The effect of harmonization on the variability of PET radiomic features extracted using various segmentation methods
Authors:
Open Access
- 4 April 2024
- journal article
- research article
- Published by Springer Nature in Annals of Nuclear Medicine
- Vol. 38 (7) , 493-507
Abstract
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.Keywords
Funding Information
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (SNSF 320030_176052)
- University of Geneva
This publication has 66 references indexed in Scilit:
- Synergistic impact of motion and acquisition/reconstruction parameters on18F‐FDG PET radiomic features in non‐small cell lung cancer: Phantom and clinical studiesMedical Physics, 2022
- Deep Generative Medical Image Harmonization for Improving Cross‐Site Generalization in Deep Learning PredictorsJournal of Magnetic Resonance Imaging, 2021
- The ever‐increasing importance of cancer as a leading cause of premature death worldwideCancer, 2021
- Lung Cancer Diagnosis Based on Image Fusion and Prediction Using CT and PET Image2020
- Ensemble Learning for AI Developers2020
- Classification and evaluation strategies of auto-segmentation approaches for PET: Report of AAPM task group No. 211Medical Physics, 2017
- Comparison of five cluster validity indices performance in brain [18F]FET‐PET image segmentation using k‐meansMedical Physics, 2016
- Characterization of PET/CT images using texture analysis: the past, the present… any future?European Journal of Nuclear Medicine and Molecular Imaging, 2016
- Comparative methods for PET image segmentation in pharyngolaryngeal squamous cell carcinomaEuropean Journal of Nuclear Medicine and Molecular Imaging, 2012
- Segmentation of lung lesion volume by adaptive positron emission tomography image thresholdingCancer, 1997