An adaptive learning method of anchor shape priors for biological cells detection and segmentation. (September 2021)

• Record Type: Journal Article
• Authors: Hu, Haigen; Liu, Aizhu; Zhou, Qianwei; Guan, Qiu; Li, Xiaoxin; Chen, Qi
• Is Part Of: Computer methods and programs in biomedicine. Volume 208(2021)
• Publication Date: 2021-09
• Subjects: Anchor shape -- ISODATA -- Cell detection and segmentation -- Anchor densification -- Mask R-CNN; 00-01 -- 99-00; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106260
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We propose an adaptive approach to learn the anchor shape priors from data samples by incorporating ISODATA into MASK R-CNN. Compared with the existing methods, the proposed method can adaptively generate the aspect ratio of anchor boxes to be suitable for cell shape distributions, thereby reducing the dependence of priori knowledge on object scale distributions. To solve the identification difficulties for small objects owing to the multiple down-samplings in a deep learning-based method, we present the densification strategy of candidate anchors for tinny object candidate anchors based on EMO score, and it can enhance the effects of identifying tinny size cells, thereby further improving the accuracy of detection and segmentation. The combination of the ISODATA learning priori knowledge and the densification strategy can obtain the best comprehensive performance for the detection and segmentation of cells. Abstract: Background and objective: Owing to the variable shapes, large size difference, uneven grayscale and dense distribution among biological cells in an image, it is still a challenging task for the standard Mask R-CNN to accurately detect and segment cells. Especially, the state-of-the-art anchor-based methods fail to generate the anchors of sufficient scales effectively according to the various sizes and shapes of cells, thereby hardly covering all scales of cells. Methods: We propose an adaptive approach to learn the anchor shape priors from data samples, and the aspect ratios and the number of anchor boxes can be dynamically adjusted by using ISODATA clustering algorithm instead of human prior knowledge in this work. To solve the identification difficulties for small objects owing to the multiple down-samplings in a deep learning-based method, a densification strategy of candidate anchors is presented to enhance the effects of identifying tinny size cells. Finally, a series of comparative experiments are conducted on various datasets to select appropriate a network structure and verify the effectiveness of the proposed methods. Results: The results show that the ResNet-50-FPN combining the ISODATA method and densification strategy can obtain better performance than other methods in multiple metrics (including AP, Precision, Recall, Dice and PQ) for various biological cell datasets, such as U373, GoTW1, SIM+ and T24. Conclusions: Our adaptive algorithm could effectively learn the anchor shape priors from the various sizes and shapes of cells. It is promising and encouraging for a real-world anchor-based detection and segmentation application of biomedical engineering in the future.