图像处理和人工神经网络在肺癌细胞病理诊断中的应用

Clinical application of image processing and neural network in cytopathological diagnosis of lung cancer

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 study a new technique （lung cancer diagnossing system, LCDS） based on the computer imaging and artificial neural network for early diagnosis of lung cancer, and evaluate it＇ s value in early cytopathological diagnosis of lung cancer. Methods The cytological smears from the specimens obtained by Percutancous Aspiration Lung Biopsy （PALB） in 512 cases were synthetically analyzed by LCDS. Among them, 362 cases received operations. The diagnoses by LCDS were compared with postoperative histopathological diagnosis. Results In cytopathological diagnoses for the 512 specimens, LCDS can judge between cancer cells and non-cancer cells from lung lesions with its image analysis and expert system. Moreover, it can distinguish squamous carcinoma, adenocarcinoma and small cell carcinoma in cytopathological diagnosis with built-in neural network. The total coincident rate of LCDS diagnosis was 91.80% compared with the pathological diagnosis. In the 362 cases, the sensitivity of LCDS diagnosis was 94.79% （291/307）, the specificity was 90.91% （50/55）, and the consistent rate was 94.20% （341/362）. Conclusion The diagnostic pattem of LCDS was practical and effective. It has applicable value in cytopathological diagnosis of lung cancer and may be an efficient means for early diagnosis of lung cancer.