Ủ mô phỏng kết hợp với giảm thiểu lỗi spin cải thiện độ chính xác tái tạo CT, đạt được tái tạo chính xác trong các sinogram bị hỏng có góc nhìn thưa thớt trong khi mở rộng quy mô đến các bài toán 100.000+ biến.
#LượngtửHìnhảnh #LượngtửTốiưuHóa #TáitạoCT
#LượngtửHìnhảnh #LượngtửTốiưuHóa #TáitạoCT
Tái tạo CT Lấy cảm hứng Lượng tử Qua Mở rộng Giảm thiểu Lỗi Spin
arxiv.org
October 27, 2026 at 6:40 AM
Ủ mô phỏng kết hợp với giảm thiểu lỗi spin cải thiện độ chính xác tái tạo CT, đạt được tái tạo chính xác trong các sinogram bị hỏng có góc nhìn thưa thớt trong khi mở rộng quy mô đến các bài toán 100.000+ biến.
#LượngtửHìnhảnh #LượngtửTốiưuHóa #TáitạoCT
#LượngtửHìnhảnh #LượngtửTốiưuHóa #TáitạoCT
Self-supervised missing-wedge correction enables accurate cellular morphology and volume reconstruction in soft X-ray tomography
Self-supervised missing-wedge correction enables accurate cellular morphology and volume reconstruction in soft X-ray tomography
Chueh et al. present a self-supervised sinogram inpainting framework to correct missing-wedge artifacts in soft X-ray tomography. By recovering unrecorded projection angles without ground-truth data, the model effectively restores cellular morphology and improves the volumetric quantification of complex structures like malaria hemozoin crystals.
dlvr.it
September 28, 2026 at 6:49 PM
Self-supervised missing-wedge correction enables accurate cellular morphology and volume reconstruction in soft X-ray tomography
Yuejie Liu, Alessandro Lupoli, David Uribe Gallo, Andreas Fischer, Felix Krahmer: Informed Sinogram Interpolation for Sparse View Reconstruction https://arxiv.org/abs/2609.18415 https://arxiv.org/pdf/2609.18415 https://arxiv.org/html/2609.18415
September 17, 2026 at 6:45 AM
Yuejie Liu, Alessandro Lupoli, David Uribe Gallo, Andreas Fischer, Felix Krahmer: Informed Sinogram Interpolation for Sparse View Reconstruction https://arxiv.org/abs/2609.18415 https://arxiv.org/pdf/2609.18415 https://arxiv.org/html/2609.18415
Shi, Pelt and Batenburg: Multi-stage deep learning artifact reduction for parallel-beam computed tomography ##ArtifactReduction##DeepLearning##ComputedTomography@UniLeiden...##IUCrhttps://journals.iucr.org/paper?S1600577525000359
Multi-stage deep learning artifact reduction for parallel-beam computed tomography
An illustration of the synchrotron-based computed tomography pipeline is given, highlighting the three key processing stages — projection, sinogram and reconstruction — each incorporating multiple processing steps to enhance image quality.
journals.iucr.org
February 18, 2025 at 1:01 AM
Shi, Pelt and Batenburg: Multi-stage deep learning artifact reduction for parallel-beam computed tomography ##ArtifactReduction##DeepLearning##ComputedTomography@UniLeiden...##IUCrhttps://journals.iucr.org/paper?S1600577525000359
Ugh ... 🧐
(Unicode has 𭨐. Apparently something in an entirely different script ["西土字"] that turned into a quasi-sinogram?)
< 佛祖統紀 @ dl.ndl.go.jp/pid/2559763/...
(Unicode has 𭨐. Apparently something in an entirely different script ["西土字"] that turned into a quasi-sinogram?)
< 佛祖統紀 @ dl.ndl.go.jp/pid/2559763/...
September 19, 2025 at 8:27 PM
Ugh ... 🧐
(Unicode has 𭨐. Apparently something in an entirely different script ["西土字"] that turned into a quasi-sinogram?)
< 佛祖統紀 @ dl.ndl.go.jp/pid/2559763/...
(Unicode has 𭨐. Apparently something in an entirely different script ["西土字"] that turned into a quasi-sinogram?)
< 佛祖統紀 @ dl.ndl.go.jp/pid/2559763/...
