Fully Automated Methods for the Detection and Segmentation of Mitochondria in Microscopy Images

Authors: Blessing Ojeme, Frederick Quinn, Russell Karls, Shannon Quinn

Abstract:

The detection and segmentation of mitochondria from fluorescence microscopy is crucial for understanding the complex structure of the nervous system. However, the constant fission and fusion of mitochondria and image distortion in the background make the task of detection and segmentation challenging. Although there exists a number of open-source software tools and artificial intelligence (AI) methods designed for analyzing mitochondrial images, the availability of only a few combined expertise in the medical field and AI required to utilize these tools poses a challenge to its full adoption and use in clinical settings. Motivated by the advantages of automated methods in terms of good performance, minimum detection time, ease of implementation, and cross-platform compactibility, this study proposes a fully automated framework for the detection and segmentation of mitochondria using both image shape information and descriptive statistics. Using the low-cost, open-source Python and OpenCV library, the algorithms are implemented in three stages: pre-processing; image binarization; and coarse-to-fine segmentation. The proposed model is validated using the fluorescence mitochondrial dataset. Ground truth labels generated using Labkit were also used to evaluate the performance of our detection and segmentation model using precision, recall and rand index. The study produces good detection and segmentation results and reports the challenges encountered during the image analysis of mitochondrial morphology from the fluorescence mitochondrial dataset. A discussion on the methods and future perspectives of fully automated frameworks concludes the paper.

Keywords: 2D, Binarization, CLAHE, detection, fluorescence microscopy, mitochondria, segmentation.

References:

