Clinical Cancer Research · 2019 · 621 citations · 35 references
MedicineOncologyRadiologyDiagnostic ImagingDiagnostic RadiologyThoracic OncologyCancer StagingDeep LearningLung CancerMedical ImagingTherapy Response AssessmentTumor ImagingConvolutional Neural NetworksNon-small Cell Lung Cancer ImagingRadiomic Recurrence PredictionRadiomicsRadiomics In Lung CancerRadiomics In Lung ImagingRecurrent Neural NetworksTumor Localization
Abstract Purpose: Tumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non–small cell lung cancer (NSCLC). Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans). Results: Deep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17–17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016). Conclusions: We demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.
35
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1)
E. Eisenhauer, P. Therasse, Jan Bogaerts et al. · European Journal of Cancer · 2008 · 29.5K citations
Global cancer statistics, 2012
Lindsey A. Torre, Freddie Bray, Rebecca L. Siegel et al. · CA A Cancer Journal for Clinicians · 2015 · 27.4K citations · Full text