Boundary information‐guided adversarial diffusion model for efficient unsupervised synthetic CT generation

Medical Physics, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 28, 2025

Abstract Background The absence of tissue electron density information derived from greyscale Hounsfield units (HUs) in magnetic resonance imaging (MRI) limits its further clinical application radiotherapy (RT). use synthetic computed tomography (sCT) with MRI simplifies RT treatment and improves positioning accuracy by eliminating the need for (CT) simulation radiation dose error‐prone image registration. Although CycleGAN variants can obtain verisimilar sCT through unsupervised learning, ensuring perfect structural consistency synthesized images this approach remains challenging, thus limiting quality diversity a given application. Purpose purpose work is to develop novel boundary information‐guided adversarial diffusion model, called RadADM, aim enhancing performance regard unpaired MR‐to‐CT translation MR‐only RT. Methods In order explicitly guide feature learning proposed RadADM mask incorporated as guidance anatomy compensation during generation simulated MR images. addition, cycle‐consistent module incorporates projections featuring coupled diffusive non‐diffusive architecture used facilitate training on MR‐CT datasets, enabling accurate efficient between source target domain To validate we conducted comprehensive quantitative qualitative comparison other state‐of‐the‐art methods, including CycleGAN, CycleSlimulationGAN, CUT, Fixed Learned Self‐Similarity (F‐LseSim), SynDiff. Results We evaluated demonstrated that outperforms comparative approaches high‐quality pelvic captures local features, achieves smaller errors mean absolute error (MAE): 62.95 ± 23.15 root square (RMSE): 135.46 23.89 higher similarities peak signal‐to‐noise ratio (PSNR): 24.70 0.52, similarity index (SSIM): 0.8673 0.01. For region soft‐tissue, PSNR SSIM were 33.99 1.09 0.931 0.01, bone, 35.79 0.87 0.993 0.04. Conclusions Extensive experiments datasets demonstrate effectiveness robustness our terms synthesizing at anatomical level. Our found offer valuable promising direction adaptive cancer.

Language: Английский

---

Magnetic resonance imaging with ultra-short echo time sequence for head and neck radiotherapy planning

Physica Medica, Journal Year: 2025, Volume and Issue: 133, P. 104974 - 104974

Published: April 9, 2025

Language: Английский

---

Enhancing Inter-AUV Perception: Adaptive 6-DOF Pose Estimation with Synthetic Images for AUV Swarm Sensing

Drones, Journal Year: 2024, Volume and Issue: 8(9), P. 486 - 486

Published: Sept. 14, 2024

The capabilities of AUV mutual perception and localization are crucial for the development swarm systems. We propose AUV6D model, a synthetic image-based approach to enhance inter-AUV through 6D pose estimation. Due challenge acquiring accurate data, dataset simulated underwater images with precise labels was generated using Unity3D. Mask-CycleGAN technology introduced transform these into realistic images, addressing scarcity available data. Furthermore, Color Intermediate Domain Mapping strategy is proposed ensure alignment across different image styles at pixel feature levels, enhancing adaptability estimation model. Additionally, Salient Keypoint Vector Voting Mechanism developed improve accuracy robustness estimation, enabling even in presence occlusions. experimental results demonstrated that our model achieved millimeter-level precision errors within five degrees, showing exceptional performance complex environments. Navigation experiments two AUVs further verified model’s reliability This research provides substantial technical support more collaborative operations swarms future.

Language: Английский

---

Research on Automated Choreography and Real-time Adjustment of Cheerleading Performance Based on Artificial Intelligence

Applied Mathematics and Nonlinear Sciences, Journal Year: 2024, Volume and Issue: 9(1)

Published: Jan. 1, 2024

Abstract The automated choreography of dance movements is a new field combining artificial intelligence and performance, which has important research value. In this paper, Transformer-based cheerleading automatic real-time adjustment algorithm are proposed, generates consistent with the music rhythm by stacking multi-layer bidirectional cross-attention layers introduces an for according to phrases emotions phrases. experimental results show that matching accuracy score 4.33, 0.95 points higher than manual matching, 80.76% judges think overall effect exercise generated better comparison algorithm. This paper’s good results, as evidenced results.

Language: Английский

---

Multi-Sequence Fusion Network via Single- Sequence CycleGANs for Improved Synthetic CT in Nasopharyngeal Carcinoma Treatment Planning

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 71433 - 71441

Published: Jan. 1, 2024

Language: Английский

---

Enhanced fully convolutional network based on external attention for low-dose CT denoising

Published: June 13, 2024

Language: Английский

---