Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI

Cervical cancer is the most common cancer and ranked as 4th in morbidity and mortality among Malaysian women. Currently, Magnetic Resonance Imaging (MRI) is considered as the gold standard imaging modality for tumours with a stage higher than IB2, due to its superiority in diagnostic assessment of t...

Full description

Bibliographic Details
Main Authors: Ramli, Zarina, Abdul Karim, Muhammad Khalis, Effendy, Nuraidayani, Abd Rahman, Mohd Amiruddin, Awang Kechik, Mohd Mustafa, Ibahim, Mohamad Johari, Mohd Haniff, Nurin Syazwina
Format: Article
Published: Multidisciplinary Digital Publishing Institute 2022
Online Access:http://psasir.upm.edu.my/id/eprint/103280/
_version_ 1848863978469457920
author Ramli, Zarina
Abdul Karim, Muhammad Khalis
Effendy, Nuraidayani
Abd Rahman, Mohd Amiruddin
Awang Kechik, Mohd Mustafa
Ibahim, Mohamad Johari
Mohd Haniff, Nurin Syazwina
author_facet Ramli, Zarina
Abdul Karim, Muhammad Khalis
Effendy, Nuraidayani
Abd Rahman, Mohd Amiruddin
Awang Kechik, Mohd Mustafa
Ibahim, Mohamad Johari
Mohd Haniff, Nurin Syazwina
author_sort Ramli, Zarina
building UPM Institutional Repository
collection Online Access
description Cervical cancer is the most common cancer and ranked as 4th in morbidity and mortality among Malaysian women. Currently, Magnetic Resonance Imaging (MRI) is considered as the gold standard imaging modality for tumours with a stage higher than IB2, due to its superiority in diagnostic assessment of tumour infiltration with excellent soft-tissue contrast. In this research, the robustness of semi-automatic segmentation has been evaluated using a flood-fill algorithm for quantitative feature extraction, using 30 diffusion weighted MRI images (DWI-MRI) of cervical cancer patients. The relevant features were extracted from DWI-MRI segmented images of cervical cancer. First order statistics, shape features, and textural features were extracted and analysed. The intra-class relation coefficient (ICC) was used to compare 662 radiomic features extracted from manual and semi-automatic segmentations. Notably, the features extracted from the semi-automatic segmentation and flood filling algorithm (average ICC = 0.952 0.009, p > 0.05) were significantly higher than the manual extracted features (average ICC = 0.897 0.011, p > 0.05). Henceforth, we demonstrate that the semi-automatic segmentation is slightly expanded to manual segmentation as it produces more robust and reproducible radiomic features.
first_indexed 2025-11-15T13:41:30Z
format Article
id upm-103280
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T13:41:30Z
publishDate 2022
publisher Multidisciplinary Digital Publishing Institute
recordtype eprints
repository_type Digital Repository
spelling upm-1032802023-11-07T05:02:04Z http://psasir.upm.edu.my/id/eprint/103280/ Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI Ramli, Zarina Abdul Karim, Muhammad Khalis Effendy, Nuraidayani Abd Rahman, Mohd Amiruddin Awang Kechik, Mohd Mustafa Ibahim, Mohamad Johari Mohd Haniff, Nurin Syazwina Cervical cancer is the most common cancer and ranked as 4th in morbidity and mortality among Malaysian women. Currently, Magnetic Resonance Imaging (MRI) is considered as the gold standard imaging modality for tumours with a stage higher than IB2, due to its superiority in diagnostic assessment of tumour infiltration with excellent soft-tissue contrast. In this research, the robustness of semi-automatic segmentation has been evaluated using a flood-fill algorithm for quantitative feature extraction, using 30 diffusion weighted MRI images (DWI-MRI) of cervical cancer patients. The relevant features were extracted from DWI-MRI segmented images of cervical cancer. First order statistics, shape features, and textural features were extracted and analysed. The intra-class relation coefficient (ICC) was used to compare 662 radiomic features extracted from manual and semi-automatic segmentations. Notably, the features extracted from the semi-automatic segmentation and flood filling algorithm (average ICC = 0.952 0.009, p > 0.05) were significantly higher than the manual extracted features (average ICC = 0.897 0.011, p > 0.05). Henceforth, we demonstrate that the semi-automatic segmentation is slightly expanded to manual segmentation as it produces more robust and reproducible radiomic features. Multidisciplinary Digital Publishing Institute 2022 Article PeerReviewed Ramli, Zarina and Abdul Karim, Muhammad Khalis and Effendy, Nuraidayani and Abd Rahman, Mohd Amiruddin and Awang Kechik, Mohd Mustafa and Ibahim, Mohamad Johari and Mohd Haniff, Nurin Syazwina (2022) Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI. Diagnostics, 12 (12). art. no. 3125. pp. 1-20. ISSN 2075-4418 https://www.mdpi.com/2075-4418/12/12/3125 10.3390/diagnostics12123125
spellingShingle Ramli, Zarina
Abdul Karim, Muhammad Khalis
Effendy, Nuraidayani
Abd Rahman, Mohd Amiruddin
Awang Kechik, Mohd Mustafa
Ibahim, Mohamad Johari
Mohd Haniff, Nurin Syazwina
Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI
title Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI
title_full Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI
title_fullStr Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI
title_full_unstemmed Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI
title_short Stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer DWI-MRI
title_sort stability and reproducibility of radiomic features based on various segmentation techniques on cervical cancer dwi-mri
url http://psasir.upm.edu.my/id/eprint/103280/
http://psasir.upm.edu.my/id/eprint/103280/
http://psasir.upm.edu.my/id/eprint/103280/