TY - JOUR
T1 - Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy
AU - Ren, Ge
AU - Lam, Sai Kit
AU - Zhang, Jiang
AU - Xiao, Haonan
AU - Cheung, Andy Lai yin
AU - Ho, Wai Yin
AU - Qin, Jing
AU - Cai, Jing
N1 - Funding Information:
Conflict of Interest: JC, JQ, and W-YH, received funding from Hong Kong Food and Health Bureau (FHB), and Hong Kong University Grants Committee (UGC).
Funding Information:
This work is supported by the Health and Medical Research Fund (HMRF 07183266); the General Research Fund (GRF 151022/19M).
Publisher Copyright:
© Copyright © 2021 Ren, Lam, Zhang, Xiao, Cheung, Ho, Qin and Cai.
PY - 2021/3/24
Y1 - 2021/3/24
N2 - Functional lung avoidance radiation therapy aims to minimize dose delivery to the normal lung tissue while favoring dose deposition in the defective lung tissue based on the regional function information. However, the clinical acquisition of pulmonary functional images is resource-demanding, inconvenient, and technically challenging. This study aims to investigate the deep learning-based lung functional image synthesis from the CT domain. Forty-two pulmonary macro-aggregated albumin SPECT/CT perfusion scans were retrospectively collected from the hospital. A deep learning-based framework (including image preparation, image processing, and proposed convolutional neural network) was adopted to extract features from 3D CT images and synthesize perfusion as estimations of regional lung function. Ablation experiments were performed to assess the effects of each framework component by removing each element of the framework and analyzing the testing performances. Major results showed that the removal of the CT contrast enhancement component in the image processing resulted in the largest drop in framework performance, compared to the optimal performance (~12%). In the CNN part, all the three components (residual module, ROI attention, and skip attention) were approximately equally important to the framework performance; removing one of them resulted in a 3–5% decline in performance. The proposed CNN improved ~4% overall performance and ~350% computational efficiency, compared to the U-Net model. The deep convolutional neural network, in conjunction with image processing for feature enhancement, is capable of feature extraction from CT images for pulmonary perfusion synthesis. In the proposed framework, image processing, especially CT contrast enhancement, plays a crucial role in the perfusion synthesis. This CTPM framework provides insights for relevant research studies in the future and enables other researchers to leverage for the development of optimized CNN models for functional lung avoidance radiation therapy.
AB - Functional lung avoidance radiation therapy aims to minimize dose delivery to the normal lung tissue while favoring dose deposition in the defective lung tissue based on the regional function information. However, the clinical acquisition of pulmonary functional images is resource-demanding, inconvenient, and technically challenging. This study aims to investigate the deep learning-based lung functional image synthesis from the CT domain. Forty-two pulmonary macro-aggregated albumin SPECT/CT perfusion scans were retrospectively collected from the hospital. A deep learning-based framework (including image preparation, image processing, and proposed convolutional neural network) was adopted to extract features from 3D CT images and synthesize perfusion as estimations of regional lung function. Ablation experiments were performed to assess the effects of each framework component by removing each element of the framework and analyzing the testing performances. Major results showed that the removal of the CT contrast enhancement component in the image processing resulted in the largest drop in framework performance, compared to the optimal performance (~12%). In the CNN part, all the three components (residual module, ROI attention, and skip attention) were approximately equally important to the framework performance; removing one of them resulted in a 3–5% decline in performance. The proposed CNN improved ~4% overall performance and ~350% computational efficiency, compared to the U-Net model. The deep convolutional neural network, in conjunction with image processing for feature enhancement, is capable of feature extraction from CT images for pulmonary perfusion synthesis. In the proposed framework, image processing, especially CT contrast enhancement, plays a crucial role in the perfusion synthesis. This CTPM framework provides insights for relevant research studies in the future and enables other researchers to leverage for the development of optimized CNN models for functional lung avoidance radiation therapy.
KW - CT based image analysis
KW - deep learning
KW - functional lung avoidance radiation therapy
KW - lung function imaging
KW - perfusion imaging
KW - perfusion synthesis
UR - http://www.scopus.com/inward/record.url?scp=85103791120&partnerID=8YFLogxK
U2 - 10.3389/fonc.2021.644703
DO - 10.3389/fonc.2021.644703
M3 - Journal article
AN - SCOPUS:85103791120
SN - 2234-943X
VL - 11
JO - Frontiers in Oncology
JF - Frontiers in Oncology
M1 - 644703
ER -