用正弦变换增强PET图像，提升肿瘤分割精度。
Sine Wave Normalization for Deep Learning-Based Tumor Segmentation in CT/PET Imaging
- 在PET数据上应用周期性正弦变换，突出病灶强度变化
- 在多示踪剂数据集上显著提升分割准确率
- 适合医学影像分析与深度学习结合的研究者
本文针对CT/PET扫描中的自动肿瘤分割任务，为autoPET III挑战赛开发了一种归一化模块。核心创新是提出SineNormal，通过在PET数据上施加周期性正弦变换，强化病灶区域的强度差异，并生成同心环状模式，从而提升病变检测能力。该方法尤其适用于具有挑战性的多示踪剂PET数据集，在提升分割精度方面表现优异。项目代码已开源，地址为https://github.com/BBQtime/Sine-Wave-Normalization-for-Deep-Learning-Based-Tumor-Segmentation-in-CT-PET。
原文摘要 · Abstract (English)
This report presents a normalization block for automated tumor segmentation in CT/PET scans, developed for the autoPET III Challenge. The key innovation is the introduction of the SineNormal, which applies periodic sine transformations to PET data to enhance lesion detection. By highlighting intensity variations and producing concentric ring patterns in PET highlighted regions, the model aims to improve segmentation accuracy, particularly for challenging multitracer PET datasets. The code for this project is available on GitHub (https://github.com/BBQtime/Sine-Wave-Normalization-for-Deep-Learning-Based-Tumor-Segmentation-in-CT-PET).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。