In this project, I will apply the skills that I have acquired for 2D medical imaging to analyze data from the NIH Chest X-ray Dataset and train a CNN to classify a given chest x-ray for the presence or absence of pneumonia. This project will culminate in a model that can predict the presence of pneumonia with human radiologist-level accuracy that can be prepared for submission to the FDA for 510(k) clearance as software as a medical device. As part of the submission preparation, I will formally describe my model, the data that it was trained on, and a validation plan that meets FDA criteria.
Complete Project with model weights and model architecture saved in .json and .hdf5 is available in zipped folder here
This project has the following steps.
- Exploratory Data Analysis
- Building and Training Your Model
- Clinical Workflow Integration
- FDA Preparation
Dataset for training:
The NIH data for EDA and training is provided to you along with the code to load the data, this can download the data from the kaggle website