Multi-centre radiomics for prediction of recurrence following radical radiotherapy for head and neck cancers: Consequences of feature selection, machine learning classifiers and batch-effect harmonization

Varghese, A.J.; Gouthamchand, Varsha; Sasidharan, Balu Krishna; Wee, Leonard; Sidhique, Sharief K; Rao, Julia Priyadarshini; Dekker, André; Hoebers, Frank; Devadhas, Devakumar; Irodi, Aparna; Balasingh, T.P.; Godson, Henry Finlay; Joel, T.; Mathew, Manu; Isiah, Rajesh; Pavamani, Simon; Hecking, Thomas

doi:10.1016/j.phro.2023.100450

Cited by 4 publications

(4 citation statements)

References 28 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, boosting specificity is essential as it may minimize the false positives rate [ 65 ]. The enhancement in sensitivity and specificity could be attributed to either the individual or combined influence of several factors: standardization of features, minimization of bias, and the improvement in data quality following the application of ComBat harmonization [ 66 ].…”

Section: Discussionmentioning

confidence: 99%

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

Hosseini,

Shiri,

Ghaffarian

et al. 2024

Ann Nucl Med

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Hosseini,

Shiri,

Ghaffarian

et al. 2024

Ann Nucl Med

View full text Add to dashboard Cite

show abstract

“…Some of the possible causes for the low reproducibility include pre-existing differences in the dataset used, for example, different acquisition parameters [14,15], reconstruction methods [16,17], pixel sizes [18] and slice thickness; low reproducibility of features due to variations in quantization parameters; and low repeatability of the features [14]. Other considerations include the preprocessing of the imaging data [19]. For instance, Mottola et al studied the effects of image resampling and showed that different resampling approaches produced very different error metrics, with Lanczos interpolation performing substantially better than simple linear interpolation [20].…”

Section: Discussionmentioning

confidence: 99%

“…Often, radiomic features identified as predictive are based on small datasets, may be biased toward the specific dataset, and have limited predictive power on another dataset. For other sources of variability affecting radiomics models, readers are directed to some of these studies [19,21,22].…”

Section: Discussionmentioning

confidence: 99%

Reproducibility in Radiomics: A Comparison of Feature Extraction Methods and Two Independent Datasets

et al. 2023

Self Cite

View full text Add to dashboard Cite

Radiomics involves the extraction of information from medical images that are not visible to the human eye. There is evidence that these features can be used for treatment stratification and outcome prediction. However, there is much discussion about the reproducibility of results between different studies. This paper studies the reproducibility of CT texture features used in radiomics, comparing two feature extraction implementations, namely the MATLAB toolkit and Pyradiomics, when applied to independent datasets of CT scans of patients: (i) the open access RIDER dataset containing a set of repeat CT scans taken 15 min apart for 31 patients (RIDER Scan 1 and Scan 2, respectively) treated for lung cancer; and (ii) the open access HN1 dataset containing 137 patients treated for head and neck cancer. Gross tumor volume (GTV), manually outlined by an experienced observer available on both datasets, was used. The 43 common radiomics features available in MATLAB and Pyradiomics were calculated using two intensity-level quantization methods with and without an intensity threshold. Cases were ranked for each feature for all combinations of quantization parameters, and the Spearman’s rank coefficient, rs, calculated. Reproducibility was defined when a highly correlated feature in the RIDER dataset also correlated highly in the HN1 dataset, and vice versa. A total of 29 out of the 43 reported stable features were found to be highly reproducible between MATLAB and Pyradiomics implementations, having a consistently high correlation in rank ordering for RIDER Scan 1 and RIDER Scan 2 (rs > 0.8). 18/43 reported features were common in the RIDER and HN1 datasets, suggesting they may be agnostic to disease site. Useful radiomics features should be selected based on reproducibility. This study identified a set of features that meet this requirement and validated the methodology for evaluating reproducibility between datasets.

show abstract

“…The outcome of radiomics studies, however, can be affected by a number of factors including study design (e.g., perspective vs. retrospective); image acquisition and reconstruction settings; spatial resampling; lesion delineation; signal quantisation and others. Such sources of uncertainty may easily lead to models that fail to generalise to new research trials [ 16 , 25 , 26 ]. Lesion delineation (also referred to as segmentation or contouring ), in particular, is a critical step in the radiomics process, as the correct identification of the ROI is crucial to the development of robust prediction models.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Six Semi-Automated Tumour Delineation Methods on [18F] Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG PET/CT) in Patients with Head and Neck Cancer

Bianconi,

Salis,

Fravolini

et al. 2023

Sensors

View full text Add to dashboard Cite

Background. Head and neck cancer (HNC) is the seventh most common neoplastic disorder at the global level. Contouring HNC lesions on [18F] Fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) scans plays a fundamental role for diagnosis, risk assessment, radiotherapy planning and post-treatment evaluation. However, manual contouring is a lengthy and tedious procedure which requires significant effort from the clinician. Methods. We evaluated the performance of six hand-crafted, training-free methods (four threshold-based, two algorithm-based) for the semi-automated delineation of HNC lesions on FDG PET/CT. This study was carried out on a single-centre population of n=103 subjects, and the standard of reference was manual segmentation generated by nuclear medicine specialists. Figures of merit were the Sørensen–Dice coefficient (DSC) and relative volume difference (RVD). Results. Median DSC ranged between 0.595 and 0.792, median RVD between −22.0% and 87.4%. Click and draw and Nestle’s methods achieved the best segmentation accuracy (median DSC, respectively, 0.792 ± 0.178 and 0.762 ± 0.107; median RVD, respectively, −21.6% ± 1270.8% and −32.7% ± 40.0%) and outperformed the other methods by a significant margin. Nestle’s method also resulted in a lower dispersion of the data, hence showing stronger inter-patient stability. The accuracy of the two best methods was in agreement with the most recent state-of-the art results. Conclusions. Semi-automated PET delineation methods show potential to assist clinicians in the segmentation of HNC lesions on FDG PET/CT images, although manual refinement may sometimes be needed to obtain clinically acceptable ROIs.

show abstract

Multi-centre radiomics for prediction of recurrence following radical radiotherapy for head and neck cancers: Consequences of feature selection, machine learning classifiers and batch-effect harmonization

Cited by 4 publications

References 28 publications

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

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

Reproducibility in Radiomics: A Comparison of Feature Extraction Methods and Two Independent Datasets

Performance Analysis of Six Semi-Automated Tumour Delineation Methods on [18F] Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG PET/CT) in Patients with Head and Neck Cancer

Contact Info

Product

Resources

About