Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic Carcinoma

Purpose: To predict distant metastasis (DM) in patients with borderline resectable pancreatic carcinoma using delta-radiomics features calculated from contrast-enhanced computed tomography (CECT) and non-CECT images. Methods and Materials: Among 250 patients who underwent radiation therapy at our in...

Full description

Saved in:
Bibliographic Details
Main Authors: Takanori Adachi, PhD, Mitsuhiro Nakamura, PhD, Takahiro Iwai, PhD, Michio Yoshimura, MD, PhD, Takashi Mizowaki, MD, PhD
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Advances in Radiation Oncology
Online Access:http://www.sciencedirect.com/science/article/pii/S245210942400232X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846148845639041024
author Takanori Adachi, PhD
Mitsuhiro Nakamura, PhD
Takahiro Iwai, PhD
Michio Yoshimura, MD, PhD
Takashi Mizowaki, MD, PhD
author_facet Takanori Adachi, PhD
Mitsuhiro Nakamura, PhD
Takahiro Iwai, PhD
Michio Yoshimura, MD, PhD
Takashi Mizowaki, MD, PhD
author_sort Takanori Adachi, PhD
collection DOAJ
description Purpose: To predict distant metastasis (DM) in patients with borderline resectable pancreatic carcinoma using delta-radiomics features calculated from contrast-enhanced computed tomography (CECT) and non-CECT images. Methods and Materials: Among 250 patients who underwent radiation therapy at our institution between February 2013 and December 2021, 67 patients were deemed eligible. A total of 11 clinical features and 3906 radiomics features were incorporated. Radiomics features were extracted from CECT and non-CECT images, and the differences between these features were calculated, resulting in delta-radiomics features. The patients were randomly divided into the training (70%) and test (30%) data sets for model development and validation. Predictive models were developed with clinical features (clinical model), radiomics features (radiomics model), and a combination of the abovementioned features (hybrid model) using Fine-Gray regression (FG) and random survival forest (RSF). Optimal hyperparameters were determined using stratified 5-fold cross-validation. Subsequently, the developed models were applied to the remaining test data sets, and the patients were divided into high- or low-risk groups based on their risk scores. Prognostic power was assessed using the concordance index, with 95% CIs obtained through 2000 bootstrapping iterations. Statistical significance between the above groups was assessed using Gray's test. Results: At a median follow-up period of 23.8 months, 47 (70.1%) patients developed DM. The concordance indices of the FG-based clinical, radiomics, and hybrid models were 0.548, 0.603, and 0.623, respectively, in the test data set, whereas those of the RSF-based models were 0.598, 0.680, and 0.727, respectively. The RSF-based model, including delta-radiomics features, significantly divided the cumulative incidence curves into two risk groups (P < .05). The feature map of the gray-level size-zone matrix showed that the difference in feature values between CECT and non-CECT images correlated with the incidence of DM. Conclusions: Delta-radiomics features obtained from CECT and non-CECT images using RSF successfully predict the incidence of DM in patients with borderline resectable pancreatic carcinoma.
format Article
id doaj-art-d6cfba93cffd417d988d8a59c7af9697
institution Kabale University
issn 2452-1094
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Advances in Radiation Oncology
spelling doaj-art-d6cfba93cffd417d988d8a59c7af96972024-11-30T07:13:21ZengElsevierAdvances in Radiation Oncology2452-10942025-01-01101101669Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic CarcinomaTakanori Adachi, PhD0Mitsuhiro Nakamura, PhD1Takahiro Iwai, PhD2Michio Yoshimura, MD, PhD3Takashi Mizowaki, MD, PhD4Department of Radiation Oncology and Image-Applied Therapy, Kyoto University, Shogoin, Sakyo-ku, Kyoto, JapanDepartment of Radiation Oncology and Image-Applied Therapy, Kyoto University, Shogoin, Sakyo-ku, Kyoto, Japan; Department of Advanced Medical Physics, Graduate School of Medicine, Kyoto University, Shogoin, Sakyo-ku, Kyoto, Japan; Corresponding author: Mitsuhiro Nakamura, PhD.Department of Radiation Oncology and Image-Applied Therapy, Kyoto University, Shogoin, Sakyo-ku, Kyoto, JapanDepartment of Radiation Oncology and Image-Applied Therapy, Kyoto University, Shogoin, Sakyo-ku, Kyoto, JapanDepartment of Radiation Oncology and Image-Applied Therapy, Kyoto University, Shogoin, Sakyo-ku, Kyoto, JapanPurpose: To predict distant metastasis (DM) in patients with borderline resectable pancreatic carcinoma using delta-radiomics features calculated from contrast-enhanced computed tomography (CECT) and non-CECT images. Methods and Materials: Among 250 patients who underwent radiation therapy at our institution between February 2013 and December 2021, 67 patients were deemed eligible. A total of 11 clinical features and 3906 radiomics features were incorporated. Radiomics features were extracted from CECT and non-CECT images, and the differences between these features were calculated, resulting in delta-radiomics features. The patients were randomly divided into the training (70%) and test (30%) data sets for model development and validation. Predictive models were developed with clinical features (clinical model), radiomics features (radiomics model), and a combination of the abovementioned features (hybrid model) using Fine-Gray regression (FG) and random survival forest (RSF). Optimal hyperparameters were determined using stratified 5-fold cross-validation. Subsequently, the developed models were applied to the remaining test data sets, and the patients were divided into high- or low-risk groups based on their risk scores. Prognostic power was assessed using the concordance index, with 95% CIs obtained through 2000 bootstrapping iterations. Statistical significance between the above groups was assessed using Gray's test. Results: At a median follow-up period of 23.8 months, 47 (70.1%) patients developed DM. The concordance indices of the FG-based clinical, radiomics, and hybrid models were 0.548, 0.603, and 0.623, respectively, in the test data set, whereas those of the RSF-based models were 0.598, 0.680, and 0.727, respectively. The RSF-based model, including delta-radiomics features, significantly divided the cumulative incidence curves into two risk groups (P < .05). The feature map of the gray-level size-zone matrix showed that the difference in feature values between CECT and non-CECT images correlated with the incidence of DM. Conclusions: Delta-radiomics features obtained from CECT and non-CECT images using RSF successfully predict the incidence of DM in patients with borderline resectable pancreatic carcinoma.http://www.sciencedirect.com/science/article/pii/S245210942400232X
spellingShingle Takanori Adachi, PhD
Mitsuhiro Nakamura, PhD
Takahiro Iwai, PhD
Michio Yoshimura, MD, PhD
Takashi Mizowaki, MD, PhD
Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic Carcinoma
Advances in Radiation Oncology
title Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic Carcinoma
title_full Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic Carcinoma
title_fullStr Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic Carcinoma
title_full_unstemmed Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic Carcinoma
title_short Delta-Radiomics Approach Using Contrast-Enhanced and Noncontrast-Enhanced Computed Tomography Images for Predicting Distant Metastasis in Patients With Borderline Resectable Pancreatic Carcinoma
title_sort delta radiomics approach using contrast enhanced and noncontrast enhanced computed tomography images for predicting distant metastasis in patients with borderline resectable pancreatic carcinoma
url http://www.sciencedirect.com/science/article/pii/S245210942400232X
work_keys_str_mv AT takanoriadachiphd deltaradiomicsapproachusingcontrastenhancedandnoncontrastenhancedcomputedtomographyimagesforpredictingdistantmetastasisinpatientswithborderlineresectablepancreaticcarcinoma
AT mitsuhironakamuraphd deltaradiomicsapproachusingcontrastenhancedandnoncontrastenhancedcomputedtomographyimagesforpredictingdistantmetastasisinpatientswithborderlineresectablepancreaticcarcinoma
AT takahiroiwaiphd deltaradiomicsapproachusingcontrastenhancedandnoncontrastenhancedcomputedtomographyimagesforpredictingdistantmetastasisinpatientswithborderlineresectablepancreaticcarcinoma
AT michioyoshimuramdphd deltaradiomicsapproachusingcontrastenhancedandnoncontrastenhancedcomputedtomographyimagesforpredictingdistantmetastasisinpatientswithborderlineresectablepancreaticcarcinoma
AT takashimizowakimdphd deltaradiomicsapproachusingcontrastenhancedandnoncontrastenhancedcomputedtomographyimagesforpredictingdistantmetastasisinpatientswithborderlineresectablepancreaticcarcinoma