Malaria Detection System
AI-Powered Diagnostic System for Rapid Microscopic Blood Smear Screening
AI-powered malaria detection system for hospitals with patient management, PDF report generation, and real-time analytics. Built with React, Supabase & FastAPI.
What Jayant Potdar Built & Owned
Engineered the end-to-end computer vision pipeline and clinical web interface: trained a convolutional neural network (CNN) on segmented erythrocyte cell images, built an asynchronous FastAPI inference service for real-time sample processing, implemented confidence probability scoring (parasitized vs uninfected), and designed an automated clinical PDF test report generation workflow.
Key Technical Decisions:
- Deep learning CNN model classifying parasitized vs uninfected thin blood smear cells with over 94% confidence.
- Sub-30 second end-to-end diagnostic turnaround time from sample upload to structured test report.
- Detailed probability metrics breakdown and automated medical diagnostic report generator.
- Responsive, clinical dashboard designed for rapid bedside triage and laboratory technician workflows.
Core System Features & Capabilities:
- ✓AI-powered malaria cell detection using Keras & deep CNNs with 94%+ accuracy.
- ✓Hospital patient management system.
- ✓Automated clinical PDF medical report generation in under 30 seconds.
- ✓Real-time analytics dashboard with probability scoring breakdown.
- ✓Hospital laboratory triage workflow integration.
- ✓Secure cloud storage with Supabase & FastAPI.
Microscopic cell images vary widely in staining intensity, illumination, and artifact noise. Classifying single-cell blood smears requires high precision to prevent false negatives while maintaining high inference speed.
I trained a deep convolutional network using transfer learning with data augmentation (rotations, flips, color jitter) to handle varying stain conditions. The FastAPI backend serves inference with batching support, returning class probabilities and generating standardized clinical laboratory reports.
Detailed interface walkthrough, diagnostic panels, and feature screenshots for Malaria Detection System.
The system delivers rapid diagnostic inference with 94%+ classification confidence, completing full sample analysis and report generation in under 30 seconds to support hospital diagnostic workflows.
AstroPixel
AstroPixel is a FastAPI + React platform for exploring NASA gigapixel imagery with buttery-smooth deep zoom, annotations, and secure user/admin workflows. It ingests GeoTIFF/PSB files, generates tile pyramids with GDAL, and serves them through an optimized viewer.
Krypton
Krypton is an AI-powered research assistant that searches arXiv and OpenAlex, ranks papers by relevance, recency, and citations, and helps users understand literature faster with Gemini-generated summaries, structured insights, research-gap analysis, and personalized topic recommendations in a FastAPI + React app.
