Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning Model

Objectives: Predicting the response to chemotherapy can lead to the optimization of neoadjuvant chemotherapy (NAC). The present study aimed to develop a non-invasive prediction model of therapeutic response to NAC for rectal cancer (RC). Methods: A dataset of the prechemotherapy computed tomography...

Full description

Saved in:
Bibliographic Details
Main Authors: Shunsuke Kubota, Taiichi Wakiya, Hajime Morohashi, Takuya Miura, Taishu Kanda, Masashi Matsuzaka, Yoshihiro Sasaki, Yoshiyuki Sakamoto, Kenichi Hakamada
Format: Article
Language:English
Published: The Japan Society of Coloproctology 2025-04-01
Series:Journal of the Anus, Rectum and Colon
Subjects:
Online Access:https://www.jstage.jst.go.jp/article/jarc/9/2/9_2024-085/_pdf/-char/en
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311121625841664
author Shunsuke Kubota
Taiichi Wakiya
Hajime Morohashi
Takuya Miura
Taishu Kanda
Masashi Matsuzaka
Yoshihiro Sasaki
Yoshiyuki Sakamoto
Kenichi Hakamada
author_facet Shunsuke Kubota
Taiichi Wakiya
Hajime Morohashi
Takuya Miura
Taishu Kanda
Masashi Matsuzaka
Yoshihiro Sasaki
Yoshiyuki Sakamoto
Kenichi Hakamada
author_sort Shunsuke Kubota
collection DOAJ
description Objectives: Predicting the response to chemotherapy can lead to the optimization of neoadjuvant chemotherapy (NAC). The present study aimed to develop a non-invasive prediction model of therapeutic response to NAC for rectal cancer (RC). Methods: A dataset of the prechemotherapy computed tomography (CT) images of 57 patients from multiple institutions who underwent rectal surgery after three courses of S-1 and oxaliplatin (SOX) NAC for RC was collected. The therapeutic response to NAC was pathologically confirmed. It was then predicted whether they were pathologic responders or non-responders. Cases were divided into training, validation and test datasets. A CT patch-based predictive model was developed using a residual convolutional neural network and the predictive performance was evaluated. Binary logistic regression analysis of prechemotherapy clinical factors showed that none of the independent variables were significantly associated with the non-responders. Results: Among the 49 patients in the training and validation datasets, there were 21 (42.9%) and 28 (57.1%) responders and non-responders, respectively. A total of 3,857 patches were extracted from the 49 patients. In the validation dataset, the average sensitivity, specificity and accuracy was 97.3, 95.7 and 96.8%, respectively. Furthermore, the area under the receiver operating characteristic curve (AUC) was 0.994 (95% CI, 0.991-0.997; P<0.001). In the test dataset, which included 750 patches from 8 patients, the predictive model demonstrated high specificity (89.9%) and the AUC was 0.846 (95% CI, 0.817-0.875; P<0.001). Conclusions: The non-invasive deep learning model using prechemotherapy CT images exhibited high predictive performance in predicting the pathological therapeutic response to SOX NAC.
format Article
id doaj-art-1c494419f08145b0875205afd4ff0952
institution Kabale University
issn 2432-3853
language English
publishDate 2025-04-01
publisher The Japan Society of Coloproctology
record_format Article
series Journal of the Anus, Rectum and Colon
spelling doaj-art-1c494419f08145b0875205afd4ff09522025-08-20T03:53:32ZengThe Japan Society of ColoproctologyJournal of the Anus, Rectum and Colon2432-38532025-04-019220221210.23922/jarc.2024-0852024-085Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning ModelShunsuke Kubota0Taiichi Wakiya1Hajime Morohashi2Takuya Miura3Taishu Kanda4Masashi Matsuzaka5Yoshihiro Sasaki6Yoshiyuki Sakamoto7Kenichi Hakamada8Department of Gastroenterological Surgery, Hirosaki University Graduate School of MedicineDepartment of Gastroenterological Surgery, Hirosaki University Graduate School of MedicineDepartment of Gastroenterological Surgery, Hirosaki University Graduate School of MedicineDepartment of Gastroenterological Surgery, Hirosaki University Graduate School of MedicineDepartment of Gastroenterological Surgery, Hirosaki University Graduate School of MedicineDepartment of Medical Informatics, Hirosaki University HospitalDepartment of Medical Informatics, Hirosaki University HospitalDepartment of Gastroenterological Surgery, Hirosaki University Graduate School of MedicineDepartment of Gastroenterological Surgery, Hirosaki University Graduate School of MedicineObjectives: Predicting the response to chemotherapy can lead to the optimization of neoadjuvant chemotherapy (NAC). The present study aimed to develop a non-invasive prediction model of therapeutic response to NAC for rectal cancer (RC). Methods: A dataset of the prechemotherapy computed tomography (CT) images of 57 patients from multiple institutions who underwent rectal surgery after three courses of S-1 and oxaliplatin (SOX) NAC for RC was collected. The therapeutic response to NAC was pathologically confirmed. It was then predicted whether they were pathologic responders or non-responders. Cases were divided into training, validation and test datasets. A CT patch-based predictive model was developed using a residual convolutional neural network and the predictive performance was evaluated. Binary logistic regression analysis of prechemotherapy clinical factors showed that none of the independent variables were significantly associated with the non-responders. Results: Among the 49 patients in the training and validation datasets, there were 21 (42.9%) and 28 (57.1%) responders and non-responders, respectively. A total of 3,857 patches were extracted from the 49 patients. In the validation dataset, the average sensitivity, specificity and accuracy was 97.3, 95.7 and 96.8%, respectively. Furthermore, the area under the receiver operating characteristic curve (AUC) was 0.994 (95% CI, 0.991-0.997; P<0.001). In the test dataset, which included 750 patches from 8 patients, the predictive model demonstrated high specificity (89.9%) and the AUC was 0.846 (95% CI, 0.817-0.875; P<0.001). Conclusions: The non-invasive deep learning model using prechemotherapy CT images exhibited high predictive performance in predicting the pathological therapeutic response to SOX NAC.https://www.jstage.jst.go.jp/article/jarc/9/2/9_2024-085/_pdf/-char/encomputational predictionctmachine learningdeep learningnacrc
spellingShingle Shunsuke Kubota
Taiichi Wakiya
Hajime Morohashi
Takuya Miura
Taishu Kanda
Masashi Matsuzaka
Yoshihiro Sasaki
Yoshiyuki Sakamoto
Kenichi Hakamada
Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning Model
Journal of the Anus, Rectum and Colon
computational prediction
ct
machine learning
deep learning
nac
rc
title Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning Model
title_full Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning Model
title_fullStr Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning Model
title_full_unstemmed Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning Model
title_short Prediction of the Therapeutic Response to Neoadjuvant Chemotherapy for Rectal Cancer Using a Deep Learning Model
title_sort prediction of the therapeutic response to neoadjuvant chemotherapy for rectal cancer using a deep learning model
topic computational prediction
ct
machine learning
deep learning
nac
rc
url https://www.jstage.jst.go.jp/article/jarc/9/2/9_2024-085/_pdf/-char/en
work_keys_str_mv AT shunsukekubota predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT taiichiwakiya predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT hajimemorohashi predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT takuyamiura predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT taishukanda predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT masashimatsuzaka predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT yoshihirosasaki predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT yoshiyukisakamoto predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel
AT kenichihakamada predictionofthetherapeuticresponsetoneoadjuvantchemotherapyforrectalcancerusingadeeplearningmodel