[1] C. A. Fischer et al., “MitoSegNet: Easy-to-use Deep Learning Segmentation for Analyzing Mitochondrial Morphology,” iScience, vol. 23, no. 10, Oct. 2020, doi: 10.1016/j.isci.2020.101601.
[2] F. Troger et al., “Identification of mitochondrial toxicants by combined in silico and in vitro studies – A structure-based view on the adverse outcome pathway,” Comput. Toxicol., vol. 14, May 2020, doi: 10.1016/j.comtox.2020.100123.
[3] N. Nguyen-Thanh, T. Pham, K. Ichikawa, and T. D. Pham, “Automated Detection and Segmentation of Mitochondrial Images based on Gradient Enhancement and Adaptive Gabor Filter,” 2019. (Online). Available: https://hal.archives-ouvertes.fr/hal-02284786
[4] A. J. Valente, L. A. Maddalena, E. L. Robb, F. Moradi, and J. A. Stuart, “A simple ImageJ macro tool for analyzing mitochondrial network morphology in mammalian cell culture,” Acta Histochem., vol. 119, no. 3, pp. 315–326, Apr. 2017, doi: 10.1016/j.acthis.2017.03.001.
[5] S. Xu, O. Amira, J. Liu, C. X. Zhang, J. Zhang, and G. Li, “HAM-MFN: Hyperspectral and multispectral image multiscale fusion network with RAP loss,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 7, pp. 4618–4628, Jul. 2020, doi: 10.1109/TGRS.2020.2964777.
[6] E. O’Toole, P. van der Heide, J. Richard McIntosh, and D. Mastronarde, “Large-Scale Electron Tomography of Cells Using SerialEM and IMOD,” Hanssen, E. Cell. Imaging. Biol. Med. Physics, Biomed. Eng. Springer, Cham. https//doi.org/10.1007/978-3-319-68997-5_4, pp. 95–116, 2018, doi: 10.1007/978-3-319-68997-5_4.
[7] C. McQuin et al., “CellProfiler 3.0: Next-generation image processing for biology,” PLoS Biol., pp. 1–17, 2018.
[8] L. Henderson and M. Beeby, “High-Throughput Electron Cryo-tomography of Protein Complexes and Their Assembly,” Marsh, J. Protein Complex Assem. Methods Mol. Biol. vol 1764. Humana Press. New York, NY. https//doi.org/10.1007/978-1-4939-7759-8_2, vol. 01, pp. 29–44, 2018.
[9] K. W. Eliceiri et al., “Biological Imaging Software Tools,” Nat Methods, vol. 9, no. 7, pp. 697–710, 2013, doi: 10.1038/nmeth.2084.Biological.
[10] W. Li, H. Deng, Q. Rao, Q. Xie, X. Chen, and H. Han, “An automated pipeline for mitochondrial segmentation on ATUM-SEM stacks,” in Journal of Bioinformatics and Computational Biology, Jun. 2017, vol. 15, no. 3. doi: 10.1142/S0219720017500159.
[11] A. E. Y. T. Lefebvre, D. Ma, K. Kessenbrock, D. A. Lawson, and M. A. Digman, “Automated segmentation and tracking of mitochondria in live-cell time-lapse images,” Nat. Methods, vol. 18, no. 9, pp. 1091–1102, Sep. 2021, doi: 10.1038/s41592-021-01234-z.
[12] C. H. Chu, W. W. Tseng, C. M. Hsu, and A. C. Wei, “Image Analysis of the Mitochondrial Network Morphology with Applications in Cancer Research,” Frontiers in Physics, vol. 10. Frontiers Media S.A., Apr. 13, 2022. doi: 10.3389/fphy.2022.855775.
[13] K. C. J. Chen, Y. Yu, R. Li, H. C. Lee, G. Yang, and J. Kovačevič, “Adaptive active-mask image segmentation for quantitative characterization of mitochondrial morphology,” in Proceedings - International Conference on Image Processing, ICIP, 2012, pp. 2033–2036. doi: 10.1109/ICIP.2012.6467289.
[14] E. Lihavainen, J. Mäkelä, J. N. Spelbrink, and A. S. Ribeiro, “Detecting and Tracking the Tips of Fluorescently Labeled Mitochondria in U2OS Cells”, doi: 10.1007/978-3-319-23234-8.
[15] E. U. Mumcuoglu, R. Hassanpour, S. F. Tasel, G. Perkins, M. E. Martone, and M. N. Gurcan, “Computerized detection and segmentation of mitochondria on electron microscope images,” J. Microsc., vol. 246, no. 3, pp. 248–265, Jun. 2012, doi: 10.1111/j.1365-2818.2012.03614.x.
[16] R. J. Giuly, M. E. Martone, and M. H. Ellisman, “Method: Automatic segmentation of mitochondria utilizing patch classification, contour pair classification, and automatically seeded level sets,” BMC Bioinformatics, vol. 13, no. 1, Feb. 2012, doi: 10.1186/1471-2105-13-29.
[17] E. Lihavainen, J. Mäkelä, J. N. Spelbrink, and A. S. Ribeiro, “Mytoe: Automatic analysis of mitochondrial dynamics,” Bioinformatics, vol. 28, no. 7, pp. 1050–1051, Apr. 2012, doi: 10.1093/bioinformatics/bts073.
[18] S. F. Tasel, R. Hassanpour, E. U. Mumcuoglu, G. C. Perkins, and M. Martone, “Automatic detection of mitochondria from electron microscope tomography images: a curve fitting approach,” in Medical Imaging 2014: Image Processing, Mar. 2014, vol. 9034, p. 903449. doi: 10.1117/12.2043517.
[19] G. M. Fogo et al., “Machine learning-based classification of mitochondrial morphology in primary neurons and brain,” Sci. Rep., vol. 11, no. 1, Dec. 2021, doi: 10.1038/s41598-021-84528-8.
[20] R. Narasimha, H. Ouyang, A. Gray, S. W. McLaughlin, and S. Subramaniam, “Automatic joint classification and segmentation of whole cell 3D images,” Pattern Recognit., vol. 42, no. 6, pp. 1067–1079, Jun. 2009, doi: 10.1016/j.patcog.2008.08.009.
[21] A. Zahedi et al., “Deep Analysis of Mitochondria and Cell Health Using Machine Learning,” Sci. Rep., vol. 8, no. 1, Dec. 2018, doi: 10.1038/s41598-018-34455-y.
[22] C. Ozgur, T. Colliau, G. Rogers, and Z. Hughes, “MatLab vs. Python vs. R,” J. Data Sci., vol. 15, no. 3, pp. 355–372, 2021, doi: 10.6339/jds.201707_15(3).0001.
[23] M. H. Hesamian, W. Jia, X. He, and P. Kennedy, “Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges,” J. Digit. Imaging, vol. 32, no. 4, pp. 582–596, 2019, doi: 10.1007/s10278-019-00227-x.
[24] M. Arzt et al., “LABKIT: Labeling and Segmentation Toolkit for Big Image Data,” Front. Comput. Sci., vol. 4, no. February, pp. 1–12, 2022, doi: 10.3389/fcomp.2022.777728.
[25] F. Altaf, S. Islam, N. Akhtar, and N. Janjua, “Going deep in medical image analysis: Concepts, methods, challenges, and future directions,” IEEE Access, vol. 7, pp. 99540–99572, 2019, doi: 10.1109/ACCESS.2019.2929365.
[26] G. Varoquaux and V. Cheplygina, “Machine learning for medical imaging: methodological failures and recommendations for the future,” npj Digit. Med., vol. 5, no. 1, 2022, doi: 10.1038/s41746-022-00592-y.
[27] C. E. Widodo, K. Adi, and R. Gernowo, “Medical image processing using python and open cv,” J. Phys. Conf. Ser., vol. 1524, no. 1, pp. 8–12, 2020, doi: 10.1088/1742-6596/1524/1/012003.
[28] D. Yatsenko et al., “DataJoint: managing big scientific data using MATLAB or Python,” bioRxiv, pp. 1–10, 2015.
[29] G. Yadav, S. Maheshwari, and A. Agarwal, “Contrast limited adaptive histogram equalization based enhancement for real time video system,” Proc. 2014 Int. Conf. Adv. Comput. Commun. Informatics, ICACCI 2014, pp. 2392–2397, 2014, doi: 10.1109/ICACCI.2014.6968381.
[30] A. Asmaidi, D. S. Putra, M. M. Risky, and F. U. R, “Implementation of Sobel Method Based Edge Detection for Flower Image Segmentation,” SinkrOn, vol. 3, no. 2, p. 161, 2019, doi: 10.33395/sinkron.v3i2.10050.
[31] M. Hill et al., “Spectral Analysis of Mitochondrial Dynamics: A Graph-Theoretic Approach to Understanding Subcellular Pathology,” Proc. 19th Python Sci. Conf., no. Scipy, pp. 91–97, 2020, doi: 10.25080/majora-342d178e-00d.