bebi 22(4): e3

Research Article

A smart cropping pipeline to improve prostate’s peripheral zone segmentation on MRI using Deep Learning

Download72 downloads
  • @ARTICLE{10.4108/eai.24-2-2022.173546,
        author={Dimitris Zaridis and Eugenia Mylona and Nikolaos Tachos and Kostas Marias and Manolis Tsiknakis and Dimitios I. Fotiadis},
        title={A smart cropping pipeline to improve prostate’s peripheral zone segmentation on MRI using Deep Learning},
        journal={EAI Endorsed Transactions on Bioengineering and Bioinformatics},
        volume={1},
        number={4},
        publisher={EAI},
        journal_a={BEBI},
        year={2022},
        month={2},
        keywords={deep learning, MRI segmentation, prostate cancer, peripheral zone, cropping},
        doi={10.4108/eai.24-2-2022.173546}
    }
    
  • Dimitris Zaridis
    Eugenia Mylona
    Nikolaos Tachos
    Kostas Marias
    Manolis Tsiknakis
    Dimitios I. Fotiadis
    Year: 2022
    A smart cropping pipeline to improve prostate’s peripheral zone segmentation on MRI using Deep Learning
    BEBI
    EAI
    DOI: 10.4108/eai.24-2-2022.173546
Dimitris Zaridis1,2, Eugenia Mylona1,2, Nikolaos Tachos1,2, Kostas Marias3, Manolis Tsiknakis3,4, Dimitios I. Fotiadis1,2,*
  • 1: Dept. of Biomedical Research, FORTH-IMBB, Ioannina, Greece
  • 2: Unit of Medical Technology and Intelligent Information Systems, Dept. of Materials Science and Engineering, University of Ioannina, Ioannina, Greece
  • 3: Institute of Computer Science, FORTH, Heraklion, Greece
  • 4: Department of Electrical and Computer Engineering, Hellenic Mediterranean University, Heraklion, Crete, Greece
*Contact email: fotiadis@uoi.gr

Abstract

INTRODUCTION: Although accurate segmentation of the prostatic subregions is a crucial step for prostate cancer diagnosis, it remains a challenge.

OBJECTIVES: To propose a deep learning (DL)-based cropping pipeline to improve the performance of DL networks for segmenting the prostate’s peripheral zone.

METHODS: A U-net network was trained to crop the area around the peripheral zone on MRI in order to reduce the class imbalance between foreground and background pixels. The DL-cropping was compared with the standard center-cropping using three segmentation networks.

RESULTS: The DL-cropping improved significantly the segmentation performance in terms of Dice score, Sensitivity, Hausdorff Distance, and Average Surface Distance, for all three networks. The improvement in Dice Score was 34%, 13% and 16% for the U-net, Dense U-net and Bridged U-net, respectively. CONCLUSION: For all the evaluated networks, the proposed DL-cropping technique outperformed the standard center-cropping.