Abstract
To characterize intra-tumor heterogeneity comprehensively, we propose a multi-level fusion strategy to combine PET and CT information at the image-, matrix-and feature-levels towards improved prognosis. Specifically, we developed fusion radiomics in the context of 3 prognostic outcomes in a multi-center setting (4 centers) involving 296 head & neck cancer patients. Eight clinical parameters were first utilized to build a (1) clinical model. We also built models by extracting 127 radiomics features from (2) PET images alone; (3-8) PET and CT images fused via wavelet-based fusion (WF) using CT-weights of 0.2, 0.4, 0.6 and 0.8, gradient transfer fusion (GTF), and guided filtering-based fusion (GFF); (9) fused matrices (sumMat); (10-11) fused features constructed via feature averaging (avgFea) and feature concatenation (conFea); and finally, (12) CT images alone; above models were also expanded to include both clinical and radiomics features. Seven variations of training and testing partitions were investigated. Highest performance in 5, 6 and 5 partitions was achieved by image-level fusion strategies for RFS, MFS and OS prediction, respectively. Among all partitions, WF0.6 and WF0.8 showed significantly higher performance than CT model for RFS (C-index: 0.60±0.04vs. 0.56±0.03, p-value: 0.015) and MFS (C-index: 0.71±0.13vs. 0.62±0.08, p-value: 0.020) predictions, respectively. In partition CER 23vs. 14, WF0.6 significantly outperformed Clinical model for RFS prediction (C-index: 0.67vs. 0.53, p-value: 0.003); both avgFea and WF0.6 showed C-index of 0.64 and significantly higher than that of PET only (C-index: 0.51, p-value: 0.018 and 0.031, respectively) for OS prediction. Fusion radiomics modeling showed varying improvements compared to single modality models for different outcome predictions in different partitions, highlighting the importance of generalizing radiomics models. Image-level fusion holds potential to capture more useful characteristics.
Highlights
T HERE are approximately 600,000 new cases of head and neck (H&N) cancer every year worldwide, with 40%−50% of these resulting in death [1]
As different modalities convey different aspects of disease [15], texture and histogram features extracted from CT image quantifying the spatial distribution of tissue intensities [16]; ring-shape 18F-fluorodeoxyglucose (FDG) uptake reflecting intratumoral necrosis had prognostic value for patients with H&N squamous cell carcinoma (HNSCC) [17]; standard uptake values (SUV) of FDG-PET correlates with microvessel density characterized by perfusion CT in H&N cancer [18]
Our findings point out future directions for investigating advanced multi-modality image fusion methods in application of radiomics analyses on outcome prediction, highlighting the potential of generalizing radiomics models when utilized in a multi-center scenario
Summary
T HERE are approximately 600,000 new cases of head and neck (H&N) cancer every year worldwide, with 40%−50% of these resulting in death [1]. Aside from conventional prognostic factors such as PET standard uptake values (SUV) [2], tumor site, stage and HPV status [3], intra-tumor heterogeneity is increasingly recognized to be related to tumor development, response to therapy and metastasis in H&N cancer [4]–[6]. As different modalities convey different aspects of disease [15], texture and histogram features extracted from CT image quantifying the spatial distribution of tissue intensities [16]; ring-shape 18F-fluorodeoxyglucose (FDG) uptake reflecting intratumoral necrosis had prognostic value for patients with H&N squamous cell carcinoma (HNSCC) [17]; SUV of FDG-PET correlates with microvessel density characterized by perfusion CT in H&N cancer [18]. Use of combined PET and CT scans for visual interpretation has shown superiority for initial diagnosis and subsequence surveillance compared with use of PET or CT alone [19], [20]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
