Utility of Ultrasound Imaging for Diagnosis of Focal Liver Lesions: A Radiomics Analysis

Ablation Clinical Trial

Official title:

Intelligent Diagnosis of Focal Liver Lesions and Thermal Ablation Zone of Liver Cancer Based on Ultrasound Imaging

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT03871140
• Other study ID #: 301jrcsk3
• Status: Recruiting
• Start date: January 1, 2017
• Est. completion date: December 30, 2021

Study information

• Verified date: April 2018
• Source: Chinese PLA General Hospital
• Contact: Jie Yu, Dr
• Phone: 15901417963
• Email: jiemi301[@]163.com
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Ultrasound (US) as first-line imaging technology in detecting focal liver lesions,also plays a crucial role in evaluating image and guiding ablation which is the main treatment for liver lesions. However, the effect of US in diagnosing liver lesions is challenged by several factors including being highly dependent on doctor's experience, low signal-to-noise ratio, low resolution for lesion feature,large error from thermal field evaluation during the process of ablation and so on. Therefore, it is of great significance to construct an intelligent US analysis system depending on the digital information technology. Basing on these problems,the following research will be involved in our project: 1) US database of liver lesions with seamless connection to Picture Archiving and Communication Systems (PACS) will be developed, with the aim to provide standard data for intelligent US analysis. 2) Deep learning model for accurate segmentation, detection and classification of liver lesions on US images will be studied. Then automatic extraction, selection and analysis of liver lesion ultrasound features and the intelligent US diagnosis for liver lesions will be realized. 3) Proposing a clustering model with deep image features, and depicting the similarity measurement of liver cancer, which can be furthered used to link the liver cancer feature to optimal ablation parameters. The intelligent decision-making system for quantifying thermal ablation will be established. 4) Regression algorithm and Generative Adversarial Nets will be developed to extract the image features of liver cancer which will predict risk factors after US-guided thermal ablation.Based on the above researches, it is of great value to establish an intelligent focal liver lesion US diagnosis system involving intelligent diagnosis,personalized ablation strategy and accurate prognosis evaluation, improving the level of accurate diagnosis and treatment of liver lesions.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 10000
• Est. completion date: December 30, 2021
• Est. primary completion date: December 30, 2020
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: N/A and older

Eligibility

Inclusion Criteria:

1. clear ultrasound imaging of focal liver lesions including malignant liver tumors such as hepatocellular carcinoma, metastatic liver cancer and benigh liver tumors such as hemangioma and focal nodular hyperplasia and so on can be acquired.

2. clear ultrasound imaging of liver tissues backgroud without lesions can be acquired.

3. disease history and pathological diagnosis of the lesions can be acquired.

Exclusion Criteria:

1. patients unsuitable for ultrasound san

2. patients counldn't provide disease history such as hepatitis, alcohol intake and so on

3. patients without pathological results

Related Conditions & MeSH terms

• Ablation
• Focal Liver Lesions
• Intelligent Diagnosis
• Radiomics
• Ultrasonics

Intervention

Other:
• diagnosis
therre is no intervention diagnosis or treatment for patients

Locations

Country	Name	City	State
China	Chinese PLA General Hospital	Beijing	Beijing

Sponsors (1)

Lead Sponsor	Collaborator
Chinese PLA General Hospital

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	AUC value	Area under the receiver operating characteristic (ROC) curve (AUC)	through study completion, an average of 3 year
Primary	specificity	diagnosis specificity of intelligent ultrasound analysis	through study completion, an average of 3 year
Primary	sensitivity	diagnosis sensitivity of intelligent ultrasound analysis	through study completion, an average of 3 year