Tinjauan Sistematis Teknik Reduksi Noise Pada Citra CT Scan Thoraks Untuk Peningkatan Kualitas Diagnostik
DOI:
https://doi.org/10.24252/sainfis.v5i2.63790Keywords:
CT Scan, Diagnostic, Image, Reconstruction, ThoraxAbstract
The use of low-dose protocols inCT examinations is increasingly preferred to reduce radiation exposure in patients.However, this reduction in dose causes an increase in noise which results in a decrease in image qualityand potentially interferes with diagnostic accuracy. To overcome this problem, various image reconstruction techniques have been developed, ranging fromfiltered back projection reconstruction, iterative reconstruction,hybrid iterative reconstruction, to artificial intelligence-based reconstruction. This studyexamined five journals that compared the performance of variousreconstruction methods based on two objective parameters, namely the signal-to-noise ratio(SNR) and the contrast-to-noise ratio (CNR). The results showthat filtered back projection reconstruction produces the lowest image qualitybecause it does not have a noise control model, while iterative reconstructionis able to suppress noise but often produces images that are too smooth, resulting in reduced anatomical detail. In contrast, artificial intelligence-based reconstruction, especially high-level artificial intelligence, consistently provides the highest SNR and CNR, maintain fine anatomical details, and preserve edge sharpnesseven when radiation dose is significantly reduced. Based on the overall findings,high-level artificial intelligence-based reconstruction is the most effective and recommended methodfor improving low-dose CT image qualitywithout compromising clinical assessment reliability.
Downloads
References
Abuya, T., Rimiru, R., & Okeyo, G. (2025). Adversarial Content–Noise Complementary Learning Model for Image Denoising and Tumor Detection in Low-Quality Medical Images. Signals, 6(2), 17. https://doi.org/10.3390/signals6020017
Beister, M., Kolditz, D., & Kalender, W. A. (2012). Iterative reconstruction methods in X-ray CT. Physica Medica, 28(2), 94–108. https://doi.org/10.1016/j.ejmp.2012.01.003
Cho, H.-H., Lee, S. M., & You, S. K. (2024). Assessment of deep learning image reconstruction (DLIR) on image quality in pediatric cardiac CT datasets type of manuscript: Original research. PLOS ONE, 19(8), e0300090. https://doi.org/10.1371/journal.pone.0300090
Hwang, M.-H., Kang, S., Lee, J. W., & Lee, G. (2024). Deep Learning-Based Reconstruction Algorithm With Lung Enhancement Filter for Chest CT: Effect on Image Quality and Ground Glass Nodule Sharpness. Korean Journal of Radiology, 25(9), 833. https://doi.org/10.3348/kjr.2024.0472
Jiang, J.-M., Miao, L., Liang, X., Liu, Z.-H., Zhang, L., & Li, M. (2022). The Value of Deep Learning Image Reconstruction in Improving the Quality of Low-Dose Chest CT Images. Diagnostics, 12(10), 2560. https://doi.org/10.3390/diagnostics12102560
Jung, Y., Hur, J., Han, K., Imai, Y., Hong, Y. J., Im, D. J., Lee, K. H., Desnoyers, M., Thomsen, B., Shigemasa, R., Um, K., & Jang, K. (2023a). Radiation dose reduction using deep learning-based image reconstruction for a low-dose chest computed tomography protocol: A phantom study. Quantitative Imaging in Medicine and Surgery, 13(3), 1937–1947. https://doi.org/10.21037/qims-22-618
Jung, Y., Hur, J., Han, K., Imai, Y., Hong, Y. J., Im, D. J., Lee, K. H., Desnoyers, M., Thomsen, B., Shigemasa, R., Um, K., & Jang, K. (2023b). Radiation dose reduction using deep learning-based image reconstruction for a low-dose chest computed tomography protocol: A phantom study. Quantitative Imaging in Medicine and Surgery, 13(3), 1937–1947. https://doi.org/10.21037/qims-22-618
Kim, W., Jeon, S.-Y., Byun, G., Yoo, H., & Choi, J.-H. (2024). A systematic review of deep learning-based denoising for low-dose computed tomography from a perceptual quality perspective. Biomedical Engineering Letters, 14(6), 1153–1173. https://doi.org/10.1007/s13534-024-00419-7
Koetzier, L. R., Mastrodicasa, D., Szczykutowicz, T. P., Van Der Werf, N. R., Wang, A. S., Sandfort, V., Van Der Molen, A. J., Fleischmann, D., & Willemink, M. J. (2023). Deep Learning Image Reconstruction for CT: Technical Principles and Clinical Prospects. Radiology, 306(3), e221257. https://doi.org/10.1148/radiol.221257
Lee, K. B., & Goo, H. W. (2018). Quantitative Image Quality and Histogram-Based Evaluations of an Iterative Reconstruction Algorithm at Low-to-Ultralow Radiation Dose Levels: A Phantom Study in Chest CT. Korean Journal of Radiology, 19(1), 119. https://doi.org/10.3348/kjr.2018.19.1.119
Otgonbaatar, C., Jeon, S.-H., Cha, S.-J., Shim, H., Kim, J. W., & Ahn, J.-H. (2025). Image quality and radiation dose of reduced-dose abdominopelvic computed tomography (CT) with silver filter and deep learning reconstruction. Scientific Reports, 15(1), 25757. https://doi.org/10.1038/s41598-025-11184-7
Sadia, R. T., Chen, J., & Zhang, J. (2024). CT image denoising methods for image quality improvement and radiation dose reduction. Journal of Applied Clinical Medical Physics, 25(2), e14270. https://doi.org/10.1002/acm2.14270
Shim, J., Lee, Y., & Kim, K. (2025a). Quantitative Evaluation of Low-Dose CT Image Quality Using Deep Learning Reconstruction: A Comparative Study of Philips Precise Image and GE TrueFidelity. Journal of Imaging, 11(9), 317. https://doi.org/10.3390/jimaging11090317
Shim, J., Lee, Y., & Kim, K. (2025b). Quantitative Evaluation of Low-Dose CT Image Quality Using Deep Learning Reconstruction: A Comparative Study of Philips Precise Image and GE TrueFidelity. Journal of Imaging, 11(9), 317. https://doi.org/10.3390/jimaging11090317
Suliman, I. I., Khouqeer, G. A., Ahmed, N. A., Abuzaid, M. M., & Sulieman, A. (2023). Low-Dose Chest CT Protocols for Imaging COVID-19 Pneumonia: Technique Parameters and Radiation Dose. Life, 13(4), 992. https://doi.org/10.3390/life13040992
Szczykutowicz, T. P., Toia, G. V., Dhanantwari, A., & Nett, B. (2022). A Review of Deep Learning CT Reconstruction: Concepts, Limitations, and Promise in Clinical Practice. Current Radiology Reports, 10(9), 101–115. https://doi.org/10.1007/s40134-022-00399-5
