Author:
Liu Yinghao,Liang Pengchen,Liang Kaiyi,Chang Qing
Abstract
AbstractPneumothorax is a condition involving a collapsed lung, which requires accurate segmentation of computed tomography (CT) images for effective clinical decision-making. Numerous convolutional neural network-based methods for medical image segmentation have been proposed, but they often struggle to balance model complexity with performance. To address this, we introduce the Efficient Feature Alignment Network (EFA-Net), a novel medical image segmentation network designed specifically for pneumothorax CT segmentation. EFA-Net uses EfficientNet as an encoder to extract features and a Feature Alignment (FA) module as a decoder to align features in both the spatial and channel dimensions. This design allows EFA-Net to achieve superior segmentation performance with reduced model complexity. In our dataset, our method outperforms various state-of-the-art methods in terms of accuracy and efficiency, achieving a Dice coefficient of 90.03%, an Intersection over Union (IOU) of 81.80%, and a sensitivity of 88.94%. Notably, EFA-Net has significantly lower FLOPs (1.549G) and parameters (0.432M), offering better robustness and facilitating easier deployment. Future work will explore the integration of downstream applications to enhance EFA-Net’s utility for clinicians and patients in real-world diagnostic scenarios. The source code of EFA-Net is available at: https://github.com/tianjiamutangchun/EFA-Net.
Funder
scientific research project of Shanghai Municipal Health Commission
The Combination of Medical Care and Health Project of Shanghai University of Traditional Chinese Medicine
Key projects of Shanghai Jiading District Health Commission
Key medical specialty of Jiading District, Shanghai
Publisher
Springer Science and Business Media LLC
Reference33 articles.
1. Tan, M. & Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning 6105–6114 (PMLR, 2019).
2. Wakai, A. P. Spontaneous pneumothorax. BMJ Clin. Evid. 2011 (2011).
3. Do, S. et al. Automated quantification of pneumothorax in CT. Comput. Math. Methods Med. 2012, 736320 (2012).
4. Langdorf, M. I. et al. Prevalence and clinical import of thoracic injury identified by chest computed tomography but not chest radiography in blunt trauma: multicenter prospective cohort study. Ann. Emerg. Med. 66, 589–600 (2015).
5. Jakhar, K., Kaur, A. & Gupta, D. M. Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax. Preprint at http://arxiv.org/abs/1912.07329 (2021).