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
87TiP - Phase I expansion study of the tissue factor (TF)–targeting antibody-drug conjugate (ADC) XB002 as a single-agent and combination therapy in patients with advanced solid tumors (JEWEL-101)
Presenter: Mustafa Syed
Session: Poster Display
Resources:
Abstract
88TiP - A phase Ib study of HMBD-001, a monoclonal antibody targeting HER3, with or without chemotherapy in patients with genetic aberrations in HER3 signaling
Presenter: Nick Pavlakis
Session: Poster Display
Resources:
Abstract
93P - Efficacy and safety of fruquintinib (F) + best supportive care (BSC) vs placebo (P) + BSC in refractory metastatic colorectal cancer (mCRC): Asian vs non-Asian outcomes in FRESCO-2
Presenter: Daisuke Kotani
Session: Poster Display
Resources:
Abstract
94P - Sidedness-dependent prognostic impact of gene alterations in metastatic colorectal cancer in the nationwide cancer genome screening project in Japan (SCRUM-Japan GI-SCREEN)
Presenter: Takeshi Kajiwara
Session: Poster Display
Resources:
Abstract
95P - Interim results of a prospective randomized controlled study to compare the clinical outcomes of total neoadjuvant therapy vs long course chemoradiotherapy in locally advanced carcinoma rectum
Presenter: Sandip Barik
Session: Poster Display
Resources:
Abstract
96P - Tyrosine kinase inhibitor (TKI) plus PD-1 blockade in TKI-responsive MSS/pMMR metastatic colorectal adenocarcinoma (mCRC): Updated results of TRAP study
Presenter: Jingdong Zhang
Session: Poster Display
Resources:
Abstract
97P - Asian subgroup analysis of the phase III LEAP-017 trial of lenvatinib plus pembrolizumab vs standard-of-care in previously treated metastatic colorectal cancer (mCRC)
Presenter: Rui-Hua Xu
Session: Poster Display
Resources:
Abstract
98P - Real clinical impact of postoperative surgical complications after colon cancer surgery
Presenter: Toru Aoyama
Session: Poster Display
Resources:
Abstract
99P - Extended lymphadenectomy may not be necessary for MSI-H colon cancer patients after immunotherapy
Presenter: Rongxin Zhang
Session: Poster Display
Resources:
Abstract
100P - Identification of phenomic data in the pathogenesis of colorectal cancer: A UK biobank data analysis
Presenter: Shirin Hui Tan
Session: Poster Display
Resources:
Abstract