Extracting Lungs from CT Images using Fully Convolutional Networks

TL;DR

This paper presents a deep learning-based method using fully convolutional networks and CRFs for lung segmentation in CT images, achieving high accuracy and demonstrating generalization across different datasets.

Contribution

The study introduces a generalized lung segmentation approach using FCNs and CRFs, evaluated on multiple datasets, outperforming previous methods in accuracy.

Findings

Achieved Dice scores of 98.67% and 99.19% on two datasets.

Outperformed previous methods on the HUG-ILD dataset.

Demonstrated effective generalization across datasets.

Abstract

Analysis of cancer and other pathological diseases, like the interstitial lung diseases (ILDs), is usually possible through Computed Tomography (CT) scans. To aid this, a preprocessing step of segmentation is performed to reduce the area to be analyzed, segmenting the lungs and removing unimportant regions. Generally, complex methods are developed to extract the lung region, also using hand-made feature extractors to enhance segmentation. With the popularity of deep learning techniques and its automated feature learning, we propose a lung segmentation approach using fully convolutional networks (FCNs) combined with fully connected conditional random fields (CRF), employed in many state-of-the-art segmentation works. Aiming to develop a generalized approach, the publicly available datasets from University Hospitals of Geneva (HUG) and VESSEL12 challenge were studied, including many healthy and pathological CT scans for evaluation. Experiments using the dataset individually, its trained model on the other dataset and a combination of both datasets were employed. Dice scores of $98.67\%\pm0.94\%$ for the HUG-ILD dataset and $99.19\%\pm0.37\%$ for the VESSEL12 dataset were achieved, outperforming works in the former and obtaining similar state-of-the-art results in the latter dataset, showing the capability in using deep learning approaches.