Abstract
Accurately segmented nuclei are important, not only for cancer classification, but also for predicting treatment effectiveness and other biomedical applications. However, the diversity of cell types, various external factors, and illumination conditions make nucleus segmentation a challenging task. In this work, we present a new deep learning-based method for cell nucleus segmentation. The proposed convolutional blur attention (CBA) network consists of downsampling and upsampling procedures. A blur attention module and a blur pooling operation are used to retain the feature salience and avoid noise generation in the downsampling procedure. A pyramid blur pooling (PBP) module is proposed to capture the multi-scale information in the upsampling procedure. The superiority of the proposed method has been compared with a few prior segmentation models, namely U-Net, ENet, SegNet, LinkNet, and Mask RCNN on the 2018 Data Science Bowl (DSB) challenge dataset and the multi-organ nucleus segmentation (MoNuSeg) at MICCAI 2018. The Dice similarity coefficient and some evaluation matrices, such as F1 score, recall, precision, and average Jaccard index (AJI) were used to evaluate the segmentation efficiency of these models. Overall, the proposal method in this paper has the best performance, the AJI indicator on the DSB dataset and MoNuSeg is 0.8429, 0.7985, respectively.
Highlights
Artificial intelligence (AI) enables computers to perform human tasks
For the multi-organ nucleus segmentation (MoNuSeg) dataset, to ensure sufficient data in the train and test processing, we extracted each original image of 1000 × 1000 to sub-patches of 250 × 250 sizes, resulting in each original image being divided into 16 smaller ones
The proposed model reached the highest score with the average Jaccard index (AJI) of 0.7925 versus U-Net (0.3605), versus LinkNet (0.3651), versus SegNet (0.4003), and versus ENet (0.51)
Summary
Artificial intelligence (AI) enables computers to perform human tasks. The development of AI can be observed in two topics, namely machine learning and deep learning. The cell nuclei biomedical datasets help the researchers and doctors in disease prognosis as well as facilitate drug development and medical treatment. Cell analysis enables researchers to determine whether or not the cells will react to certain drug treatments. By analyzing the cells in drug development, the researchers are able to suggest new treatment methods and improve the patient’s health. Due to the demands for automatic cell nuclei analysis, many research works have been conducted on related topics. The cell nuclei have been analyzed by applying nucleus detection on highresolution, histopathology, breast cancer images to categorize the subjects in the images into nuclear or non-nuclear [4]. Nucleus detection and classification have been combined simultaneously for a typical histopathology image dataset [8]
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.
