Mela_DNN An integrated method based on deep convolutional neural network to recognize melanoma

Introduction

Our software contains an integrated method based on deep convolutional neural network to recognize melanoma. We first crop the original images using segmentation masks which are generated from segmentation network, then we use five state-of-the-art networks to extract features, and add SE block to the network to help highlight more effective features. Finally, we construct a new neural network use local connection to integrate the classification results of these models.

Publications

  1. Melanoma Classification in Dermoscopy Images via Ensemble Learning on Deep Neural Network
    Song, Jie and Li, Jiawei and Ma, Shiqiang and Tang, Jijun and Guo, Fei, - 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

Credits

  1. Fei Guo fguo@tju.edu.cn
    Investigator

    School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, China

  2. Jie Song songjie@tju.edu.cn
    Developer

    School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, China

  3. Jiawei Li jiawei6636@tju.edu.cn
    Developer

    School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, China

  4. Shiqiang Ma shiqiang@tju.edu.cn
    Developer

    School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, China

  5. Jijun Tang tangjijun@tju,edu,cn
    Developer

    School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, China

Community Ratings

UsabilityEfficiencyReliabilityRated By
0 user
Sign in to rate
Summary
AccessionBT007141
Tool TypeApplication
CategoryData management and annotation
PlatformsLinux/Unix
TechnologiesPython3
User InterfaceTerminal Command Line
Latest Release1.0 (May 31, 2021)
Download Count797
Country/RegionChina
Submitted ByFei Guo
Fundings

2018YFC0910400