A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy
Abstract Early regression—the regression in tumor volume during the initial phase of radiotherapy (approximately 2 weeks after treatment initiation)—is a common occurrence during radiotherapy. This rapid radiation-induced tumor regression may alter target coordinates, necessitating adaptive radiothe...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-05-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-12170-z |
| _version_ | 1811254221905854464 |
|---|---|
| author | Shohei Tanaka Noriyuki Kadoya Yuto Sugai Mariko Umeda Miyu Ishizawa Yoshiyuki Katsuta Kengo Ito Ken Takeda Keiichi Jingu |
| author_facet | Shohei Tanaka Noriyuki Kadoya Yuto Sugai Mariko Umeda Miyu Ishizawa Yoshiyuki Katsuta Kengo Ito Ken Takeda Keiichi Jingu |
| author_sort | Shohei Tanaka |
| collection | DOAJ |
| description | Abstract Early regression—the regression in tumor volume during the initial phase of radiotherapy (approximately 2 weeks after treatment initiation)—is a common occurrence during radiotherapy. This rapid radiation-induced tumor regression may alter target coordinates, necessitating adaptive radiotherapy (ART). We developed a deep learning-based radiomics (DLR) approach to predict early head and neck tumor regression and thereby facilitate ART. Primary gross tumor volume (GTVp) was monitored in 96 patients and nodal GTV (GTVn) in 79 patients during treatment. All patients underwent two computed tomography (CT) scans: one before the start of radiotherapy for initial planning and one during radiotherapy for boost planning. Patients were assigned to regression and nonregression groups according to their median tumor regression rate (ΔGTV/treatment day from initial to boost CT scan). We input a GTV image into the convolutional neural network model, which was pretrained using natural image datasets, via transfer learning. The deep features were extracted from the last fully connected layer. To clarify the prognostic power of the deep features, machine learning models were trained. The models then predicted the regression and nonregression of GTVp and GTVn and evaluated the predictive performance by 0.632 + bootstrap area under the curve (AUC). Predictive performance for GTVp regression was highest using the InceptionResNetv2 model (mean AUC = 0.75) and that for GTVn was highest using NASNetLarge (mean AUC = 0.73). Both models outperformed the handcrafted radiomics features (mean AUC = 0.63 for GTVp and 0.61 for GTVn) or clinical factors (0.64 and 0.67, respectively). DLR may facilitate ART for improved radiation side-effects and target coverage. |
| first_indexed | 2024-04-12T17:03:11Z |
| format | Article |
| id | doaj.art-3249c9ff1d1c44e3a008bbcacdfbc949 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T17:03:11Z |
| publishDate | 2022-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-3249c9ff1d1c44e3a008bbcacdfbc9492022-12-22T03:24:00ZengNature PortfolioScientific Reports2045-23222022-05-0112111310.1038/s41598-022-12170-zA deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapyShohei Tanaka0Noriyuki Kadoya1Yuto Sugai2Mariko Umeda3Miyu Ishizawa4Yoshiyuki Katsuta5Kengo Ito6Ken Takeda7Keiichi Jingu8Department of Radiation Oncology, Tohoku University Graduate School of MedicineDepartment of Radiation Oncology, Tohoku University Graduate School of MedicineDepartment of Radiation Oncology, Tohoku University Graduate School of MedicineDepartment of Radiation Oncology, Tohoku University Graduate School of MedicineDepartment of Radiological Technology, School of Health Sciences, Faculty of Medicine, Tohoku UniversityDepartment of Radiation Oncology, Tohoku University Graduate School of MedicineDepartment of Radiation Oncology, Tohoku University Graduate School of MedicineDepartment of Radiological Technology, School of Health Sciences, Faculty of Medicine, Tohoku UniversityDepartment of Radiation Oncology, Tohoku University Graduate School of MedicineAbstract Early regression—the regression in tumor volume during the initial phase of radiotherapy (approximately 2 weeks after treatment initiation)—is a common occurrence during radiotherapy. This rapid radiation-induced tumor regression may alter target coordinates, necessitating adaptive radiotherapy (ART). We developed a deep learning-based radiomics (DLR) approach to predict early head and neck tumor regression and thereby facilitate ART. Primary gross tumor volume (GTVp) was monitored in 96 patients and nodal GTV (GTVn) in 79 patients during treatment. All patients underwent two computed tomography (CT) scans: one before the start of radiotherapy for initial planning and one during radiotherapy for boost planning. Patients were assigned to regression and nonregression groups according to their median tumor regression rate (ΔGTV/treatment day from initial to boost CT scan). We input a GTV image into the convolutional neural network model, which was pretrained using natural image datasets, via transfer learning. The deep features were extracted from the last fully connected layer. To clarify the prognostic power of the deep features, machine learning models were trained. The models then predicted the regression and nonregression of GTVp and GTVn and evaluated the predictive performance by 0.632 + bootstrap area under the curve (AUC). Predictive performance for GTVp regression was highest using the InceptionResNetv2 model (mean AUC = 0.75) and that for GTVn was highest using NASNetLarge (mean AUC = 0.73). Both models outperformed the handcrafted radiomics features (mean AUC = 0.63 for GTVp and 0.61 for GTVn) or clinical factors (0.64 and 0.67, respectively). DLR may facilitate ART for improved radiation side-effects and target coverage.https://doi.org/10.1038/s41598-022-12170-z |
| spellingShingle | Shohei Tanaka Noriyuki Kadoya Yuto Sugai Mariko Umeda Miyu Ishizawa Yoshiyuki Katsuta Kengo Ito Ken Takeda Keiichi Jingu A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy Scientific Reports |
| title | A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy |
| title_full | A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy |
| title_fullStr | A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy |
| title_full_unstemmed | A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy |
| title_short | A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy |
| title_sort | deep learning based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy |
| url | https://doi.org/10.1038/s41598-022-12170-z |
| work_keys_str_mv | AT shoheitanaka adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT noriyukikadoya adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT yutosugai adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT marikoumeda adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT miyuishizawa adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT yoshiyukikatsuta adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT kengoito adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT kentakeda adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT keiichijingu adeeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT shoheitanaka deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT noriyukikadoya deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT yutosugai deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT marikoumeda deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT miyuishizawa deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT yoshiyukikatsuta deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT kengoito deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT kentakeda deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy AT keiichijingu deeplearningbasedradiomicsapproachtopredictheadandnecktumorregressionforadaptiveradiotherapy |