Swinburne
Browse
- No file added yet -

PGD-UNet: A Position-Guided Deformable Network for Simultaneous Segmentation of Organs and Tumors

Download (1.16 MB)
conference contribution
posted on 2024-07-11, 14:16 authored by Ziqiang Li, Hong Pan, Yaping Zhu, Kai QinKai Qin
Precise segmentation of organs and tumors plays a crucial role in clinical applications. It is a challenging task due to the irregular shapes and various sizes of organs and tumors as well as the significant class imbalance between the anatomy of interest (AOI) and the background region. In addition, in most situation tumors and normal organs often overlap in medical images, but current approaches fail to delineate both tumors and organs accurately. To tackle such challenges, we propose a position-guided deformable UNet, namely PGD-UNet, which exploits the spatial deformation capabilities of deformable convolution to deal with the geometric transformation of both organs and tumors. Position information is explicitly encoded into the network to enhance the capabilities of deformation. Meanwhile, we introduce a new pooling module to preserve position information lost in conventional max-pooling operation. Besides, due to unclear boundaries between different structures as well as the subjectivity of annotations, labels are not necessarily accurate for medical image segmentation tasks. It may cause the overfitting of the trained network due to label noise. To address this issue, we formulate a novel loss function to suppress the influence of potential label noise on the training process. Our method was evaluated on two challenging segmentation tasks and achieved very promising segmentation accuracy in both tasks.

Funding

Identifying technological trajectories using machine learning algorithms

Australian Research Council

Find out more...

Data-driven Traffic Analytics for Incident Analysis and Management

Australian Research Council

Find out more...

Next-generation Intelligent Explorations of Geo-located Data

Australian Research Council

Find out more...

History

Available versions

PDF (Accepted manuscript)

ISBN

9781728169262

Journal title

Proceedings of the International Joint Conference on Neural Networks

Conference name

International Joint Conference on Neural Networks, IJCNN 2020; Virtual

Location

Glasgow

Start date

2019-07-19

End date

2019-07-24

Publisher

IEEE

Copyright statement

Copyright © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Language

eng

Usage metrics

    Publications

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC