# Improved Detection of Small (<2 cm) Hepatocellular Carcinoma via Deep Learning-Based Synthetic CT Hepatic Arteriography: A Multi-Center External Validation Study

## TL;DR

A deep learning model improves detection of small liver cancers in CT scans, offering a non-invasive alternative with high accuracy.

## Contribution

A deep learning model generates synthetic CTHA images from LDCT, improving detection of small HCCs with multi-center validation.

## Key findings

- Synthetic CTHA detected 69.6% of sub-centimeter HCCs versus 47.8% with LDCT in internal validation.
- External validation confirmed improved detection of small HCCs with synthetic CTHA over LDCT.
- Synthetic CTHA showed high structural fidelity with good similarity and signal-to-noise metrics.

## Abstract

Background/Objectives: Early detection of hepatocellular carcinoma (HCC), particularly small lesions (<2 cm), which is crucial for curative treatment, remains challenging with conventional liver dynamic computed tomography (LDCT). We aimed to develop a deep learning algorithm to generate synthetic CT during hepatic arteriography (CTHA) from non-invasive LDCT and evaluate its lesion detection performance. Methods: A cycle-consistent generative adversarial network with an attention module [Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization (U-GAT-IT)] was trained using paired LDCT and CTHA images from 277 patients. The model was validated using internal (68 patients, 139 lesions) and external sets from two independent centers (87 patients, 117 lesions). Two radiologists assessed detection performance using a 5-point scale and the detection rate. Results: Synthetic CTHA significantly improved the detection of sub-centimeter (<1 cm) HCCs compared with LDCT in the internal set (69.6% vs. 47.8%, p < 0.05). This improvement was robust in the external set; synthetic CTHA detected a greater number of small lesions than LDCT. Quantitative metrics (structural similarity index measure and peak signal-to-noise ratio) indicated high structural fidelity. Conclusions: Deep-learning–based synthetic CTHA significantly enhanced the detection of small HCCs compared with standard LDCT, offering a non-invasive alternative with high detection sensitivity, which was validated across multicentric data.