基于智能影像的肿瘤分析技术
李依格

西北大学 信息科学与技术学院，陕西西安，710127；

摘要：本文提出一种深度学习与放射组学融合的肿瘤智能辅助诊断系统，构建"分割-特征提取-分类"三级协同框架提升诊断效能。针对病灶定位，优化Keras框架下的U-Net网络，通过多尺度特征融合实现高精度医学图像分割；利用Pyradiomics工具包对分割区域进行高通量特征提取，涵盖纹理、形态及频域多维描述符；采用遗传算法优化SVM分类器参数，基于临床数据构建良恶性预测模型。研究创新开发端云协同诊断平台，实现多模态影像分布式处理与跨机构协作，实验表明微小病灶检出敏感度提升12.6%。

关键词：U-Net网络；智能诊断云平台；多模态数据分析；微小病灶检测；Pyradiomics

参考文献

[1] Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60-88.

[2] Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118.

[3] Ardila, D., Kiraly, A. P., Bharadwaj, S., Choi, B., Reicher, J. J., Peng, L., ... & Tsao, D. (2019). End-to-end lung cancer screening with three-dimensional deep learning on low-dose CT scans. Nature Medicine, 25(6), 954-961.

[4] Liu, X., Faes, L., Kale, A. U., Wagner, S. K., Fu, D. J., Bruynseels, A., ... & Sim, D. (2019). A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. The Lancet Digital Health, 1(6), e271-e297.

[5] O. Ronneberger et al. U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI, 2015