A healthcare company partnered with Elinext to develop a pneumonia diagnosis tool that uses machine learning to analyze lung X-ray images. Using the InceptionV3 neural network, they created a web-based application that allows users to upload images and receive feedback on lung health. The tool aims to reduce human error in pneumonia identification, especially useful during the pandemic, with potential for scaling to other diseases.

1. Client
A company developing a healthcare platform hired Elinext to help it build a pneumonia
diagnosis tool.
Challenge
The company has been developing a comprehensive healthcare platform. Treating pneumonia
has been one of its focus areas due to COVID, and it wanted to build a pneumonia diagnosis
tool for the platform.
The tool was destined to analyze lung X-ray images and identify signs of pneumonia using
machine learning (ML), an artificial intelligence (AI) technique. The company didn’t have
relevant in-house experts, so they reached out for help and found it with Elinext.
Solution
We began by looking for a neural network that would best analyze lung images and found four
candidates: ResNet (50, 101, 152), VGG (16, 19), MobileNet and Inception (V2, V3). After
digging deeper into each of them, we chose InceptionV3 developed by Google Research Lab.
Once we chose our neural network, we moved on to designing the software architecture and
training the algorithm.

2. Architecture
The software is based on web technology and can be integrated into other systems like desktop
applications and mobile apps.
We used publicly available frameworks, libraries and technologies to develop the software. To
create a static HTML5 web page, we deployed a web server in a Docker container. On that
page, a user can upload a lung image and get feedback. The image is sent for processing
through the HTTP protocol.
Training
Training is the most challenging part in building ML algorithms. Your ability to source enough
data, avoid errors and be consistent throughout the process can make or break the algorithm.
Manual training is often inconsistent. You may forget which steps you have taken and in which
order, or occasionally delete logs. As a result, you won’t be able to accurately repeat a training
session. Therefore, we automated the process from A to Z.
We needed to train complex models with huge datasets fast. To do that, we rented an Amazon
Web Services (AWS) g3s.xlarge instance and used Deep Learning Base AMI (Ubuntu 18.10). The
latter is a powerful machine boasting 16GB of RAM, a 4-core CPU and an Nvidia Tesla M60 GPU.
It was a perfect fit for the task. Once we have chosen the technology, the training could begin.
We built a clean Docker container to isolate the model from outer influences and downloaded a
ton of lung images from Kaggle. To be able to work with the images, we subsampled them,
narrowing them down to a relevant and consistent selection. The dataset and training
environment were ready.
The training began. We faced a challenge in overtraining, whereby the model could memorize
training images and as a result fail to accurately analyze new images in the future. Our solution
was to slightly modify the images’ width, height, graininess and some other parameters. We
also launched Tensorboard to monitor training metrics.
At the final stages, we exported the model to an H5 file, a format commonly used across
industries from healthcare to aerospace, for testing. We tested it manually and automatically,
using preset scripts.
Accuracy
The model we’ve developed has a margin of confidence and uses binary identification. What
does this mean? It means if the algorithm identifies 80% of lungs as unaffected, it will say the
lungs are healthy. If the figure is below 80%, it will assume the lungs might be affected and
require medical attention.
How It Works
The user opens the web application in their browser, uploads a lung image, sends it to the
service and receives feedback. The feedback will show whether the lungs are healthy or if a
doctor should take a look at the image.
Result
The tool we’ve built can help reduce human error in identifying pneumonia. This is particularly
useful during the pandemic when doctors are overloaded and might overlook some signs of
illness. We can also scale the model up to identify some other diseases. Scaling the model down
will help integrate it into other systems, speed things up and allow for the analysis of multiple
images simultaneously.