Transformer Model Integrating CT Habitat and Deep Learning Predicts Outcomes in HCC Immunotherapy

ECOS-Net, a CT-based multitask AI model integrating habitat and deep learning features, predicted early disease control (AUC 0.817) and overall survival (C-index 0.720) in an external test set of immunotherapy-treated HCC, outperforming clinical models.

• In an external test set, the model predicted early disease control with an AUC of 0.817, significantly outperforming clinical models (p<0.05).
• For overall survival prediction, the model achieved a C-index of 0.720 in the external test set.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.