论文部分内容阅读
目的探求基于计算机图像处理和人工神经网络的“肺癌早期细胞病理电脑诊断系统”(lungcancerdiagnosingsystem,LCDS)在肺癌临床细胞病理诊断中的应用价值。方法运用LCDS对512例经皮肺穿刺标本的细胞学涂片进行检测评判和综合分析,并对其中手术治疗的362例进行LCDS细胞病理诊断与术后组织病理诊断对比分析研究。结果LCDS能运用图像处理和专家系统完成对肺部病灶癌细胞和非癌细胞的识别诊断,进而运用人工神经网络能完成肺鳞癌、腺癌、小细胞癌等主要病理类型的细胞病理诊断,与临床组织病理或细胞病理诊断结果对比,总符合率为91.80%。其中362例接受外科手术者以术后组织病理诊断结果为标准,LCDS检测诊断的敏感性为94.79%(291/307例),特异性为90.91%(50/55例),准确性为94.20%(341/362例)。结论LCDS所采用的诊断模型是实用而有效的,具有诊断准确率高、易于操作培训等优势,有可能为肺癌早期细胞病理诊断提供又一实用有效的手段。
Objective To explore the value of lung cancer microscopic diagnosis system (LCDS) in the diagnosis of lung cancer based on computer image processing and artificial neural network. Methods Cytological smears of 512 cases of percutaneous lung biopsy specimens were evaluated by LCDS, and 362 cases were treated by LCDS for pathological diagnosis and histopathological diagnosis of LCDS. Results LCDS can use image processing and expert system to diagnose lung cancer cells and non-cancer cells, and then use artificial neural network to diagnose the pathological types of lung squamous cell carcinoma, adenocarcinoma and small cell carcinoma, Compared with clinical histopathology or cytopathology, the overall coincidence rate was 91.80%. Among 362 cases, the sensitivity of LCDS was 94.79% (291/307), the specificity was 90.91% (50/55), the accuracy was 94.20% (341/362 cases). Conclusion The diagnosis model adopted by LCDS is practical and effective. It has the advantages of high diagnostic accuracy and easy operation and training, which may provide a practical and effective method for the early diagnosis of lung cancer.