Abstract
Automated cell nucleus segmentation is the key to gain further insight into cell features and functionality which support computer-aided pathology in early diagnosis of diseases such as breast cancer and brain tumour. Despite considerable advances in automated segmentation, it still remains a challenging task to split heavily clustered nuclei due to intensity variations caused by noise and uneven absorption of stains. To address this problem, we propose a novel method applicable to variety of histopathological images stained for different proteins, with high speed, accuracy and level of automation. Our algorithm is initiated by applying a new locally adaptive thresholding method on watershed regions. Followed by a new splitting technique based on multilevel thresholding and the watershed algorithm to separate clustered nuclei. Finalized by a model-based merging step to eliminate oversegmentation and a model-based correction step to improve segmentation results and eliminate small objects. We have applied our method to three image datasets: breast cancer stained for hematoxylin and eosin (H&E), Drosophila Kc167 cells stained for DNA to label nuclei, and mature neurons stained for NeuN. Evaluated results show our method outperforms the state-of-the-art methods in terms of accuracy, precision, F1-measure, and computational time.
Highlights
Despite considerable progress in automated segmentation, it remains a challenging task to separate a large clump of nuclei and delineate their boundaries with a high accuracy and speed
Breast cancer images were quantized through these thresholds to segment the nuclei
A very similar convolutional neural network (CNN) was developed by Kumar et al.[11] to generate ternary maps of the image datasets stained for hematoxylin and eosin (H&E)
Summary
Despite considerable progress in automated segmentation, it remains a challenging task to separate a large clump of nuclei and delineate their boundaries with a high accuracy and speed. A deep convolutional neural network (CNN) was learned by Xing et al.[12] using three annotated datasets (brain tumour, pancreatic neuroendocrine tumour, and breast cancer), and a region growing approach was employed to generate binary maps of images. Learning a machine/network to segment a desired object requires preparing a sufficiently large manually annotated dataset of the object This tedious and painstaking task impedes the development of machine learning approaches applicable to images of various cell types which are stained for diverse proteins and produced by different labs
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
