Biologically explicable multimodal model predicting local tumor progression and tumor invasiveness of hepatocellular...

Local tumor progression (LTP) of hepatocellular carcinoma (HCC) after thermal ablation (TA) is associated with tumor invasiveness and poses a significant threat to patient outcomes. We aim to build a multimodal model to explicable tumor invasiveness and reduce LTP.

From January 2015 to August 2023, 1208 HCC lesions were collected as training (n=502), validation (n=180), internal test (n=250), and external test (n=276) sets. Contrast-enhanced ultrasound (CEUS), magnetic resonance imaging (MRI), biological, clinical, and prognostic information were collected to build the model. A long short-term memory network and radiomics were used to extract image features. Logistic regression was used to combine image and clinical information. Pathological, immunohistochemical, and RNA sequencing analyses were used to explicable tumor invasiveness. Moderation analysis was applied to determine an appropriate minimum ablation margin (MAM) for high-invasiveness tumors in a safe location to reduce LTP. AUC of the multimodal model was 0.809 and 0.811 in internal and external test sets, respectively. The high-invasiveness group showed lower differentiation, higher microvascular invasion proportion, macrotrabecular-massive HCC proportion, CK-7 and GPC-3 positive rate, and increased expression of VEGFA, MMP-9, and HSPA1A (all p<0.05). KEGG and GSEA analyses revealed the upregulation of pathways related to angiogenesis, tolerance to stress response, and tumor metastasis in high-invasiveness group. The 8-mm MAM ablation strategy can effectively decrease the LTP incidence of high-invasiveness group (from 42.4% to 10.5%, p=0.027) to the level comparable to low-invasiveness group (10.5% vs. 6.1%, p=0.613) in external test set.

The multimodal model achieved satisfactory performance on classifying tumor invasiveness, and provided effective strategy for high-invasiveness tumors to reduce LTP occurrence.