Method and system for identifying lesion cells in cervical cytopathological slices based on cell clusters

Abstract

The invention discloses a method and system for identifying diseased cells in cervical cytopathological slice images based on cell clusters, comprising the following steps: extracting a single cell cluster region on the cervical pathological slice image; The threshold cell cluster is regarded as a super large cell cluster; the super large cell cluster is split into sub-cell clusters; the cell cluster area outside the super-large cell cluster and the sub-cell cluster obtained by splitting are used as boundary filling processing to obtain the area to be identified; Diseased cells were identified in the identified area. The present invention is aimed at full slice images of massive pixels, and uses cell clusters as the processing and identification unit instead of the conventional image block fusion framework, which is more suitable for the characteristics of cervical cytopathological slice images, and improves efficiency and accuracy at the same time.

Description

technical field [0001] The invention belongs to the field of medical cytopathological image processing, and more specifically relates to a method and system for identifying lesion cells in cervical cytopathological slices based on cell clusters. Background technique [0002] Cervical cancer is a malignant tumor with high incidence in women. Cervical liquid-based cytopathology is currently the most important means of preventing and screening cervical cancer. Accurate interpretation of diseased cells in cytopathological slice images is an important basis for doctors to determine the patient's condition and formulate a treatment plan. At present, the manual interpretation of cytopathological images is not only time-consuming, but also the interpretation results are very dependent on the experience of doctors. Therefore, automatically interpreting diseased cells in pathological slides can not only improve the efficiency of diagnosis but also provide doctors with a more unified...

AI Technical Summary

Problems solved by technology

However, this block fusion scheme has the following disadvantages: the cells at the boundaries of the sub-blocks are artificially cut, reducing the recognition accuracy; too large a block is still difficult to deal with directly, and too small a block brings more boundary problems and increases processing overhead ;Inconsistency in processing results of adjacent blocks at subblock boundaries

Although the conventional image block fusion strategy can handle full slice images, it introduces redundant calculations and sub-block boundary problems at the same time.

Images