paper-with-me

Papers

Self-supervised OCT Image Denoising with Slice-to-Slice Registration and Reconstruction

2023-11-26 · Shijie Li, Palaiologos Alexopoulos, Anse Vellappally, Ronald Zambrano, Wollstein Gadi, Guido Gerig

Strong speckle noise is inherent to optical coherence tomography (OCT) imaging and represents a significant obstacle for accurate quantitative analysis of retinal structures which is key for advances in clinical diagnosis and monitoring of disease. Learning-based self-supervised methods for structure-preserving noise reduction have demonstrated superior performance over traditional methods but face unique challenges in OCT imaging. The high correlation of voxels generated by coherent A-scan beams undermines the efficacy of self-supervised learning methods as it violates the assumption of independent pixel noise. We conduct experiments demonstrating limitations of existing models due to this independence assumption. We then introduce a new end-to-end self-supervised learning framework specifically tailored for OCT image denoising, integrating slice-by-slice training and registration modules into one network. An extensive ablation study is conducted for the proposed approach. Comparison to previously published self-supervised denoising models demonstrates improved performance of the proposed framework, potentially serving as a preprocessing step towards superior segmentation performance and quantitative analysis.

📄 PDF Abstract BibTeX arXiv:2311.15167

Code (1)

cjlee94/slice2slice 공식 구현 pytorch

Tasks

DenoisingImage DenoisingSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Neighboring Slice Noise2Noise: Self-Supervised Medical Image Denoising from Single Noisy Image Volume

2024-11-16 · Langrui Zhou, Ziteng Zhou, Xinyu Huang, Huiru Wang 외

In the last few years, with the rapid development of deep learning technologies, supervised methods based on convolutional neural networks have greatly enhanced the performance of medical image denoising. However, these …

DenoisingImage DenoisingMedical Image Denoising

Self Supervised Low Dose Computed Tomography Image Denoising Using Invertible Network Exploiting Inter Slice Congruence

2022-11-03 · Sutanu Bera, Prabir Kumar Biswas

The resurgence of deep neural networks has created an alternative pathway for low-dose computed tomography denoising by learning a nonlinear transformation function between low-dose CT (LDCT) and normal-dose CT (NDCT) im…

DenoisingImage Denoising

Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imaging

2021-06-23 · Junshen Xu, Elfar Adalsteinsson

Image denoising is of great importance for medical imaging system, since it can improve image quality for disease diagnosis and downstream image analyses. In a variety of applications, dynamic imaging techniques are util…

DenoisingImage Denoising

NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling

2026-06-22 · Jaehyun Cho, YoungJoon Yoo arxiv

Neighboring-slice self-supervised denoising is attractive for volumetric medical imaging, yet inter-slice misalignment breaks anatomical correspondence and often yields ghosting and blurred margins when adjacent slices a…

Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning

2024-06-10 · Xin Wang, Zhiyun Song, Yitao Zhu, Sheng Wang 외

In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can pose challenges for both image visualiz…

Super-Resolution