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

1. Automatic recognition/Efficient diagnosis of hepatic Echinococcosis: Development of a deep learn-based AI diagnostic tool aimed at improving the differentiation of hepatic echinococcosis from other liver diseases such as liver cysts, liver abscesses, and other hepatic cystic space occupying lesions. The tool will utilize generative adversarial networks and polarized self-attention algorithms to effectively identify and classify hepatic echinococcosis to make up for the uneven medical resources and shortage of professional physicians in the western region
2. Differential diagnosis of specific types of hepatic echinococcosis: To explore the use of multimodal imaging combined with deep learning methods to distinguish CL type, CE1 type and hepatic cyst of hepatic echinococcosis. This research will apply DINOv2 medical image segmentation algorithm and deep learning technology to accurately identify cases with relatively unevenly distributed and complex data.
3. Prediction of postoperative recurrence of hepatic echinococcosis: Transfer learning and Deep-SVDD algorithm are used to predict the risk of postoperative recurrence of hepatic echinococcosis, providing an effective solution for unbalanced sample size data sets. In addition, by integrating the data on the medical big data platform, an AI-based postoperative recurrence prediction model was established

Inclusion Criteria:

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

Exclusion Criteria:

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

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

Relevant medical image data involves patient privacy, and the research group refused to share it