PMID- 35864282 OWN - NLM STAT- MEDLINE DCOM- 20230314 LR - 20230413 IS - 1860-2002 (Electronic) IS - 1536-1632 (Linking) VI - 25 IP - 2 DP - 2023 Apr TI - The Usefulness of Machine Learning-Based Evaluation of Clinical and Pretreatment [(18)F]-FDG-PET/CT Radiomic Features for Predicting Prognosis in Hypopharyngeal Cancer. PG - 303-313 LID - 10.1007/s11307-022-01757-7 [doi] AB - PURPOSE: To examine whether the machine learning (ML) analyses using clinical and pretreatment 2-deoxy-2-[(18)F]fluoro-D-glucose positron emission tomography ([(18)F]-FDG-PET)-based radiomic features were useful for predicting prognosis in patients with hypopharyngeal cancer. PROCEDURES: This retrospective study included 100 patients with hypopharyngeal cancer who underwent [(18)F]-FDG-PET/X-ray computed tomography (CT) before treatment, and these patients were allocated to the training (n=80) and validation (n=20) cohorts. Eight clinical (age, sex, histology, T stage, N stage, M stage, UICC stage, and treatment) and 40 [(18)F]-FDG-PET-based radiomic features were used to predict disease progression. A feature reduction procedure based on the decrease of the Gini impurity was applied. Six ML algorithms (random forest, neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine) were compared using the area under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis. RESULTS: The five most important features for predicting disease progression were UICC stage, N stage, gray level co-occurrence matrix entropy (GLCM_Entropy), gray level run length matrix run length non-uniformity (GLRLM_RLNU), and T stage. Patients who experienced disease progression displayed significantly higher UICC stage, N stage, GLCM_Entropy, GLRLM_RLNU, and T stage than those without progression (each, p<0.001). In both cohorts, the logistic regression model constructed by these 5 features was the best performing classifier (training: AUC=0.860, accuracy=0.800; validation: AUC=0.803, accuracy=0.700). In the logistic regression model, 5-year PFS was significantly higher in patients with predicted non-progression than those with predicted progression (75.8% vs. 8.3%, p<0.001), and this model was only the independent factor for PFS in multivariate analysis (hazard ratio = 3.22; 95% confidence interval = 1.03-10.11; p=0.045). CONCLUSIONS: The logistic regression model constructed by UICC, T and N stages and pretreatment [(18)F]-FDG-PET-based radiomic features, GLCM_Entropy, and GLRLM_RLNU may be the most important predictor of prognosis in patients with hypopharyngeal cancer. CI - (c) 2022. The Author(s), under exclusive licence to World Molecular Imaging Society. FAU - Nakajo, Masatoyo AU - Nakajo M AD - Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. toyo.nakajo@dolphin.ocn.ne.jp. FAU - Kawaji, Kodai AU - Kawaji K AD - Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. FAU - Nagano, Hiromi AU - Nagano H AD - Department of Otolaryngology Head and Neck Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. FAU - Jinguji, Megumi AU - Jinguji M AD - Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. FAU - Mukai, Akie AU - Mukai A AD - Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. FAU - Kawabata, Hiroshi AU - Kawabata H AD - Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. FAU - Tani, Atsushi AU - Tani A AD - Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. FAU - Hirahara, Daisuke AU - Hirahara D AD - Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan. FAU - Yamashita, Masaru AU - Yamashita M AD - Department of Otolaryngology Head and Neck Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. FAU - Yoshiura, Takashi AU - Yoshiura T AD - Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan. LA - eng PT - Journal Article DEP - 20220721 PL - United States TA - Mol Imaging Biol JT - Molecular imaging and biology JID - 101125610 RN - 0Z5B2CJX4D (Fluorodeoxyglucose F18) SB - IM MH - Humans MH - *Fluorodeoxyglucose F18 MH - Positron Emission Tomography Computed Tomography/methods MH - Retrospective Studies MH - *Hypopharyngeal Neoplasms MH - Bayes Theorem MH - Tomography, X-Ray Computed MH - Machine Learning MH - Disease Progression OTO - NOTNLM OT - Machine learning OT - PET/CT OT - Pharyngeal neoplasm OT - Prognosis OT - [18F]-FDG EDAT- 2022/07/22 06:00 MHDA- 2023/03/15 06:00 CRDT- 2022/07/21 23:27 PHST- 2022/04/12 00:00 [received] PHST- 2022/07/11 00:00 [accepted] PHST- 2022/06/06 00:00 [revised] PHST- 2022/07/22 06:00 [pubmed] PHST- 2023/03/15 06:00 [medline] PHST- 2022/07/21 23:27 [entrez] AID - 10.1007/s11307-022-01757-7 [pii] AID - 10.1007/s11307-022-01757-7 [doi] PST - ppublish SO - Mol Imaging Biol. 2023 Apr;25(2):303-313. doi: 10.1007/s11307-022-01757-7. Epub 2022 Jul 21.