Related Experiment Video
Updated: Jul 19, 2026
Hybrid µCT-FMT imaging and image analysis
Published on: June 4, 2015
Radiomics and deep learning fusion model based on multiphasic CT for predicting HER2 expression status in bladder
Wenbang Pan1, Liu Yang1, Lin Yang1
1Department of General Surgery, Dalian Second People's Hospital, Dalian, China.
Background:
Human epidermal growth factor receptor 2 (HER2) overexpression is a key therapeutic target for novel antibody-drug conjugates (ADCs) like disitamab vedotin (RC48) in bladder urothelial carcinoma (BLCA), but immunohistochemistry-based assessment is limited by intratumoral heterogeneity and sampling bias. A noninvasive and reliable imaging-based approach is therefore urgently needed. Therefore, this study aimed to construct a noninvasive, imaging-based multimodal model for predicting HER2 expression status in BLCA using tri-phasic CT.
Methods:
A total of 411 patients from three institutions (2021-2024) who underwent tri-phasic contrast-enhanced computed tomography (CT) and HER2 immunohistochemistry (IHC) were included. Patients were classified as HER2-positive (IHC 2+/3+) or negative (IHC 0/1+) based on therapeutic criteria for ADCs. Patients were divided into training, internal validation, and external validation cohorts. Radiomics models, 2.5D and 3D ResNet50 deep learning models, a clinical model, and a multimodal fusion model were developed. Model performance was evaluated using receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis.
Results:
Tumor architecture (sessile pattern), hydronephrosis, pelvic pain, and radiological lymph node status were identified as independent predictors of HER2 positivity. The 2.5D ResNet50 model achieved an external area under the curve (AUC) of 0.827, significantly outperforming the 3D model (AUC =0.608). The multimodal fusion model showed the best performance, with AUCs of 0.960, 0.908, and 0.873 in the training, internal validation, and external validation cohorts, respectively. In the external cohort, accuracy, sensitivity, and specificity were 0.819, 0.857, and 0.784. The multimodal model significantly outperformed all single-modality models.
Conclusions:
A tri-phasic CT-based multimodal model enables noninvasive assessment of HER2 expression status in BLCA, providing a promising tool for selection of patients likely to benefit from ADC therapy.
Insights
A new tri-phasic CT imaging model accurately predicts Human Epidermal growth factor Receptor 2 (HER2) expression in bladder cancer. This noninvasive approach aids in selecting patients for targeted antibody-drug conjugate (ADC) therapy.
Area of Science:
- Oncology
- Radiology
- Medical Imaging
Background:
- Human Epidermal growth factor Receptor 2 (HER2) overexpression is a critical therapeutic target in bladder urothelial carcinoma (BLCA), particularly for antibody-drug conjugates (ADCs).
- Current immunohistochemistry (IHC)-based HER2 assessment in BLCA faces limitations due to intratumoral heterogeneity and sampling bias.
- There is a significant need for noninvasive, reliable imaging-based methods to predict HER2 expression status in BLCA.
Purpose of the Study:
- To develop and validate a noninvasive, imaging-based multimodal model for predicting HER2 expression status in BLCA.
- To utilize tri-phasic computed tomography (CT) imaging features for HER2 status prediction.
- To assess the performance of the multimodal model against single-modality approaches.
Main Methods:
- A cohort of 411 patients with BLCA from three institutions underwent tri-phasic contrast-enhanced CT and HER2 IHC.
- Patients were categorized as HER2-positive (IHC 2+/3+) or HER2-negative (IHC 0/1+).
- Radiomics, 2.5D/3D ResNet50 deep learning, clinical, and multimodal fusion models were developed and evaluated using ROC analysis, calibration curves, and decision curve analysis.
Main Results:
- Tumor architecture, hydronephrosis, pelvic pain, and lymph node status were identified as independent predictors of HER2 positivity.
- The 2.5D ResNet50 deep learning model achieved an external AUC of 0.827, outperforming the 3D model (AUC=0.608).
- The multimodal fusion model demonstrated superior performance with external AUCs of 0.873, accuracy 0.819, sensitivity 0.857, and specificity 0.784, significantly outperforming single-modality models.
Conclusions:
- A tri-phasic CT-based multimodal model provides a noninvasive method for assessing HER2 expression status in BLCA.
- This imaging-based model shows promise for identifying patients who may benefit from HER2-targeted ADC therapy.
- The multimodal approach offers a more accurate and reliable prediction of HER2 status compared to individual imaging or clinical factors.
