PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Capstone
Hippocampus MRI Segmentation for Alzheimer's Screening
Segments the hippocampus in brain MRI and reports its volume
4-5 weeks build
Overview
Trains a 3D U-Net on the Medical Segmentation Decathlon hippocampus task to label the anterior and posterior hippocampus in cropped MRI volumes. Predicted masks are converted to volumes in cubic millimetres, since hippocampal shrinkage is a studied Alzheimer's marker, and a viewer shows the result slice by slice.
What makes it stand up
- 01Medical Segmentation Decathlon Task04 hippocampus volumes
- 023D U-Net with patch sampling to fit student GPUs
- 03Volume measurement from voxel spacing, compared with ground truth
- 04Dice, Jaccard and Hausdorff distance reported per structure
- 05Academic screening prototype, not a diagnostic instrument
Module breakdown
- 01
Data loading
NIfTI volumes, intensity normalisation and patch sampling.
- 02
Model
3D U-Net trained with Dice-based loss in MONAI.
- 03
Volumetry
Voxel counting scaled by spacing into cubic millimetres.
- 04
Evaluation
Per-structure overlap and boundary metrics with plots.
- 05
Viewer and API
Upload endpoint and three-plane slice viewer.
After this, you will be able to
- Explain why 3D convolutions help on volumetric scans
- Defend what a volume estimate can and cannot tell a clinician
- Demo segmentation and volume output on a held-out scan
Technology stack
- Python
- PyTorch
- MONAI
- Nibabel
- FastAPI
- React
- Level
- Capstone
- Domain
- Artificial Intelligence
- Build time
- 4-5 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support