Vision Transformers for Preoperative CT-Based Prediction of Histopathologic Chemotherapy Response Score in High-Grade Serous Ovarian Carcinoma
Summary: arXiv:2604.09197v1 Announce Type: cross
Abstract
Purpose: High-grade serous ovarian carcinoma (HGSOC) is characterized by pronounced biological and spatial heterogeneity and is frequently diagnosed at an advanced stage. Neoadjuvant chemotherapy (NACT) followed by delayed primary surgery is commonly employed in patients unsuitable for primary cytoreduction. The Chemotherapy Response Score (CRS) is a validated histopathological biomarker of response to NACT, but it is only available postoperatively. In this study, we investigate whether pre-treatment computed tomography (CT) imaging and clinical data can be used to predict CRS as an investigational decision-support adjunct to inform multidisciplinary team (MDT) discussions regarding expected treatment response.
Methods
We proposed a 2.5D multimodal deep learning framework that processes lesion-dense omental slices using a pre-trained Vision Transformer encoder and integrates the resulting visual representations with clinical variables through an intermediate fusion module to predict CRS.
Results
Our multimodal model, integrating imaging and clinical data, achieved a ROC-AUC of 0.95 alongside 95% accuracy and 80% precision on the internal test cohort (IEO, n=41 patients). On the external test set (OV04, n=70 patients), it achieved a ROC-AUC of 0.68, alongside 67% accuracy and 75% precision.
Conclusion
These preliminary results demonstrate the feasibility of transformer-based deep learning for preoperative prediction of CRS in HGSOC using routine clinical data and CT imaging. As an investigational, pre-treatment decision-support tool, this approach may assist MDT discussions by providing early, non-invasive estimates of treatment response.
Key Findings
- High-grade serous ovarian carcinoma (HGSOC) presents significant treatment challenges due to its advanced stage at diagnosis.
- The Chemotherapy Response Score (CRS) is a critical biomarker for assessing response to neoadjuvant chemotherapy (NACT).
- A novel 2.5D multimodal deep learning framework was developed to enhance prediction capabilities.
- Integration of CT imaging and clinical data resulted in a high ROC-AUC of 0.95 in internal testing.
- External validation showed a ROC-AUC of 0.68, indicating room for improvement and further validation.
- This approach aims to provide early insights into treatment response, potentially improving clinical decision-making.
Future Directions
The ongoing research in this area emphasizes the need for larger cohorts and diverse datasets to enhance the robustness of the model. Future studies will also explore the integration of additional imaging modalities and clinical parameters to further refine the predictive capabilities of the framework. As the technology matures, it holds the potential to become a standard adjunct in preoperative assessment for HGSOC, ultimately leading to improved patient outcomes and personalized treatment strategies.