Abstract
Extracting massive features from images to quantify tumors provides a new insight to solve the problem that tumor heterogeneity is difficult to assess quantitatively. However, quantification of tumors by single-mode methods often has defects such as difficulty in features extraction and high computational complexity. The multimodal approach has shown effective application prospects in solving these problems. In this paper, we propose a feature fusion method based on positron emission tomography (PET) images and clinical information, which is used to obtain features for lung metastasis prediction of soft tissue sarcomas (STSs). Random forest method was adopted to select effective features by eliminating irrelevant or redundant features, and then they were used for the prediction of the lung metastasis combined with back propagation (BP) neural network. The results show that the prediction ability of the proposed model using fusion features is better than that of the model using an image or clinical feature alone. Furthermore, a good performance can be obtained using 3 standard uptake value (SUV) features of PET image and 7 clinical features, and its average accuracy, sensitivity, and specificity on all the sets can reach 92%, 91%, and 92%, respectively. Therefore, the fusing features have the potential to predict lung metastasis for STSs.
Highlights
Sarcomas are a highly heterogeneous group of tumors classified according to the similar adult tissue types in tissue occurrence [1]
Feature selection can improve the performance of the model and help us to understand the characteristics of the data and the underlying structure, which plays a significant role in the further improvement of model and algorithm
It can be found that the prediction accuracy of the model without texture features decreased by less than 1% compared to the model with 25 features, and the sensitivity increased significantly the specificity does not seem to be as ideal. These results suggest that the effect of the 10 features is similar to that of the 26 features, which means that it may be not necessary to do a lot of complex texture feature calculations to obtain the same good prediction effect, while the basic clinical features and standard uptake value (SUV) features are easier to obtain to get than texture features
Summary
Sarcomas are a highly heterogeneous group of tumors classified according to the similar adult tissue types in tissue occurrence [1]. It is characterized by invasive or destructive growth that can recur and by distant metastasis [2]. 10%-20% of the patients with sarcomas or STSs have distant metastasis at the time of diagnosis. There is a great deficiency in the cognition of the prognostic factors of lung metastatic tumor resection and the recurrence rate after resection is high [7]. Early screening and prediction of lung metastasis can help patients with STSs find corresponding self-treatment measures at an early stage and improve the survival rate of patients
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callMore From: Computational and mathematical methods in medicine
Disclaimer: 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.
