SoftwareImpacts / SIMPAC-2023-245

Adaptive Shape Prediction Model

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ASPM is a Matlab package to predict the shape of touched and overlapping cells in Pap test images. You can start running with "demo" module. By running demo, the input image along with corresponding clusters are first loaded. Then, some parameters are identified, i.e., the number of inner and outer iterations, the cell diameter, and the minimum and maximum cell size to be submitted to ASPM module. You can change this parameter to fit your dataset. At the end of model process, demo visualizes the predicted shapes. The outcomes are changed by changing these parameters. Each sub-module is descried before calling in the code.

Please cite the following paper:

[1] Tareef. (2023). Adaptive Shape Prediction Model (ASPM) for Touched and Overlapping Cells Segmentation in Cytology Images. Software Impacts. (when published) [2] Tareef, A., Song, Y., Cai, W., Huang, H., Chang, H., Wang, Y., ... & Chen, M. (2017). Automatic segmentation of overlapping cervical smear cells based on local distinctive features and guided shape deformation. Neurocomp., vol. 221, pp. 94–107, 2017.

About

Adaptive Shape Prediction Model

License:MIT License


Languages

Language:MATLAB 96.9%Language:Objective-C 3.1%