Towards a privacy-preserving distributed cloud service for preprocessing very large medical images

被引:1
作者
Wang, Yuandou [1 ]
Kanwal, Neel [2 ]
Engan, Kjersti [2 ]
Rong, Chunming [2 ]
Zhao, Zhiming [1 ,3 ]
机构
[1] Univ Amsterdam, Multiscale Networked Syst, Amsterdam, Netherlands
[2] Univ Stavanger, Dept Elect Engn & Comp Sci, Stavanger, Norway
[3] LifeWatch ERIC Virtual Lab & Innovat Ctr VLIC, Amsterdam, Netherlands
来源
2023 IEEE INTERNATIONAL CONFERENCE ON DIGITAL HEALTH, ICDH | 2023年
关键词
Computational Pathology; Cloud Computing; Privacy-preserving; Image Preprocessing; Virtual Research Environment; Infrastructure Planning;
D O I
10.1109/ICDH60066.2023.00055
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Digitized histopathology glass slides, known as Whole Slide Images (WSIs), are often several gigapixels large and contain sensitive metadata information, which makes distributed processing unfeasible. Moreover, artifacts in WSIs may result in unreliable predictions when directly applied by Deep Learning (DL) algorithms. Therefore, preprocessing WSIs is beneficial, e.g., eliminating privacy-sensitive information, splitting a gigapixel medical image into tiles, and removing the diagnostically irrelevant areas. This work proposes a cloud service to parallelize the preprocessing pipeline for large medical images. The data and model parallelization will not only boost the end-to-end processing efficiency for histological tasks but also secure the reconstruction of WSI by randomly distributing tiles across processing nodes. Furthermore, the initial steps of the pipeline will be integrated into the Jupyter-based Virtual Research Environment (VRE) to enable image owners to configure and automate the execution process based on resource allocation.
引用
收藏
页码:325 / 327
页数:3
相关论文
共 12 条
  • [1] HURWICZ L, 1973, AM ECON REV, V63, P1
  • [2] Vision Transformers for Small Histological Datasets Learned Through Knowledge Distillation
    Kanwal, Neel
    Eftestol, Trygve
    Khoraminia, Farbod
    Zuiverloon, Tahlita C. M.
    Engan, Kjersti
    [J]. ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2023, PT III, 2023, 13937 : 167 - 179
  • [3] Quantifying the effect of color processing on blood and damaged tissue detection in Whole Slide Images
    Kanwal, Neel
    Fuster, Saul
    Khoraminia, Farbod
    Zuiverloon, Tahlita C. M.
    Rong, Chunming
    Engan, Kjersti
    [J]. 2022 IEEE 14TH IMAGE, VIDEO, AND MULTIDIMENSIONAL SIGNAL PROCESSING WORKSHOP (IVMSP), 2022,
  • [4] The Devil is in the Details: Whole Slide Image Acquisition and Processing for Artifacts Detection, Color Variation, and Data Augmentation: A Review
    Kanwal, Neel
    Perez-Bueno, Fernando
    Schmidt, Arne
    Engan, Kjersti
    Molina, Rafael
    [J]. IEEE ACCESS, 2022, 10 : 58821 - 58844
  • [5] Random-data perturbation techniques and privacy-preserving data mining
    Kargupta, H
    Datta, S
    Wang, Q
    Sivakumar, K
    [J]. KNOWLEDGE AND INFORMATION SYSTEMS, 2005, 7 (04) : 387 - 414
  • [6] Privacy-Preserving Distributed Processing: Metrics, Bounds and Algorithms
    Li, Qiongxiu
    Gundersen, Jaron Skovsted
    Heusdens, Richard
    Christensen, Mads Graesboll
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2021, 16 : 2090 - 2103
  • [7] Balancing At All Loads
    Soljanin, Emina
    [J]. COMMUNICATIONS OF THE ACM, 2022, 65 (05) : 110 - 110
  • [8] Profiling the scheduling decisions for handling critical paths in deadline-constrained cloud workflows
    Taal, Arie
    Wang, Junchao
    de Laat, Cees
    Zhao, Zhiming
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2019, 100 : 237 - 249
  • [9] A Single-Link Failure Recovery Approach Based on Resource Sharing and Performance Prediction in SDN
    Wang, Ying
    Feng, Sixiang
    Guo, Hantao
    Qiu, Xuesong
    An, Hengbin
    [J]. IEEE ACCESS, 2019, 7 : 174750 - 174763
  • [10] Scaling Notebooks as Re-configurable Cloud Workflows
    Wang, Yuandou
    Koulouzis, Spiros
    Bianchi, Riccardo
    Li, Na
    Shi, Yifang
    Timmermans, Joris
    Kissling, W. Daniel
    Zhao, Zhiming
    [J]. DATA INTELLIGENCE, 2022, 4 (02) : 409 - 425