Application of cell‐image analysis to the diagnosis of cellular atypias in sputum: A review

Abstract

The incidence of carcinoma of the lung continues to steadily rise, and attempts at early diagnosis to improve prognosis have not yet been rewarding. The goal of our research is to decrease the incidence of lung cancer by detecting premalignant bronchial dysplasias in individuals in whom development of lung cancer is potentially preventable. To achieve this, we have developed an atypia status index (ASI)--the assignment of numerical values to the various stages of atypical bronchial epithelial cells in sputum, and a cell atypia profile (CAP)--an ASI-generated scale of 200 such atypical bronchial epithelial cells in a single sputum specimen. Computerized cell-image analysis techniques and statistical data analysis are used to generate the ASIs and CAPs for each subject. This study is a step toward the development of an automated cell-image analysis system for mass screening of premalignant atypias in sputum of those considered at high risk for lung cancer (i.e., men and women of 40 yr of age and older, with more than 20 pack-yr of cigarette smoking).

Sputum examination for early detection of lung cancer

“…Nuclear image analysis is a relatively old approach that has been used to distinguish between small cell and non-small cell lung cancer. [36][37][38] Basically, nuclei are stained stochiometrically with a Feulgen reaction (in which there is a linear relation between the degree of staining and the amount of DNA) suitable for image acquisition and digitisation of the chromatin pattern (euchromatin and heterochromatin). Each pixel of the image has a certain value that relates to DNA density.…”

Diagnosing intra-abdominal malignancy

“…[36][37][38] Basically, nuclei are stained stochiometrically with a Feulgen reaction (in which there is a linear relation between the degree of staining and the amount of DNA) suitable for image acquisition and digitisation of the chromatin pattern (euchromatin and heterochromatin). Each pixel of the image has a certain value that relates to DNA density.…”