Multimodal Imaging Diagnosis and Decision Aid System for Hepatic Echinococcosis Based on Image Omics and Vision Macromodel

NCT06540742 | Completed

• 1 other identifier: SYSKY-2024-517-01
• Study Type: observational
• Target: 1,000
• Locations: 1 country
• Sites: 1

Brief Summary

Hepatic echinococcosis (hepatic echinococcosis) is an important zoonotic disease widely existing in the agricultural and pastoral areas of northwest China. The disease can be parasitic in any part of the human body and may affect multiple organs. In severe cases, patients will lose the ability to work. At present, the disease faces challenges in diagnostic accuracy, specific type identification, preoperative activity assessment, postoperative recurrence prediction, and decision evaluation of T-tube indentation. This problem is particularly significant in high incidence areas with uneven distribution of medical resources and shortage of excellent imaging physicians and clinicians. Our previous studies have demonstrated that the use of visual large models and imaging omics algorithms can effectively segment liver echinococcus lesions, extract key features, and provide clinicians with accurate and reliable diagnosis and treatment recommendations. We believe that on the basis of the transformation of different medical image modes (such as MRI, CT and ultrasound) based on a broader multicentre large data set, the goal of effective identification, diagnosis, surgical decision support, and postoperative accurate prediction of hepatic echinococcosis can be achieved. We will use artificial intelligence technology solutions such as adversarial generation network, vision large model, image omics and decision level fusion, taking into account diagnosis and treatment efficiency, diagnosis and treatment automation and interpretability of diagnosis results, to build a comprehensive accurate diagnosis and prognosis system for hepatic echinococcosis

Conditions

Hepatic Echinococcosis

Keywords

hepatic echinococcosis

Outcome Measures

Primary Outcomes (4)

• roc curve

  Receiver operating characteristic curve

  2024.7-2026.3

• AUC

  Area under the ROC curve

  2024.7-2026.3

• PPV

  Positive Predictive Value

  2024.7-2026.3

• NPV

  Negative Predictive Value

  2024.7-2026.3

Study Arms (2)

Observation group

In this study, preoperative image data of patients with hepatic hydatid were taken as the research object

Diagnostic Test: Artificial intelligence identifies liver hydatids

Control group

Hepatic cyst, hepatic abscess and normal liver were the control group

Diagnostic Test: Artificial intelligence identifies liver hydatids

Interventions

Artificial intelligence identifies liver hydatids DIAGNOSTIC_TEST

Artificial neural network was constructed to automatically identify liver hydatid by using deep learning technology

Control group; Observation group

Eligibility Criteria

• Age: 1 Year - 80 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

In this study, based on the image data of patients with liver hydatid confirmed by pathology after surgery, deep learning technology was used to distinguish liver hydatid from hepatic cystic station lesions such as liver cyst and liver abscess

You may qualify if:

• Patients with complete original images in CT, ultrasound, and MRI dcim formats
• Patients with liver hydatid confirmed by pathology after operation
• Patients with complete clinical data preservation

You may not qualify if:

• Patients with poor quality imaging data
• Patients with incomplete clinical data
• CE4 and CE5 liver hydatid patients diagnosed by imaging alone without surgical treatment

Sponsors & Collaborators

• Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University: lead

Study Sites (1)

Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

Guangzhou, China/Guangdong, China

Location

Related Publications (1)

• Wang Z, Bian H, Li J, Xu J, Fan H, Wu X, Cao Y, Guo B, Xu X, Wang H, Zhang L, Zhou H, Fan J, Ren Y, Geng Y, Feng X, Li L, Wei L, Zhang X. Detection and subtyping of hepatic echinococcosis from plain CT images with deep learning: a retrospective, multicentre study. Lancet Digit Health. 2023 Nov;5(11):e754-e762. doi: 10.1016/S2589-7500(23)00136-X. Epub 2023 Sep 26.

  PMID: 37770335 BACKGROUND

Related Links

• This study has been registered in China\'s National Medical Research Registration and Archival Information System

MeSH Terms

Conditions

Echinococcosis, Hepatic

Condition Hierarchy (Ancestors)

Echinococcosis; Cestode Infections; Helminthiasis; Parasitic Diseases; Infections; Liver Diseases, Parasitic; Liver Diseases; Digestive System Diseases

Study Officials

• Yajin Chen

  Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

  STUDY DIRECTOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 2, 2024
• First Posted: August 6, 2024
• Study Start: September 30, 2023
• Primary Completion: September 12, 2024
• Study Completion: September 12, 2024
• Last Updated: September 19, 2024

Record last verified: 2024-09

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)