Technical Note: Deriving ventilation imaging from 4<scp>DCT</scp> by deep convolutional neural network

Zhong, Yuncheng; Vinogradskiy, Yevgeniy; Chen, Liyuan; Myziuk, Nick; Castillo, Richard; Castillo, Edward M.; Guerrero, Thomas; Jiang, Steve B; Wang, Jing

doi:10.1002/mp.13421

Cited by 26 publications

(27 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks have also been proposed as a means of generating ventilation images. 21 The majority of described CT ventilation methods have been applied to 4DCT data; however, Eslick et al 23 recently demonstrated improved accuracy of CT ventilation images using breath-hold CTs for ventilation image calculation. Although these more recently proposed methods of calculating CT ventilation are in their nascent state, early results suggest promise in overcoming some of the challenges associated with conventional CT-ventilation calculation methodologies.…”

Section: Calculation Methodsologies Of Ct-based Ventilation Imagingmentioning

confidence: 99%

CT-based ventilation imaging in radiation oncology

Vinogradskiy

2019

BJR|Open

Self Cite

View full text Add to dashboard Cite

A form of lung function imaging is emerging that uses phase-resolved four-dimensional CT (4DCT or breath-hold CT) images along with image processing techniques to generate lung function maps that provide a surrogate of lung ventilation. CT-based ventilation (referred to as CT-ventilation) research has gained momentum in Radiation Oncology because many lung cancer patients undergo four-dimensional CT simulation as part of the standard treatment planning process. Therefore, generating CT-ventilation images provides functional information without burdening the patient with an extra imaging procedure. CT-ventilation has progressed from an image processing calculation methodology, to validation efforts, to retrospective demonstration of clinical utility in Radiation Oncology. In particular, CT-ventilation has been proposed for two main clinical applications: functional avoidance radiation therapy and thoracic dose–response assessment. The idea of functional avoidance radiation therapy is to preferentially spare functional portions of the lung (as measured by CT-ventilation) during radiation therapy with the hypothesis that reducing dose to functional portions of the lung will lead to reduced rates of radiation-related thoracic toxicity. The idea of imaging-based dose–response assessment is to evaluate pre- to post-treatment CT-ventilation-based imaging changes. The hypothesis is that early, imaging-change-based response can be an early predictor of subsequent thoracic toxicity. Based on the retrospective evidence, the clinical applications of CT-ventilation have progressed from the retrospective setting to on-going prospective clinical trials. This review will cover basic CT-ventilation calculation methodologies, validation efforts, presentation of clinical applications, summarize on-going clinical trials, review potential uncertainties and shortcomings of CT-ventilation, and discuss future directions of CT-ventilation research.

show abstract

Section: Calculation Methodsologies Of Ct-based Ventilation Imagingmentioning

confidence: 99%

CT-based ventilation imaging in radiation oncology

Vinogradskiy

2019

BJR|Open

Self Cite

View full text Add to dashboard Cite

show abstract

“…Convolutional neural networks (CNNs), which is the main DL tool to handle medical images, can utilize spatial and structural information effectively duo to the ability of taking two‐dimensional (2D) or three‐dimensional (3D) information as input. More recently, Zhong et al employed a deep CNNs with nine layers to derive ventilation maps from 4DCT, which can well illustrate the feasibility of the DL method in generating pulmonary ventilation images. However, the main limitation in that study is the label data is the ventilation images calculated from HU method, which highly depends on the accuracy of the employed DIR algorithm.…”

Section: Introductionmentioning

confidence: 98%

A deep learning method for producing ventilation images from 4DCT: First comparison with technegas SPECT ventilation

et al. 2020

View full text Add to dashboard Cite

Purpose The purpose of this study is to develop a deep learning (DL) method for producing four‐dimensional computed tomography (4DCT) ventilation imaging and to evaluate the accuracy of the DL‐based ventilation imaging against single‐photon emission‐computed tomography (SPECT) ventilation imaging (SPECT‐VI). The performance of the DL‐based method is assessed by comparing with density change‐ and Jacobian‐based (HU and JAC) methods. Materials and methods Fifty patients with esophagus or lung cancer who underwent thoracic radiotherapy were enrolled in this study. For each patient, 4DCT scans paired with 99mTc‐Technegas SPECT/CT were acquired before the first radiotherapy treatment. 4DCT and SPECT/CT were first rigidly registered using MIMvista and converted to data matrix using MATLAB, and then transferred to a DL model based on U‐net for correlating 4DCT features and SPECT‐VI. Two forms of 4DCT dataset [(a) ten phases and (b) two phases of peak‐exhalation and peak‐inhalation] as input are studied. Tenfold cross‐validation procedure was used to evaluate the performance of the DL model. For comparative evaluation, HU and JAC methodologies are used to calculate specific ventilation imaging based on 4DCT (CTVI) for each patient. The voxel‐wise Spearman’s correlation was evaluated over the whole lung between each of CTVI and corresponding SPECT‐VI. The SPECT‐VI and produced CTVIs were segmented into high, median, and low functional lung (HFL, MFL, and LFL) regions. The spatial overlap of corresponding HFL, MFL, and LFL for each CTVI against SPECT‐VI was also evaluated using the dice similarity coefficient (DSC). The averaged DSC of functional lung regions was calculated and statistically analyzed with a one‐factor ANONA model among different methods. Results The voxel‐wise Spearman rs values were (0.22 ± 0.31), (−0.09 ± 0.18), and (0.73 ± 0.16)/(0.71 ± 0.17) for the CTVIHU, CTVIJAC, and CTVIDL(1)/CTVIDL(2). These results showed the DL method yielded the strongest correlation with SPECT‐VI. Using the DSC as the spatial overlap metric, we found that the CTVIHU, CTVIJAC, and CTVIDL(1)/CTVIDL(2) methods achieved averaged DSC values for all patients to be (0.45 ± 0.08), (0.33 ± 0.04), and (0.73 ± 0.09)/(0.71 ± 0.09), respectively. The results demonstrated that the DL method yielded the highest similarity with SPECT‐VI with the prominently significant difference (P < 10−7). Conclusions This study developed a DL method for producing CTVI and performed a validation against SPECT‐VI. The results demonstrated that DL method can derive CTVI with greatly improved accuracy in comparison to HU and JAC methods. The produced ventilation images can be more accurate and useful for lung functional avoidance radiotherapy and treatment response modeling.

show abstract

“…In the proposed framework, image processing, especially CT contrast enhancement, plays a crucial role in the perfusion synthesis. Before our study, most of the existing CT based pulmonary function studies used ( 24 , 36 , 37 ) deformable image registration (DIR) algorithms to derive ventilation in view of that both pulmonary ventilation and perfusion are correlated with the radiotherapy-induced pneumonitis ( 38 ). However, the accuracy of DIR based lung function mapping methods may be variable in different DIR algorithms and settings ( 39 ).…”

Section: Discussionmentioning

confidence: 99%

Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

et al. 2021

View full text Add to dashboard Cite

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.

show abstract

Technical Note: Deriving ventilation imaging from 4DCT by deep convolutional neural network

Cited by 26 publications

References 45 publications

CT-based ventilation imaging in radiation oncology

CT-based ventilation imaging in radiation oncology

A deep learning method for producing ventilation images from 4DCT: First comparison with technegas SPECT ventilation

Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

Contact Info

Product

Resources

About