Related Experiment Video
Updated: Jul 7, 2026
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
[Implementation and application of a digital cytopathological lung cancer diagnosing system]
Dong Wang1, Yu-Kun Ye, Ying Zhang
1Cancer Center of People's Liberation Army, Nanjing 81st Hospital, Nanjing, China.
Objective:
To evaluate the efficacy of the digital cytopathological lung cancer diagnosing system (DCLCDS) utilizing the latest computer technologies (including reinforcement learning, image segmentation and classifier) and the cytopathological knowledge on lung cancer cells.
Methods:
Separate the overlapped lung cancer cells in a slice image applying the improved deBoor-Cox B-Spline algorithm; Segment cell regions in a slice image using an image segmentation algorithm based on reinforcement learning; Ensemble different classifiers, including Decision Tree classifier, Support Vector Machine (SVM) classifier and Bayesian classifier, to achieve an accurate result of cytopathological lung cancer diagnosis.
Results:
The accurate diagnosis rate for lung cancer identification of 224 images of small lung lesions aspiration biopsy from 120 cases randomly selected was 92.3%. The accurate diagnosis rate for type classification of lung cancer was 82.5%. The identification rate for abnormal nuclear cells was 71.6%.
Conclusions:
The DCLCDS achieves a high accuracy on cytopathological lung cancer diagnosis by solving some major problems on the cytology smears, including cell overlapping, uneven coloration and impurity. It provides a relatively objective, standard tool on cytopathological lung cancer diagnosis. It has good efficacy on early diagnosis of lung cancer.