Rautio, Meaney, Latva-\o, Agrawal, Brix, Jayakody, Siltanen: Complex Wavelet-Based Sinogram Segmentation for Metal Artifact Reduction in Cone-Beam CT https://arxiv.org/abs/2602.14315 https://arxiv.org/pdf/2602.14315 https://arxiv.org/html/2602.14315
February 17, 2026 at 6:48 AM
Rautio, Meaney, Latva-\o, Agrawal, Brix, Jayakody, Siltanen: Complex Wavelet-Based Sinogram Segmentation for Metal Artifact Reduction in Cone-Beam CT https://arxiv.org/abs/2602.14315 https://arxiv.org/pdf/2602.14315 https://arxiv.org/html/2602.14315
Liyang Hu, Chong Chen: An efficient approach with theoretical guarantees to simultaneously reconstruct activity and attenuation sinogram for TOF-PET https://arxiv.org/abs/2510.13562 https://arxiv.org/pdf/2510.13562 https://arxiv.org/html/2510.13562
October 16, 2025 at 6:48 AM
Liyang Hu, Chong Chen: An efficient approach with theoretical guarantees to simultaneously reconstruct activity and attenuation sinogram for TOF-PET https://arxiv.org/abs/2510.13562 https://arxiv.org/pdf/2510.13562 https://arxiv.org/html/2510.13562
diffusion models. Such methods train a diffusion model (without sinogram data) on high-quality, but still noisy, PET images. In this work, we propose a simple method for generating subject-specific PET images from a dataset of multi-subject PET-MR [2/7 of https://arxiv.org/abs/2506.03804v1]
June 5, 2025 at 6:14 AM
diffusion models. Such methods train a diffusion model (without sinogram data) on high-quality, but still noisy, PET images. In this work, we propose a simple method for generating subject-specific PET images from a dataset of multi-subject PET-MR [2/7 of https://arxiv.org/abs/2506.03804v1]
removal in sinogram images was proposed. The proposed method classifies ring artifacts into single stripes and multiple stripes, which were identified and eliminated using median filtering and multiphase decomposition, respectively. A novel algorithm [3/5 of https://arxiv.org/abs/2505.19513v1]
May 27, 2025 at 6:14 AM
removal in sinogram images was proposed. The proposed method classifies ring artifacts into single stripes and multiple stripes, which were identified and eliminated using median filtering and multiphase decomposition, respectively. A novel algorithm [3/5 of https://arxiv.org/abs/2505.19513v1]
Zou, Qi, Zhang, Zhang, Wang, Zhang, Yao, Jiang: Ring artifacts correction method in x-ray computed tomography based on stripe classification and removal in sinogram images https://arxiv.org/abs/2505.19513 https://arxiv.org/pdf/2505.19513 https://arxiv.org/html/2505.19513
May 27, 2025 at 6:14 AM
Zou, Qi, Zhang, Zhang, Wang, Zhang, Yao, Jiang: Ring artifacts correction method in x-ray computed tomography based on stripe classification and removal in sinogram images https://arxiv.org/abs/2505.19513 https://arxiv.org/pdf/2505.19513 https://arxiv.org/html/2505.19513
optimizer enabling execution on a mashed TOF sinogram in 12 minutes on six-core CPU. The proposed method enhances both the accuracy and computational efficiency of EBSE, making it well-suited for clinical applications. [8/8 of https://arxiv.org/abs/2504.15969v1]
April 23, 2025 at 6:14 AM
optimizer enabling execution on a mashed TOF sinogram in 12 minutes on six-core CPU. The proposed method enhances both the accuracy and computational efficiency of EBSE, making it well-suited for clinical applications. [8/8 of https://arxiv.org/abs/2504.15969v1]
April 17, 2025 at 5:51 PM
March 9, 2025 at 1:26 PM
March 1, 2025 at 2:50 PM
NOTABLE ARTICLE, June 2026 #MedicalPhysics: Sinogram‐based flow estimation in computed tomography using a physics‐informed neural network: Impact of gantry rotation speed, X‐ray fluence & pulsed acquisition on accuracy
https://ow.ly/tJi850ZwCuu
Please join us in congratulating Jinyuxuan Guo et al
https://ow.ly/tJi850ZwCuu
Please join us in congratulating Jinyuxuan Guo et al
August 5, 2026 at 6:01 PM
NOTABLE ARTICLE, June 2026 #MedicalPhysics: Sinogram‐based flow estimation in computed tomography using a physics‐informed neural network: Impact of gantry rotation speed, X‐ray fluence & pulsed acquisition on accuracy
https://ow.ly/tJi850ZwCuu
Please join us in congratulating Jinyuxuan Guo et al
https://ow.ly/tJi850ZwCuu
Please join us in congratulating Jinyuxuan Guo et al
Farhan Sadik, Christopher L. Newman, Stuart J. Warden, Rachel K. Surowiec: Simulating Sinogram-Domain Motion and Correcting Image-Domain Artifacts Using Deep Learning in HR-pQCT Bone Imaging https://arxiv.org/abs/2509.10961 https://arxiv.org/pdf/2509.10961 https://arxiv.org/html/2509.10961
September 16, 2025 at 6:30 AM
Farhan Sadik, Christopher L. Newman, Stuart J. Warden, Rachel K. Surowiec: Simulating Sinogram-Domain Motion and Correcting Image-Domain Artifacts Using Deep Learning in HR-pQCT Bone Imaging https://arxiv.org/abs/2509.10961 https://arxiv.org/pdf/2509.10961 https://arxiv.org/html/2509.10961
Xingyu Ai, Shaoyu Wang, Zhiyuan Jia, Ao Xu, Hongming Shan, Jianhua Ma, Qiegen Liu: UniSino: Physics-Driven Foundational Model for Universal CT Sinogram Standardization https://arxiv.org/abs/2508.17816 https://arxiv.org/pdf/2508.17816 https://arxiv.org/html/2508.17816
