Department of Gastroenterology, West District of Qingdao Municipal Hospital, Qingdao 266000, Shandong, China.
Internal Medicine, Songshan Hospital of Medical College of Qingdao University, Qingdao 266000, Shandong, China.
J Healthc Eng. 2021 Jun 16;2021:9996565. doi: 10.1155/2021/9996565. eCollection 2021.
With the advancement and development of medical equipment, CT images have become a common lung examination tool. This article mainly studies the application of CT imaging examination based on virtual reality analysis in the clinical diagnosis of gastrointestinal stromal tumors. Before extracting suspected lymph nodes from a CT image of the stomach, the CT image sequence is preprocessed first, which can reduce the cumbersomeness of subsequent extraction of suspected lymph nodes and speed up the subsequent processing. According to medical knowledge, CT images of the stomach show that lymph nodes mainly exist in the adipose tissue around the gastric wall, but there are no lymph nodes in the subcutaneous fat outside the chest. The most basic gray value in the image and the neighborhood average difference feature related to gray level are used as the primary features of visual attention detection. When extracting the neighborhood average difference feature, we use a 3 3 sliding window method to traverse each point of the pixel matrix in the image, thereby calculating the feature value of each pixel in the image. After the feature extraction is completed, it is necessary to calibrate the data and make a training data set. The SP immunohistochemical staining method was used. The specimens were fixed with 10% formaldehyde, routinely embedded in paraffin, sectioned, and stained with HE. The tumor tissue was determined by immunohistochemistry, and the reagents were products of Maixin Company. All patients were followed up by regular outpatient review, letters, and visits or phone calls. The data showed that immunohistochemical tumor cells showed positive staining for CD117 (14/15, 93.3%) and CD34 (10/15, 66.7%). The results show that the application of virtual reality technology to CT imaging examination can significantly improve the diagnostic accuracy of gastrointestinal stromal tumors.
随着医疗设备的进步和发展，CT 图像已成为一种常见的肺部检查工具。本文主要研究基于虚拟现实分析的 CT 成像检查在胃肠道间质瘤临床诊断中的应用。在从胃部 CT 图像中提取可疑淋巴结之前，首先对 CT 图像序列进行预处理，这可以减少后续提取可疑淋巴结的繁琐程度，并加快后续处理速度。根据医学知识，胃部 CT 图像显示，淋巴结主要存在于胃壁周围的脂肪组织中，但胸部以外的皮下脂肪中没有淋巴结。图像中最基本的灰度值和与灰度级相关的邻域平均差特征被用作视觉注意检测的主要特征。在提取邻域平均差特征时，我们使用 3 3 滑动窗口方法遍历图像中像素矩阵的每个点，从而计算图像中每个像素的特征值。完成特征提取后，需要对数据进行校准并制作训练数据集。采用 SP 免疫组织化学染色法。标本用 10%甲醛固定，常规石蜡包埋，切片，HE 染色。免疫组织化学法确定肿瘤组织，试剂为迈新公司产品。所有患者均通过定期门诊复查、信件、访问或电话进行随访。数据显示，免疫组化肿瘤细胞 CD117（14/15，93.3%）和 CD34（10/15，66.7%）阳性染色。结果表明，虚拟现实技术在 CT 成像检查中的应用可以显著提高胃肠道间质瘤的诊断准确性。
