Mazen Soufi1, Hidetaka Arimura2, Noriyuki Nagami3. 1. Division of Information Science, Graduate School of Science and Technology, Nara Institute of Science and Technology, 8916-5, Takayama-cho, Ikoma, Nara, 630-0192, Japan. 2. Faculty of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka, 812-8582, Japan. 3. Graduate School of Medical Sciences, Kyushu University, 3-1-1, Maidashi, Higashi-ku, Fukuoka, 812-8582, Japan.
Abstract
PURPOSE: To identify the optimal mother wavelets in survival prediction of lung cancer patients using wavelet decomposition-based (WDB) radiomic features in CT images. MATERIALS AND METHODS: The CT images of patients with histologically confirmed nonsmall cell lung carcinomas (NSCLCs) in training (Dataset T; n = 162) and validation (Dataset V; n = 143) datasets were analyzed for this study. The optimal mother wavelets were identified based on the impacts of the WDB radiomic features on the patient survival times. Four hundred and thirty-two three-dimensional WDB radiomic features were calculated from regions of interest (ROI) of 162 tumor contours. A Coxnet algorithm was used to select a subset of radiomic features (signature) based on the prediction of survival times with a fivefold cross validation. The impacts of the radiomic features on the patients' survival times were assessed by using a multivariate Cox proportional hazard regression (MCPHR) model. The major contribution of this study was to identify optimal mother wavelets based on a maximization of a novel ranking index (RI) incorporating the Coxnet cross-validated partial log-likelihood and the summation of the P-values of the radiomic features in the MCPHR model on Dataset T. The prognostic performance of the optimal mother wavelets was validated based on the concordance index (CI) of the MCPHR models when applied to Dataset V. The proposed approach was tested by using 31 mother wavelets from 6 wavelet families that were available in a commercially available software (Matlab® 2016b). RESULTS: The optimal mother wavelets were Symlet 5 and Biorthogonal 2.6 at 128 requantization levels, which yielded RIs of 4.27 ± 0.29 (3 features) and 6.50 ± 0.50 (5 features), respectively. The CIs of the MCPHR models of Symlet 5 were 0.66 ± 0.03 (Dataset T) and 0.64 ± 0.00 (Dataset V), whereas those of Biorthogonal 2.6 were 0.68 ± 0.03 (Dataset T) and 0.62 ± 0.02 (Dataset V). The radiomic signatures included the GLRLM-based LHL gray level nonuniformity feature that demonstrated statistically significant differences in stratifying patients with better and worse prognoses in Datasets T and V. CONCLUSION: This study has revealed the potential of Symlet and Biorthogonal mother wavelets in the survival prediction of lung cancer patients by using WDB radiomic features in CT images.
PURPOSE: To identify the optimal mother wavelets in survival prediction of lung cancerpatients using wavelet decomposition-based (WDB) radiomic features in CT images. MATERIALS AND METHODS: The CT images of patients with histologically confirmed nonsmall cell lung carcinomas (NSCLCs) in training (Dataset T; n = 162) and validation (Dataset V; n = 143) datasets were analyzed for this study. The optimal mother wavelets were identified based on the impacts of the WDB radiomic features on the patient survival times. Four hundred and thirty-two three-dimensional WDB radiomic features were calculated from regions of interest (ROI) of 162 tumor contours. A Coxnet algorithm was used to select a subset of radiomic features (signature) based on the prediction of survival times with a fivefold cross validation. The impacts of the radiomic features on the patients' survival times were assessed by using a multivariate Cox proportional hazard regression (MCPHR) model. The major contribution of this study was to identify optimal mother wavelets based on a maximization of a novel ranking index (RI) incorporating the Coxnet cross-validated partial log-likelihood and the summation of the P-values of the radiomic features in the MCPHR model on Dataset T. The prognostic performance of the optimal mother wavelets was validated based on the concordance index (CI) of the MCPHR models when applied to Dataset V. The proposed approach was tested by using 31 mother wavelets from 6 wavelet families that were available in a commercially available software (Matlab® 2016b). RESULTS: The optimal mother wavelets were Symlet 5 and Biorthogonal 2.6 at 128 requantization levels, which yielded RIs of 4.27 ± 0.29 (3 features) and 6.50 ± 0.50 (5 features), respectively. The CIs of the MCPHR models of Symlet 5 were 0.66 ± 0.03 (Dataset T) and 0.64 ± 0.00 (Dataset V), whereas those of Biorthogonal 2.6 were 0.68 ± 0.03 (Dataset T) and 0.62 ± 0.02 (Dataset V). The radiomic signatures included the GLRLM-based LHL gray level nonuniformity feature that demonstrated statistically significant differences in stratifying patients with better and worse prognoses in Datasets T and V. CONCLUSION: This study has revealed the potential of Symlet and Biorthogonal mother wavelets in the survival prediction of lung cancerpatients by using WDB radiomic features in CT images.
Authors: Laure Fournier; Lena Costaridou; Luc Bidaut; Nicolas Michoux; Frederic E Lecouvet; Lioe-Fee de Geus-Oei; Ronald Boellaard; Daniela E Oprea-Lager; Nancy A Obuchowski; Anna Caroli; Wolfgang G Kunz; Edwin H Oei; James P B O'Connor; Marius E Mayerhoefer; Manuela Franca; Angel Alberich-Bayarri; Christophe M Deroose; Christian Loewe; Rashindra Manniesing; Caroline Caramella; Egesta Lopci; Nathalie Lassau; Anders Persson; Rik Achten; Karen Rosendahl; Olivier Clement; Elmar Kotter; Xavier Golay; Marion Smits; Marc Dewey; Daniel C Sullivan; Aad van der Lugt; Nandita M deSouza Journal: Eur Radiol Date: 2021-01-25 Impact factor: 5.315
Authors: Reza Reiazi; Colin Arrowsmith; Mattea Welch; Farnoosh Abbas-Aghababazadeh; Christopher Eeles; Tony Tadic; Andrew J Hope; Scott V Bratman; Benjamin Haibe-Kains Journal: Cancers (Basel) Date: 2021-05-08 Impact factor: 6.639