Deep LF-Net: Semantic lung segmentation from Indian chest radiographs including severely unhealthy images. (July 2021)

• Record Type: Journal Article
• Authors: Singh, Anushikha; Lall, Brejesh; Panigrahi, B.K.; Agrawal, Anjali; Agrawal, Anurag; Thangakunam, Balamugesh; Christopher, D.J.
• Is Part Of: Biomedical signal processing and control. Volume 68(2021)
• Publication Date: 2021-07
• Subjects: Chest radiographs -- Lung Field -- Deep neural network -- Semantic segmentation; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102666
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The proposed work attempt deep learning based automatic lung segmentation which is required to design a computer-aided diagnostic tool for examination of a CxR. We construct the dataset of CxR images with corresponding ground truth lung mask of the Indian population including healthy and patients with various lung diseases. Extensive experiments on in-house Indian dataset including severe abnormal images, and common benchmark datasets. The proposed method achieved more than 99 % accuracy and outperforms the state of art on Indian and public datasets. Abstract: A chest radiograph, commonly called chest x-ray (CxR), plays a vital role in the diagnosis of various lung diseases. Automated segmentation of the lungs is an important step to design a computer-aided diagnostic tool for examination of a CxR. Precise lung segmentation is considered extremely challenging because of variance in the shape of the lung caused by health issues, age, and gender. The proposed work investigates the use of an efficient deep convolutional neural network for accurate segmentation of lungs from CxR. We attempt an end to end DeepLabv3+ network which integrates DeepLab architecture, encoder-decoder, and dilated convolution for semantic lung segmentation with fast training and high accuracy. We experimented with the different pre-trained base networks: Resnet18 and Mobilenetv2, associated with the Deeplabv3+ model for performance analysis. The proposed approach does not require any pre-processing technique on chest x-ray images before being fed to a neural network. We construct a dataset of CxR images with corresponding lung mask of the Indian population that contain healthy and unhealthy CxRs of clinically confirmed patients of tuberculosis, chronic obstructive pulmonary disease, interstitial lung disease, pleural effusion, and lung cancer. The proposed method is tested on 688 images of our Indian CxR dataset including images with severe abnormal findings to validate its robustness. We also experimented on commonly used benchmark datasets such as Japanese Society of Radiological Technology; Montgomery County, and Shenzhen, China for state-of-the-art comparison. The performance of our method is tested against techniques described in the literature and achieved the superior performance.