You will get Pneumonia Detection using Chest X-Rays
Project details
This model detects pneumonia from chest X-ray images using a Convolutional Neural Network (CNN) inspired by AlexNet architecture. It classifies input images into two categories: Pneumonia and Normal. The model is trained on the widely used Chest X-ray dataset by Paul Mooney and achieves over 94% accuracy. It also includes Grad-CAM visualization for interpretability, allowing users to see what regions of the X-ray influenced the decision.
Machine Learning Tools
OpenCV, pandas, Python, TensorFlowWhat's included $35
These options are included with the project scope.
$35
- Delivery Time 1 day
- Number of Revisions 0
- Number of Model Variations 1
- Number of Graphs/Charts 2
- Model Validation/Testing
- Model Documentation
- Source Code
Optional add-ons
You can add these on the next page.
Additional Graph/Chart
+$2About Dhruva
AI/RAG Engineer | LangChain, LangGraph & LLM Systems | I build product
Bengaluru, India - 8:16 am local time
I build production-grade AI systems — not prototypes, not demos, but tools that hold up under real enterprise constraints like compliance, confidentiality, and scale.
Currently, I work as a Data Science Engineer where I've built:
→ A RAG-based clinical document generation system for a Fortune 500 pharma client, using MMR retrieval, ChromaDB, LangChain, and a FastAPI/React stack — cut manual protocol drafting time significantly while keeping outputs auditable and accurate.
→ An automated clinical data mapping pipeline (SDTM) with a 385-rule validation engine across 10 data domains, including a redaction-before-reasoning architecture and role-based access controls — built specifically to satisfy strict data confidentiality requirements in regulated healthcare environments.
→ Agentic AI systems using LangGraph — covering state management, human-in-the-loop workflows, multi-agent orchestration, and observability — going beyond simple chatbots into systems that actually reason, retrieve, validate, and act.
I also created and published a full prompt engineering curriculum (PromptCraft Academy) used by developers looking to go from "I can write a decent prompt" to "I can architect reliable LLM systems."
What I bring to your project:
✅ Real production experience, not just tutorial-following — my systems run against real pharma-grade data with real compliance requirements
✅ End-to-end capability: retrieval architecture → agent design → validation loops → frontend delivery
✅ I explain technical trade-offs in plain language, so you always know why a system is built the way it is
✅ Fast iteration — I test rigorously before I hand anything off
If you need a RAG pipeline, an AI agent, an automation system, or someone to make sense of a messy LLM integration — let's talk about what you're building.
Steps for completing your project
After purchasing the project, send requirements so Dhruva can start the project.
Delivery time starts when Dhruva receives requirements from you.
Dhruva works on your project following the steps below.
Revisions may occur after the delivery date.
Commitment
I have already committed my time in this project ,so further things are not required.