de la Rosette J J, Giesen R J, Huynen A L, Aarnink R G, Debruyne F M, Wijkstra H
Department of Urology, University Hospital Nijmegen, The Netherlands.
Br J Urol. 1995 Apr;75(4):485-91. doi: 10.1111/j.1464-410x.1995.tb07270.x.
To report on the use of automated image analysis in the interpretation of transrectal ultrasonographic images of the prostate.
During transrectal ultrasonography, images were recorded from biopsies performed in 127 patients. Subsequently in the image, the puncture place was marked and analysed. Analysis of the images was performed with the Automated Urologic Diagnostic Expert (AUDEX) system, consisting of a personal computer connected to the ultrasound machine. From the images collected, parameters can be calculated for image classification. The parameters obtained with this procedure were correlated with the histological result.
Evaluation showed a sensitivity of 84.8% and specificity of 87.5%. The positive and negative predictive values, to predict prostate carcinoma, were 84.8% and 87.5%, respectively.
Automated image analysis can help in the diagnosis of prostate carcinoma. In patients with non-palpable lesions or with poorly visualized tumours, image analysis is superior to the standard current diagnostic techniques.
报告自动图像分析在经直肠超声前列腺图像解读中的应用。
在经直肠超声检查期间，记录了127例患者活检时的图像。随后在图像中标记并分析穿刺部位。使用自动泌尿外科诊断专家（AUDEX）系统对图像进行分析，该系统由一台连接超声机的个人计算机组成。从收集的图像中，可以计算出用于图像分类的参数。通过该程序获得的参数与组织学结果相关。
评估显示敏感性为84.8%，特异性为87.5%。预测前列腺癌的阳性和阴性预测值分别为84.8%和87.5%。
自动图像分析有助于前列腺癌的诊断。对于无法触及病变或肿瘤可视化不佳的患者，图像分析优于目前的标准诊断技术。
