Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images
Abstract Objectives Lymphovascular invasion significantly impacts the prognosis of urothelial carcinoma of the bladder. Traditional lymphovascular invasion detection methods are time-consuming and costly. This study aims to develop a deep learning-based model to preoperatively predict lymphovascular...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-05-01
|
| Series: | Insights into Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13244-025-01988-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849725307077001216 |
|---|---|
| author | Bangxin Xiao Yang Lv Canjie Peng Zongjie Wei Qiao Xv Fajin Lv Qing Jiang Huayun Liu Feng Li Yingjie Xv Quanhao He Mingzhao Xiao |
| author_facet | Bangxin Xiao Yang Lv Canjie Peng Zongjie Wei Qiao Xv Fajin Lv Qing Jiang Huayun Liu Feng Li Yingjie Xv Quanhao He Mingzhao Xiao |
| author_sort | Bangxin Xiao |
| collection | DOAJ |
| description | Abstract Objectives Lymphovascular invasion significantly impacts the prognosis of urothelial carcinoma of the bladder. Traditional lymphovascular invasion detection methods are time-consuming and costly. This study aims to develop a deep learning-based model to preoperatively predict lymphovascular invasion status in urothelial carcinoma of bladder using CT images. Methods Data and CT images of 577 patients across four medical centers were retrospectively collected. The largest tumor slices from the transverse, coronal, and sagittal planes were selected and used to train CNN models (InceptionV3, DenseNet121, ResNet18, ResNet34, ResNet50, and VGG11). Deep learning features were extracted and visualized using Grad-CAM. Principal Component Analysis reduced features to 64. Using the extracted features, Decision Tree, XGBoost, and LightGBM models were trained with 5-fold cross-validation and ensembled in a stacking model. Clinical risk factors were identified through logistic regression analyses and combined with DL scores to enhance lymphovascular invasion prediction accuracy. Results The ResNet50-based model achieved an AUC of 0.818 in the validation set and 0.708 in the testing set. The combined model showed an AUC of 0.794 in the validation set and 0.767 in the testing set, demonstrating robust performance across diverse data. Conclusion We developed a robust radiomics model based on deep learning features from CT images to preoperatively predict lymphovascular invasion status in urothelial carcinoma of the bladder. This model offers a non-invasive, cost-effective tool to assist clinicians in personalized treatment planning. Critical relevance statement We developed a robust radiomics model based on deep learning features from CT images to preoperatively predict lymphovascular invasion status in urothelial carcinoma of the bladder. Key Points We developed a deep learning feature-based stacking model to predict lymphovascular invasion in urothelial carcinoma of the bladder patients using CT. Max cross sections from three dimensions of the CT image are used to train the CNN model. We made comparisons across six CNN networks, including ResNet50. Graphical Abstract |
| format | Article |
| id | doaj-art-e400a4a2b4b64753981f94dc642b5e9f |
| institution | DOAJ |
| issn | 1869-4101 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Insights into Imaging |
| spelling | doaj-art-e400a4a2b4b64753981f94dc642b5e9f2025-08-20T03:10:30ZengSpringerOpenInsights into Imaging1869-41012025-05-0116111210.1186/s13244-025-01988-6Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT imagesBangxin Xiao0Yang Lv1Canjie Peng2Zongjie Wei3Qiao Xv4Fajin Lv5Qing Jiang6Huayun Liu7Feng Li8Yingjie Xv9Quanhao He10Mingzhao Xiao11Department of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, Yongchuan Hospital of Chongqing Medical UniversityDepartment of Radiology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The Second Affiliated Hospital of Chongqing Medical UniversityOutpatient Department, The Second Affiliated Hospital, Army Medical UniversityDepartment of Urology, Chongqing University Three Gorges HospitalDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityDepartment of Urology, The First Affiliated Hospital of Chongqing Medical UniversityAbstract Objectives Lymphovascular invasion significantly impacts the prognosis of urothelial carcinoma of the bladder. Traditional lymphovascular invasion detection methods are time-consuming and costly. This study aims to develop a deep learning-based model to preoperatively predict lymphovascular invasion status in urothelial carcinoma of bladder using CT images. Methods Data and CT images of 577 patients across four medical centers were retrospectively collected. The largest tumor slices from the transverse, coronal, and sagittal planes were selected and used to train CNN models (InceptionV3, DenseNet121, ResNet18, ResNet34, ResNet50, and VGG11). Deep learning features were extracted and visualized using Grad-CAM. Principal Component Analysis reduced features to 64. Using the extracted features, Decision Tree, XGBoost, and LightGBM models were trained with 5-fold cross-validation and ensembled in a stacking model. Clinical risk factors were identified through logistic regression analyses and combined with DL scores to enhance lymphovascular invasion prediction accuracy. Results The ResNet50-based model achieved an AUC of 0.818 in the validation set and 0.708 in the testing set. The combined model showed an AUC of 0.794 in the validation set and 0.767 in the testing set, demonstrating robust performance across diverse data. Conclusion We developed a robust radiomics model based on deep learning features from CT images to preoperatively predict lymphovascular invasion status in urothelial carcinoma of the bladder. This model offers a non-invasive, cost-effective tool to assist clinicians in personalized treatment planning. Critical relevance statement We developed a robust radiomics model based on deep learning features from CT images to preoperatively predict lymphovascular invasion status in urothelial carcinoma of the bladder. Key Points We developed a deep learning feature-based stacking model to predict lymphovascular invasion in urothelial carcinoma of the bladder patients using CT. Max cross sections from three dimensions of the CT image are used to train the CNN model. We made comparisons across six CNN networks, including ResNet50. Graphical Abstracthttps://doi.org/10.1186/s13244-025-01988-6Urothelial carcinoma of the bladderLymphovascular invasionDeep learning modelStacking learning modelMulticenter retrospective study |
| spellingShingle | Bangxin Xiao Yang Lv Canjie Peng Zongjie Wei Qiao Xv Fajin Lv Qing Jiang Huayun Liu Feng Li Yingjie Xv Quanhao He Mingzhao Xiao Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images Insights into Imaging Urothelial carcinoma of the bladder Lymphovascular invasion Deep learning model Stacking learning model Multicenter retrospective study |
| title | Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images |
| title_full | Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images |
| title_fullStr | Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images |
| title_full_unstemmed | Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images |
| title_short | Deep learning feature-based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using CT images |
| title_sort | deep learning feature based model for predicting lymphovascular invasion in urothelial carcinoma of bladder using ct images |
| topic | Urothelial carcinoma of the bladder Lymphovascular invasion Deep learning model Stacking learning model Multicenter retrospective study |
| url | https://doi.org/10.1186/s13244-025-01988-6 |
| work_keys_str_mv | AT bangxinxiao deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT yanglv deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT canjiepeng deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT zongjiewei deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT qiaoxv deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT fajinlv deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT qingjiang deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT huayunliu deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT fengli deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT yingjiexv deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT quanhaohe deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages AT mingzhaoxiao deeplearningfeaturebasedmodelforpredictinglymphovascularinvasioninurothelialcarcinomaofbladderusingctimages |