Abstract 204P
Background
Although neoadjuvant chemoradiotherapy followed by surgery is the standard treatment for esophageal cancer patients, most patients are unable to achieve pathological complete response with neoadjuvant therapy, resulting in poor outcomes. The aim of this study is to develop a method for selecting patients who can achieve pathological complete response through pre-neoadjuvant therapy chest-enhanced CT scans.
Methods
Two hundreds and one patients with esophageal cancer were enrolled and divided into a training set and a testing set in a 7:3 ratio. Radiomics features of intra-tumoral and peritumoral images were extracted from preoperative chest-enhanced CT scans of these patients. The features were dimensionally reduced in two steps. The selected intra-tumoral and peritumoral features, including marginal (with a distance of 0-3mm from the tumor) and adjacent (with a distance of 3-6mm from the tumor) ROI, were used to build models with four machine learning classifiers, including Support Vector Machine, XG-Boost, Random Forest and Naive Bayes. Models with satisfied accuracy and stability levels were considered to perform well. Finally, the performance of these well-performing models on the testing set was displayed using ROC curves.
Results
Among the 16 models, the best-performing models were the integrated (intra-tumoral and peritumoral features)-XGBoost and integrated-random forest models, which had average ROC AUCs of 0.906 and 0.918, respectively, with relative standard deviations (RSDs) of 6.26 and 6.89 in the training set. In the testing set, the AUCs were 0.845 and 0.871, respectively. There was no significant difference in the ROC curves between the two models. Table: 204P
The performance of the selected models on the testing set
Model | AUC (95% CI) | Specificity | Sensitivity |
Integrated-XGBoost | 0.845 (0.764, 0.928) | 0.864 | 0.777 |
Original-XGBoost | 0.759 (0.660, 0.857) | 0.900 | 0.592 |
Integrated-Random Forest | 0.871 (0.796, 0.946) | 0.682 | 0.933 |
Original-Random Forest | 0.795 (0.703, 0.887) | 0.825 | 0.673 |
Adjacent-Random Forest | 0.769 (0.671, 0.868) | 0.886 | 0.533 |
Integrated-Support Vector Machine | 0.719 (0.613, 0.825) | 0.795 | 0.622 |
Conclusions
The addition of peritumoral radiomics features to the radiomics analysis may improve the predictive performance of pathological response for esophageal cancer patients to neoadjuvant chemoradiotherapy.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
73TiP - Global phase III studies evaluating vepdegestrant in estrogen receptor (ER)+/human epidermal growth factor receptor 2 (HER2)- advanced breast cancer: VERITAC-2 and VERITAC-3
Presenter: Hiroji Iwata
Session: Poster Display
Resources:
Abstract
78P - First-in-human phase I study of TT-00434, an orally available FGFR (1-3) inhibitor in patients with advanced solid tumors
Presenter: Chia Jui Yen
Session: Poster Display
Resources:
Abstract
79P - Accelerated identification of recurrent neoantigens for the development of off-the-shelf cancer vaccines
Presenter: Le Son Tran
Session: Poster Display
Resources:
Abstract
80P - Safety, preliminary efficacy, and pharmacokinetics of HLX26 plus serplulimab in advanced solid tumours: An open-label, dose-escalation phase I study
Presenter: Yanmin Wu
Session: Poster Display
Resources:
Abstract
81P - A first-in-human, multiple dose and dose escalation phase I study to investigate the safety, tolerability and antitumor activity of SmarT cells plus PD-1 blocking antibodies in patients with far advanced/metastatic solid tumors
Presenter: Qin Liu
Session: Poster Display
Resources:
Abstract
82P - NEXUS: A phase I dose escalation study of selinexor plus nivolumab and ipilimumab in Asian patients with advanced/metastatic solid malignancies
Presenter: Gloria Chan
Session: Poster Display
Resources:
Abstract
83P - The updated report of phase I trial of VG2025, a non-attenuated HSV-1 oncolytic virus expressing IL-12 and IL-15/RA payloads, in patients with advanced solid tumors
Presenter: Yinan Shen
Session: Poster Display
Resources:
Abstract
84P - T cell receptor repertoire profiles of tumor -infiltrating lymphocytes improves neoantigen prioritization for personalized cancer immunotherapy
Presenter: Tran Nguyen
Session: Poster Display
Resources:
Abstract
85P - Oligometastatic solid tumors: Disease characteristics and role of local therapies
Presenter: Alshimaa Al Hanafy
Session: Poster Display
Resources:
Abstract
86P - Efficacy and safety of HLX07 monotherapy in advanced cutaneous squamous cell carcinoma: An open-label, multicentre phase II study
Presenter: Changxing Li
Session: Poster Display
Resources:
Abstract