集成分析引擎 面向多学科协作诊治与贯穿医疗全过程的集成分析引擎技术

Introduction

这是一种可变形多路径集成模型用于医学图像的自动分割方法。该模型采用U型卷积网络作为骨干网络，并在其中采用密集连接块以更有效地传递特征信息。为了增加模型的灵活性，使用可变形卷积处理不同具有不规则形状和大小的物体。为了减少预测偏差，我们进一步构建了具有不同参数设置的多个网络，从而形成了最终的集成模型。

Publications

  1. Automated Segmentation Of Cervical Nuclei In Pap Smear Images Using Deformable Multi-Path Ensemble Model
    Jie Zhao, Quanzheng Li, Xiang Li, Hongfeng Li, Li Zhang, 2019/7/11 - 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
    Cited by 15 (Google Schoolar as of June 2, 2021)

Credits

  1. Jie Zhao jiezhao@pku.edu.cn
    Contributor

    Center for Data Science, Peking University, China

Community Ratings

UsabilityEfficiencyReliabilityRated By
0 user
Sign in to rate
Summary
AccessionBT007200
Tool TypeApplication
CategoryImage analysis
PlatformsLinux/Unix
TechnologiesPython3
User InterfaceTerminal Command Line
Latest Release1.0 (June 2, 2021)
Download Count36
Submitted Bybin dong
Fundings

This work was supported by National Key R&D Program of China (No.2018YFC0910700)