Radiomics from Various Tumour Volume Sizes for Prognosis Prediction of Head and Neck Squamous Cell Carcinoma: A Voted Ensemble Machine Learning Approach

• Published in: Life (Basel, Switzerland) Vol. 12; no. 9; p. 1380
• Main Authors: Tang, Fuk-Hay, Cheung, Eva-Yi-Wah, Wong, Hiu-Lam, Yuen, Chun-Ming, Yu, Man-Hei, Ho, Pui-Ching
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 05.09.2022; MDPI
• Subjects: Accuracy; Algorithms; Archives & records; Artificial intelligence; artificial intelligence (AI); Cancer; Cancer therapies; Chemotherapy; Chi-square test; Computed tomography; Decision analysis; Decision trees; Feature extraction; GTV; Head & neck cancer; Head and neck carcinoma; HNSCC; Image acquisition; Laboratories; Learning algorithms; Lymph nodes; Lymphatic system; Machine learning; Medical prognosis; Medical research; Metastases; Metastasis; Patients; Predictions; Prognosis; PTV; Radiation therapy; Radiomics; radiotherapy; Sensitivity; Squamous cell carcinoma; Support vector machines; Tumors; United States > US; TCIA; radiomics; PTV; head and neck cancer; HNSCC; artificial intelligence (AI); GTV; radiotherapy; machine learning; prognosis prediction
• ISSN: 2075-1729; 2075-1729
• DOI: 10.3390/life12091380

Background: Traditionally, cancer prognosis was determined by tumours size, lymph node spread and presence of metastasis (TNM staging). Radiomics of tumour volume has recently been used for prognosis prediction. In the present study, we evaluated the effect of various sizes of tumour volume. A voted ensemble approach with a combination of multiple machine learning algorithms is proposed for prognosis prediction for head and neck squamous cell carcinoma (HNSCC). Methods: A total of 215 HNSCC CT image sets with radiotherapy structure sets were acquired from The Cancer Imaging Archive (TCIA). Six tumour volumes, including gross tumour volume (GTV), diminished GTV, extended GTV, planning target volume (PTV), diminished PTV and extended PTV were delineated. The extracted radiomics features were analysed by decision tree, random forest, extreme boost, support vector machine and generalized linear algorithms. A voted ensemble machine learning (VEML) model that optimizes the above algorithms was used. The receiver operating characteristic area under the curve (ROC-AUC) were used to compare the performance of machine learning methods, including accuracy, sensitivity and specificity. Results: The VEML model demonstrated good prognosis prediction ability for all sizes of tumour volumes with reference to GTV and PTV with high accuracy of up to 88.3%, sensitivity of up to 79.9% and specificity of up to 96.6%. There was no significant difference between the various target volumes for the prognostic prediction of HNSCC patients (chi-square test, p > 0.05). Conclusions: Our study demonstrates that the proposed VEML model can accurately predict the prognosis of HNSCC patients using radiomics features from various tumour volumes.