Automated Pulmonary Fibrosis Segmentation Using a 3D Multi-Scale Convolutional Encoder-Decoder Approach in Thoracic CT f
- PDF / 2,649,767 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 87 Downloads / 217 Views
Automated Pulmonary Fibrosis Segmentation Using a 3D Multi-Scale Convolutional Encoder-Decoder Approach in Thoracic CT for the Rhesus Macaque with Radiation-Induced Lung Damage Dong Yang 1 & Giovanni Lasio 2 & Baoshe Zhang 2 & Byong Yi 2 & Shifeng Chen 2 & Yin Zhang 3 & Thomas J. Macvittie 2 & Dimitris Metaxas 1 & Jinghao Zhou 3 Received: 27 May 2020 / Revised: 24 July 2020 / Accepted: 5 October 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract To develop an automated pulmonary fibrosis (PF) segmentation methodology using a 3D multi-scale convolutional encoderdecoder approach following the robust atlas-based active volume model in thoracic CT for Rhesus Macaques with radiationinduced lung damage. 152 thoracic computed tomography scans of Rhesus Macaques with radiation-induced lung damage were collected. The 3D input data are randomly augmented with the Gaussian blurring when applying the 3D multi-scale convolutional encoder-decoder (3D MSCED) segmentation method.PF in each scan was manually segmented in which 70% scans were used as training data, 20% scans were used as validation data, and 10% scans were used as testing data. The performance of the method is assessed based on a10-fold cross validation method. The workflow of the proposed method has two parts. First, the compromised lung volume with acute radiation-induced PF was segmented using a robust atlas-based active volume model. Next, a 3D multi-scale convolutional encoder-decoder segmentation method was developed which merged the higher spatial information from low-level features with the high-level object knowledge encoded in upper network layers. It included a bottom-up feed-forward convolutional neural network and a top-down learning mask refinement process. The quantitative results of our segmentation method achieved mean Dice score of (0.769, 0.853), mean accuracy of (0.996, 0.999), and mean relative error of (0.302, 0.512) with 95% confidence interval. The qualitative and quantitative comparisons show that our proposed method can achieve better segmentation accuracy with less variance in testing data. This method was extensively validated in NHP datasets. The results demonstrated that the approach is more robust relative to PF than other methods. It is a general framework which can easily be applied to segmentation other lung lesions. Keywords Computed tomography . Pulmonary fibrosis . Image segmentation
1 Introduction There are more than 15.5 million cancer survivors in the United States in 2016 and it is estimated that the cancer survivors will increase to 20.3 million in 2026 [1]. Approximately 50% of all cancer patients who receive radiation therapy during their course of illness will undergo * Jinghao Zhou [email protected] 1
Department of Computer Science, Rutgers, the State University of New Jersey, Piscataway, NJ 08854, USA
2
Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, MD 21201, USA
3
Department of Radiation Oncology, Rutgers Cancer Institute of New Jersey
Data Loading...
