Determining HPV Status in Patients with Oropharyngeal Cancer from 3D CT Images Using Radiomics: Effect of Sampling Methods

Sarac, Kamil; Güveniş, Albert

doi:10.1007/978-3-031-34960-7_3

Cited by 2 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies partly confirm our results. Sarac and Guvenis considered six different resampling methods in a cohort of patients with oropharyngeal cancer to determine their HPV status 25 . They demonstrated that oversampling performed better overall than undersampling, with SMOTE obtaining the highest performance.…”

Section: Discussionmentioning

confidence: 99%

The effect of data resampling methods in radiomics

Demircioğlu

2024

Sci Rep

View full text Add to dashboard Cite

Radiomic datasets can be class-imbalanced, for instance, when the prevalence of diseases varies notably, meaning that the number of positive samples is much smaller than that of negative samples. In these cases, the majority class may dominate the model's training and thus negatively affect the model's predictive performance, leading to bias. Therefore, resampling methods are often utilized to class-balance the data. However, several resampling methods exist, and neither their relative predictive performance nor their impact on feature selection has been systematically analyzed. In this study, we aimed to measure the impact of nine resampling methods on radiomic models utilizing a set of fifteen publicly available datasets regarding their predictive performance. Furthermore, we evaluated the agreement and similarity of the set of selected features. Our results show that applying resampling methods did not improve the predictive performance on average. On specific datasets, slight improvements in predictive performance (+ 0.015 in AUC) could be seen. A considerable disagreement on the set of selected features was seen (only 28.7% of features agreed), which strongly impedes feature interpretability. However, selected features are similar when considering their correlation (82.9% of features correlated on average).

show abstract

Section: Discussionmentioning

confidence: 99%

The effect of data resampling methods in radiomics

Demircioğlu

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

Using radiomics for predicting the HPV status of oropharyngeal tumors

Sarac,

Guvenis

2024

J. Eng. Appl. Sci.

View full text Add to dashboard Cite

Knowing human papillomavirus (HPV) status has important consequences for treatment selection in oropharyngeal cancer. The gold standard is to perform a biopsy. The objective of this paper is to develop a new computed tomography (CT) radiomics-based non-invasive solution to HPV status determination and investigate if and how it can be a viable and accurate complementary technique. Two hundred thirty-eight patients’ CT scans were normalized and resampled. One thousand one hundred forty-two radiomics features were obtained from the segmented CT scans. The number of radiomic attributes was decreased by applying correlation coefficient analysis, backward elimination, and random forest feature importance analysis. Random over-sampling (ROSE) resampling algorithm was performed on the training set for data balancing, and as a result, 161 samples were obtained for each of the HPV classes of the training set. A random forest (RF) classification algorithm was used as a prediction model using five-fold cross-validation (CV). Model effectiveness was evaluated on the unused 20% of the imbalanced data. The applicability of the model was investigated based on previous research and error rates reported for biopsy procedures. The HPV status was determined with an accuracy of 91% (95% CI 83–99) and an area under the curve (AUC) of 0.77 (95% CI 65–89) on the test data. The error rates were comparable to those encountered in biopsy. As a conclusion, radiomics has the potential to predict HPV status with accuracy levels that are comparable to biopsy. Future work is needed to improve standardization, interpretability, robustness, and reproducibility before clinical translation.

show abstract

Determining HPV Status in Patients with Oropharyngeal Cancer from 3D CT Images Using Radiomics: Effect of Sampling Methods

Cited by 2 publications

References 39 publications

The effect of data resampling methods in radiomics

The effect of data resampling methods in radiomics

Using radiomics for predicting the HPV status of oropharyngeal tumors

Contact Info

Product

Resources

About