SICDN通过可解释性特征选择，实现小样本医疗图像高精度分类。
SHAP-Integrated Convolutional Diagnostic Networks for Feature-Selective Medical Analysis
- 融合SHAP与卷积网络，实现医学图像关键特征可解释选择
- 在肺炎和乳腺癌数据集上准确率超97%，优于四种主流CNN模型
- 适合医疗领域小样本、高隐私要求场景，代码已开源
本研究提出一种集成SHAP的卷积诊断网络（SICDN），针对医疗数据受隐私法规限制导致数据量有限的问题，设计了可解释的特征选择方法。SICDN在肺炎和乳腺癌分类任务中表现优异，准确率超过97%，超越四种主流CNN模型。研究还引入历史加权移动平均技术以优化特征选择过程。结果表明，SICDN在医疗图像预测中具有应用潜力，相关代码已公开于https://github.com/AIPMLab/SICDN。
原文摘要 · Abstract (English)
This study introduces the SHAP-integrated convolutional diagnostic network (SICDN), an interpretable feature selection method designed for limited datasets, to address the challenge posed by data privacy regulations that restrict access to medical datasets. The SICDN model was tested on classification tasks using pneumonia and breast cancer datasets, demonstrating over 97% accuracy and surpassing four popular CNN models. We also integrated a historical weighted moving average technique to enhance feature selection. The SICDN shows potential in medical image prediction, with the code available on https://github.com/AIPMLab/SICDN.
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。