Cargando…

A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery

SIMPLE SUMMARY: The authors conducted this research to improve the prediction of how patients with esophageal cancer respond to a treatment called neoadjuvant chemoradiotherapy, which can enhance survival rates. However, doctors struggle to accurately predict how well a patient will respond to this...

Descripción completa

Detalles Bibliográficos
Autores principales: Yap, Wing-Keen, Hsiao, Ing-Tsung, Yap, Wing-Lake, Tsai, Tsung-You, Lu, Yi-An, Yang, Chan-Keng, Peng, Meng-Ting, Su, En-Lin, Cheng, Shih-Chun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10669191/
https://www.ncbi.nlm.nih.gov/pubmed/38002072
http://dx.doi.org/10.3390/biomedicines11113072
_version_ 1785149214107369472
author Yap, Wing-Keen
Hsiao, Ing-Tsung
Yap, Wing-Lake
Tsai, Tsung-You
Lu, Yi-An
Yang, Chan-Keng
Peng, Meng-Ting
Su, En-Lin
Cheng, Shih-Chun
author_facet Yap, Wing-Keen
Hsiao, Ing-Tsung
Yap, Wing-Lake
Tsai, Tsung-You
Lu, Yi-An
Yang, Chan-Keng
Peng, Meng-Ting
Su, En-Lin
Cheng, Shih-Chun
author_sort Yap, Wing-Keen
collection PubMed
description SIMPLE SUMMARY: The authors conducted this research to improve the prediction of how patients with esophageal cancer respond to a treatment called neoadjuvant chemoradiotherapy, which can enhance survival rates. However, doctors struggle to accurately predict how well a patient will respond to this treatment using existing imaging methods. To address this, the researchers developed a computer-based method called DCRNet, that not only analyzes medical images but also considers the distribution of radiation therapy doses on the radiotherapy treatment plans to make more accurate predictions. They tested this method on 80 patients with esophageal cancer and found that the HRNetV2p model with DCR performed the best, significantly improving prediction accuracy compared to other models. This breakthrough has the potential to help doctors better anticipate patient responses to treatment, which could lead to more personalized and effective care, and improving the treatment planning of radiotherapy. ABSTRACT: Esophageal cancer is a deadly disease, and neoadjuvant chemoradiotherapy can improve patient survival, particularly for patients achieving a pathological complete response (ypCR). However, existing imaging methods struggle to accurately predict ypCR. This study explores computer-aided detection methods, considering both imaging data and radiotherapy dose variations to enhance prediction accuracy. It involved patients with node-positive esophageal squamous cell carcinoma undergoing neoadjuvant chemoradiotherapy and surgery, with data collected from 2014 to 2017, randomly split into five subsets for 5-fold cross-validation. The algorithm DCRNet, an advanced version of OCRNet, integrates RT dose distribution into dose contextual representations (DCR), combining dose and pixel representation with ten soft regions. Among the 80 enrolled patients (mean age 55.68 years, primarily male, with stage III disease and middle-part lesions), the ypCR rate was 28.75%, showing no significant demographic or disease differences between the ypCR and non-ypCR groups. Among the three summarization methods, the maximum value across the CTV method produced the best results with an AUC of 0.928. The HRNetV2p model with DCR performed the best among the four backbone models tested, with an AUC of 0.928 (95% CI, 0.884–0.972) based on 5-fold cross-validation, showing significant improvement compared to other models. This underscores DCR-equipped models’ superior AUC outcomes. The study highlights the potential of dose-guided deep learning in ypCR prediction, necessitating larger, multicenter studies to validate the results.
format Online
Article
Text
id pubmed-10669191
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106691912023-11-16 A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery Yap, Wing-Keen Hsiao, Ing-Tsung Yap, Wing-Lake Tsai, Tsung-You Lu, Yi-An Yang, Chan-Keng Peng, Meng-Ting Su, En-Lin Cheng, Shih-Chun Biomedicines Article SIMPLE SUMMARY: The authors conducted this research to improve the prediction of how patients with esophageal cancer respond to a treatment called neoadjuvant chemoradiotherapy, which can enhance survival rates. However, doctors struggle to accurately predict how well a patient will respond to this treatment using existing imaging methods. To address this, the researchers developed a computer-based method called DCRNet, that not only analyzes medical images but also considers the distribution of radiation therapy doses on the radiotherapy treatment