Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax
Karan Jakhar, Avneet Kaur, Meenu Gupta
TL;DR
This study tackles rapid pneumothorax diagnosis from chest X-rays by framing segmentation as a pixel-wise mask prediction task that highlights affected regions. It proposes a U-net architecture with a ResNet backbone, 256×256 preprocessing, pretrained encoder weights, and post-processing thresholding to deliver mask outputs mapped to the original images. On a Kaggle chest X-ray dataset with 12,047 images, the method achieves a Dice coefficient of $D=\frac{2|X\cap Y|}{|X|+|Y|}$ where $D=0.843$ and IoU of $IoU=\frac{|X\cap Y|}{|X\cup Y|}$ where $IoU=0.826$, indicating strong segmentation performance. The approach provides interpretable masks to assist clinicians and demonstrates potential for real-time deployment, addressing access and time constraints in emergency settings.
Abstract
Computer vision has shown promising results in medical image processing. Pneumothorax is a deadly condition and if not diagnosed and treated at time then it causes death. It can be diagnosed with chest X-ray images. We need an expert and experienced radiologist to predict whether a person is suffering from pneumothorax or not by looking at the chest X-ray images. Everyone does not have access to such a facility. Moreover, in some cases, we need quick diagnoses. So we propose an image segmentation model to predict and give the output a mask that will assist the doctor in taking this crucial decision. Deep Learning has proved their worth in many areas and outperformed man state-of-the-art models. We want to use the power of these deep learning model to solve this problem. We have used U-net [13] architecture with ResNet [17] as a backbone and achieved promising results. U-net [13] performs very well in medical image processing and semantic segmentation. Our problem falls in the semantic segmentation category.