Radiomic Analysis of CT Predicts Tumor Response in Human Lung Cancer with Radiotherapy
- PDF / 158,795 Bytes
- 3 Pages / 595.276 x 790.866 pts Page_size
- 33 Downloads / 174 Views
ORIGINAL PAPER
Radiomic Analysis of CT Predicts Tumor Response in Human Lung Cancer with Radiotherapy Mengmeng Yan 1,2 & Weidong Wang 3,4 Received: 7 May 2019 / Revised: 9 September 2020 / Accepted: 14 September 2020 # The Author(s) 2020
Abstract Purpose Radiomics features can be positioned to monitor changes throughout treatment. In this study, we evaluated machine learning for predicting tumor response by analyzing CT images of lung cancer patients treated with radiotherapy. Experimental Design For this retrospective study, screening or standard diagnostic CT images were collected for 100 patients (mean age, 67 years; range, 55–82 years; 64 men [mean age, 68 years; range, 55–82 years] and 36 women [mean age, 65 years; range, 60–72 years]) from two institutions between 2013 and 2017. Radiomics analysis was available for each patient. Features were pruned to train machine learning classifiers with 50 patients, then trained in the test dataset. Result A support vector machine classifier with 2 radiomic features (flatness and coefficient of variation) achieved an area under the receiver operating characteristic curve (AUC) of 0.91 on the test set. Conclusion The 2 radiomic features, flatness, and coefficient of variation, from the volume of interest of lung tumor, can be the biomarkers for predicting tumor response at CT. Keywords Radiomics . Lung cancer . Radiotherapy . Machine learning
Introduction Radiation therapy is a crucial and cost-effective lung cancer curative treatment [1], and its curative effect largely depends on the radiosensitivity of tumor cells of the different patients [2]. So, the valuation of radiosensitivity with respect to radiotherapy has significant potential to contribute to further therapeutic gain. Key points • Predicting the tumor response of lung cancer patients by CT images • A classification model of predicting tumor response based on quantitative imaging features * Weidong Wang [email protected] 1
Urban Vocational College of Sichuan, Chengdu, China
2
Sichuan Cancer Hospital & Institute, Chengdu, China
3
Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Chengdu 610041, China
4
Radiation Oncology, Key Laboratory of Sichuan Province, Chengdu, China
Radiomics provides a quantitative method to mine useful data as much as possible from medical images and can be applied to clinical decision support systems [3–10]. And CT-based radiomics can quantify tumor phenotypic differences in CT images using radiomic features. Radiomic features (such as intensity, shape, texture, or wavelet), extracted from medical images, when combined with clinical parameters can make clinical decision more precise [11]. It has shown a great ability to be the biomarkers in predicting clinical events of lung cancer patients, recent examples like predicting the response of enzymes, gene and immunity therapy which are associated with lung tumor [12], evaluating the drug reaction [13], radiation pneumonitis [14], and distinguishing lung cancer histologic subtypes [15]. However, there are
Data Loading...
