Markiewicz Tomasz, Osowski Stanislaw, Patera Janusz, Kozlowski Wojciech
Warsaw University of Technology, Warsaw, Poland.
Anal Quant Cytol Histol. 2006 Oct;28(5):281-91.
To design an automatic system for recognition and count of two different cell families on histologic slides.
The segmentation strategy uses color information on the image. The morphologic operations and Support Vector Machine approaches are used for each color to obtain precise segmentation of the image into separate cells for recognition.
A large set of histologic slides of bone marrow was assessed byour system and the results compared to the score of a human expert. The results are in good agreement. The difference is within acceptable limits (below 10%).
The automatic system of cell recognition and extraction is accurate and provides a useful tool for cell recognition and count on histologic slides.
设计一种用于识别和计数组织学切片上两种不同细胞群的自动系统。
分割策略利用图像上的颜色信息。针对每种颜色使用形态学操作和支持向量机方法，以将图像精确分割成单个细胞以便识别。
我们的系统对大量骨髓组织学切片进行了评估，并将结果与人类专家的评分进行了比较。结果吻合良好。差异在可接受范围内（低于10%）。
细胞识别与提取自动系统准确无误，为组织学切片上的细胞识别和计数提供了一个有用的工具。
