With the development of artificial intelligence technology, the automatic reading system plays an increasingly important role in assisting the diagnosis of pathologists, improving the accuracy of pathology diagnosis and reducing labor intensity. Accurate segmentation of the nucleus is the primary factor affecting the performance of the automated reading system. Because the boundary between the nucleus, the cytoplasm and the background is unclear, and the color difference between the cells is large, the nuclear segmentation is challenged. In order to solve this problem, a method of cervical nucleus segmentation based on optimal maximum stability regions(Maximally Stable Extremal Regions, MSER) algorithm is proposed. This method first converts the image to the HSV (Hue, Saturation, Value) color space. Then, after weighted combination of S and V channels, the optimized MSER algorithm is used to obtain a coarse segmentation region with uniform gray values. The parameter segmentation method is used to perform fine segmentation. Finally, the feature extraction technique is used to extract various features from the nuclear image, and the artificial neural network classifier is trained to judge whether the result obtained after segmentation is the nucleus. Experiments show that the method can accurately segment the cervical nucleus

With the development of instrument automation, the microscope based automatic reading system is used widely in the medical field. This system needs moving many positions under the microscope and capturing the images to complete the scanning task. However, because it is difficult to ensure the plane of the platform and the axis of the object lens are vertical, and the surface of the observed samples may be not even, the focuses in different locations are not in a plane. Therefore, it is necessary to run auto focusing to obtain clear images. Conventional methods perform focusing at each location, causing excessive movements and inefficient scanning. In order to reduce the scanning time, this paper presents a fast scanning method based on focal plane estimation. By acquiring the focuses at several representative positions, the focuses of the position near them are estimated, and the platform (or the lens) can be moved directly to the estimated position. Experiments show that this method can reduce the number of focus searching effectively and improve the scanning efficiency.