Semi-Supervised Segmentation of Radiation-Induced Pulmonary Fibrosis From Lung CT Scans With Multi-Scale Guided Dense Attention
Top Cited Papers
- 2 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (3) , 531-542
Abstract
Computed Tomography (CT) plays an important role in monitoring radiation-induced Pulmonary Fibrosis (PF), where accurate segmentation of the PF lesions is highly desired for diagnosis and treatment follow-up. However, the task is challenged by ambiguous boundary, irregular shape, various position and size of the lesions, as well as the difficulty in acquiring a large set of annotated volumetric images for training. To overcome these problems, we propose a novel convolutional neural network called PF-Net and incorporate it into a semi-supervised learning framework based on Iterative Confidence-based Refinement And Weighting of pseudo Labels (I-CRAWL). Our PF-Net combines 2D and 3D convolutions to deal with CT volumes with large inter-slice spacing, and uses multi-scale guided dense attention to segment complex PF lesions. For semi-supervised learning, our I-CRAWL employs pixel-level uncertainty-based confidence-aware refinement to improve the accuracy of pseudo labels of unannotated images, and uses image-level uncertainty for confidence-based image weighting to suppress low-quality pseudo labels in an iterative training process. Extensive experiments with CT scans of Rhesus Macaques with radiation-induced PF showed that: 1) PF-Net achieved higher segmentation accuracy than existing 2D, 3D and 2.5D neural networks, and 2) I-CRAWL outperformed state-of-the-art semi-supervised learning methods for the PF lesion segmentation task. Our method has a potential to improve the diagnosis of PF and clinical assessment of side effects of radiotherapy for lung cancers.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (81771921, 61901084)
This publication has 42 references indexed in Scilit:
- Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentationMedical Image Analysis, 2017
- Deep Learning in Medical Image AnalysisAnnual Review of Biomedical Engineering, 2017
- Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentationMedical Image Analysis, 2017
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- 3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes2016
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- A homotopy-based sparse representation for fast and accurate shape prior modeling in liver surgical planningMedical Image Analysis, 2015
- Automated segmentation of pulmonary structures in thoracic computed tomography scans: a reviewPhysics in Medicine & Biology, 2013
- Cancer and Radiation Therapy: Current Advances and Future DirectionsInternational Journal of Medical Sciences, 2012
- Pulmonary fibrosis: pathogenesis, etiology and regulationMucosal Immunology, 2009