Development of Artificial Intelligence-Based Dual-Energy Subtraction for Chest Radiography
Source abstract
Abstract
Recently, some facilities have utilized the dual-energy subtraction (DES) technique for chest radiography to increase pulmonary lesion detectability. However, the availability of the technique is limited to certain facilities, in addition to other limitations, such as increased noise in high-energy images and motion artifacts with the one-shot and two-shot methods, respectively. The aim of this study was to develop artificial intelligence-based DES (AI–DES) technology for chest radiography to overcome these limitations. Using a trained pix2pix model on clinically acquired chest radiograph pairs, we successfully converted 130 kV images into virtual 60 kV images that closely resemble the real images. The averaged peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) between virtual and real 60 kV images were 33.8 dB and 0.984, respectively. We also achieved the production of soft-tissue- and bone-enhanced images using a weighted image subtraction process with the virtual 60 kV images. The soft-tissue-enhanced images exhibited sufficient bone suppression, particularly within lung fields. Although the bone-enhanced images contained artifacts on and around the lower thoracic and lumbar spines, superior sharpness and noise characteristics were presented. The main contribution of our development is its ability to provide selectively enhanced images for specific tissues using only high-energy images obtained via routine chest radiography. This suggests the potential to improve the detectability of pulmonary lesions while addressing challenges associated with the existing DES technique. However, further improvements are necessary to improve the image quality.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Lung Cancer Diagnosis and Treatment · COVID-19 diagnosis using AI · Advanced X-ray and CT Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Division of Health Sciences, Graduate School of Medicine, Osaka University, Suita 565-0871, Japan
Department of Radiology, National Cerebral and Cardiovascular Center, Suita 564-8565, Japan
Department of Radiology, Kitasato University Hospital, Sagamihara 252-0329, Japan
References (46)
Show source-provided references
1. Distribution, risk factors, and temporal trends for lung cancer incidence and mortality: A global analysis10.1016/j.chest.2021.12.655 ↗
2. Lung cancer and radiological imaging10.2174/1874471013666200523161849 ↗
3. Early diagnosis of lung cancer: Which is the optimal choice?10.18632/aging.202504 ↗
4. Use of CT and chest radiography for lung cancer screening before and after publication of screening guidelines: Intended and unintended uptake10.1001/jamainternmed.2016.9016 ↗
5. Lung cancer screening10.1016/S0140-6736(22)01694-4 ↗
6. American Cancer Society lung cancer screening guidelines10.3322/caac.21172 ↗
7. Lung cancer screening, Version 3.2018, NCCN Clinical Practice Guidelines in Oncology
8. Sensitivity and specificity of lung cancer screening using chest low-dose computed tomography
9. Radiographic screening in the early detection of lung cancer
10. Improved detection of small lung cancers with dual-energy subtraction chest radiography10.2214/AJR.07.2875 ↗
11. Dual-energy subtraction X-ray digital tomosynthesis: Basic physical evaluation10.4236/ojmi.2012.23021 ↗
12. Dual energy subtraction and temporal subtraction chest radiography10.1097/RTI.0b013e318173dd38 ↗
13. Dual-energy subtraction chest radiography: What to look for beyond calcified nodules10.1148/rg.261055034 ↗
14. Effects of dual-energy subtraction chest radiography on detection of small pulmonary nodules with varying attenuation: Receiver operating characteristic analysis using a phantom study10.1007/s11604-009-0411-7 ↗
15. Detection of small pulmonary nodules on chest radiographs: Efficacy of dual-energy subtraction technique using flat-panel detector chest radiography10.1016/j.crad.2010.02.012 ↗
16. Comparison of dual energy subtraction chest radiography and traditional chest X-rays in the detection of pulmonary nodules
17. The potential application of dual-energy subtraction radiography for COVID-19 pneumonia imaging10.1259/bjr.20201384 ↗
18. Optimization of dual-energy subtraction chest radiography by use of a direct-conversion flat-panel detector system10.1007/s12194-014-0285-y ↗
19. Automatic algorithm for determining bone and soft-tissue factors in dual-energy subtraction chest radiography10.1016/j.bspc.2022.104354 ↗
20. Dual energy subtraction: Principles and clinical applications
21. Noise-reduction approaches to single-shot dual-energy imaging with a multilayer detector10.1088/1748-0221/14/01/C01021 ↗
22. Motion artefact reduction in dual-energy radiography10.1007/s10527-022-10148-9 ↗
23. Value of bone suppression software in chest radiographs for improving image quality and reducing radiation dose10.1007/s00330-020-07596-w ↗
24. Bone suppression for chest X-ray image using a convolutional neural filter10.1007/s13246-019-00822-w ↗
25. Liu, Y., Liu, M., Xi, Y., Qin, G., Shen, D., and Yang, W. (2020). Medical Image Computing and Computer Assisted Intervention—MICCAI 2020, Springer. Lecture Notes in Computer Science.
