Automatic Nuclear Segmentation Using Multiscale Radial Line Scanning With Dynamic Programming

Autor: Hongming Xu, Cheng Lu, Richard Berendt, Naresh Jha, Mrinal Mandal
Rok vydání: 2017
Předmět:
Skin Neoplasms
Quantitative Biology::Tissues and Organs
Nuclear Theory
0206 medical engineering
Biomedical Engineering
Scale-space segmentation
02 engineering and technology
Radial line
Blob detection
Sensitivity and Specificity
Pattern Recognition
Automated
Sørensen–Dice coefficient
Image Interpretation
Computer-Assisted
0202 electrical engineering
electronic engineering
information engineering
Humans
Segmentation
Computer vision
Nuclear Experiment
Image resolution
Mathematics
Cell Nucleus
business.industry
Segmentation-based object categorization
Reproducibility of Results
Pattern recognition
Image segmentation
020601 biomedical engineering
Computer Science::Computer Vision and Pattern Recognition
020201 artificial intelligence & image processing
Artificial intelligence
business
Algorithms
Zdroj: IEEE Transactions on Biomedical Engineering. 64:2475-2485
ISSN: 1558-2531
0018-9294
Popis: In the diagnosis of various cancers by analyzing histological images, automatic nuclear segmentation is an important step. However, nuclear segmentation is a difficult problem because of overlapping nuclei, inhomogeneous staining, and presence of noisy pixels and other tissue components. In this paper, we present an automatic technique for nuclear segmentation in skin histological images. The proposed technique first applies a bank of generalized Laplacian of Gaussian kernels to detect nuclear seeds. Based on the detected nuclear seeds, a multiscale radial line scanning method combined with dynamic programming is applied to extract a set of candidate nuclear boundaries. The gradient, intensity, and shape information are then integrated to determine the optimal boundary for each nucleus in the image. Nuclear overlap limitation is finally imposed based on a Dice coefficient measure such that the obtained nuclear contours do not severely intersect with each other. Experiments have been thoroughly performed on two datasets with H&E and Ki-67 stained images, which show that the proposed technique is superior to conventional schemes of nuclear segmentation.
Databáze: OpenAIRE
Externí odkaz: