1. Computerized contextual analysis in diagnosis
- Author
-
Martha L. Hutchinson, David J. Zahniser, and Louise M. Isenstein
- Subjects
Vaginal Smears ,Cancer Research ,Pathology ,medicine.medical_specialty ,business.industry ,Discriminant Analysis ,Uterine Cervical Neoplasms ,Cervical cytology ,Pattern recognition ,Context analysis ,Investigation methods ,Uterine cervix ,Oncology ,Image Processing, Computer-Assisted ,medicine ,Humans ,Female ,Artificial intelligence ,business ,Cervical neoplasm - Abstract
Cervical cytology specimens prepared as monolayers were analyzed with a combination of high-resolution single-cell image analysis and lower-resolution contextual image analysis. For the latter, quantitative features of cluster architecture, object distribution and background were used to mimic the pathologists global assessment of a specimen. Contextual analysis correctly calssified 81% of the cases for diagnosis, about on a par with the companion single-cell cytometric analysis. Contextual and single cell analysis complemented each other, yielding greater accuracy when the two methods were combined. Additional applications of contextual analysis are discussed.
- Published
- 1994
- Full Text
- View/download PDF