Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients
Abstract Background and objective: Identifying patients suitable for conversion therapy through early non-invasive screening is crucial for tailoring treatment in advanced gastric cancer (AGC). This study aimed to develop and validate a deep learning method, utilizing preoperative computed tomograph...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-01063-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849726007733387264 |
|---|---|
| author | Saiyi Han Tong Zhang Wenzhuo Deng Shaoliang Han Honghao Wu Beier Jiang Weidong Xie Yide Chen Tao Deng Xuewen Wen Nianbo Liu Jianping Fan |
| author_facet | Saiyi Han Tong Zhang Wenzhuo Deng Shaoliang Han Honghao Wu Beier Jiang Weidong Xie Yide Chen Tao Deng Xuewen Wen Nianbo Liu Jianping Fan |
| author_sort | Saiyi Han |
| collection | DOAJ |
| description | Abstract Background and objective: Identifying patients suitable for conversion therapy through early non-invasive screening is crucial for tailoring treatment in advanced gastric cancer (AGC). This study aimed to develop and validate a deep learning method, utilizing preoperative computed tomography (CT) images, to predict the response to conversion therapy in AGC patients. This retrospective study involved 140 patients. We utilized Progressive Distill (PD) methodology to construct a deep learning model for predicting clinical response to conversion therapy based on preoperative CT images. Patients in the training set (n = 112) and in the test set (n = 28) were sourced from The First Affiliated Hospital of Wenzhou Medical University between September 2017 and November 2023. Our PD models’ performance was compared with baseline models and those utilizing Knowledge Distillation (KD), with evaluation metrics including accuracy, sensitivity, specificity, receiver operating characteristic curves, areas under the receiver operating characteristic curve (AUCs), and heat maps. The PD model exhibited the best performance, demonstrating robust discrimination of clinical response to conversion therapy with an AUC of 0.99 and accuracy of 99.11% in the training set, and 0.87 AUC and 85.71% accuracy in the test set. Sensitivity and specificity were 97.44% and 100% respectively in the training set, 85.71% and 85.71% each in the test set, suggesting absence of discernible bias. The deep learning model of PD method accurately predicts clinical response to conversion therapy in AGC patients. Further investigation is warranted to assess its clinical utility alongside clinicopathological parameters. |
| format | Article |
| id | doaj-art-dd67b9a4b99a4ed7b82126c86cb57f2e |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-dd67b9a4b99a4ed7b82126c86cb57f2e2025-08-20T03:10:20ZengNature PortfolioScientific Reports2045-23222025-05-0115111310.1038/s41598-025-01063-6Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patientsSaiyi Han0Tong Zhang1Wenzhuo Deng2Shaoliang Han3Honghao Wu4Beier Jiang5Weidong Xie6Yide Chen7Tao Deng8Xuewen Wen9Nianbo Liu10Jianping Fan11The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalDepartment of The Gastrointestinal Surgery, First Affiliated Hospital of Wenzhou Medical UniversityThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalDepartment of The Gastrointestinal Surgery, First Affiliated Hospital of Wenzhou Medical UniversityThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalDepartment of The Gastrointestinal Surgery, First Affiliated Hospital of Wenzhou Medical UniversityThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalThe Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People’s HospitalAbstract Background and objective: Identifying patients suitable for conversion therapy through early non-invasive screening is crucial for tailoring treatment in advanced gastric cancer (AGC). This study aimed to develop and validate a deep learning method, utilizing preoperative computed tomography (CT) images, to predict the response to conversion therapy in AGC patients. This retrospective study involved 140 patients. We utilized Progressive Distill (PD) methodology to construct a deep learning model for predicting clinical response to conversion therapy based on preoperative CT images. Patients in the training set (n = 112) and in the test set (n = 28) were sourced from The First Affiliated Hospital of Wenzhou Medical University between September 2017 and November 2023. Our PD models’ performance was compared with baseline models and those utilizing Knowledge Distillation (KD), with evaluation metrics including accuracy, sensitivity, specificity, receiver operating characteristic curves, areas under the receiver operating characteristic curve (AUCs), and heat maps. The PD model exhibited the best performance, demonstrating robust discrimination of clinical response to conversion therapy with an AUC of 0.99 and accuracy of 99.11% in the training set, and 0.87 AUC and 85.71% accuracy in the test set. Sensitivity and specificity were 97.44% and 100% respectively in the training set, 85.71% and 85.71% each in the test set, suggesting absence of discernible bias. The deep learning model of PD method accurately predicts clinical response to conversion therapy in AGC patients. Further investigation is warranted to assess its clinical utility alongside clinicopathological parameters.https://doi.org/10.1038/s41598-025-01063-6Advanced gastricCancer conversionTherapy deepLearningPreoperativeProgressive distill |
| spellingShingle | Saiyi Han Tong Zhang Wenzhuo Deng Shaoliang Han Honghao Wu Beier Jiang Weidong Xie Yide Chen Tao Deng Xuewen Wen Nianbo Liu Jianping Fan Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients Scientific Reports Advanced gastric Cancer conversion Therapy deep Learning Preoperative Progressive distill |
| title | Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients |
| title_full | Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients |
| title_fullStr | Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients |
| title_full_unstemmed | Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients |
| title_short | Deep learning progressive distill for predicting clinical response to conversion therapy from preoperative CT images of advanced gastric cancer patients |
| title_sort | deep learning progressive distill for predicting clinical response to conversion therapy from preoperative ct images of advanced gastric cancer patients |
| topic | Advanced gastric Cancer conversion Therapy deep Learning Preoperative Progressive distill |
| url | https://doi.org/10.1038/s41598-025-01063-6 |
| work_keys_str_mv | AT saiyihan deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT tongzhang deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT wenzhuodeng deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT shaolianghan deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT honghaowu deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT beierjiang deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT weidongxie deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT yidechen deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT taodeng deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT xuewenwen deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT nianboliu deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients AT jianpingfan deeplearningprogressivedistillforpredictingclinicalresponsetoconversiontherapyfrompreoperativectimagesofadvancedgastriccancerpatients |