Semi-Supervised Segmentation of Radiation-Induced Pulmonary Fibrosis from Lung CT Scans with Multi-Scale Guided Dense Attention

Autor: B Yi, Shifeng Chen, Shuwei Zhai, Shaoting Zhang, Dimitris N. Metaxas, Thomas J. MacVittie, Baoshe Zhang, Guotai Wang, Jinghao Zhou, G Lasio
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer science
Pulmonary Fibrosis
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
Boundary (topology)
Radiation induced
Convolutional neural network
Article
Pulmonary fibrosis
Image Processing
Computer-Assisted
medicine
FOS: Electrical engineering
electronic engineering
information engineering
Animals
Segmentation
Electrical and Electronic Engineering
Lung
Radiological and Ultrasound Technology
Artificial neural network
business.industry
Image and Video Processing (eess.IV)
Pattern recognition
Electrical Engineering and Systems Science - Image and Video Processing
medicine.disease
Macaca mulatta
Computer Science Applications
Weighting
Artificial intelligence
Tomography
X-Ray Computed
Scale (map)
business
Software
Zdroj: IEEE Trans Med Imaging
DOI: 10.48550/arxiv.2109.14172
Popis: 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.
Comment: 12 pages, 9 figures. Submitted to IEEE TMI
Databáze: OpenAIRE
Externí odkaz: