Published April 17, 2023 | Version v1
Other Open

Airway-Informed Quantitative CT Imaging Biomarker for Fibrotic Lung Disease

  • 1. National Heart and Lung Institute, Imperial College London, London, UK
  • 2. National Heart and Lung Institute, Imperial College London, London, UK; Royal Brompton Hospital, London, UK

Description

Airway-related quantitative imaging biomarkers (QIB) are crucial for examination, diagnosis, and prognosis in lung diseases, while the manual delineation of airway structures is unduly burdensome [1, 2]. Several efforts have been made to improve the performance of automatic airway modelling [3-7]; however, current datasets only focus on
diseases that have minor tracheal changes and do not incorporate complex pulmonary diseases. For instance, the honeycombing within the lung tissue in patients with fibrotic lung disease makes the annotation much more complicated and error-prone. To bridge this gap, 285 cases (235 from patients with fibrotic lung disease and 50 from patients with COVID-19) were collected and included in this challenge. The airway structures were meticulously annotated by three experienced radiologists. Competitors are first encouraged to devise automatic airway segmentation models with high robustness and generalization abilities, followed by exploring the most correlated QIB of mortality prediction. This challenge is an open-call challenge and new submissions are allowed after the conference.

[1] T. M. Maher et al., "An epithelial biomarker signature for idiopathic pulmonary fibrosis: an analysis from the multicentre PROFILE cohort study," The Lancet Respiratory Medicine, vol. 5, no. 12, pp. 946-955, 2017.
[2] S. L. Walsh, N. Sverzellati, A. Devaraj, A. U. Wells, and D. M. Hansell, "Chronic hypersensitivity pneumonitis: high resolution computed tomography patterns and pulmonary function indices as prognostic determinants," European radiology, vol. 22, no. 8, pp. 1672-1679, 2012.
[3] Y. Qin et al., "Airwaynet: a voxel-connectivity aware approach for accurate airway segmentation using convolutional neural networks," in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019: Springer, pp. 212-220.
[4] A. Garcia-Uceda, R. Selvan, Z. Saghir, H. A. Tiddens, and M. de Bruijne, "Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks," Scientific Reports, vol. 11, no. 1, pp. 1-15, 2021.
[5] Y. Qin, Y. Gu, H. Zheng, M. Chen, J. Yang, and Y.-M. Zhu, "AirwayNet-SE: A simple-yet-effective approach to improve airway segmentation using context scale fusion," in 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 2020: IEEE, pp. 809-813.
[6] H. Zheng et al., "Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation," IEEE Transactions on Medical Imaging, 2021.
[7] S. A. Nadeem et al., "A CT-based automated algorithm for airway segmentation using freeze-and-grow propagation and deep learning," IEEE Transactions on Medical Imaging, vol. 40, no. 1, pp. 405-418, 2020.

Files

Airway-InformedQuantitativeCTImagingBiomarkerforFibroticLungDisease_04-17-2023_03-38-25.pdf