Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell Carcinoma

Predicting treatment failure (TF) in head-and-neck squamous cell carcinoma (HNSCC) patients before treatment can help in selecting a more appropriate treatment approach. We investigated a novel radiodosiomics approach to predict TF prior to chemoradiation in HNSCC patients. Computed tomography (CT)...

Full description

Saved in:
Bibliographic Details
Main Authors: Hidemi Kamezawa, Hidetaka Arimura
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/12/6941
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849435407702294528
author Hidemi Kamezawa
Hidetaka Arimura
author_facet Hidemi Kamezawa
Hidetaka Arimura
author_sort Hidemi Kamezawa
collection DOAJ
description Predicting treatment failure (TF) in head-and-neck squamous cell carcinoma (HNSCC) patients before treatment can help in selecting a more appropriate treatment approach. We investigated a novel radiodosiomics approach to predict TF prior to chemoradiation in HNSCC patients. Computed tomography (CT) images, dose distributions (DDs), and clinical data from 172 cases were collected from a public database. The cases were divided into the training (<i>n</i> = 140) and testing (<i>n</i> = 32) datasets. A total of 1027 features, including conventional radiomic (<i>R</i>) features, local binary pattern-based (<i>L</i>) features, and topological (<i>T</i>) features, were extracted from the CT images and DDs of the tumor region. Moreover, deep (<i>D</i>) features were extracted from a deep learning-based prediction model. The Coxnet algorithm was employed to select significant features. Twenty-two treatment failure prediction models were constructed based on Rad-scores. TF prediction models were assessed using the concordance index (C-index) and statistically significant variations in the Kaplan–Meier curves between the two risk groups. The Kaplan–Meier curves of the DD-based <i>T</i> (DD-<i>T</i>) model displayed statistically significant differences. The highest C-index of the testing dataset for this model was 0.760. The proposed radiodosiomics models could potentially demonstrate greater accuracy in anticipating TF before chemoradiation in HNSCC patients.
format Article
id doaj-art-894d960e7fe648598fe13a746cc0bc03
institution Kabale University
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-894d960e7fe648598fe13a746cc0bc032025-08-20T03:26:17ZengMDPI AGApplied Sciences2076-34172025-06-011512694110.3390/app15126941Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell CarcinomaHidemi Kamezawa0Hidetaka Arimura1Department of Radiological Technology, Faculty of Fukuoka Medical Technology, Teikyo University, 6-22 Misaki-machi, Omuta 836-8505, Fukuoka, JapanDivision of Medical Quantum Science, Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Fukuoka, JapanPredicting treatment failure (TF) in head-and-neck squamous cell carcinoma (HNSCC) patients before treatment can help in selecting a more appropriate treatment approach. We investigated a novel radiodosiomics approach to predict TF prior to chemoradiation in HNSCC patients. Computed tomography (CT) images, dose distributions (DDs), and clinical data from 172 cases were collected from a public database. The cases were divided into the training (<i>n</i> = 140) and testing (<i>n</i> = 32) datasets. A total of 1027 features, including conventional radiomic (<i>R</i>) features, local binary pattern-based (<i>L</i>) features, and topological (<i>T</i>) features, were extracted from the CT images and DDs of the tumor region. Moreover, deep (<i>D</i>) features were extracted from a deep learning-based prediction model. The Coxnet algorithm was employed to select significant features. Twenty-two treatment failure prediction models were constructed based on Rad-scores. TF prediction models were assessed using the concordance index (C-index) and statistically significant variations in the Kaplan–Meier curves between the two risk groups. The Kaplan–Meier curves of the DD-based <i>T</i> (DD-<i>T</i>) model displayed statistically significant differences. The highest C-index of the testing dataset for this model was 0.760. The proposed radiodosiomics models could potentially demonstrate greater accuracy in anticipating TF before chemoradiation in HNSCC patients.https://www.mdpi.com/2076-3417/15/12/6941treatment failure predictionhead-and-neck squamous cell carcinomatopologyradiodosiomics
spellingShingle Hidemi Kamezawa
Hidetaka Arimura
Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell Carcinoma
Applied Sciences
treatment failure prediction
head-and-neck squamous cell carcinoma
topology
radiodosiomics
title Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell Carcinoma
title_full Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell Carcinoma
title_fullStr Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell Carcinoma
title_full_unstemmed Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell Carcinoma
title_short Radiodosiomics Prediction of Treatment Failures Prior to Chemoradiotherapy in Head-and-Neck Squamous Cell Carcinoma
title_sort radiodosiomics prediction of treatment failures prior to chemoradiotherapy in head and neck squamous cell carcinoma
topic treatment failure prediction
head-and-neck squamous cell carcinoma
topology
radiodosiomics
url https://www.mdpi.com/2076-3417/15/12/6941
work_keys_str_mv AT hidemikamezawa radiodosiomicspredictionoftreatmentfailurespriortochemoradiotherapyinheadandnecksquamouscellcarcinoma
AT hidetakaarimura radiodosiomicspredictionoftreatmentfailurespriortochemoradiotherapyinheadandnecksquamouscellcarcinoma