AUTHOR=Li Kaiyuan , Li Yuetong , Wang Zhulin , Huang Chunyao , Sun Shaowu , Liu Xu , Fan Wenbo , Zhang Guoqing , Li Xiangnan 

TITLE=Delta-radiomics based on CT predicts pathologic complete response in ESCC treated with neoadjuvant immunochemotherapy and surgery

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1131883

DOI=10.3389/fonc.2023.1131883

ISSN=2234-943X

ABSTRACT=Background and purpose: Unnecessary surgery can be avoided, and more appropriate treatment plans can be developed for patients if the efficacy of neoadjuvant immunochemotherapy for esophageal cancer (EC) can be predicted before surgery. The purpose of this study was to evaluate the ability of machine learning models based on delta features of immunochemotherapy CT images to predict the efficacy of neoadjuvant immunochemotherapy in patients with esophageal squamous cell carcinoma (ESCC) compared with machine learning models based solely on postimmunochemotherapy CT images.
Materials and methods: A total of 95 patients were enrolled in our study and randomly divided into the training group (n = 66) and the test group (n = 29). We extracted preimmunochemotherapy radiomics features from preimmunochemotherapy enhanced CT images in the preimmunochemotherapy group (pregroup). Similarly, we extracted postimmunochemotherapy radiomics features from postimmunochemotherapy enhanced CT images in the postimmunochemotherapy group (postgroup). We subtracted the preimmunochemotherapy features from the postimmunochemotherapy features, and then we obtained a series of new radiomics features which were included in the delta group. The reduction and screening of radiomics features were carried out by using the Mann‒Whitney U test and LASSO regression. Five pairwise machine learning models were established. The performance of the models was evaluated by receiver operating characteristic (ROC) curves and decision curves.
Results: The radiomics signature of the postgroup was composed of 6 radiomics features, and the radiomics signature of the delta-group was composed of 8 radiomics features. The area under the ROC curve (AUC) of the machine learning model with the best efficacy in the postgroup reached 0.824 (0.706-0.917), and the machine learning model with the best efficacy in the delta-group reached an AUC value of 0.848 (0.765-0.917). The decision curve showed that our machine learning models had good predictive performance. The delta group performed better than the postgroup for each corresponding machine learning model.
Conclusions: We established machine learning models that have good predictive efficacy and can provide certain reference values for clinical treatment decision-making. Our machine learning models based on delta imaging features performed better than the machine learning models based on single time-stage postimmunochemotherapy imaging features.