将2D高斯点阵与Transformer UNet融合，实现皮肤病变精准分割与分类。
GS-TransUNet: Integrated 2D Gaussian Splatting and Transformer UNet for Accurate Skin Lesion Analysis
- 用2D高斯点阵增强图像表示，结合Transformer UNet进行多任务分析。
- 在ISIC-2017和PH2数据集上，分割与分类精度均超越现有模型。
- 适合需要高效一体化诊断的临床场景，推动医学影像多任务研究。
借助计算机视觉与深度学习的进展，我们可实现快速且一致的早期皮肤癌检测。然而，现有的皮肤病变分割与分类模型独立运行，错失了联合执行的潜在效率。为此，本文提出高斯点阵-Transformer UNet（GS-TransUNet），一种创新方法，将2D高斯点阵与Transformer UNet架构协同整合，实现自动化皮肤癌诊断。该统一深度学习模型高效完成双功能任务：皮肤病变分类与分割，适用于临床诊断。在ISIC-2017与PH2数据集上，通过5折交叉验证，本模型在多个指标上表现优于现有最先进模型。结果表明，在分割与分类精度方面均有显著提升。该集成方法树立了新基准，凸显了多任务医学图像分析方法的潜力，为自动诊断系统改进提供了新方向。
原文摘要 · Abstract (English)
We can achieve fast and consistent early skin cancer detection with recent developments in computer vision and deep learning techniques. However, the existing skin lesion segmentation and classification prediction models run independently, thus missing potential efficiencies from their integrated execution. To unify skin lesion analysis, our paper presents the Gaussian Splatting - Transformer UNet (GS-TransUNet), a novel approach that synergistically combines 2D Gaussian splatting with the Transformer UNet architecture for automated skin cancer diagnosis. Our unified deep learning model efficiently delivers dual-function skin lesion classification and segmentation for clinical diagnosis. Evaluated on ISIC-2017 and PH2 datasets, our network demonstrates superior performance compared to existing state-of-the-art models across multiple metrics through 5-fold cross-validation. Our findings illustrate significant advancements in the precision of segmentation and classification. This integration sets new benchmarks in the field and highlights the potential for further research into multi-task medical image analysis methodologies, promising enhancements in automated diagnostic systems.
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。