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

Official title

Hybrid Deep Learning Models Based on Multimodal CEUS and Enhanced MRI Can Optimize Treatment Decisions for Early-stage Hepatocellular Carcinoma

Overview

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.

Detailed description

Core ObjectiveTo develop a hybrid deep learning model based on contrast-enhanced ultrasound (CEUS) clinical data for predicting the early recurrence (ER) probability within 2 years after liver resection (LH) or microwave ablation (MWA) in patients with early-stage liver cancer (CNLC I/IIa), providing a basis for individualized treatment decisions.Key MethodsStudy DesignType: Multicenter retrospective cohort study (2009.10-2026.12, 30 hospitals)Population:Inclusion: First diagnosed HCC (single lesion ≤5cm or 2-3 lesions with the largest ≤3cm), Child-Pugh A/B grade, CEUS/MRI examination within one month before surgery.Exclusion: Extrahepatic metastasis/other malignancies, previous treatment history, missing imaging/follow-up data.Sample size: 1441 cases (LH group 609 cases, MWA group 831 cases).Data CollectionClinical Data: Age, hepatitis type, cirrhosis, tumor characteristics (size/location/number), laboratory indicators (AFP, etc.).Imaging Data:CEUS: Dynamic acquisition of arterial phase (AP), portal venous phase (PVP), and delayed phase (LP) videos after SonoVue injection.Enhanced MRI: Acquisition of AP, PVP, transitional phase (TP), and hepatobiliary-specific phase (HBP) images after Gd-EOB-DTPA enhancement.Follow-Up: Imaging re-examination (CEUS/CT/MRI) every 3-6 months within 2 years after surgery, with endpoints being recurrence/death/last follow-up (≥24 months).Model ConstructionInput Data:Imaging ROI: Manual drawing of the tumor and a 5mm peritumoral area, extracting 64×64 pixel frames (CEUS videos downsampled to 32 frames).Fusion Methods: Clinical CEUS, clinical MRI, and clinical CEUS MRI.Deep Learning Architecture:Feature Extraction: 2D-CNN (convolutional layers → spatial features) → Bi-LSTM (fusion of spatiotemporal features) → Attention module.Data Augmentation: Translation and flipping to reduce overfitting.Training/Validation:5-fold cross-validation, dividing the training/validation set in a 4:1 ratio (training LH and MWA groups separately).Optimal Model Selection: The one with the highest AUC.Decision ApplicationHybrid model: To predict the ER probabilities for LH or MWA treatment for the same patient separately.Treatment Recommendations:If the predicted ER probability: MWA \> LH → recommend LH;If the predicted ER probability: LH ≥ MWA → recommend MWA.

Interventions

• Procedure surgery
  The surgery was performed in supine position under general anesthesia with open/laparoscopic liver resection (LH), and the main and secondary incisions were made based on the tumor location. Intraoperative ultrasound was routinely used to assess the tumor, remnant liver volume, and the feasibility of negative margins. The type of liver resection followed established guidelines.
• Procedure ablation
  Ablation is performed under ultrasound guidance and intravenous anesthesia, using the KY-2000 treatment device with disposable ablation needles and monitoring software. For tumors with a diameter of less than 2cm, a single needle is used; for tumors of 2cm or more, dual needles (needle spacing ≤ 2cm) are used. The ablation parameters are set to a power of 40-65W and a duration of 1-15 minutes, with immediate post-operative ultrasound (contrast) assessment of the ablation range.

Primary outcome measures

• Early recurrence status (binary: recurrence vs. non-recurrence within 2 years) [Time frame: 2 years]

Eligibility criteria

Inclusion criteria

• Preoperative enhanced imaging examination or pathological diagnosis is HCC;
• CNLC Stage I, IIa, Child-Pugh Class A/B;
• A single tumor with a diameter ≤ 5 cm or 2-3 tumors, with the maximum diameter ≤ 3 cm;
• Perform liver resection surgery or MWA surgery treatment;
• 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

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: No

Study design

Observational model

Cohort

Study locations

China · 1 center

• The First Hospital of jilin University — Changchun

Identifiers

NCT: NCT07582419 · 2025-MS-269

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