Digital Health Innovation and Informatics

PV QA 2 - Poster Viewing Q&A 2

MO_17_2469 - Radiomics Analysis Using Contrast-Enhanced CT: Predict Treatment Response to Pulsed Low Dose Rate Radiation Therapy in Gastric Carcinoma with Peritoneal Cavity Metastasis

Monday, October 22
10:45 AM - 12:15 PM
Location: Innovation Hub, Exhibit Hall 3

Radiomics Analysis Using Contrast-Enhanced CT: Predict Treatment Response to Pulsed Low Dose Rate Radiation Therapy in Gastric Carcinoma with Peritoneal Cavity Metastasis
Z. Hou1, S. Wan1, S. Li2, K. Wang2, J. Liu2, J. Yan2, B. Liu2, and Y. Yang2; 1State Key Laboratory of Bioelectronics, Laboratory for Medical Electronics, School of Biological Sciences and Medical Engineering, Southeast University, Nanjing, China, 2The Comprehensive Cancer Centre of Nanjing Drum Tower Hospital, Medical School of Nanjing University & Clinical Cancer Institute of Nanjing University, Nanjing, China

Purpose/Objective(s): To determine the feasibility of radiomic analysis for predicting the therapeutic response of gastric carcinoma with peritoneal cavity metastasis (GCPCM) to pulsed low dose rate radiotherapy (PLDRT) using contrast-enhanced computed tomography (CECT) images.

Materials/Methods: Pretreatment CECT images of 43 GCPCM patients were analyzed. Patients with complete response (CR) and partial response (PR) were considered responders, while stable disease (SD) and progressive disease (PD) as non-responders. 1117 radiomic features (including 13 shape-based, 18 first order-based, 74 texture-based, 276 Laplacian of Gaussian [LoG]-based and 736 wavelet-based) were quantified from tumor region. The capability of each feature on treatment response classification was assessed using Kruskal-Wallis test (P < 0.05) and receiver operating characteristic (ROC) analysis. Moreover, artificial neural network (ANN) and k-nearest neighbor (KNN) predictive models were constructed based on the training set (18 responders, 14 non-responders) and the testing set (6 responders, 5 non-responders) validated the reliability of the models. Comparison between the performances of the models was performed by using McNemar’s test.

Results: The analyses showed that six features (1 first order-based, 1 texture-based, 1 LoG-based, and 3 wavelet-based) were significantly different between responders and non-responders (areas under the ROC curves [AUCs] range from 0.686 to 0.728). Both two prediction models based on features extracted from CECT showed potential in predicting the treatment response with higher accuracies (ANN: 0.714, KNN: 0.749 for training set; ANN: 0.816, KNN: 0.816 for testing set). No statistical difference was observed in the performance of the two classifiers (P = 0.999).

Conclusion: Pretreatment radiomics analysis using CECT can potentially provide important information regarding the therapeutic response to PLDRT for GCPCM, improving risk stratification.

Author Disclosure: Z. Hou: None. S. Li: None. K. Wang: None.

Send Email for Zhen Hou


Assets

MO_17_2469 - Radiomics Analysis Using Contrast-Enhanced CT: Predict Treatment Response to Pulsed Low Dose Rate Radiation Therapy in Gastric Carcinoma with Peritoneal Cavity Metastasis



Attendees who have favorited this

Please enter your access key

The asset you are trying to access is locked. Please enter your access key to unlock.

Send Email for Radiomics Analysis Using Contrast-Enhanced CT: Predict Treatment Response to Pulsed Low Dose Rate Radiation Therapy in Gastric Carcinoma with Peritoneal Cavity Metastasis