Automatic segmentation of prostate and organs at risk in CT images using an encoder–decoder structure based on residual neural network

Accurate segmentation of the prostate and surrounding organs at risk (OARs) from CT scans is critical for radiotherapy treatment planning in prostate cancer. However, manual segmentation is time-consuming and prone to variability. This paper proposes a deep learning-based approach using a pre-traine...

Full description

Saved in:
Bibliographic Details
Published in:Biomedical signal processing and control Vol. 101; p. 107234
Main Authors: Gutiérrez-Ramos, Silvia M., Altuve, Miguel
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.03.2025
Subjects:
Automatic segmentation
Computed tomography imaging
Deep learning
Dice similarity coefficient
Prostate cancer
ResNet-18
Deep learning
ResNet-18
Automatic segmentation
Computed tomography imaging
Prostate cancer
Dice similarity coefficient
ISSN:1746-8094
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate segmentation of the prostate and surrounding organs at risk (OARs) from CT scans is critical for radiotherapy treatment planning in prostate cancer. However, manual segmentation is time-consuming and prone to variability. This paper proposes a deep learning-based approach using a pre-trained ResNet-18 combined with an encoder–decoder structure based on DeepLabv3+. The method automates the segmentation of the prostate, bladder, and rectum in male pelvic CT scans, achieving precise and efficient results without requiring preprocessing or extensive manual refinement. Evaluated on 100 CT scans using 10-fold cross-validation, the model demonstrates strong performance (Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD)) on prostate (DSC: 84.32±4.88%, HD: 3.95±0.60mm), bladder (DSC: 86.53±3.66%, HD: 4.58±0.72mm), and rectum (DSC: 83.92±4.18%, HD: 2.99±0.40mm) segmentation. Additionally, a user-friendly MATLAB application is developed to automate the segmentation process. This approach has the potential to improve treatment planning efficiency, accuracy, and consistency for better patient outcomes. •Automatically segment prostate, bladder, and rectum in CT images.•Efficient single-step segmentation with accurate results.•High Dice coefficients and low Hausdorff distances achieved.•Precise organ segmentation enhances prostate targeting.•MATLAB app developed for easy automated segmentation.
ISSN:1746-8094
DOI:10.1016/j.bspc.2024.107234