plans to make more accurate predictions. They tested this method on 80 patients with esophageal cancer and found that the HRNetV2p model with DCR performed the best, significantly improving prediction accuracy compared to other models. This breakthrough has the potential to help doctors better anticipate patient responses to treatment, which could lead to more personalized and effective care, and improving the treatment planning of radiotherapy. ABSTRACT: Esophageal cancer is a deadly disease, and neoadjuvant chemoradiotherapy can improve patient survival, particularly for patients achieving a pathological complete response (ypCR). However, existing imaging methods struggle to accurately predict ypCR. This study explores computer-aided detection methods, considering both imaging data and radiotherapy dose variations to enhance prediction accuracy. It involved patients with node-positive esophageal squamous cell carcinoma undergoing neoadjuvant chemoradiotherapy and surgery, with data collected from 2014 to 2017, randomly split into five subsets for 5-fold cross-validation. The algorithm DCRNet, an advanced version of OCRNet, integrates RT dose distribution into dose contextual representations (DCR), combining dose and pixel representation with ten soft regions. Among the 80 enrolled patients (mean age 55.68 years, primarily male, with stage III disease and middle-part lesions), the ypCR rate was 28.75%, showing no significant demographic or disease differences between the ypCR and non-ypCR groups. Among the three summarization methods, the maximum value across the CTV method produced the best results with an AUC of 0.928. The HRNetV2p model with DCR performed the best among the four backbone models tested, with an AUC of 0.928 (95% CI, 0.884–0.972) based on 5-fold cross-validation, showing significant improvement compared to other models. This underscores DCR-equipped models’ superior AUC outcomes. The study highlights the potential of dose-guided deep learning in ypCR prediction, necessitating larger, multicenter studies to validate the results. MDPI 2023-11-16 /pmc/articles/PMC10669191/ /pubmed/38002072 http://dx.doi.org/10.3390/biomedicines11113072 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yap, Wing-Keen
Hsiao, Ing-Tsung
Yap, Wing-Lake
Tsai, Tsung-You
Lu, Yi-An
Yang, Chan-Keng
Peng, Meng-Ting
Su, En-Lin
Cheng, Shih-Chun
A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery
title A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery
title_full A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery
title_fullStr A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery
title_full_unstemmed A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery
title_short A Radiotherapy Dose Map-Guided Deep Learning Method for Predicting Pathological Complete Response in Esophageal Cancer Patients after Neoadjuvant Chemoradiotherapy Followed by Surgery
title_sort radiotherapy dose map-guided deep learning method for predicting pathological complete response in esophageal cancer patients after neoadjuvant chemoradiotherapy followed by surgery
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10669191/
https://www.ncbi.nlm.nih.gov/pubmed/38002072
http://dx.doi.org/10.3390/biomedicines11113072
work_keys_str_mv AT yapwingkeen aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT hsiaoingtsung aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT yapwinglake aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT tsaitsungyou aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT luyian aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT yangchankeng aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT pengmengting aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT suenlin aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT chengshihchun aradiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT yapwingkeen radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT hsiaoingtsung radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT yapwinglake radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT tsaitsungyou radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT luyian radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT yangchankeng radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT pengmengting radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT suenlin radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery
AT chengshihchun radiotherapydosemapguideddeeplearningmethodforpredictingpathologicalcompleteresponseinesophagealcancerpatientsafterneoadjuvantchemoradiotherapyfollowedbysurgery