Hybrid Deep Learning Integrating Multimodal CEUS and Enhanced MRI to Optimize Early-Stage HCC Treatment Decisions (HDL-CEUS-MRI)
2026년 5월 7일 업데이트: Dezhi Zhang, The First Hospital of Jilin University
Hybrid Deep Learning Models Based on Multimodal CEUS and Enhanced MRI Can Optimize Treatment Decisions for Early-stage Hepatocellular Carcinoma
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.
연구 개요
상세 설명
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.
연구 유형
관찰
등록 (추정된)
1424
연락처 및 위치
이 섹션에서는 연구를 수행하는 사람들의 연락처 정보와 이 연구가 수행되는 장소에 대한 정보를 제공합니다.
연구 연락처
- 이름: Dezhi Zhang
- 전화번호: +8618186876068
- 이메일: dezhi@ilu.edu.cn
연구 장소
-
-
Jilin
-
Changchun, Jilin, 중국
- The First Hospital of Jilin University
-
-
참여기준
연구원은 적격성 기준이라는 특정 설명에 맞는 사람을 찾습니다. 이러한 기준의 몇 가지 예는 개인의 일반적인 건강 상태 또는 이전 치료입니다.
자격 기준
공부할 수 있는 나이
- 성인
- 고령자
건강한 자원 봉사자를 받아들입니다
아니
샘플링 방법
비확률 샘플
연구 인구
Hepatocellular carcinoma (HCC) patients who underwent microwave ablation (MWA) or surgical resection (liver hepatectomy, LH) at the First Hospital of Jilin University, the PLA General Hospital, and 18 other hospitals between October 2009 and May 2023, and who received contrast-enhanced ultrasound and/or MRI examinations prior to the procedure.
설명
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
공부 계획
이 섹션에서는 연구 설계 방법과 연구가 측정하는 내용을 포함하여 연구 계획에 대한 세부 정보를 제공합니다.
연구는 어떻게 설계됩니까?
디자인 세부사항
코호트 및 개입
그룹/코호트 |
개입 / 치료 |
|---|---|
|
Surgical group
The group of patients underwent surgical resection treatment.
|
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.
|
|
Microwave Ablation Group
The group of patients underwent microwave ablation treatment.
|
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.
|
연구는 무엇을 측정합니까?
주요 결과 측정
결과 측정 |
측정값 설명 |
기간 |
|---|---|---|
|
Early recurrence status (binary: recurrence vs. non-recurrence within 2 years)
기간: 2 years
|
Follow-up strategy (telephone follow-up or clinical database): Routine check-ups, serum AFP tests, contrast-enhanced ultrasound (CEUS), or enhanced CT/MRI examinations are performed at 1, 3, 6 months, 1 year, and 2 years after treatment to confirm tumor recurrence.
Follow-up starts from the date of surgery and ends at the first recurrence, death, or last follow-up (≥24 months).
Early recurrence is defined as recurrence occurring within 2 years after surgical treatment.
The outcome is recorded as a binary variable: recurrence (yes) or no recurrence (no) within 2 years.
|
2 years
|
공동 작업자 및 조사자
여기에서 이 연구와 관련된 사람과 조직을 찾을 수 있습니다.
연구 기록 날짜
이 날짜는 ClinicalTrials.gov에 대한 연구 기록 및 요약 결과 제출의 진행 상황을 추적합니다. 연구 기록 및 보고된 결과는 공개 웹사이트에 게시되기 전에 특정 품질 관리 기준을 충족하는지 확인하기 위해 국립 의학 도서관(NLM)에서 검토합니다.
연구 주요 날짜
연구 시작 (추정된)
2026년 4월 30일
기본 완료 (추정된)
2027년 10월 30일
연구 완료 (추정된)
2027년 10월 30일
연구 등록 날짜
최초 제출
2026년 4월 26일
QC 기준을 충족하는 최초 제출
2026년 5월 7일
처음 게시됨 (실제)
2026년 5월 12일
연구 기록 업데이트
마지막 업데이트 게시됨 (실제)
2026년 5월 12일
QC 기준을 충족하는 마지막 업데이트 제출
2026년 5월 7일
마지막으로 확인됨
2026년 5월 1일
추가 정보
이 정보는 변경 없이 clinicaltrials.gov 웹사이트에서 직접 가져온 것입니다. 귀하의 연구 세부 정보를 변경, 제거 또는 업데이트하도록 요청하는 경우 register@clinicaltrials.gov. 문의하십시오. 변경 사항이 clinicaltrials.gov에 구현되는 즉시 저희 웹사이트에도 자동으로 업데이트됩니다. .