Abstract
In slide based automation of cervical cytology the first stage of analysis involves finding possibly suspicious cells, or areas on the slide with these types of cells. By using a television based system such as the Leyden Television Analysis System (LEYTAS), a number of detection methods can be applied to rapidly screen a large number of fields automatically for suspicious cells. In this paper, results using a parameter based on increased nuclear DNA content of cells are given and a second detection method based on a chromatin pattern feature, called chromatin contrast, is discussed. Two blind trials on 41 positive and 22 negative cervical slides, using the Leyden Television Analysis System to detect suspicious cells with an increased nuclear DNA content, were promising. In 1 of the 41 positive cases no suspicious cells were found. In the negative specimens, suspicious cells were detected in 1 of 9 cases and 1 of 13 cases, with the two detection parameters investigated. These findings are discussed and some automatic artefact rejection procedures with preliminary results are given.
Cited by
28 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Cytology image analysis;Deep Learning Models for Medical Imaging;2022
2. Cytology Image Analysis Techniques Toward Automation;ACM Computing Surveys;2021-06
3. Appropriate Technology for the Quantitative Assessment of the Final Reaction Product of Histochemical Techniques;Ciba Foundation Symposium 73 - Trends in Enzyme Histochemistry and Cytochemistry;2008-05-30
4. Editorial Comment;The Journal of Urology;1996-07
5. EDITORIAL COMMENT;Journal of Urology;1996-07