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
571P - Dacomitinib in treatment-naïve EGFR-mutant NSCLC patients with multiple brain metastases: Initial efficacy and safety data from a phase II study
Presenter: Yongfeng Yu
Session: Poster Display
Resources:
Abstract
572P - Multivariable five-year survival prediction model for prognosing patients with EGFR-mutated NSCLC treated with EGFR-TKIs
Presenter: Qi-An Wang
Session: Poster Display
Resources:
Abstract
573P - LUMINATE-103: Real-world treatment patterns and outcomes of patients (pts) with epidermal growth factor receptor mutant (EGFR MU), non-squamous (NSQ) locally advanced/metastatic non-small cell lung cancer (a/mNSCLC): Pooled analysis of large US electronic health record (EHR) datasets
Presenter: Byoung Chul Cho
Session: Poster Display
Resources:
Abstract
574P - Efficacy and safety of dacomitinib in treatment-naïve patients with advanced NSCLC harboring uncommon EGFR mutations
Presenter: Lin Wu
Session: Poster Display
Resources:
Abstract
575P - Efficacy and safety of dacomitinib in treatment-naïve patients with advanced NSCLC and brain metastasis: A multicenter cohort study
Presenter: Puyuan Xing
Session: Poster Display
Resources:
Abstract
576P - Clonality of both EGFR and co-occurring TP53 mutations affect the treatment efficacy of the third-generation EGFR-TKIs in advanced-stage EGFR-mutant non-small cell lung cancer
Presenter: Wen Feng Fang
Session: Poster Display
Resources:
Abstract
577P - A study of the efficacy and safety of amivantamab in EGFR exon 20 insertion (E20I) mutations in NSCLC
Presenter: Daeho Choi
Session: Poster Display
Resources:
Abstract
578P - Tyrosine kinase inhibitor treatment of elderly patients with epidermal growth factor receptor mutated advanced non-small cell lung cancer: A multi-institute retrospective study
Presenter: Ling-Jen Hung
Session: Poster Display
Resources:
Abstract
579P - Real-world study of dacomitinib as first-line treatment for patients with EGFR-mutant non-small cell lung cancer
Presenter: Ji Eun Shin
Session: Poster Display
Resources:
Abstract
580P - Efficacy and safety of dacomitinib as first-line treatment for advanced non-small cell lung cancer (NSCLC) patients with epidermal growth factor receptor <italic>(EGFR)</italic> 21L858R mutation: A multicenter, ambispective, consecutive case-series study
Presenter: Shouzheng Wang
Session: Poster Display
Resources:
Abstract