer Biomarker Discovery Statistics

View more stats

All Time Stats

Volunteers0
Classifications0

Active Stats

Active stats provide information about currently active workflows and subjects.

0%
Project not launchedPercent complete
Classifications0
Subjects0
Completed subjects0

Message from the researcher

marioparreno avatar

AI often struggles with broken adipocyte boundaries, but people can recognize these patterns visually. By working together, researchers and volunteers can create higher-quality data and open new paths for biomarker discovery.

marioparreno

About Adipose Tissue Mask Repair for Cancer Biomarker Discovery

H&E images can reveal tissue structures that help researchers study diseases such as cancer. AI can help analyse these images, but adipose tissue is challenging: thin tissue walls may look broken, faint, or incomplete because of tissue preparation. This can make tissue measurements less accurate.

In this project, you will compare the original image with a predicted mask and decide whether the mask is acceptable, whether a tissue wall is missing, or whether the case is too difficult to judge confidently. If the mask is wrong and the missing structure is clear, you will improve it by redrawing the missing or incorrect parts.

Your contributions will help create better annotations for digital pathology research, improve future AI models, and support the discovery of new biomarkers for diseases such as cancer.

No previous pathology experience is required. A short tutorial and examples will guide you step by step.