BACKGROUND AND PURPOSE: Prediction of local failure in radiotherapy patients with non-small cell lung cancer (NSCLC) remains a challenging task. Recent evidence suggests that FDG-PET images can be used to predict outcomes. We investigate an alternative multimodality image-feature approach for predicting post-radiotherapy tumor progression in NSCLC. MATERIAL AND METHODS: We analyzed pre-treatment FDG-PET/CT studies of twenty-seven NSCLC patients for local and loco-regional failures. Thirty-two tumor region features based on SUV or HU, intensity-volume-histogram (IVH) and texture characteristics were extracted. Statistical analysis was performed using Spearman's correlation (rs) and multivariable logistic regression. RESULTS: For loco-regional recurrence, IVH variables had the highest univariate association. In PET, IVH-slope reached rs=0.3426 (p=0.0403). Motion correction slightly improved correlation of texture features. In CT, coefficient of variation had the highest association rs=-0.2665 (p=0.0871). Similarly for local failure, a CT-IVH parameter reached rs=0.4530 (p=0.0105). For loco-regional and local failures, a 2-parameter model of PET-V(80) and CT-V(70) yielded rs=0.4854 (p=0.0067) and rs=0.5908 (p=0.0013), respectively. Addition of dosimetric variables provided improvement in cases of loco-regional but not local failures. CONCLUSIONS: We proposed a feature-based approach to evaluate radiation tumor response. Our study demonstrates that multimodality image-feature modeling provides better performance compared to existing metrics and holds promise for individualizing radiotherapy planning.
BACKGROUND AND PURPOSE: Prediction of local failure in radiotherapy patients with non-small cell lung cancer (NSCLC) remains a challenging task. Recent evidence suggests that FDG-PET images can be used to predict outcomes. We investigate an alternative multimodality image-feature approach for predicting post-radiotherapy tumor progression in NSCLC. MATERIAL AND METHODS: We analyzed pre-treatment FDG-PET/CT studies of twenty-seven NSCLCpatients for local and loco-regional failures. Thirty-two tumor region features based on SUV or HU, intensity-volume-histogram (IVH) and texture characteristics were extracted. Statistical analysis was performed using Spearman's correlation (rs) and multivariable logistic regression. RESULTS: For loco-regional recurrence, IVH variables had the highest univariate association. In PET, IVH-slope reached rs=0.3426 (p=0.0403). Motion correction slightly improved correlation of texture features. In CT, coefficient of variation had the highest association rs=-0.2665 (p=0.0871). Similarly for local failure, a CT-IVH parameter reached rs=0.4530 (p=0.0105). For loco-regional and local failures, a 2-parameter model of PET-V(80) and CT-V(70) yielded rs=0.4854 (p=0.0067) and rs=0.5908 (p=0.0013), respectively. Addition of dosimetric variables provided improvement in cases of loco-regional but not local failures. CONCLUSIONS: We proposed a feature-based approach to evaluate radiation tumor response. Our study demonstrates that multimodality image-feature modeling provides better performance compared to existing metrics and holds promise for individualizing radiotherapy planning.
Authors: Matthew J Nyflot; Fei Yang; Darrin Byrd; Stephen R Bowen; George A Sandison; Paul E Kinahan Journal: J Med Imaging (Bellingham) Date: 2015-08-05
Authors: Nitin Ohri; Fenghai Duan; Bradley S Snyder; Bo Wei; Mitchell Machtay; Abass Alavi; Barry A Siegel; Douglas W Johnson; Jeffrey D Bradley; Albert DeNittis; Maria Werner-Wasik; Issam El Naqa Journal: J Nucl Med Date: 2016-02-11 Impact factor: 10.057
Authors: Ralph T H Leijenaar; Sara Carvalho; Emmanuel Rios Velazquez; Wouter J C van Elmpt; Chintan Parmar; Otto S Hoekstra; Corneline J Hoekstra; Ronald Boellaard; André L A J Dekker; Robert J Gillies; Hugo J W L Aerts; Philippe Lambin Journal: Acta Oncol Date: 2013-09-09 Impact factor: 4.089