Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET Images
Background: This study aimed to propose a machine learning model to predict the local response of resectable locally advanced esophageal squamous cell carcinoma (LA-ESCC) treated by neoadjuvant chemoradiotherapy (NCRT) using pretreatment 18-fluorodeoxyglucose positron emission tomography (FDG PET) i...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/6/1049 |
| _version_ | 1797531055407759360 |
|---|---|
| author | Yuji Murakami Daisuke Kawahara Shigeyuki Tani Katsumaro Kubo Tsuyoshi Katsuta Nobuki Imano Yuki Takeuchi Ikuno Nishibuchi Akito Saito Yasushi Nagata |
| author_facet | Yuji Murakami Daisuke Kawahara Shigeyuki Tani Katsumaro Kubo Tsuyoshi Katsuta Nobuki Imano Yuki Takeuchi Ikuno Nishibuchi Akito Saito Yasushi Nagata |
| author_sort | Yuji Murakami |
| collection | DOAJ |
| description | Background: This study aimed to propose a machine learning model to predict the local response of resectable locally advanced esophageal squamous cell carcinoma (LA-ESCC) treated by neoadjuvant chemoradiotherapy (NCRT) using pretreatment 18-fluorodeoxyglucose positron emission tomography (FDG PET) images. Methods: The local responses of 98 patients were categorized into two groups (complete response and noncomplete response). We performed a radiomics analysis using five segmentations created on FDG PET images, resulting in 4250 features per patient. To construct a machine learning model, we used the least absolute shrinkage and selection operator (LASSO) regression to extract radiomics features optimal for the prediction. Then, a prediction model was constructed by using a neural network classifier. The training model was evaluated with 5-fold cross-validation. Results: By the LASSO analysis of the training data, 22 radiomics features were extracted. In the testing data, the average accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve score of the five prediction models were 89.6%, 92.7%, 89.5%, and 0.95, respectively. Conclusions: The proposed machine learning model using radiomics showed promising predictive accuracy of the local response of LA-ESCC treated by NCRT. |
| first_indexed | 2024-03-10T10:38:42Z |
| format | Article |
| id | doaj.art-10118f6ccc9a4d9393c19ebcd6e44bf6 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T10:38:42Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-10118f6ccc9a4d9393c19ebcd6e44bf62023-11-21T23:07:01ZengMDPI AGDiagnostics2075-44182021-06-01116104910.3390/diagnostics11061049Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET ImagesYuji Murakami0Daisuke Kawahara1Shigeyuki Tani2Katsumaro Kubo3Tsuyoshi Katsuta4Nobuki Imano5Yuki Takeuchi6Ikuno Nishibuchi7Akito Saito8Yasushi Nagata9Department of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanSchool of Medicine, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanDepartment of Radiation Oncology, Graduate School of Biomedical & Health Sciences, Hiroshima University, Hiroshima 734-8551, JapanBackground: This study aimed to propose a machine learning model to predict the local response of resectable locally advanced esophageal squamous cell carcinoma (LA-ESCC) treated by neoadjuvant chemoradiotherapy (NCRT) using pretreatment 18-fluorodeoxyglucose positron emission tomography (FDG PET) images. Methods: The local responses of 98 patients were categorized into two groups (complete response and noncomplete response). We performed a radiomics analysis using five segmentations created on FDG PET images, resulting in 4250 features per patient. To construct a machine learning model, we used the least absolute shrinkage and selection operator (LASSO) regression to extract radiomics features optimal for the prediction. Then, a prediction model was constructed by using a neural network classifier. The training model was evaluated with 5-fold cross-validation. Results: By the LASSO analysis of the training data, 22 radiomics features were extracted. In the testing data, the average accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve score of the five prediction models were 89.6%, 92.7%, 89.5%, and 0.95, respectively. Conclusions: The proposed machine learning model using radiomics showed promising predictive accuracy of the local response of LA-ESCC treated by NCRT.https://www.mdpi.com/2075-4418/11/6/1049esophageal cancersquamous cell carcinomaneoadjuvant chemoradiotherapypathological responsemachine learningradiomics |
| spellingShingle | Yuji Murakami Daisuke Kawahara Shigeyuki Tani Katsumaro Kubo Tsuyoshi Katsuta Nobuki Imano Yuki Takeuchi Ikuno Nishibuchi Akito Saito Yasushi Nagata Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET Images Diagnostics esophageal cancer squamous cell carcinoma neoadjuvant chemoradiotherapy pathological response machine learning radiomics |
| title | Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET Images |
| title_full | Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET Images |
| title_fullStr | Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET Images |
| title_full_unstemmed | Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET Images |
| title_short | Predicting the Local Response of Esophageal Squamous Cell Carcinoma to Neoadjuvant Chemoradiotherapy by Radiomics with a Machine Learning Method Using <sup>18</sup>F-FDG PET Images |
| title_sort | predicting the local response of esophageal squamous cell carcinoma to neoadjuvant chemoradiotherapy by radiomics with a machine learning method using sup 18 sup f fdg pet images |
| topic | esophageal cancer squamous cell carcinoma neoadjuvant chemoradiotherapy pathological response machine learning radiomics |
| url | https://www.mdpi.com/2075-4418/11/6/1049 |
| work_keys_str_mv | AT yujimurakami predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT daisukekawahara predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT shigeyukitani predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT katsumarokubo predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT tsuyoshikatsuta predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT nobukiimano predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT yukitakeuchi predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT ikunonishibuchi predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT akitosaito predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages AT yasushinagata predictingthelocalresponseofesophagealsquamouscellcarcinomatoneoadjuvantchemoradiotherapybyradiomicswithamachinelearningmethodusingsup18supffdgpetimages |