Machine learning-based FDG PET-CT radiomics for outcome prediction in larynx and hypopharynx squamous cell carcinoma. Issue 1 (January 2021)

• Record Type: Journal Article
• Authors: Zhong, J.; Frood, R.; Brown, P.; Nelstrop, H.; Prestwich, R.; McDermott, G.; Currie, S.; Vaidyanathan, S.; Scarsbrook, A.F.
• Is Part Of: Clinical radiology. Volume 76:Issue 1(2021)
• Page Start: 78.e9
• Page End: 78.e17
• Publication Date: 2021-01
• Subjects: Medical radiology -- Periodicals; Radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiology -- Periodicals; Societies, Medical -- Periodicals; Medical radiology; Radiotherapy; Electronic journals; Periodicals; 616.0757
• DOI: 10.1016/j.crad.2020.08.030
• Languages: English
• ISSNs: 0009-9260

Abstract

Abstract : AIM: To determine whether machine learning-based radiomic feature analysis of baseline integrated 2-[ 18 F]-fluoro-2-deoxy-d- glucose (FDG) positron-emission tomography (PET) computed tomography (CT) predicts disease progression in patients with locally advanced larynx and hypopharynx squamous cell carcinoma (SCC) receiving (chemo)radiotherapy. MATERIALS AND METHODS: Patients with larynx and hypopharynx SCC treated with definitive (chemo)radiotherapy at a specialist cancer centre undergoing pre-treatment PET-CT between 2008 and 2017 were included. Tumour segmentation and radiomic analysis was performed using LIFEx software (University of Paris-Saclay, France). Data were assigned into training (80%) and validation (20%) cohorts adhering to TRIPOD guidelines. A random forest classifier was created for four predictive models using features determined by recursive feature elimination: (A) PET, (B) CT, (C) clinical, and (D) combined PET-CT parameters. Model performance was assessed using area under the curve (AUC) receiver operating characteristic (ROC) analysis. RESULTS: Seventy-two patients (40 hypopharynx 32 larynx tumours) were included, mean age 61 (range 41–77) years, 50 (69%) were men. Forty-five (62.5%) had chemoradiotherapy, 27 (37.5%) had radiotherapy alone. Median follow-up 26 months (range 12–105 months). Twenty-seven (37.5%) patients progressed within 12 months. ROC AUC for models A, B, C, and D were 0.91, 0.94, 0.88, and 0.93 in training and 0.82, 0.72, 0.70, and 0.94 in validation cohorts. Parameters in model D were metabolic tumour volume (MTV), maximum CT value, minimum standardized uptake value (SUVmin), grey-level zone length matrix (GLZLM) small-zone low grey-level emphasis (SZLGE) and histogram kurtosis. CONCLUSION: FDG PET-CT derived radiomic features are potential predictors of early disease progression in patients with locally advanced larynx and hypopharynx SCC. Highlights: Radiomic features predict disease recurrence in larynx/hypopharyx cancer. Machine-learning methods selected the radiomic/clinical features for the 4 models. The 4 models were PET only, CT only, clinical features only and combined PET and CT. The combined PET/CT radiomics model had the highest AUC value (0.94).