Improving Cone-Beam CT Image Quality with Knowledge Distillation-Enhanced Diffusion Model in Imbalanced Data Settings

• URL: http://arxiv.org/abs/2409.12539v1
• Date: Thu, 19 Sep 2024 07:56:06 GMT
• Title: Improving Cone-Beam CT Image Quality with Knowledge Distillation-Enhanced Diffusion Model in Imbalanced Data Settings
• Authors: Joonil Hwang, Sangjoon Park, NaHyeon Park, Seungryong Cho, Jin Sung Kim,
• Abstract summary: Daily cone-beam CT (CBCT) imaging, pivotal for therapy adjustment, falls short in tissue density accuracy. We maximize CBCT data during therapy, complemented by sparse paired fan-beam CTs. Our approach shows promise in generating high-quality CT images from CBCT scans in RT.
• Score: 6.157230849293829
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In radiation therapy (RT), the reliance on pre-treatment computed tomography (CT) images encounter challenges due to anatomical changes, necessitating adaptive planning. Daily cone-beam CT (CBCT) imaging, pivotal for therapy adjustment, falls short in tissue density accuracy. To address this, our innovative approach integrates diffusion models for CT image generation, offering precise control over data synthesis. Leveraging a self-training method with knowledge distillation, we maximize CBCT data during therapy, complemented by sparse paired fan-beam CTs. This strategy, incorporated into state-of-the-art diffusion-based models, surpasses conventional methods like Pix2pix and CycleGAN. A meticulously curated dataset of 2800 paired CBCT and CT scans, supplemented by 4200 CBCT scans, undergoes preprocessing and teacher model training, including the Brownian Bridge Diffusion Model (BBDM). Pseudo-label CT images are generated, resulting in a dataset combining 5600 CT images with corresponding CBCT images. Thorough evaluation using MSE, SSIM, PSNR and LPIPS demonstrates superior performance against Pix2pix and CycleGAN. Our approach shows promise in generating high-quality CT images from CBCT scans in RT.

Related papers

• HC$^3$L-Diff: Hybrid conditional latent diffusion with high frequency enhancement for CBCT-to-CT synthesis [10.699377597641137]
  We propose a novel conditional latent diffusion model for efficient CBCT-to-CT synthesis. We employ the Unified Feature (UFE) to compress images into a low-dimensional latent space. Our method can efficiently achieve high-quality CBCT-to-CT synthesis in only over 2 mins per patient.
  arXiv  Detail & Related papers  (2024-11-03T14:00:12Z)
• SinoSynth: A Physics-based Domain Randomization Approach for Generalizable CBCT Image Enhancement [19.059201978992064]
  Cone Beam Computed Tomography (CBCT) finds diverse applications in medicine. The susceptibility of CBCT images to noise and artifacts undermines both their usefulness and reliability. We present Sino Synth, a physics-based degradation model that simulates various CBCT-specific artifacts to generate a diverse set of synthetic CBCT images.
  arXiv  Detail & Related papers  (2024-09-27T00:22:02Z)
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction [83.73429628413773]
  Supervised deep learning methods have shown the ability to remove noise in images but require accurate ground truth. We propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN) Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented Noise2Inverse (RAN2I) method keeps better image quality over a different range of sampling angles.
  arXiv  Detail & Related papers  (2023-12-19T22:40:51Z)
• A multi-channel cycleGAN for CBCT to CT synthesis [0.0]
  Image synthesis is used to generate synthetic CTs from on-treatment cone-beam CTs (CBCTs) Our contribution focuses on the second task, CBCT-to-sCT synthesis. By leveraging a multi-channel input to emphasize specific image features, our approach effectively addresses some of the challenges inherent in CBCT imaging.
  arXiv  Detail & Related papers  (2023-12-04T16:40:53Z)
• Energy-Guided Diffusion Model for CBCT-to-CT Synthesis [8.888473799320593]
  Cone Beam CT (CBCT) plays a crucial role in Adaptive Radiation Therapy (ART) by accurately providing radiation treatment when organ anatomy changes occur. CBCT images suffer from scatter noise and artifacts, making relying solely on CBCT for precise dose calculation and accurate tissue localization challenging. We propose an energy-guided diffusion model (EGDiff) and conduct experiments on a chest tumor dataset to generate synthetic CT (sCT) from CBCT.
  arXiv  Detail & Related papers  (2023-08-07T07:23:43Z)
• Enhancing Super-Resolution Networks through Realistic Thick-Slice CT Simulation [4.43162303545687]
  Deep learning-based Generative Models have the potential to convert low-resolution CT images into high-resolution counterparts without long acquisition times and increased radiation exposure in thin-slice CT imaging. procuring appropriate training data for these Super-Resolution (SR) models is challenging. Previous SR research has simulated thick-slice CT images from thin-slice CT images to create training pairs. We introduce a simple yet realistic method to generate thick CT images from thin-slice CT images, facilitating the creation of training pairs for SR algorithms.
  arXiv  Detail & Related papers  (2023-07-02T11:09:08Z)
• Enhanced Sharp-GAN For Histopathology Image Synthesis [63.845552349914186]
  Histopathology image synthesis aims to address the data shortage issue in training deep learning approaches for accurate cancer detection. We propose a novel approach that enhances the quality of synthetic images by using nuclei topology and contour regularization. The proposed approach outperforms Sharp-GAN in all four image quality metrics on two datasets.
  arXiv  Detail & Related papers  (2023-01-24T17:54:01Z)
• Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis [88.39466012709205]
  This paper builds a novel medical slice to increase the between-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy. Our method outperforms state-of-the-art algorithms by clear margins.
  arXiv  Detail & Related papers  (2021-12-20T03:38:37Z)
• CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation [56.622832383316215]
  We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans. Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran. Our empirical results show that CyTran outperforms all competing methods.
  arXiv  Detail & Related papers  (2021-10-12T23:25:03Z)
• A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis [49.3704402041314]
  We propose a multi-stage attentive transfer learning framework for improving COVID-19 diagnosis. Our proposed framework consists of three stages to train accurate diagnosis models through learning knowledge from multiple source tasks and data of different domains. Importantly, we propose a novel self-supervised learning method to learn multi-scale representations for lung CT images.
  arXiv  Detail & Related papers  (2021-01-14T01:39:19Z)
• A Learning-based Method for Online Adjustment of C-arm Cone-Beam CT Source Trajectories for Artifact Avoidance [47.345403652324514]
  The reconstruction quality attainable with commercial CBCT devices is insufficient due to metal artifacts in the presence of pedicle screws. We propose to adjust the C-arm CBCT source trajectory during the scan to optimize reconstruction quality with respect to a certain task. We demonstrate that convolutional neural networks trained on realistically simulated data are capable of predicting quality metrics that enable scene-specific adjustments of the CBCT source trajectory.
  arXiv  Detail & Related papers  (2020-08-14T09:23:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.