Ensemble lung segmentation system using deep neural networks

Document Type

Conference Paper

Publication Date


Publication Source

Proceedings - Applied Imagery Pattern Recognition Workshop


Lung segmentation is a significant step in developing computer-aided diagnosis (CAD) using Chest Radiographs (CRs). CRs are used for diagnosis of the 2019 novel coronavirus disease (COVID-19), lung cancer, tuberculosis, and pneumonia. Hence, developing a Computer-Aided Detection (CAD) system would provide a second opinion to help radiologists in the reading process, increase objectivity, and reduce the workload. In this paper, we present the implementation of our ensemble deep learning model for lung segmentation. This model is based on the original DeepLabV3+, which is the extended model of DeepLabV3. Our model utilizes various architectures as a backbone of DeepLabV3+, such as ResNet18, ResNet50, Mo-bilenetv2, Xception, and inceptionresnetv2. We improved the encoder module of DeepLabV3+ by adjusting the receptive field of the Spatial Pyramid Pooling (ASPP). We also studied our algorithm's performance on a publicly available dataset provided by Shenzhen Hospital, that contains 566 CRs with manually segmented lungs (ground truth). The experimental result demonstrate the effectiveness of the proposed model on the dataset, achieving an Intersection-Over-Union (IoU, Jaccard Index) score of 0.97 on the test set.




Chest Radiographs, Computer Aided Diagnosis, Convolutional Neural Networks, DeepLabV3+, Ensemble model, Lung Segmentation, University of Dayton Electro-optics and Photonics