Quantification of Lung Abnormalities in Cystic Fibrosis using Deep Networks

TL;DR

This paper presents a deep learning cascade approach to detect and classify lung abnormalities in cystic fibrosis from CT scans, achieving high accuracy and outperforming traditional methods.

Contribution

It introduces a novel cascade of convolutional neural networks for detecting and classifying lung abnormalities, along with a pixel-wise heatmap network learned from patch annotations.

Findings

Disease detection accuracy of 0.94, outperforming random forest and single neural network.

Cascade approach achieves a class-averaged F1-score of 0.33, better than baseline methods.

Method effectively distinguishes between different types of lung abnormalities.

Abstract

Cystic fibrosis is a genetic disease which may appear in early life with structural abnormalities in lung tissues. We propose to detect these abnormalities using a texture classification approach. Our method is a cascade of two convolutional neural networks. The first network detects the presence of abnormal tissues. The second network identifies the type of the structural abnormalities: bronchiectasis, atelectasis or mucus plugging.We also propose a network computing pixel-wise heatmaps of abnormality presence learning only from the patch-wise annotations. Our database consists of CT scans of 194 subjects. We use 154 subjects to train our algorithms and the 40 remaining ones as a test set. We compare our method with random forest and a single neural network approach. The first network reaches an accuracy of 0,94 for disease detection, 0,18 higher than the random forest classifier and 0,37 higher than the single neural network. Our cascade approach yields a final class-averaged F1-score of 0,33, outperforming the baseline method and the single network by 0,10 and 0,12.