Deep learning-based automated liver contouring using a small sample of radiotherapy planning computed tomography images
Radiography · 2024
DOI: 10.1016/j.radi.2024.08.005 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiography, 2024. Verfasst von N Arjmandi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Student research committee, Mashhad Univers…. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Radiotherapy Planning, Computer-Assisted, Liver. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: Mashhad University of Medical Sciences.
Abstract (Originalsprache)
INTRODUCTION: No study has yet investigated the minimum amount of data required for deep learning-based liver contouring. Therefore, this study aimed to investigate the feasibility of automated liver contouring using limited data. METHODS: Radiotherapy planning Computed tomography (CT) images were subjected to various preprocessing methods, such as denoising and windowing. Segmentation was conducted using the modified Attention U-Net and Residual U-Net networks. Two different modified networks were trained separately for different training sizes. For each architecture, the model trained with the training set size that achieved the highest dice similarity coefficient (DSC) score was selected for further evaluation. Two unseen external datasets with different distributions from the training set were also used to examine the generalizability of the proposed method. RESULTS: The modified Residual U-Net and Attention U-Net networks achieved average DSCs of 97.62% and 96.48%, respectively, on the test set, using 62 training cases. The average Hausdorff distances (AHDs) for the modified Residual U-Net and Attention U-Net networks were 0.57 mm and 0.71 mm, respectively. Also, the modified Residual U-Net and Attention U-Net networks were tested on two unseen external datasets, achieving DSCs of 95.35% and 95.82% for data from another center and 95.16% and 94.93% for the AbdomenCT-1K dataset, respectively. CONCLUSION: This study demonstrates that deep learning models can accurately segment livers using a small training set. The method, utilizing simple preprocessing and modified network architectures, shows strong performance on unseen datasets, indicating its generalizability. IMPLICATIONS FOR PRACTICE: This promising result suggests its potential for automated liver contouring in radiotherapy planning.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Physics, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Student research committee, Mashhad University of medical sciences, Mashhad, Iran. Electronic address: narjmandib…
- Department of Medical Physics, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Medical Physics Research Center, School of Medicine, Mashhad University of Medical Sciences, Mashhad. Electronic…
- Department of Radiation Oncology, Mashhad University of Medical Sciences, Mashhad, Iran. Electronic address: sou.arastouei@gmail.com.
- Physics Unit, Department of Radio-Oncology, Shiraz University of Medical Sciences, Shiraz, Iran; Ionizing and Non-Ionizing Radiation Protection Research Center, School of Paramedical Sciences, Shiraz University of Medic…
- Radiology Techniques Department, College of Medical Technology, The Islamic University, Najaf, Iraq; Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran. Electronic address: ali.albawi.ai@i…
- Department of Radiation Oncology, Mashhad University of Medical Sciences, Mashhad, Iran. Electronic address: pshvrfz1988@email.com.
Förderung
- Mashhad University of Medical Sciences
Zitieren
APA
Arjmandi, N., Momennezhad, M., Arastouei, S., Mosleh-Shirazi, M. A., Albawi, A., Pishevar, Z., & Nasseri, S. (2024). Deep learning-based automated liver contouring using a small sample of radiotherapy planning computed tomography images. Radiography. https://doi.org/10.1016/j.radi.2024.08.005
Vancouver
Arjmandi N, Momennezhad M, Arastouei S, Mosleh-Shirazi MA, Albawi A, Pishevar Z, et al. Deep learning-based automated liver contouring using a small sample of radiotherapy planning computed tomography images. Radiography. 2024. doi:10.1016/j.radi.2024.08.005
BibTeX
@article{Arjmandi2024,
author = {Arjmandi, N and Momennezhad, M and Arastouei, S and Mosleh-Shirazi, M A and Albawi, A and Pishevar, Z and Nasseri, S},
title = {Deep learning-based automated liver contouring using a small sample of radiotherapy planning computed tomography images},
journal = {Radiography},
year = {2024},
doi = {10.1016/j.radi.2024.08.005}
}
EUVIMED