August 26, 2025 at 6:32 AM
Xingyu Ai, Shaoyu Wang, Zhiyuan Jia, Ao Xu, Hongming Shan, Jianhua Ma, Qiegen Liu: UniSino: Physics-Driven Foundational Model for Universal CT Sinogram Standardization https://arxiv.org/abs/2508.17816 https://arxiv.org/pdf/2508.17816 https://arxiv.org/html/2508.17816
post-processing module back-projects the inpainted sinogram into the image domain and further refines the reconstruction, effectively suppressing artifacts while preserving critical structural details. Quantitative experimental results demonstrate [4/5 of https://arxiv.org/abs/2505.19385v1]
May 27, 2025 at 6:27 AM
post-processing module back-projects the inpainted sinogram into the image domain and further refines the reconstruction, effectively suppressing artifacts while preserving critical structural details. Quantitative experimental results demonstrate [4/5 of https://arxiv.org/abs/2505.19385v1]
combining distillation with constraining the output of the model using the pseudo-inverse of the inpainting matrix, the diffusion process is accelerated and done in a step, enabling efficient and accurate sinogram completion. A subsequent [3/5 of https://arxiv.org/abs/2505.19385v1]
May 27, 2025 at 6:27 AM
combining distillation with constraining the output of the model using the pseudo-inverse of the inpainting matrix, the diffusion process is accelerated and done in a step, enabling efficient and accurate sinogram completion. A subsequent [3/5 of https://arxiv.org/abs/2505.19385v1]
focuses on sinogram inpainting. We leverage MR-SDEs, a variant of diffusion models that characterize the diffusion process with mean-reverting stochastic differential equations, to fill in missing angular data at the projection level. Furthermore, by [2/5 of https://arxiv.org/abs/2505.19385v1]
May 27, 2025 at 6:27 AM
focuses on sinogram inpainting. We leverage MR-SDEs, a variant of diffusion models that characterize the diffusion process with mean-reverting stochastic differential equations, to fill in missing angular data at the projection level. Furthermore, by [2/5 of https://arxiv.org/abs/2505.19385v1]
Jiaqi Guo, Santiago Lopez-Tapia, Aggelos K. Katsaggelos: Advancing Limited-Angle CT Reconstruction Through Diffusion-Based Sinogram Completion https://arxiv.org/abs/2505.19385 https://arxiv.org/pdf/2505.19385 https://arxiv.org/html/2505.19385
May 27, 2025 at 6:27 AM
Jiaqi Guo, Santiago Lopez-Tapia, Aggelos K. Katsaggelos: Advancing Limited-Angle CT Reconstruction Through Diffusion-Based Sinogram Completion https://arxiv.org/abs/2505.19385 https://arxiv.org/pdf/2505.19385 https://arxiv.org/html/2505.19385
optimized non-linear extension of the Radon transform, generates sinogram representations to capture complex retinal lesion patterns. By leveraging both spatial and transformed domain information, RadFuse enriches the feature set available to deep [4/8 of https://arxiv.org/abs/2504.15883v1]
April 23, 2025 at 6:03 AM
optimized non-linear extension of the Radon transform, generates sinogram representations to capture complex retinal lesion patterns. By leveraging both spatial and transformed domain information, RadFuse enriches the feature set available to deep [4/8 of https://arxiv.org/abs/2504.15883v1]
study introduces RadFuse, a multi-representation deep learning framework that integrates non-linear RadEx-transformed sinogram images with traditional fundus images to enhance diabetic retinopathy detection and grading. Our RadEx transformation, an [3/8 of https://arxiv.org/abs/2504.15883v1]
April 23, 2025 at 6:03 AM
study introduces RadFuse, a multi-representation deep learning framework that integrates non-linear RadEx-transformed sinogram images with traditional fundus images to enhance diabetic retinopathy detection and grading. Our RadEx transformation, an [3/8 of https://arxiv.org/abs/2504.15883v1]
mask-driven latent space is de-signed to accelerate the diffusion process by leveraging sinogram-driven and mask-driven compact priors, which reduce computational complexity while preserving essen-tial data characteristics. A hierarchical masking [5/8 of https://arxiv.org/abs/2503.08339v1]
March 12, 2025 at 6:02 AM
mask-driven latent space is de-signed to accelerate the diffusion process by leveraging sinogram-driven and mask-driven compact priors, which reduce computational complexity while preserving essen-tial data characteristics. A hierarchical masking [5/8 of https://arxiv.org/abs/2503.08339v1]
(DREAM). To the best of our knowledge, this is the first work to integrate mask mechanisms into both the sinogram domain and the latent space, pioneering their role in PET reconstruction and demonstrating their ability to enhance reconstruction [3/8 of https://arxiv.org/abs/2503.08339v1]
March 12, 2025 at 6:02 AM
(DREAM). To the best of our knowledge, this is the first work to integrate mask mechanisms into both the sinogram domain and the latent space, pioneering their role in PET reconstruction and demonstrating their ability to enhance reconstruction [3/8 of https://arxiv.org/abs/2503.08339v1]