Automated microscopy in diagnostic histopathology: From image processing to automated reasoning

✍ Scribed by Peter H. Bartels; Thomas Gahm; D. Thompson

• Publisher: John Wiley and Sons
• Year: 1997
• Tongue: English
• Weight: 765 KB
• Volume: 8
• Category: Article
• ISSN: 0899-9457
• DOI: 10.1002/(sici)1098-1098(1997)8:2<214::aid-ima8>3.0.co;2-d

✦ Synopsis

A machine vision system for diagnostic histopathology sion can be extracted from histopathologically seemingly normal offers five modules: 1) for the automated detection of regions of tissues [3][4][5].

abnormality in histopathologic sections; 2) for fully automated image

Quantitative imaging provides options for automation: in highsegmentation and diagnostic information extraction by a knowledgevolume applications such as screening for cervical cancer, or guided procedure; 3) for the derivation of histometric indices, such when it is necessary to analyze a diagnostically representative as a progression index or grade for a lesion; 4) for diagnostic evidence region in a tissue section, which may involve several hundred evaluation by Bayesian inference networks; and 5) for individual pavideo frames.

tient targeted prognosis based on a case-based reasoning process.

At the Optical Sciences Center at the University of Arizona,

The system has been in operation for several years. Correct segmena machine vision system for histopathologic diagnosis has been tation for even complex scenes such as cribriform glands has been achieved with a high success rate for histopathologic sections from under development for several years [6]. The purpose of this prostate, colon, and breast. The lesion search module and prognostic article is to present the considerations that entered into the design module have passed feasibility testing and are still undergoing of such a system, and to report on insights and experiences gained development.