About this article
- Submitted: Jun 12, 2024
- Final Revised: Nov 05, 2024
- Accepted: Jan 21, 2026
- Published: Dec 30, 2024
- Abstract view: 14
- PDF Download: 1
- Volumes: Vol. 2 No. 2 (2024) Pages 85-100
- DOI: 10.63208/21018-107
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright (c) 2024 Author(s)
Cite this article
Abstract
The reliability of deep learning (DL) denoising models in low-dose computed tomography (CT) is vital to prevent hallucinated structures and ensure clinical trust. This study introduces AntiHalluciNet, a novel framework designed to detect spurious structural components in residual noise from DL denoising models. Trained on paired structure-embedded and pure noise images, AntiHalluciNet identifies unwanted artifacts using the Residual Structure Index (RSI), a new metric for quantifying prediction confidence. Its ability to assess denoised image fidelity using only noise residuals offers a practical alternative to the Structural Similarity Index (SSIM), which requires reference images. Applied to audit RED-CNN, CTformer, and ClariCT.AI (version 1.2.3), AntiHalluciNet achieved RSI values of 0.57 ± 0.31 for structure-embedded noise and 0.02 ± 0.02 for pure noise in a 50% low-dose dataset (p < 0.0001). For degraded images, RSI outperformed SSIM across 25%–100% degradation levels, showing greater differentiation. Distinct RSI distributions 0.28 ± 0.06 (RED-CNN), 0.21 ± 0.06 (CTformer), and 0.15 ± 0.03 (ClariCT.AI) highlight AntiHalluciNet’s precision in auditing DL denoising models, enhancing clinical reliability by detecting structural artifacts in residual noise.
References
R. Smith-Bindman, D. L. Miglioretti, and E. B. Larson, “Rising use of diagnostic medical imaging in a large integrated health system,” Health Affairs, vol. 27, no. 6, pp. 1491–1502, Nov. 2008.
D. J. Brenner and E. J. Hall, “Computed tomography An increasing source of radiation exposure,” New England Journal of Medicine, vol. 357, no. 22, pp. 2277–2284, Nov. 2007.
A. Berrington de González et al., “Projected cancer risks from computed tomographic scans performed in the United States in 2007,” Archives of Internal Medicine, vol. 169, no. 22, pp. 2071–2077, Dec. 2009.
R. Smith-Bindman et al., “Radiation dose associated with common computed tomography examinations and the associated lifetime attributable risk of cancer,” Archives of Internal Medicine, vol. 169, no. 22, pp. 2078–2086, Dec. 2009.
H. W. Goo, “CT radiation dose optimization and estimation: An update for radiologists,” Korean Journal of Radiology, vol. 13, no. 1, pp. 1–11, Jan. 2012.
L. Yu et al., “Radiation dose reduction in computed tomography: Techniques and future perspective,” Imaging in Medicine, vol. 1, no. 1, pp. 65–84, Oct. 2009.
H. Chen et al., “Low-dose CT with a residual encoder-decoder convolutional neural network,” IEEE Transactions on Medical Imaging, vol. 36, no. 12, pp. 2524–2535, Dec. 2017.
E. Kang, J. Min, and J. C. Ye, “A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction,” Medical Physics, vol. 44, no. 10, pp. e360–e375, Oct. 2017.
P. Bao et al., “Convolutional sparse coding for compressed sensing CT reconstruction,” IEEE Transactions on Medical Imaging, vol. 38, no. 11, pp. 2607–2619, Nov. 2019.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
H. Choi et al., “Dose reduction potential of vendor-agnostic deep learning model in comparison with deep learning–based image reconstruction algorithm on CT: A phantom study,” European Radiology, vol. 32, no. 2, pp. 1247–1255, Feb. 2022.
J. G. Nam et al., “Image quality of ultralow-dose chest CT using deep learning techniques: Potential superiority of vendor-agnostic post-processing over vendor-specific techniques,” European Radiology, vol. 31, no. 7, pp. 5139–5147, Jul. 2021.
C. Belthangady and L. A. Royer, “Applications, promises, and pitfalls of deep learning for fluorescence image reconstruction,” Nature Methods, vol. 16, no. 12, pp. 1215–1225, Dec. 2019.
C. Cruz, A. Foi, V. Katkovnik, and K. Egiazarian, “Nonlocality-reinforced convolutional neural networks for image denoising,” IEEE Signal Processing Letters, vol. 25, no. 8, pp. 1216–1220, Aug. 2018.
S. Bhadra, V. A. Kelkar, F. J. Brooks, and M. A. Anastasio, “On hallucinations in tomographic image reconstruction,” IEEE Transactions on Medical Imaging, vol. 40, no. 11, pp. 3249–3260, Nov. 2021.
R. Zeng et al., “Performance of a deep learning-based CT image denoising method: Generalizability over dose, reconstruction kernel, and slice thickness,” Medical Physics, vol. 49, no. 2, pp. 836–853, Feb. 2022.
