Pixel-level Diabetic Retinopathy Lesion Detection Using Multi-scale Convolutional Neural Network

被引：0
|
作者：
Li, Qi [1 ]
Peng, Chenglei [1 ]
Ma, Yazhen [2 ]
Du, Sidan [3 ]
Guo, Bin [2 ]
Li, Yang [3 ]
机构：
[1] Nanjing Univ, Sch Elect Sci & Engn, Nanjing Inst Adv Artificial Intelligence, Nanjing, Peoples R China
[2] Nanjing Univ, Med Coll, Taikang Xianlin Drum Tower Hosp, Nanjing, Peoples R China
[3] Nanjing Univ, Sch Elect Sci & Engn, Nanjing, Peoples R China
来源：
2021 IEEE 3RD GLOBAL CONFERENCE ON LIFE SCIENCES AND TECHNOLOGIES (IEEE LIFETECH 2021) | 2021年
关键词：
medical image processing; diabetic retinopathy; lesion detection; multi-scale CNN; computer-aided diagnosis;
D O I：
10.1109/LIFETECH52111.2021.9391891
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Diabetic retinopathy (DR) is one of the leading causes of preventable blindness. It's urgent to develop reliable methods for auto DR screening, the key of which is the detection of lesions. This paper presents an innovative method to detect DR lesions in pixel-level. We design a multi-scale Convolution Neural Network (CNN) that make the full use of multiple different scales with complementary image information. Experiments are carried out on both private and public datasets. Results show that multi-scale CNN model outperforms single-scale CNN model and other state-of-the-art approaches.
引用
收藏
页码：438 / 440
页数：3
相关论文
共 50 条
  • [41] Multi-Scale Scene Text Detection Based on Convolutional Neural Network
    Lu, Yan-Feng
    Zhang, Ai-Xuan
    Li, Yi
    Yu, Qian-Hui
    Qiao, Hong
    2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 583 - 587
  • [42] DDoS Attack Detection via Multi-Scale Convolutional Neural Network
    Cheng, Jieren
    Liu, Yifu
    Tang, Xiangyan
    Sheng, Victor S.
    Li, Mengyang
    Li, Junqi
    CMC-COMPUTERS MATERIALS & CONTINUA, 2020, 62 (03): : 1317 - 1333
  • [43] Multi-scale convolutional neural network model for pipeline leak detection
    Tan Z.
    Guo X.
    Li J.
    Guo Y.
    Pan J.
    Shuili Xuebao/Journal of Hydraulic Engineering, 2023, 54 (02): : 220 - 231
  • [44] PLDMLT: Multi-Task Learning of Diabetic Retinopathy Using the Pixel-Level Labeled Fundus Images
    Liu, Hengyang
    Huang, Chuncheng
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 76 (02): : 1745 - 1761
  • [45] Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network
    Li, Shengyuan
    Zhao, Xuefeng
    Zhou, Guangyi
    COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2019, 34 (07) : 616 - 634
  • [46] Identifying the Strength Level of Objects' Tactile Attributes Using a Multi-Scale Convolutional Neural Network
    Zhang, Peng
    Yu, Guoqi
    Shan, Dongri
    Chen, Zhenxue
    Wang, Xiaofang
    SENSORS, 2022, 22 (05)
  • [47] Multi-Scale Attention Network for Diabetic Retinopathy Classification
    Al-Antary, Mohammad T.
    Arafa, Yasmine
    IEEE ACCESS, 2021, 9 : 54190 - 54200
  • [48] In-Vehicle Network Intrusion Detection System Using Convolutional Neural Network and Multi-Scale Histograms
    Baldini, Gianmarco
    INFORMATION, 2023, 14 (11)
  • [49] A multi-branch multi-scale convolutional neural network using automatic detection of fetal arrhythmia
    Kanna, S. K. Rajesh
    Shajin, Francis H.
    Rajesh, P.
    Mannepalli, Kasiprasad
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (SUPPL 1) : 87 - 96
  • [50] Multi-scale Stepwise Training Strategy of Convolutional Neural Networks for Diabetic Retinopathy Severity Assessment
    Li, Fangjun
    Yuan, Dongfeng
    Zhang, Mingqiang
    Liang, Cong
    Zhou, Xiaotian
    Zhang, Haixia
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
12345