Hybrid Deep Learning Integrating Multimodal CEUS and Enhanced MRI to Optimize Early-Stage HCC Treatment Decisions

This study aims to address the issue of a lack of individualized basis for selecting liver resection (LH) or microwave ablation (MWA) in early-stage hepatocellular carcinoma (HCC) patients to reduce the early recurrence rate (≤2 years). Given that existing machine learning-based recurrence prediction studies have failed to guide the optimal treatment plan selection, and that multidisciplinary consultations rely on guidelines (universality) and experience (subjectivity) which have their limitations, we propose to utilize artificial intelligence (AI), specifically the advantages of multimodal deep learning technology (which outperforms traditional machine learning by integrating complementary information to provide more accurate predictions), to establish a hybrid deep learning model that integrates contrast-enhanced ultrasound (CEUS) and enhanced magnetic resonance imaging (MRI) features. This model will predict the probability of early recurrence (ER≤2 years) in patients and, based on this, recommend LH or MWA as the optimal first treatment option for newly diagnosed early HCC patients to optimize individualized treatment decisions.

Sex

All

Minimum age

18 Years

Maximum age

85 Years

Inclusion Criteria:

1. Preoperative enhanced imaging examination or pathological diagnosis is HCC;
2. CNLC Stage I, IIa, Child-Pugh Class A/B;
3. A single tumor with a diameter ≤ 5 cm or 2-3 tumors, with the maximum diameter ≤ 3 cm;
4. Perform liver resection surgery or MWA surgery treatment;
5. MRI and/or CEUS examinations performed within one month before surgery

Exclusion Criteria:

1：There is already extrahepatic metastasis or the presence of other malignant tumors;

2: History of other treatments prior to surgery;

3: Incomplete preoperative ultrasound contrast and/or MRI imaging data, with images missing or unclear;

4: Missing postoperative follow-up data