AI-Driven Pneumothorax Detection in X-ray Imaging

This project aims to enhance the accuracy of identifying health issues in chest X-ray images. The team will develop a specialized tool, known as a “chest-tube detection model”, which will initially examine all X-rays to identify cases where patients have already received medical assistance, making it unnecessary to flag these cases. Subsequently, the remaining X-rays will undergo evaluation by a “pneumothorax-detection model” to identify potential instances of pneumothorax, a condition where air accumulates in the space between the lungs and the chest wall, causing breathing difficulties. The primary objective is to assist medical professionals by streamlining the process of identifying and prioritizing cases that require additional attention. The anticipated outcome is an improved method for detecting health concerns in chest X-rays, ultimately supporting healthcare providers in delivering more effective patient care.

Faculty Supervisor:

Michael Brudno

Student:

Partner:

Lviv Polytechnic National University

Discipline:

Computer science

Sector:

Artificial Intelligence; Technology

University:

University of Toronto

Program: