Academic Journal
Accurate CT-free correction of attenuation, scatter, and aperture effects using deep learning in dedicated cardiac pinhole SPECT.
| Τίτλος: | Accurate CT-free correction of attenuation, scatter, and aperture effects using deep learning in dedicated cardiac pinhole SPECT. |
|---|---|
| Συγγραφείς: | Inaba S; Graduate School of Science and Engineering, Hosei University, 3-7-2 Kajinocho, Koganei, 184-8584, Tokyo, Japan., Nawano Y; Graduate School of Science and Engineering, Hosei University, 3-7-2 Kajinocho, Koganei, 184-8584, Tokyo, Japan., Ogawa K; Graduate School of Science and Engineering, Hosei University, 3-7-2 Kajinocho, Koganei, 184-8584, Tokyo, Japan. ogawa@hosei.ac.jp. |
| Πηγή: | Annals of nuclear medicine [Ann Nucl Med] 2026 Jul; Vol. 40 (7), pp. 795-803. Date of Electronic Publication: 2026 Mar 09. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Springer Japan Country of Publication: Japan NLM ID: 8913398 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1864-6433 (Electronic) Linking ISSN: 09147187 NLM ISO Abbreviation: Ann Nucl Med Subsets: MEDLINE |
| Imprint Name(s): | Publication: Tokyo, Japan : Springer Japan Original Publication: Tokyo, Japan : Japanese Society of Nuclear Medicine, [1987- |
| Ιατρικοί όροι (MeSH): | Image Processing, Computer-Assisted*/methods , Heart*/diagnostic imaging , Tomography, Emission-Computed, Single-Photon*/instrumentation , Scattering, Radiation* , Deep Learning* , Tomography, X-Ray Computed*, Humans ; Convolutional Neural Networks |
| Περίληψη: | OBJECTIVE: In dedicated cardiac SPECT systems, attenuation correction using X-ray CT images is often difficult to perform. This study aimed to improve image quality and achieve quantitative image reconstruction for a dedicated cardiac SPECT system equipped with pinhole collimators. METHODS: A pinhole geometry simulating the detector configuration of the Discovery NM 530c system was employed. Using this geometry, the attenuation coefficient distribution (µ-map) and the projection data of scattered photons were estimated. Attenuation, scatter, and pinhole aperture blurring were corrected using convolutional neural networks (CNNs). For µ-map estimation, reconstructed images from projection data acquired in two low-energy windows were used as CNN inputs, and the µ-map at 140 keV was used as the reference data. For scatter estimation, the CNN was trained using projection data including both attenuation and scatter effects, and data including only attenuation effects. The supervised data were projection data of scattered photons that considered attenuation. For aperture correction, projection data containing pinhole aperture blurring were used as inputs, and projection data calculated by a ray-tracing method served as reference data. A total of 269 image datasets were used for µ-map estimation and 5111 projection datasets were used for scatter estimation and aperture correction. All projection data required for these corrections were generated using Monte Carlo photon transport simulations. The reconstructed SPECT images corrected by the proposed CNN-based method without µ-maps were compared with those obtained by a conventional model-based method using known µ-maps, based on the normalized mean squared error (NMSE), structural similarity index (SSIM), and polar maps. RESULTS: Simulation results showed that the NMSE(%) of SPECT images decreased from 9.22 ± 3.36 (conventional) to 4.62 ± 1.37 (proposed) and the SSIM of SPECT images increased from 0.816 ± 0.048 (conventional) to 0.910 ± 0.029 (proposed). CONCLUSIONS: We developed a CNN-based method for attenuation, scatter, and aperture correction without using µ-maps in a dedicated cardiac pinhole SPECT system. The simulation results demonstrated the feasibility and effectiveness of the proposed method for improving quantitative image reconstruction. |
| Competing Interests: | Declarations. Conflict of interest: The authors declare no potential conflicts of interest. |
| References: | Bocher M, Blevis IM, Tsukerman L, Shrem Y, Kovalski G, Volokh L. A fast cardiac gamma camera with dynamic SPECT capabilities: design, system validation and future potential. Eur J Nucl Med Mol Imaging. 2010;37(10):1887–902. (PMID: 10.1007/s00259-010-1488-z205857752933031) Erlandsson K, Kacperski K, van Gramberg D, Hutton BF. Performance evaluation of D-SPECT: a novel SPECT system for nuclear cardiology. Phys Med Biol. 2009;54(9):2635–49. (PMID: 10.1088/0031-9155/54/9/00319351981) Hawman PC, Haines EJ. The cardiofocal collimator: a variable-focus collimator for cardiac SPECT. Phys Med Biol. 1994;39(3):439–50. (PMID: 10.1088/0031-9155/39/3/01115551592) Xiao J, Verzijlbergen FJ, Viergever MA, Beekman FJ. Small field-of-view dedicated cardiac SPECT systems: impact of projection truncation. Eur J Nucl Med Mol Imaging. 2010;37(3):528–36. (PMID: 10.1007/s00259-009-1223-919722106) Chen X, Zhou B, Xie H, Shi L, Liu H, Holler W, et al. Direct and indirect strategies of deep-learning-based attenuation correction for general purpose and dedicated cardiac SPECT. Eur J Nucl Med Mol Imaging. 2022;49(9):3046–60. (PMID: 10.1007/s00259-022-05718-8351698879253078) Yang P, Zhang Z, Wei J, Jiang L, Yu L, Cai H, et al. Deep learning-based CT-free attenuation correction for cardiac SPECT: a new approach. BMC Med Imaging. 2025;25(1):38. (PMID: 10.1186/s12880-025-01570-y3990532011796265) Shi L, Onofrey JA, Liu H, Liu YH, Liu C. Deep learning-based attenuation map generation for myocardial perfusion SPECT. Eur J Nucl Med Mol Imaging. 2020;47(10):2383–95. (PMID: 10.1007/s00259-020-04746-632219492) Huxohl T, Patel G, Zabel R, Burchert W. Deep learning approximation of attenuation maps for myocardial perfusion SPECT with an IQ・SPECT collimator. Eur J Nucl Med Mol Imag Phy. 2023;10(1):49. Ogawa K, Harata Y, Ichihara T, Kubo A, Hashimoto S. A practical method for position-dependent Compton-scatter correction in single photon emission CT. IEEE Trans Med Imag. 1991;10(3):408–12. (PMID: 10.1109/42.97591) Slomka PJ, Miller RJH, Hu LH, Germano G, Berman DS. Solid-state detector SPECT myocardial perfusion imaging. J Nucl Med. 2019;60(9):1194–204. (PMID: 10.2967/jnumed.118.22065731375568) Kim H, Li Z, Son J, Fessler JA, Dewaraja YK, Chun SY. Physics-guided deep scatter estimation by weak supervision for quantitative SPECT. IEEE Trans Med Imaging. 2023;42(10):2961–73. (PMID: 10.1109/TMI.2023.32708683710411010593395) Chan C, Dey J, Grobshtein Y, Wu J, Liu YH, Lampert R, et al. The impact of system matrix dimension on small FOV SPECT reconstruction with truncated projections. Med Phys. 2016;43(1):213–24. (PMID: 10.1118/1.4938098267459144691252) Garduno E, Herman GT. Superiorization of the ML-EM algorithm. IEEE Trans Nucl Sci. 2013;61(1):162–72. (PMID: 10.1109/TNS.2013.2283529) Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Inter Conf Med Imag Comput Comput assist Interv (MICCAI). 2015;9351:234 – 41. Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. Inter Conf Med Imag Comput Comput assist Interv (MICCAI). 2016;9901:424–32. Manglos SH, Thomas FD, Capone RB. Attenuation compensation of cone beam SPECT images using maximum likelihood reconstruction. IEEE Trans Med Imaging. 1991;10(1):66–73. (PMID: 10.1109/42.7561218222801) de Bourbon Q, Klein R. Synthetic lesions in real FDG PET images [Data set]. Kaggle. 2024. Kinahan P, Muzi M, Bialecki B, Herman B, Coombs L. Data from the ACRIN 6668 Trial NSCLC-FDG-PET (Version 2) [Dataset]. The Cancer Imaging Archive; 2019. LaCroix KJ. Evaluation of an attenuation compensation method with respect to defect detection in Tc-99mMIBI myocardial SPECT images. [dissertation] The University of North Carolina at Chapel Hill, Chapel Hill (NC), 1997. Berger MJ, Hubbell JH, Seltzer SM, Chang J, Coursey JS, Sukmar R et al. XCOM: Photon Cross Sections Database. NIST Standard Ref Database 8 (XGAM), 1987. Hirayama H, Namito Y, Bielajew AF, Wilderman SJ, Nelson WR. The EGS5 Code System. High Energy Accelerator Research Organization (KEK); 2005. (PMID: 10.2172/877459) Yagi S, Usui K, Ogawa K. Scatter and beam hardening effect corrections in pelvic region cone-beam CT images using a convolutional neural network. Radiol Phys Technol. 2025;18:457–68. (PMID: 10.1007/s12194-025-00896-040183875) He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. IEEE Inter Conf Comput Vis (ICCV) 2015;1026–34. Vanhove C, Andreyev A, Defrise M, Nuyts J, Bossuyt A. Resolution recovery in pinhole SPECT based on multi-ray projections: a phantom study. Eur J Nucl Med Mol Imaging. 2007;34(2):170–80. (PMID: 10.1007/s00259-006-0225-016953400) |
| Contributed Indexing: | Keywords: Attenuation correction; Cardiac pinhole SPECT; Convolutional neural network; Monte Carlo simulation; Scatter correction |
| Entry Date(s): | Date Created: 20260309 Date Completed: 20260627 Latest Revision: 20260627 |
| Update Code: | 20260627 |
| DOI: | 10.1007/s12149-026-02187-z |
| PMID: | 41801662 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1864-6433 |
|---|---|
| DOI: | 10.1007/s12149-026-02187-z |