Poster Poster Program Therapy Physics

CT-Based Radiomics for Preoperative Prediction Lymph Node Metastases of the Esophagogastric Junction Adenocarcinoma

Abstract
Purpose

To investigate the value of CT-based radiomics for preoperative prediction lymph node status of the esophagogastric junction adenocarcinoma.

Methods

The imaging and clinicopathological data of 160 esophagogastric junction adenocarcinoma patients June 2018 to June 2024. According to the ratio of 7:3, the enrolled cases were randomly divided into the training set and the test set. There are three steps for the radiomics features selection, namely statistical analysis, correlation analysis, and The Least Absolute Shrinkage and Selection Operator (LASSO). The best features were input into the Multilayer Perceptron (MLP) model, and the radiomics model was constructed using five-fold cross-validation. The Rad-score (RS) was calculated. Logistic regression was used to establish a clinical factor (degree of differentiation) model and a combined model of radiomics combined with clinical factors to evaluate whether there was lymph node metastasis in patients with adenocarcinoma at the esophagogastric junction. The clinical model, radiomics model, and combined model were assessed by ROC curve, calibration curve, and DCA curve, respectively.

Results

The AUC of the clinical model, radiomics model and combined model were 0.592, 0.842 and 0.823 in the training set, respectively. In the test set, were 0.689, 0.833 and 0.863, respectively. Delong's test showed that there was a statistically significant difference of AUC between the combined model and the radiomics model, the combined model and the clinical model (p=0.049, p=0.017) in the test set. There was no statistical difference of AUC between the radiomics model and the clinical model (p=0.133). Through the comprehensive evaluation of the combined model in DCA, ROC curve and calibration curve, it was shown that the combined model had better clinical value.

Conclusion

The combined model incorporating the independent clinical factor and radiomics signature has favorable predictive value for preoperative prediction lymph node metastases of the esophagogastric junction adenocarcinoma.

People

Related

Similar sessions

Poster Poster Program
Jul 19 · 07:00
Python-Based Automation Framework for Annual Machine QA Data Archiving In Qatrack+

Annual water-tank measurements help ensure beam characteristics remain consistent with commissioning baselines. However, the lack of a standardized processing workflow and decentralized data storage makes it difficult to analyze...

Syed Bilal Ahmad, PhD
Therapy Physics 0 people interested
Poster Poster Program
Jul 19 · 07:00
User Expectations and Current Availability of HDR Brachytherapy Audits In Europe

The aim of this work was to evaluate the need to implement more dosimetric audits in high‐dose‐rate brachytherapy (HDR-BT) in Europe and to identify which characteristics such audits should meet according to users.

Javier Vijande, PhD Laura Oliver Cañamás
Therapy Physics 0 people interested