EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods

Seyyed Ali Hosseini, Isaac Shiri, Pardis Ghaffarian, Ghasem Hajianfar, Atlas Haddadi Avval, Milad Seyfi, Stijn Servaes, Pedro Rosa-Neto, Habib Zaidi, Mohammad Reza Ay

Annals of Nuclear Medicine · 2024

DOI: 10.1007/s12149-024-01923-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of Nuclear Medicine, 2024. Verfasst von Seyyed Ali Hosseini und 9 weiteren Autor:innen. Beteiligte Einrichtung: Translational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, QC,…. Hauptthemen laut MEDLINE: Carcinoma, Non-Small-Cell Lung, Lung Neoplasms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, University of Geneva.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This study aimed to examine the robustness of positron emission tomography (PET) radiomic features extracted via different segmentation methods before and after ComBat harmonization in patients with non-small cell lung cancer (NSCLC).

Methods

We included 120 patients (positive recurrence = 46 and negative recurrence = 74) referred for PET scanning as a routine part of their care. All patients had a biopsy-proven NSCLC. Nine segmentation methods were applied to each image, including manual delineation, K-means (KM), watershed, fuzzy-C-mean, region-growing, local active contour (LAC), and iterative thresholding (IT) with 40, 45, and 50% thresholds. Diverse image discretizations, both without a filter and with different wavelet decompositions, were applied to PET images. Overall, 6741 radiomic features were extracted from each image (749 radiomic features from each segmented area). Non-parametric empirical Bayes (NPEB) ComBat harmonization was used to harmonize the features. Linear Support Vector Classifier (LinearSVC) with L1 regularization For feature selection and Support Vector Machine classifier (SVM) with fivefold nested cross-validation was performed using StratifiedKFold with ‘n_splits’ set to 5 to predict recurrence in NSCLC patients and assess the impact of ComBat harmonization on the outcome.

Results

From 749 extracted radiomic features, 206 (27%) and 389 (51%) features showed excellent reliability (ICC ≥ 0.90) against segmentation method variation before and after NPEB ComBat harmonization, respectively. Among all, 39 features demonstrated poor reliability, which declined to 10 after ComBat harmonization. The 64 fixed bin widths (without any filter) and wavelets (LLL)-based radiomic features set achieved the best performance in terms of robustness against diverse segmentation techniques before and after ComBat harmonization. The first-order and GLRLM and also first-order and NGTDM feature families showed the largest number of robust features before and after ComBat harmonization, respectively. In terms of predicting recurrence in NSCLC, our findings indicate that using ComBat harmonization can significantly enhance machine learning outcomes, particularly improving the accuracy of watershed segmentation, which initially had fewer reliable features than manual contouring. Following the application of ComBat harmonization, the majority of cases saw substantial increase in sensitivity and specificity.

Conclusion

Radiomic features are vulnerable to different segmentation methods. ComBat harmonization might be considered a solution to overcome the poor reliability of radiomic features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, Non-Small-Cell LungLung NeoplasmsImage Processing, Computer-AssistedHumansMaleFemaleMiddle AgedAgedPositron-Emission TomographySupport Vector MachineAdultRadiomics

Stichwörter der Autor:innen

HarmonizationLung cancerPETRadiomicsRobustnessSegmentation

Autor:innen und Institutionen

  • Translational Neuroimaging Laboratory, The McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, QC, Canada.
  • Department of Neurology and Neurosurgery, Faculty of Medicine, McGill University, Montréal, QC, Canada.
  • Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, 1211, Geneva 4, Switzerland.
  • Chronic Respiratory Diseases Research Center, National Research Institute of Tuberculosis and Lung Diseases (NRITLD), Shahid Beheshti University of Medical Sciences, Tehran, Iran.
  • PET/CT and Cyclotron Center, Masih Daneshvari Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
  • School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.

Förderung

  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
  • University of Geneva

Zitieren

APA

Hosseini, S. A., Shiri, I., Ghaffarian, P., Hajianfar, G., Avval, A. H., Seyfi, M., Servaes, S., Rosa-Neto, P., Zaidi, H., & Ay, M. R. (2024). The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods. Annals of Nuclear Medicine. https://doi.org/10.1007/s12149-024-01923-7

Vancouver

Hosseini SA, Shiri I, Ghaffarian P, Hajianfar G, Avval AH, Seyfi M, et al. The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods. Annals of Nuclear Medicine. 2024. doi:10.1007/s12149-024-01923-7

BibTeX
@article{Hosseini2024,
  author = {Hosseini, Seyyed Ali and Shiri, Isaac and Ghaffarian, Pardis and Hajianfar, Ghasem and Avval, Atlas Haddadi and Seyfi, Milad and Servaes, Stijn and Rosa-Neto, Pedro and Zaidi, Habib and Ay, Mohammad Reza},
  title = {The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods},
  journal = {Annals of Nuclear Medicine},
  year = {2024},
  doi = {10.1007/s12149-024-01923-7}
}
Kostenlos starten →