Artificial Intelligence-Driven Ultrasound Identifies Rare Triphasic Colon Cancer and Unlocks Candidate Genomic Mechanisms via Ultrasound Genomic Techniques

Abstract

Background:

Colon cancer is a heterogeneous disease, and rare subtypes like triphasic colon cancer are difficult to detect with standard methods. Artificial intelligence (AI)-driven ultrasound combined with genomic analysis offers a promising approach to improve subtype identification and uncover molecular mechanisms.

Methods:

The authors used an AI-driven ultrasound model to identify rare triphasic colon cancer, characterized by a mix of epithelial, mesenchymal, and proliferative components. The molecular features were validated using immunohistochemistry, targeting classical epithelial markers, mesenchymal markers, and proliferation indices. Subsequently, ultrasound genomic techniques were applied to map transcriptomic alterations in conventional colon cancer onto ultrasound images. Differentially expressed genes were identified using the edgeR package. Pearson correlation analysis was performed to assess the relationship between imaging features and molecular markers.

Results:

The AI-driven ultrasound model successfully identified rare triphasic features in colon cancer. These imaging features showed significant correlation with immunohistochemical expression of epithelial markers, mesenchymal markers, and proliferation index. Moreover, ultrasound genomic techniques revealed that multiple oncogenic transcripts could be spatially mapped to distinct patterns within the ultrasound images of conventional colon cancer and were involved in classical cancer-related pathway.

Conclusions:

AI-enhanced ultrasound imaging enables noninvasive identification of rare triphasic colon cancer and reveals functional molecular signatures in general colon cancer. This integrative approach may support future precision diagnostics and image-guided therapies.