Search

Background/aim: Recently, an increase in the number of asymptomatic rare benign liver tumors (BLTs) has been reported during health check-ups. It is difficult to determine the nature of partial rare BLTs and not easy to distinguish from malignant liver tumors. This study aimed to analysis clinical features, diagnosis and treatment of rare BLTs to reduce misdiagnosis and provide reference for clinical practice. Methods: From January 2012 to January 2021, we treated 112 rare BLTs by hepatectomy, including 54 focal nodular hyperplasias, 14 hepatocellular adenomas, 28 hepatic angiomyolipomas, 3 hepatic granulomas, 2 inflammatory pseudotumors of the liver, 2 nodular regenerative hyperplasia, 2 hepatic lipomas, 1 solitary fibrous tumor of the liver, 1 hepatic schwannoma and 1 hepatic myelolipoma. Results: The majority of patients were middle-aged female and asymptomatic. Single tumors were dominant. The diagnostic accuracies of computed tomography (CT) and magnetic resonance imaging (MRI) were 32.5% and 44.2%, respectively. The majority of tumors were likely to be misdiagnosed as hepatocellular carcinoma (HCC) or difficult to distinguish from HCC. All patients underwent surgical treatment. Postoperative pathological and immunohistochemical examination can confirm the diagnosis. No patients without tumor recurrence or metastasis during follow-up period. Conclusion: Altogether, the clinical symptoms of rare BLTs lack specificity, and their preoperative diagnosis largely depends on imaging examination, with a low diagnostic accuracy rate and high chances of misdiagnosis as HCC. Diagnosis is confirmed by pathological and immunohistochemical examination. Surgical resection for rare BLT is safe and effective, regular postoperative follow-up is necessary. [ABSTRACT FROM AUTHOR]

The medical image storage and transmission system completes the collection, storage, management, diagnosis and information processing of digital medical image information generated from digital medical devices, accumulates a large amount of data resources, and uses these valuable data resources to extract corresponding diseases. Diagnostic rules that help improve the accuracy of clinical disease diagnosis have always been the subject of medical research and management. Gastrointestinal diseases are common high-risk digestive diseases. This paper studies the imaging detection and quantitative detection and analysis of gastrointestinal diseases based on data mining, aiming to improve the accuracy of doctors' clinical diagnosis, reduce the misdiagnosis and misdiagnosis of patients' diseases, and reduce the burden on patients. With the high computing speed and computational accuracy of the computer, combined with the flexible analysis and judgment ability of the human body, the doctor can help the semi-structured and unstructured diagnosis problems. Experiments demonstrate the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]