A Morphological Post-Processing Approach for Overlapped Segmentation of Bacterial Cell Images

被引:6
作者
Abeyrathna, Dilanga [1 ]
Rauniyar, Shailabh [2 ]
Sani, Rajesh K. K. [2 ]
Huang, Pei-Chi [1 ]
机构
[1] Univ Nebraska Omaha, Dept Comp Sci, Omaha, NE 68182 USA
[2] South Dakota Sch Mines & Technol, Dept Chem & Biol Engn, Rapid City, SD 57701 USA
关键词
overlapping cell segmentation; bacterial cell segmentation; U-Net; scanning electron microscopy; deep learning; corner point detection; morphological post-processing; ALGORITHM; CONTOURS;
D O I
10.3390/make4040052
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Scanning electron microscopy (SEM) techniques have been extensively performed to image and study bacterial cells with high-resolution images. Bacterial image segmentation in SEM images is an essential task to distinguish an object of interest and its specific region. These segmentation results can then be used to retrieve quantitative measures (e.g., cell length, area, cell density) for the accurate decision-making process of obtaining cellular objects. However, the complexity of the bacterial segmentation task is a barrier, as the intensity and texture of foreground and background are similar, and also, most clustered bacterial cells in images are partially overlapping with each other. The traditional approaches for identifying cell regions in microscopy images are labor intensive and heavily dependent on the professional knowledge of researchers. To mitigate the aforementioned challenges, in this study, we tested a U-Net-based semantic segmentation architecture followed by a post-processing step of morphological over-segmentation resolution to achieve accurate cell segmentation of SEM-acquired images of bacterial cells grown in a rotary culture system. The approach showed an 89.52% Dice similarity score on bacterial cell segmentation with lower segmentation error rates, validated over several cell overlapping object segmentation approaches with significant performance improvement.
引用
收藏
页码:1024 / 1041
页数:18
相关论文
共 69 条
[11]   Integrated morphologic analysis for the identification and characterization of disease subtypes [J].
Cooper, Lee A. D. ;
Kong, Jun ;
Gutman, David A. ;
Wang, Fusheng ;
Gao, Jingjing ;
Appin, Christina ;
Cholleti, Sharath ;
Pan, Tony ;
Sharma, Ashish ;
Scarpace, Lisa ;
Mikkelsen, Tom ;
Kurc, Tahsin ;
Moreno, Carlos S. ;
Brat, Daniel J. ;
Saltz, Joel H. .
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2012, 19 (02) :317-323
[12]   MEASURES OF THE AMOUNT OF ECOLOGIC ASSOCIATION BETWEEN SPECIES [J].
DICE, LR .
ECOLOGY, 1945, 26 (03) :297-302
[13]   The VIA Annotation Software for Images, Audio and Video [J].
Dutta, Abhishek ;
Zisserman, Andrew .
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, :2276-2279
[14]   Advanced level-set based multiple-cell segmentation and tracking in time-lapse fluorescence microscopy images [J].
Dzyubachyk, Oleh ;
Niessen, Wiro ;
Meijering, Erik .
2008 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, VOLS 1-4, 2008, :185-188
[15]  
Fernandez G., 1995, Image Analysis and Processing. 8th International Conference, ICIAP '95. Proceedings, P229
[16]   Highly -defined bioprinting of long-term vascularized scaffolds with Bio-Trap: Complex geometry functionalization and process parameters with computer aided tissue engineering [J].
Foresti, Ruben ;
Rossi, Stefano ;
Pinelli, Silvana ;
Alinovi, Rossella ;
Barozzi, Matteo ;
Sciancalepore, Corrado ;
Galetti, Maricla ;
Caffarra, Cristina ;
Lagonegro, Paola ;
Scavia, Guido ;
Mattarozzi, Monica ;
Careri, Maria ;
Macaluso, Claudio ;
Miragoli, Michele ;
Selleri, Stefano .
MATERIALIA, 2020, 9
[17]   The scanning electron microscope in microbiology and diagnosis of infectious disease [J].
Golding, Christine G. ;
Lamboo, Lindsey L. ;
Beniac, Daniel R. ;
Booth, Timothy F. .
SCIENTIFIC REPORTS, 2016, 6
[18]   A review of semantic segmentation using deep neural networks [J].
Guo, Yanming ;
Liu, Yu ;
Georgiou, Theodoros ;
Lew, Michael S. .
INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2018, 7 (02) :87-93
[19]   A Biofilm Pocket Model to Evaluate Different Non-Surgical Periodontal Treatment Modalities in Terms of Biofilm Removal and Reformation, Surface Alterations and Attachment of Periodontal Ligament Fibroblasts [J].
Haegi, Tobias T. ;
Klemensberger, Sabrina ;
Bereiter, Riccarda ;
Nietzsche, Sandor ;
Cosgarea, Raluca ;
Flury, Simon ;
Lussi, Adrian ;
Sculean, Anton ;
Eick, Sigrun .
PLOS ONE, 2015, 10 (06)
[20]  
He KM, 2020, IEEE T PATTERN ANAL, V42, P386, DOI [10.1109/TPAMI.2018.2844175, 10.1109/ICCV.2017.322]