26. Bone suppression on chest radiographs for pulmonary nodule detection: Comparison between a generative adversarial network and dual-energy subtraction10.3348/kjr.2021.0146 ↗
27. Bone suppression on pediatric chest radiographs via a deep learning-based cascade model10.1016/j.cmpb.2022.106627 ↗
28. Dilated conditional GAN for bone suppression in chest radiographs with enforced semantic features10.1002/mp.14371 ↗
29. Separation of bones from soft tissue in chest radiographs: Anatomy-specific orientation-frequency-specific deep neural network convolution10.1002/mp.13468 ↗
30. Rajaraman, S., Cohen, G., Spear, L., Folio, L., and Antani, S. (2022). DeBoNet: A deep bone suppression model ensemble to improve disease detection in chest radiographs. PLoS ONE, 17.10.1371/journal.pone.0265691 ↗
31. Spatial feature and resolution maximization GAN for bone suppression in chest radiographs10.1016/j.cmpb.2022.107024 ↗
32. Isora, P., Zhu, J.-Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
33. Yoshida, N., Kageyama, H., Akai, H., Yasaka, K., Sugawara, H., Okada, Y., and Kunimatsu, A. (2022). Motion correction in MR image for analysis of VSRAD using generative adversarial network. PLoS ONE, 17.10.1371/journal.pone.0274576 ↗
34. Pix2Pix generative adversarial network for low dose myocardial perfusion SPECT denoising10.21037/qims-21-1042 ↗
35. Mirza, M., and Osindero, S. (2014). Conditional Generative Adversarial Nets. arXiv.
36. (2023, June 05). junyanz/pytorch-CycleGAN-and-pix2pix. Available online: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix.
37. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. arXiv.10.1007/978-3-319-24574-4_28 ↗
38. Pathak, D., Krähenbühl, P., Donahue, J., Darrell, T., and Efros, A.A. (2016, January 27–30). Context encoders: Feature learning by inpainting. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.278 ↗
39. Development of a digital chest phantom for studies on energy subtraction techniques10.6009/jjrt.2014_JSRT_70.3.191 ↗
40. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017, January 4–9). GANs trained by a two time-scale update rule converge to a local nash equilibrium. Proceedings of the Advances in Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
41. Borji, A. (2018). Pros and cons of GAN evaluation measures. arXiv.10.1016/j.cviu.2018.10.009 ↗
42. Image quality assessment: From error measurement to structural similarity10.1109/TIP.2003.819861 ↗
43. Hóre, A., and Ziou, D. (2010, January 23–26). Image Quality Metrics: PSNR vs. SSIM. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.10.1109/ICPR.2010.579 ↗
44. Wang, Z., Simoncelli, E.P., and Bovik, A.C. (2003, January 9–12). Multiscale structural similarity for image quality assessment. Proceedings of the 37th IEEE Asilomar Conference on Signals, Systems & Computers, Pacific Grove, CA, USA.
45. Image quality assessment through FSIM, SSIM, MSE and PSNR—A comparative study10.4236/jcc.2019.73002 ↗
46. Mudeng, V., Kim, M., and Choe, S. (2022). Prospects of structual similarity index for medical image analysis. Appl. Sci., 12.10.3390/app12083754 ↗