Improved lung segmentation based on U-Net architecture and morphological operations

TL;DR

This paper introduces an improved lung segmentation model using U-Net architecture combined with morphological operations, achieving high accuracy on public chest X-ray datasets for better diagnosis support.

Contribution

The paper presents a novel lung segmentation approach that enhances U-Net with morphological operations, improving accuracy and robustness over existing methods.

Findings

Achieved a DICE coefficient of 98.1% on public datasets

Effectively ignores unimportant areas in chest radiographs

Demonstrates reliable lung segmentation performance

Abstract

An essential stage in computer aided diagnosis of chest X rays is automated lung segmentation. Due to rib cages and the unique modalities of each persons lungs, it is essential to construct an effective automated lung segmentation model. This paper presents a reliable model for the segmentation of lungs in chest radiographs. Our model overcomes the challenges by learning to ignore unimportant areas in the source Chest Radiograph and emphasize important features for lung segmentation. We evaluate our model on public datasets, Montgomery and Shenzhen. The proposed model has a DICE coefficient of 98.1 percent which demonstrates the reliability of our model.