Assessment of algorithmic performance in PET-CT segmentation of solitary lung tumors
- 1Division of Nuclear Medicine and Translational Imaging, Department of Medical Imaging, Faculty of Medicine, University of Debrecen, Debrecen, Hungary
- 2Scanomed Ltd., Debrecen, Hungary
Abstract
Background: PET-CT (Positron emission tomography–computed tomography), a nuclear medicine imaging technique is preferably used for lung tumor detection. However, manual image analysis may be time-consuming. To enhance efficiency, many automated segmentation algorithms have been developed. This study aims to develop a radiomics agreement-based method to evaluate segmentation algorithms and to compare the performance of two deep learning-based algorithms nnU-Net (No-new-net Convolutional Neural Network) and RECOMIA (Research Consortium for Medical Image Analysis Lung Cancer “Lung Cancer FDG-PET/CT v1.5”) for PET-CT solitary lung tumor segmentation. Methods and results: PET-CT images of 221 patients at the University of Debrecen’s Hospital were collected and anonymized. The predictions of segmented lung tumors done by nnU-Net and RECOMIA were compared with the manual segmented masks via Wilcoxon signed-rank test and Pearson correlation values, based on eight groups of radiomics parameters calculated by PyRadiomics software. The combined p-values were calculated using Brown’s method, which were 0.481 and < 0.001 for nnU-Net and RECOMIA, respectively. The absolute values of correlation were summed, which were 37.259 and 16.358 for nnU-Net and RECOMIA, respectively. Altogether, RECOMIA shows statistically greater differences, therefore, it performs worse than nnU-Net does. Statistical analyses with Intraclass correlation coefficients (ICC), Multivariate analysis of variance (MANOVA) and follow up pairwise t-test further confirmed stronger agreement between extracted radiomics features from nnU-Net predicted masks and manual masks than RECOMIA and manual masks, which validated the proposed comparison method. Conclusion: The superior performance of nnU-Net highlights the importance of training data alignment and model adaptability in achieving accurate and reliable segmentation in medical imaging. However, nnU-Net requirements for training and extra computational demands may limit its application in some clinical environments. Despite lower accuracy, RECOMIA remains valuable because of its efficiency and intuitiveness. These findings provide valuable guidance for selecting segmentation algorithms in real-world clinical and research settings.
Related
- The Kefallinia Score: Development and Apparent Performance Assessment of a Flow Cytometry-Based Intraoperative Classification System for Intracranial Tumors
- Clinical outcomes and quality of life after proton therapy for cranial and extracranial solitary fibrous tumors
- Solitary Fibrous Tumors: Clinicopathologic Spectrum and Risk Stratification From Tertiary Care Centers in India.
- Semi-automatic segmentation of pelvic bone tumors: Usability testing
- Segmentation of brain tumors using a morphological Laplacian-enhanced active contour model on MRI
BibTeX
@article{le2026assessment,
title = {{Assessment of algorithmic performance in PET-CT segmentation of solitary lung tumors}},
author = {Duc Trung Le and Dániel Szabó and Sándor Aranyi and Márton Mikó and Zita Képes and Iván Mihovk and Anna Rebeka Kovács and Iván Gábor Nagy and Bence Farkas and István Hajdú and György Trencsényi and Lajos Trón and Miklós Emri and Gábor Opposits},
journal = {PLOS One},
year = {2026},
month = nov,
doi = {10.1371/journal.pone.0360849},
url = {https://doi.org/10.1371/journal.pone.0360849},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Assessment of algorithmic performance in PET-CT segmentation of solitary lung tumors
AU - Duc Trung Le
AU - Dániel Szabó
AU - Sándor Aranyi
AU - Márton Mikó
AU - Zita Képes
AU - Iván Mihovk
AU - Anna Rebeka Kovács
AU - Iván Gábor Nagy
AU - Bence Farkas
AU - István Hajdú
AU - György Trencsényi
AU - Lajos Trón
AU - Miklós Emri
AU - Gábor Opposits
PY - 2026
DA - 2026/11/05
JO - PLOS One
DO - 10.1371/journal.pone.0360849
UR - https://doi.org/10.1371/journal.pone.0360849
AB - Background: PET-CT (Positron emission tomography–computed tomography), a nuclear medicine imaging technique is preferably used for lung tumor detection. However, manual image analysis may be time-consuming. To enhance efficiency, many automated segmentation algorithms have been developed. This study aims to develop a radiomics agreement-based method to evaluate segmentation algorithms and to compare the performance of two deep learning-based algorithms nnU-Net (No-new-net Convolutional Neural Network) and RECOMIA (Research Consortium for Medical Image Analysis Lung Cancer “Lung Cancer FDG-PET/CT v1.5”) for PET-CT solitary lung tumor segmentation. Methods and results: PET-CT images of 221 patients at the University of Debrecen’s Hospital were collected and anonymized. The predictions of segmented lung tumors done by nnU-Net and RECOMIA were compared with the manual segmented masks via Wilcoxon signed-rank test and Pearson correlation values, based on eight groups of radiomics parameters calculated by PyRadiomics software. The combined p-values were calculated using Brown’s method, which were 0.481 and < 0.001 for nnU-Net and RECOMIA, respectively. The absolute values of correlation were summed, which were 37.259 and 16.358 for nnU-Net and RECOMIA, respectively. Altogether, RECOMIA shows statistically greater differences, therefore, it performs worse than nnU-Net does. Statistical analyses with Intraclass correlation coefficients (ICC), Multivariate analysis of variance (MANOVA) and follow up pairwise t-test further confirmed stronger agreement between extracted radiomics features from nnU-Net predicted masks and manual masks than RECOMIA and manual masks, which validated the proposed comparison method. Conclusion: The superior performance of nnU-Net highlights the importance of training data alignment and model adaptability in achieving accurate and reliable segmentation in medical imaging. However, nnU-Net requirements for training and extra computational demands may limit its application in some clinical environments. Despite lower accuracy, RECOMIA remains valuable because of its efficiency and intuitiveness. These findings provide valuable guidance for selecting segmentation algorithms in real-world clinical and research settings.
SN - 1932-6203
ER -