Largest diameter delineations can substitute 3D tumor volume delineations for radiomics prediction of human papillomavirus status on MRI's of oropharyngeal cancer. (September 2022)

• Record Type: Journal Article
• Authors: Bos, Paula; van den Brekel, Michiel W.M.; Taghavi, Marjaneh; Gouw, Zeno A.R.; Al-Mamgani, Abrahim; Waktola, Selam; J.W.L. Aerts, Hugo; Beets-Tan, Regina G.H.; Castelijns, Jonas A.; Jasperse, Bas
• Is Part Of: Physica medica. Volume 101(2022)
• Page Start: 36
• Page End: 43
• Publication Date: 2022-09
• Subjects: AUC Area under the curve -- 95% CI 95% Confidence interval -- CRT Chemoradiation therapy -- DSC Dice Similarity Coefficient -- GTV Gross Tumor Volume -- HD Hausdorff Distance -- HPV Human Papilloma Virus -- ICC Intraclass Correlation Coefficient -- LoG Laplacian of Gaussian -- OPSCC Oropharyngeal squamous cell carcinoma; Machine learning -- Human papillomavirus -- Radiomics -- Segmentation; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2022.07.004
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: Clinical adoption of radiomics is hampered by the need of expert tumor delineations. Different tumor delineation methods are investigated in HPV tumor status prediction. Prediction performance of 2D delineations outperforms 3D tumor volume delineations. Simple delineations can substitute labor and time intensive full tumor delineations. Future research should investigate if this is valid in other radiomics models. Abstract: Purpose: Laborious and time-consuming tumor segmentations are one of the factors that impede adoption of radiomics in the clinical routine. This study investigates model performance using alternative tumor delineation strategies in models predictive of human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC). Methods: Of 153 OPSCC patients, HPV status was determined using p16/p53 immunohistochemistry. MR-based radiomic features were extracted within 3D delineations by an inexperienced observer, experienced radiologist or radiation oncologist, and within a 2D delineation of the largest axial tumor diameter and 3D spheres within the tumor. First, logistic regression prediction models were constructed and tested separately for each of these six delineation strategies. Secondly, the model trained on experienced delineations was tested using these delineation strategies. The latter methodology was repeated with the omission of shape features. Model performance was evaluated using area under the curve (AUC), sensitivity and specificity. Results: Models constructed and tested using single-slice delineations (AUC/Sensitivity/Specificity: 0.84/0.75/0.84) perform better compared to 3D experienced observer delineations (AUC/Sensitivity/Specificity: 0.76/0.76/0.71), where models based on 4 mm sphere delineations (AUC/Sensitivity/Specificity: 0.77/0.59/0.71) show similar performance. Similar performance was found when experienced and largest diameter delineations (AUC/Sens/Spec: 0.76/0.75/0.65 vs 0.76/0.69/0.69) was used to test the model constructed using experienced delineations without shape features. Conclusion: Alternative delineations can substitute labor and time intensive full tumor delineations in a model that predicts HPV status in OPSCC. These faster delineations may improve adoption of radiomics in the clinical setting. Future research should evaluate whether these alternative delineations are valid in other radiomics models.