According to a study conducted by the BJM Quality & Safety Journal, as much as 28% of medical misdiagnoses turn out to be life-threatening or life-altering, and a significant portion of common misdiagnoses across healthcare providers worldwide belongs to x-rays. This program looks at taking the first step towards solving this problem by utilizing a web application that houses a pre-trained deep learning neural network capable of taking x-ray scan images as input and outputting a result as to whether a patient is positive for a certain medical condition. Despite the small time constraints of this project, we take pride in the fact that we were able to re-train and complete a working network, as well as the user interface that we used to house it in order to make it more accessible to the average user. More importantly, we see a brighter future in which further development on this project will allow for more efficient training of the neural network, and thus the growth of a new software that has the potential to revolutionize healthcare by utilizing the power of data.
Using a Neural Network to Detect Conditions in Chest X-Rays
This project uses a neural network to detect certain medical conditions in chest x-rays.
Updates
Leave feedback in the comments!
Log in or sign up for Devpost to join the conversation.