ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images
Background: Accurate estimation of recurrence risk for cervical cancer plays a pivot role in making individualized treatment plans. We aimed to develop and externally validate an end-to-end deep learning model for predicting recurrence risk in cervical cancer patients following surgery by using mult...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Translational Oncology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1936523325000129 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591877918949376 |
|---|---|
| author | Ji Wu Jian Li Bo Huang Sunbin Dong Luyang Wu Xiping Shen Zhigang Zheng |
| author_facet | Ji Wu Jian Li Bo Huang Sunbin Dong Luyang Wu Xiping Shen Zhigang Zheng |
| author_sort | Ji Wu |
| collection | DOAJ |
| description | Background: Accurate estimation of recurrence risk for cervical cancer plays a pivot role in making individualized treatment plans. We aimed to develop and externally validate an end-to-end deep learning model for predicting recurrence risk in cervical cancer patients following surgery by using multiparametric MRI images. Methods: The clinicopathologic data and multiparametric MRI images of 406 cervical cancer patients from three institutions were collected. We designed a novel deep learning model called “ConvXGB” for predicting recurrence risk by combining the convolutional neural network (CNN) and eXtreme Gradient Boost (XGBoost). The predictive performance of the ConvXGB model was evaluated using time-dependent area under curve (AUC), compared with the deep learning radio-clinical model, clinical model, conventional radiomics nomogram and an existing histology-specific tool. The potential of the ConvXGB model in predicting the recurrence-free survival (RFS) and overall survival (OS) was assessed. Results: The ConvXGB model outperformed other models in predicting recurrence risk, with AUCs for 1 and 3 year-RFS of 0.872(95% CI, 0.857–0.906) and 0.882(95% CI, 0.860–0.904) respectively in the test cohort. This model showed better discrimination, calibration and clinical utility. Grad-CAM analysis was adopted to help clinicians better understand the predictive results. Moreover, Kaplan–Meier survival analysis revealed that patients who were stratified into high-risk group by the ConvXGB model were significantly susceptible to higher cumulative recurrence risk rates and worse outcome. Conclusion: The ConvXGB model allowed for predicting postoperative recurrence risk in cervical cancer patients and for stratifying the risk of RFS and OS. |
| format | Article |
| id | doaj-art-e4e0e91541e34db6a9e0b6a0c4ad2645 |
| institution | Kabale University |
| issn | 1936-5233 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Translational Oncology |
| spelling | doaj-art-e4e0e91541e34db6a9e0b6a0c4ad26452025-01-22T05:41:37ZengElsevierTranslational Oncology1936-52332025-02-0152102281ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI imagesJi Wu0Jian Li1Bo Huang2Sunbin Dong3Luyang Wu4Xiping Shen5Zhigang Zheng6Department of Radiology, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, Jiangsu Province, China; Department of General surgery, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, Jiangsu Province, ChinaDepartment of Radiology, Changshu No.2 People's Hospital, The Affiliated Changshu Hospital of Nantong University, Changshu, Jiangsu, ChinaDepartment of Radiology, Municipal Hospital Affiliated to Nanjing Medical University, Suzhou, Jiangsu Province, ChinaDepartment of Radiology, Municipal Hospital Affiliated to Nanjing Medical University, Suzhou, Jiangsu Province, ChinaDepartment of Radiology, Municipal Hospital Affiliated to Nanjing Medical University, Suzhou, Jiangsu Province, ChinaDepartment of Radiology, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, Jiangsu Province, China; Department of General surgery, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, Jiangsu Province, China; Corresponding authors.State Key Laboratory of Oncogenes and Related Genes, Shanghai Cancer Institute, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Department of Radiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Corresponding authors.Background: Accurate estimation of recurrence risk for cervical cancer plays a pivot role in making individualized treatment plans. We aimed to develop and externally validate an end-to-end deep learning model for predicting recurrence risk in cervical cancer patients following surgery by using multiparametric MRI images. Methods: The clinicopathologic data and multiparametric MRI images of 406 cervical cancer patients from three institutions were collected. We designed a novel deep learning model called “ConvXGB” for predicting recurrence risk by combining the convolutional neural network (CNN) and eXtreme Gradient Boost (XGBoost). The predictive performance of the ConvXGB model was evaluated using time-dependent area under curve (AUC), compared with the deep learning radio-clinical model, clinical model, conventional radiomics nomogram and an existing histology-specific tool. The potential of the ConvXGB model in predicting the recurrence-free survival (RFS) and overall survival (OS) was assessed. Results: The ConvXGB model outperformed other models in predicting recurrence risk, with AUCs for 1 and 3 year-RFS of 0.872(95% CI, 0.857–0.906) and 0.882(95% CI, 0.860–0.904) respectively in the test cohort. This model showed better discrimination, calibration and clinical utility. Grad-CAM analysis was adopted to help clinicians better understand the predictive results. Moreover, Kaplan–Meier survival analysis revealed that patients who were stratified into high-risk group by the ConvXGB model were significantly susceptible to higher cumulative recurrence risk rates and worse outcome. Conclusion: The ConvXGB model allowed for predicting postoperative recurrence risk in cervical cancer patients and for stratifying the risk of RFS and OS.http://www.sciencedirect.com/science/article/pii/S1936523325000129Cervical cancerRecurrence-free survival;Overall survivalDeep learningMRI scan |
| spellingShingle | Ji Wu Jian Li Bo Huang Sunbin Dong Luyang Wu Xiping Shen Zhigang Zheng ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images Translational Oncology Cervical cancer Recurrence-free survival;Overall survival Deep learning MRI scan |
| title | ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images |
| title_full | ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images |
| title_fullStr | ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images |
| title_full_unstemmed | ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images |
| title_short | ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images |
| title_sort | convxgb a novel deep learning model to predict recurrence risk of early stage cervical cancer following surgery using multiparametric mri images |
| topic | Cervical cancer Recurrence-free survival;Overall survival Deep learning MRI scan |
| url | http://www.sciencedirect.com/science/article/pii/S1936523325000129 |
| work_keys_str_mv | AT jiwu convxgbanoveldeeplearningmodeltopredictrecurrenceriskofearlystagecervicalcancerfollowingsurgeryusingmultiparametricmriimages AT jianli convxgbanoveldeeplearningmodeltopredictrecurrenceriskofearlystagecervicalcancerfollowingsurgeryusingmultiparametricmriimages AT bohuang convxgbanoveldeeplearningmodeltopredictrecurrenceriskofearlystagecervicalcancerfollowingsurgeryusingmultiparametricmriimages AT sunbindong convxgbanoveldeeplearningmodeltopredictrecurrenceriskofearlystagecervicalcancerfollowingsurgeryusingmultiparametricmriimages AT luyangwu convxgbanoveldeeplearningmodeltopredictrecurrenceriskofearlystagecervicalcancerfollowingsurgeryusingmultiparametricmriimages AT xipingshen convxgbanoveldeeplearningmodeltopredictrecurrenceriskofearlystagecervicalcancerfollowingsurgeryusingmultiparametricmriimages AT zhigangzheng convxgbanoveldeeplearningmodeltopredictrecurrenceriskofearlystagecervicalcancerfollowingsurgeryusingmultiparametricmriimages |