Planaria Antioxidant Regeneration Screen

By /

Planaria Antioxidant Regeneration Screen

ISEF Category: Biomedical Engineering

Ready to Turn This Idea Into a Real Project?

This guide was put together with the help of AI research tools to give you a solid starting point. But a competitive science fair project lives in the details: refining your research question, fine-tuning your variables, analyzing your data, and presenting your findings like a seasoned scientist.

For next steps tailored to your interests, skill level, and timeline, work one-on-one with a MehtA+ mentor. Learn more about MehtA+ Science & Engineering Research Mentorship →

Subcategory: Biomaterials and Regenerative Medicine  ·  Difficulty: Beginner  ·  Setup: Home Setup  ·  Time: 1 to 2 Weeks

The Hook

Cut a planarian flatworm in half and you get two worms in two weeks. They are nature's regeneration champions. You can buy them for a few dollars and screen common household antioxidants to see which one speeds their regrowth. A small neural network turns time-lapse phone videos into precise growth curves.

What Is It?

Planaria are non-vertebrate flatworms with extraordinary stem cells. When cut, they regenerate missing body parts. Researchers use them to study how chemicals influence stem-cell-driven regeneration without working on vertebrates.

Vitamin C, green-tea EGCG, and turmeric curcumin are antioxidants found in food and supplements. Antioxidants reduce oxidative stress, which may either help or hurt regeneration depending on dose. By placing planaria in baths with different antioxidant concentrations, you can compare regrowth rate against a plain-water control.

U-Net is a deep-learning model designed for image segmentation. Trained on a few labeled phone snapshots, it can find the worm outline in every video frame and measure its length over time. Slope of length-versus-day equals regrowth rate.

Why This Is a Good Topic

Planaria fit ISEF rules with minimal paperwork compared to vertebrate work. The experiment is cheap, the variables are clean, and the image-analysis step lets you add a serious ML component. You will learn experimental design, dose-response, and convolutional segmentation.

Research Questions

  • How does vitamin C concentration change daily regrowth length?
  • What is the effect of EGCG dose on percent of worms reaching full regeneration?
  • Does curcumin shorten the time to head regrowth compared to control?
  • To what extent does temperature shift the dose response?
  • Which antioxidant gives the largest effect-size at non-toxic doses?
  • How does light exposure affect regrowth rate?
  • What is the effect of pretreatment time on outcomes?

Basic Materials

  • Planaria starter culture (online biology supplier).
  • Vitamin C tablets, green-tea extract capsules, turmeric capsules.
  • Spring water (no chlorine).
  • Plastic petri dishes.
  • Single-edge razor blade and forceps.
  • Smartphone with stand for time-lapse capture.
  • LED ring light.
  • Ruler and tape.

Advanced Materials

  • Spectrophotometer for antioxidant concentration verification.
  • Stereo microscope with camera mount.
  • Temperature-controlled incubator.
  • GPU for U-Net training.

Software & Tools

  • Python (PyTorch or TensorFlow): Trains the U-Net segmentation model.
  • ImageJ: Provides ground-truth length measurements.
  • OpenCV: Stabilizes frames and crops worm regions.
  • Roboflow free tier: Labels training images.

Experiment Steps

  1. Lock a single worm-cut protocol so every animal starts with the same wound geometry.
  2. Decide the antioxidant concentrations you will compare and the number of worms per group.
  3. Build a fixed imaging jig so frames are comparable across days.
  4. Label a starter dataset by hand before training the U-Net.
  5. Plan controls (plain water, vehicle-only, no cut) that rule out non-drug effects.
  6. Compare regrowth slopes across groups using analysis of variance.

Common Pitfalls

  • Cutting worms at different positions, which makes the regrowth target inconsistent.
  • Letting room temperature fluctuate and confounding drug effects.
  • Training U-Net on too few labeled frames, which hides segmentation errors.
  • Reusing dishes between groups without rinsing, which carries over antioxidants.
  • Reporting only the worms that survived, biasing toward responders.

What Makes This Competitive

Move beyond one dose per drug to a real dose-response with at least three concentrations and ten worms per condition. Report effect sizes with confidence intervals, hold out a test set the U-Net never saw, and benchmark observed regrowth against published planarian regeneration kinetics.

Project Variations

  • Swap planaria for hydra ($10 culture) and compare regrowth response.
  • Add an oxidative-stress challenge (low-dose hydrogen peroxide) and test whether antioxidants rescue.
  • Replace U-Net with a classical thresholding pipeline and compare accuracy.

Learn More

  • PubMed: Search planarian regeneration small-molecule screens.
  • NIH PubMed Central: Open-access papers on Schmidtea mediterranea.
  • MIT OpenCourseWare: Course 7.013 Introductory Biology lecture videos.
  • U-Net original paper on arXiv: Open-access architecture reference.
  • Carolina Biological Supply educational guides: Free planaria care sheets.
Shopping Cart