Deep-learning-based Attenuation Correction for 68 Ga-DOTATATE Whole-body PET Imaging: A Dual-center Clinical Study.

Autor: Lord MS; Tabriz University of Medical Sciences School of Medicine, Department of Medical Physics, Tabriz, Iran., Islamian JP; Tabriz University of Medical Sciences School of Medicine, Department of Medical Physics, Tabriz, Iran., Seyyedi N; Iran University of Medical Sciences, Nursing and Midwifery Care Research Center, Tehran, Iran., Samimi R; Shahid Beheshti University, Department of Medical Radiation Engineering, Tehran, Iran., Farzanehfar S; Tehran University of Medical Sciences Faculty of Medicine, Imam Khomeini Hospital Complex, Department of Nuclear Medicine, Tehran, Iran., Shahrbabki M; Tehran University of Medical Sciences Faculty of Medicine, Department of Medical Physics and Biomedical Engineering, Tehran, Iran., Sheikhzadeh P; Tehran University of Medical Sciences Faculty of Medicine, Imam Khomeini Hospital Complex, Department of Nuclear Medicine, Tehran, Iran.; Tehran University of Medical Sciences Faculty of Medicine, Department of Medical Physics and Biomedical Engineering, Tehran, Iran.
Jazyk: angličtina
Zdroj: Molecular imaging and radionuclide therapy [Mol Imaging Radionucl Ther] 2024 Oct 07; Vol. 33 (3), pp. 138-146.
DOI: 10.4274/mirt.galenos.2024.86422
Abstrakt: Objectives: Attenuation correction is a critical phenomenon in quantitative positron emission tomography (PET) imaging with its own special challenges. However, computed tomography (CT) modality which is used for attenuation correction and anatomical localization increases patient radiation dose. This study was aimed to develop a deep learning model for attenuation correction of whole-body 68 Ga-DOTATATE PET images.
Methods: Non-attenuation-corrected and computed tomography-based attenuation-corrected (CTAC) whole-body 68 Ga-DOTATATE PET images of 118 patients from two different imaging centers were used. We implemented a residual deep learning model using the NiftyNet framework. The model was trained four times and evaluated six times using the test data from the centers. The quality of the synthesized PET images was compared with the PET-CTAC images using different evaluation metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), mean square error (MSE), and root mean square error (RMSE).
Results: Quantitative analysis of four network training sessions and six evaluations revealed the highest and lowest PSNR values as (52.86±6.6) and (47.96±5.09), respectively. Similarly, the highest and lowest SSIM values were obtained (0.99±0.003) and (0.97±0.01), respectively. Additionally, the highest and lowest RMSE and MSE values fell within the ranges of (0.0117±0.003), (0.0015±0.000103), and (0.01072±0.002), (0.000121±5.07xe -5 ), respectively. The study found that using datasets from the same center resulted in the highest PSNR, while using datasets from different centers led to lower PSNR and SSIM values. In addition, scenarios involving datasets from both centers achieved the best SSIM and the lowest MSE and RMSE.
Conclusion: Acceptable accuracy of attenuation correction on 68 Ga-DOTATATE PET images using a deep learning model could potentially eliminate the need for additional X-ray imaging modalities, thereby imposing a high radiation dose on the patient.
Competing Interests: Conflict of Interest: No conflict of interest was declared by the authors.
(Copyright© 2024 The Author. Published by Galenos Publishing House on behalf of the Turkish Society of Nuclear Medicine.)
Databáze: MEDLINE
Externí odkaz: