Using Uncertainty Information for Kidney Tumor Segmentation

被引:0
|
作者
Michaud, Joffrey [1 ]
Arega, Tewodros Weldebirhan [1 ]
Bricq, Stephanie [1 ]
机构
[1] Univ Bourgogne, ImViA Lab, EA 7535, Dijon, France
关键词
Kidney semantic segmentation; 3D U-Net; Uncertainty;
D O I
10.1007/978-3-031-54806-2_8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Kidney cancer occurrence increases since 1990's and its main treatment is surgery. According to this, performing automatic segmentation is an important tool to develop. In this paper, we used a two stages pipeline to get the segmentation of kidney, tumor and cyst. The first stage is used to segment the kidney region to allow us to crop the data. The second stage leverages uncertainty using Monte-Carlo dropout during training by introducing an uncertainty estimate term in the loss function.
引用
收藏
页码:54 / 59
页数:6
相关论文
共 50 条
  • [1] Leveraging Uncertainty Estimation for Segmentation of Kidney, Kidney Tumor and Kidney Cysts
    Salahuddin, Zohaib
    Kuang, Sheng
    Lambin, Philippe
    Woodruff, Henry C.
    [J]. KIDNEY AND KIDNEY TUMOR SEGMENTATION, KITS 2023, 2024, 14540 : 40 - 46
  • [2] Kidney Tumor Image Segmentation Method Based on Uncertainty Guidance and Scale Consistency
    Hou, Bingzhen
    Zhang, Guimei
    Peng, Kun
    [J]. Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2023, 36 (02): : 95 - 107
  • [3] An automated segmentation method of kidney using statistical information
    Tsagaan, B
    Shimizu, A
    Kobatake, H
    Miyakawa, K
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION-MICCAI 2002, PT 1, 2002, 2488 : 556 - 563
  • [4] Uncertainty Estimation in Liver Tumor Segmentation Using the Posterior Bootstrap
    Wang, Shishuai
    Nuyts, Johan
    Filipovic, Marina
    [J]. UNCERTAINTY FOR SAFE UTILIZATION OF MACHINE LEARNING IN MEDICAL IMAGING, UNSURE 2023, 2023, 14291 : 188 - 197
  • [5] Spatial Information Using CRF for Brain Tumor Segmentation
    Chen, Yawen
    Kamata, Sei-ichiro
    Fan, Rong
    [J]. THIRTEENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2021), 2021, 11878
  • [6] Kidney and Kidney Tumor Segmentation Using a Two-Stage Cascade Framework
    Lin, Chaonan
    Fu, Rongda
    Zheng, Shaohua
    [J]. KIDNEY AND KIDNEY TUMOR SEGMENTATION, KITS 2021, 2022, 13168 : 59 - 70
  • [7] Exploration and Visualization of Segmentation Uncertainty Using Shape and Appearance Prior Information
    Saad, Ahmed
    Hamarneh, Ghassan
    Moeller, Torsten
    [J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2010, 16 (06) : 1366 - 1375
  • [8] Cascade UNets for Kidney and Kidney Tumor Segmentation
    Koukoutegos, Konstantinos
    Maes, Frederik
    Bosmans, Hilde
    [J]. KIDNEY AND KIDNEY TUMOR SEGMENTATION, KITS 2023, 2024, 14540 : 107 - 113
  • [9] Mixup Augmentation for Kidney and Kidney Tumor Segmentation
    Gazda, Matej
    Bugata, Peter
    Gazda, Jakub
    Hubacek, David
    Hresko, David Jozef
    Drotar, Peter
    [J]. KIDNEY AND KIDNEY TUMOR SEGMENTATION, KITS 2021, 2022, 13168 : 90 - 97
  • [10] A unified uncertainty network for tumor segmentation using uncertainty cross entropy loss and prototype similarity
    Diao, Zhaoshuo
    Jiang, Huiyan
    Shi, Tianyu
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 246