Generation of Virtual Non-Contrast CT From Intravenous Enhanced CT in Radiotherapy Using Convolutional Neural Networks

Objective: To generate virtual non-contrast (VNC) computed tomography (CT) from intravenous enhanced CT through convolutional neural networks (CNN) and compare calculated dose among enhanced CT, VNC, and real non-contrast scanning. Method: 50 patients who accepted non-contrast and enhanced CT scanning before and after intravenous contrast agent injections were selected, and two sets of CT images were registered. A total of 40 and 10 groups were used as training and test datasets, respectively. The U-Net architecture was applied to learn the relationship between the enhanced and non-contrast CT. VNC images were generated in the test through the trained U-Net. The CT values of non-contrast, enhanced and VNC CT images were compared. The radiotherapy treatment plans for esophageal cancer were designed, and dose calculation was performed. Dose distributions in the three image sets were compared. Results: The mean absolute error of CT values between enhanced and non-contrast CT reached 32.3 ± 2.6 HU, and that between VNC and non-contrast CT totaled 6.7 ± 1.3 HU. The average CT values in enhanced CT of great vessels, heart, lungs, liver, and spinal cord were all significantly higher than those of non-contrast CT (p < 0.05), with the differences reaching 97, 83, 42, 40, and 10 HU, respectively. The average CT values of the organs in VNC CT showed no significant differences from those in non-contrast CT. The relative dose differences of the enhanced and non-contrast CT were −1.2, −1.3, −2.1, and −1.5% in the comparison of mean doses of planned target volume, heart, great vessels, and lungs, respectively. The mean dose calculated by VNC CT showed no significant difference from that by non-contrast CT. The average γ passing rate (2%, 2 mm) of VNC CT image was significantly higher than that of enhanced CT image (0.996 vs. 0.973, p < 0.05). Conclusion: Designing a treatment plan based on enhanced CT will enlarge the dose calculation uncertainty in radiotherapy. This paper proposed the generation of VNC CT images from enhanced CT images based on U-Net architecture. The dose calculated through VNC CT images was identical with that obtained through real non-contrast CT.

[1]  J. Affeldt,et al.  The feasibility study , 2019, The Information System Consultant’s Handbook.

[2]  J. Herndon,et al.  Lung cancer staging and management: comparison of contrast-enhanced and nonenhanced helical CT of the thorax. , 1999, Radiology.

[3]  J. Robar,et al.  Tumour dose enhancement using modified megavoltage photon beams and contrast media. , 2002, Physics in medicine and biology.

[4]  K. Ahn,et al.  Influence of intravenous contrast agent on dose calculations of intensity modulated radiation therapy plans for head and neck cancer. , 2006, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[5]  Y. Shibamoto,et al.  Influence of contrast materials on dose calculation in radiotherapy planning using computed tomography for tumors at various anatomical regions: a prospective study. , 2007, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[6]  Tae Hyun Kim,et al.  Influence of lipiodol agent on proton beam range in radiotherapy planning using computed tomography for hepatocellular carcinoma. , 2008, International journal of radiation oncology, biology, physics.

[7]  N. Nitta,et al.  Detection of mediastinal and hilar lymph nodes by 16-row MDCT: is contrast material needed? , 2008, European journal of radiology.

[8]  Jianghong Xiao,et al.  Feasibility of using intravenous contrast-enhanced computed tomography (CT) scans in lung cancer treatment planning. , 2010, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[9]  The effect of a contrast agent on proton beam range in radiotherapy planning using computed tomography for patients with locoregionally advanced lung cancer. , 2011, International journal of radiation oncology, biology, physics.

[10]  Shu Liao,et al.  Unsupervised Deep Feature Learning for Deformable Registration of MR Brain Images , 2013, MICCAI.

[11]  H. Lusic,et al.  X-ray-computed tomography contrast agents. , 2013, Chemical reviews.

[12]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[13]  D. Low,et al.  Prospective study evaluating the use of IV contrast on IMRT treatment planning for lung cancer. , 2014, Medical physics.

[14]  H. Kwon,et al.  Prospective Study , 2020, Encyclopedia of Behavioral Medicine.

[15]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[16]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[17]  Xiao Han,et al.  MR‐based synthetic CT generation using a deep convolutional neural network method , 2017, Medical physics.

[18]  Heung-Il Suk,et al.  Deep Learning in Medical Image Analysis. , 2017, Annual review of biomedical engineering.

[19]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[20]  Ronald M. Summers,et al.  A Bottom-Up Approach for Pancreas Segmentation Using Cascaded Superpixels and (Deep) Image Patch Labeling , 2015, IEEE Transactions on Image Processing.

[21]  Ronald M. Summers,et al.  Holistic segmentation of the lung in cine MRI , 2017, Journal of medical imaging.

[22]  Gustavo Carneiro,et al.  Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support , 2017, Lecture Notes in Computer Science.

[23]  K. Mouridsen,et al.  Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning , 2018, Stroke.

[24]  Hengyong Yu,et al.  Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography , 2017, IEEE Transactions on Medical Imaging.

[25]  Xiaoying Wang,et al.  Respiratory motion correction for free-breathing 3D abdominal MRI using CNN-based image registration: a feasibility study. , 2018, The British journal of radiology.

[26]  Nima Tajbakhsh,et al.  UNet++: A Nested U-Net Architecture for Medical Image Segmentation , 2018, DLMIA/ML-CDS@MICCAI.

[27]  Chi-Wing Fu,et al.  H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes , 2018, IEEE Transactions on Medical Imaging.

[28]  Loïc Le Folgoc,et al.  Attention U-Net: Learning Where to Look for the Pancreas , 2018, ArXiv.

[29]  Peter R Seevinck,et al.  Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy , 2018, Physics in medicine and biology.

[30]  Ahmed Hosny,et al.  Artificial intelligence in radiology , 2018, Nature Reviews Cancer.

[31]  Jie Fu,et al.  Deep learning approaches using 2D and 3D convolutional neural networks for generating male pelvic synthetic CT from MRI. , 2018, Medical physics.

[32]  Karen A. Vineberg,et al.  Generation of Synthetic CT Images From MRI for Treatment Planning and Patient Positioning Using a 3-Channel U-Net Trained on Sagittal Images , 2019, Front. Oncol..

[33]  Berkman Sahiner,et al.  Deep learning in medical imaging and radiation therapy. , 2018, Medical physics.

[34]  Bakhtyar Ahmed Mohammed,et al.  using Deep Learning , 2020 .