E. Samei et al., “Performance evaluation of computed tomography systems: Summary of AAPM Task Group 233,” Medical Physics, vol. 46, no. 11, pp. e735–e756, Nov. 2019.
L. S. Chow and H. Rajagopal, “Modified-BRISQUE as no reference image quality assessment for structural MR images,” Magnetic Resonance Imaging, vol. 43, pp. 74–87, Nov. 2017.
Z. Zhang et al., “Can signal-to-noise ratio perform as a baseline indicator for medical image quality assessment,” IEEE Access, vol. 6, pp. 11534–11543, 2018.
C. H. Kim et al., “The impact of deep learning reconstruction in low dose computed tomography on the evaluation of interstitial lung disease,” PLoS ONE, vol. 18, no. 10, p. e0291745, Oct. 2023.
Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, Apr. 2004.
A. Mittal, R. Soundararajan, and A. C. Bovik, “Making a ‘completely blind’ image quality analyzer,” IEEE Signal Processing Letters, vol. 20, no. 3, pp. 209–212, Mar. 2013.
A. Mittal, A. K. Moorthy, and A. C. Bovik, “No-reference image quality assessment in the spatial domain,” IEEE Transactions on Image Processing, vol. 21, no. 12, pp. 4695–4708, Dec. 2012.
N. Venkatanath, D. Praneeth, B. H. Maruthi Chandrasekhar, S. S. Channappayya, and S. S. Medasani, “Blind image quality evaluation using perception based features,” in Proc. 21st National Conference on Communications (NCC), Mumbai, India, Feb. 2015, pp. 1–6.
P. Birch et al., “Approximate bandpass and frequency response models of the difference of Gaussian filter,” Optics Communications, vol. 283, no. 24, pp. 4942–4948, Dec. 2010.
C. Won Kim and J. H. Kim, “Realistic simulation of reduced-dose CT with noise modeling and sinogram synthesis using DICOM CT images,” Medical Physics, vol. 41, no. 1, p. 011901, Jan. 2014.
A. E. Othman et al., “Impact of image denoising on image quality, quantitative parameters and sensitivity of ultra-low-dose volume perfusion CT imaging,” European Radiology, vol. 26, no. 1, pp. 167–174, Jan. 2016.
T. Hepp et al., “Effects of simulated dose variation on contrast-enhanced CT-based radiomic analysis for non-small cell lung cancer,” European Journal of Radiology, vol. 124, p. 108804, Mar. 2020.
S. Afat et al., “Diagnostic accuracy of simulated low-dose perfusion CT to detect cerebral perfusion impairment after aneurysmal subarachnoid hemorrhage: A retrospective analysis,” Radiology, vol. 287, no. 2, pp. 643–650, May 2018.
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Lecture Notes in Computer Science, vol. 9351, Berlin, Germany: Springer, 2015, pp. 234–241.
D. P. Kingma and J. L. Ba, “Adam: A method for stochastic optimization,” in Proc. 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA, May 2015, pp. 1–15.
P. Prakash et al., “Reducing abdominal CT radiation dose with adaptive statistical iterative reconstruction technique,” Investigative Radiology, vol. 45, no. 4, pp. 202–210, Apr. 2010.
A. Mileto et al., “State of the art in abdominal CT: The limits of iterative reconstruction algorithms,” Radiology, vol. 293, no. 3, pp. 491–503, Dec. 2019.
J. Solomon, A. Mileto, J. C. Ramirez-Giraldo, and E. Samei, “Diagnostic performance of an advanced modeled iterative reconstruction algorithm for low-contrast detectability with a third-generation dual-source multidetector CT scanner: Potential for radiation dose reduction in a multireader study,” Radiology, vol. 275, no. 3, pp. 735–745, Jun. 2015.
D. Wang et al., “CTformer: Convolution-free Token2Token dilated vision transformer for low-dose CT denoising,” Physics in Medicine & Biology, vol. 68, no. 6, p. 065012, Mar. 2023.
ClariPi Inc., “ClariCT.AI,” FDA 510(k) Premarket Notification K212074, 2021. [Online]. Available: https://www.accessdata.fda.gov/cdrh_docs/pdf21/K212074.pdf
C. H. McCollough et al., “Low-dose CT for the detection and classification of metastatic liver lesions: Results of the 2016 Low Dose CT Grand Challenge,” Medical Physics, vol. 44, no. 10, pp. e339–e352, Oct. 2017.
W. Lee et al., “No-reference perceptual CT image quality assessment based on a self-supervised learning framework,” Machine Learning: Science and Technology, vol. 3, no. 4, p. 045033, Dec. 2022.
Q. Gao et al., “Blind CT image quality assessment via deep learning framework,” in Proc. IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Manchester, UK, Oct. 2019, pp. 1–3.
S. Li et al., “Blind CT image quality assessment via deep learning strategy: Initial study,” in Medical Imaging 2018: Physics of Medical Imaging, vol. 10577, Houston, TX, USA, Feb. 2018, pp. 293–297.