Deep learning method for comet segmentation and comet assay image analysis

Comet assay is a widely used method, especially in the field of genotoxicity, to quantify and measure DNA damage visually at the level of individual cells with high sensitivity and efficiency. Generally, computer programs are used to analyze comet assay output images following two main steps. First, each comet region must be located and segmented, and next, it is scored using common metrics (e.g., tail length and tail moment). Currently, most studies on comet assay image analysis have adopted hand-crafted features rather than the recent and effective deep learning (DL) methods. In this paper, however, we propose a DL-based baseline method, called DeepComet, for comet segmentation. Furthermore, we created a trainable and testable comet assay image dataset that contains 1037 comet assay images with 8271 manually annotated comet objects. From the comet segmentation test results with the proposed dataset, the DeepComet achieves high average precision (AP), which is an essential metric in image segmentation and detection tasks. A comparative analysis was performed between the DeepComet and the state-of-the-arts automatic comet segmentation programs on the dataset. Besides, we found that the DeepComet records high correlations with a commercial comet analysis tool, which suggests that the DeepComet is suitable for practical application.

[1]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[2]  Peter Møller,et al.  Measurement of DNA damage with the comet assay in high-prevalence diseases: current status and future directions. , 2019, Mutagenesis.

[3]  M. Zafiropoulou,et al.  DNA damage and repair efficiency in lymphocytes from schizophrenic patients. , 2004, Cancer letters.

[4]  Tomasz Kuszewski,et al.  A cross-platform public domain PC image-analysis program for the comet assay. , 2003, Mutation research.

[5]  GUIDANCE DOCUMENT,et al.  Guidance on Genotoxicity Testing and Data Interpretation for Pharmaceuticals Intended for Human Use , 2008 .

[6]  Afiahayati,et al.  Comet Assay Classification for Buccal Mucosa's DNA Damage Measurement with Super Tiny Dataset Using Transfer Learning , 2019, ACIIDS.

[7]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[8]  Yugyung Lee,et al.  Utilizing Mask R-CNN for Detection and Segmentation of Oral Diseases , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[9]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[10]  V. Garaj-vrhovac,et al.  Assessment of chemotherapy-induced DNA damage in peripheral blood leukocytes of cancer patients using the alkaline comet assay. , 2002, Teratogenesis, carcinogenesis, and mutagenesis.

[11]  A. Vindigni,et al.  DNA Fiber Analysis: Mind the Gap! , 2017, Methods in enzymology.

[12]  Amaya Azqueta,et al.  The comet assay, DNA damage, DNA repair and cytotoxicity: hedgehogs are not always dead. , 2013, Mutagenesis.

[13]  Eftal Sehirli,et al.  A novel method to identify and grade DNA damage on comet images , 2017, Comput. Methods Programs Biomed..

[14]  David Hsu,et al.  OpenComet: An automated tool for comet assay image analysis , 2014, Redox biology.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  João Paulo Teixeira,et al.  Potassium bromate as positive assay control for the Fpg-modified comet assay. , 2020, Mutagenesis.

[17]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[19]  G. Horneck,et al.  Fluorometric Analysis of DNA Unwinding (FADU) as a Method for Detecting Repair-induced DNA Strand Breaks in UV-irradiated Mammalian Cells¶ , 2000, Photochemistry and photobiology.

[20]  Abhishek Dutta,et al.  The VIA Annotation Software for Images, Audio and Video , 2019, ACM Multimedia.

[21]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[22]  Samuel H. Wilson,et al.  Micro-irradiation tools to visualize base excision repair and single-strand break repair. , 2015, DNA repair.

[23]  P. Olive,et al.  Heterogeneity in Radiation-Induced DNA Damage and Repair in Tumor and Normal Cells Measured Using the “Comet” Assay , 1990 .

[24]  Ali Esat Karakaya,et al.  Detection of oxidative DNA damage in lymphocytes of patients with Alzheimer's disease , 2004, Biomarkers : biochemical indicators of exposure, response, and susceptibility to chemicals.

[25]  Awadhesh N Jha,et al.  Reliable Comet assay measurements for detecting DNA damage induced by ionising radiation and chemicals. , 2006, Mutation research.

[26]  E. P. Lewis.  In perspective. , 1972, Nursing outlook.

[27]  C Helma,et al.  A public domain image-analysis program for the single-cell gel-electrophoresis (comet) assay. , 2000, Mutation research.

[28]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Miran Pobar,et al.  Mask R-CNN and Optical Flow Based Method for Detection and Marking of Handball Actions , 2018, 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[30]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[31]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Parkash Chand,et al.  CometQ: An automated tool for the detection and quantification of DNA damage using comet assay image analysis , 2016, Comput. Methods Programs Biomed..

[34]  B. Hellman,et al.  The concepts of tail moment and tail inertia in the single cell gel electrophoresis assay. , 1995, Mutation research.

[35]  Parkash Chand,et al.  A comprehensive review on clinical applications of comet assay. , 2015, Journal of clinical and diagnostic research : JCDR.

[36]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[37]  Seth Pettie,et al.  Mind the gap , 2006, Nature Reviews Drug Discovery.

[38]  Ana Cristina Andreazza,et al.  DNA damage in bipolar disorder , 2007, Psychiatry Research.

[39]  A. Collins,et al.  DNA damage in diabetes: correlation with a clinical marker. , 1998, Free radical biology & medicine.

[40]  Stuart Moss,et al.  Current Status and Future Directions , 2013 .

[41]  Eftal Sehirli,et al.  Classification of DNA damages on segmented comet assay images using convolutional neural network , 2019, Comput. Methods Programs Biomed..

[42]  B. Van Houten,et al.  Quantitative PCR-based measurement of nuclear and mitochondrial DNA damage and repair in mammalian cells. , 2014, Methods in molecular biology.

[43]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Jia Deng,et al.  A large-scale hierarchical image database , 2009, CVPR 2009.

[45]  Joong-Ho Won,et al.  HiComet: a high-throughput comet analysis tool for large-scale DNA damage assessment , 2018, BMC Bioinformatics.

[46]  R. Tice,et al.  A simple technique for quantitation of low levels of DNA damage in individual cells. , 1988, Experimental cell research.

[47]  Awadhesh N. Jha,et al.  Comet Assay measurements: a perspective , 2009, Cell Biology and Toxicology.

[48]  J. Hoeijmakers.  DNA damage, aging, and cancer. , 2009, The New England journal of medicine.

[49]  K J Johanson,et al.  Microelectrophoretic study of radiation-induced DNA damages in individual mammalian cells. , 1984, Biochemical and biophysical research communications.