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
[1]  
Abdulla W., 2017, GITHUB REPOSITORY
[2]  
Abeyrathna D., 2021, 2021 IEEE INT C BIOI, P3548
[3]   Improved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images [J].
Al-Kofahi, Yousef ;
Lassoued, Wiem ;
Lee, William ;
Roysam, Badrinath .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2010, 57 (04) :841-852
[4]   Deploying swarm intelligence in medical imaging identifying metastasis, microcalcifications and brain image segmentation [J].
al-Rifaie, Mohammad Majid ;
Aber, Ahmed ;
Hemanth, Duraiswamy Jude .
IET SYSTEMS BIOLOGY, 2015, 9 (06) :234-244
[5]  
[Anonymous], 1988, P ALV VIS C
[6]   Learning to Detect Partially Overlapping Instances [J].
Arteta, Carlos ;
Lempitsky, Victor ;
Noble, J. Alison ;
Zisserman, Andrew .
2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, :3230-3237
[7]   The Strengths of Scanning Electron Microscopy in Deciphering SARS-CoV-2 Infectious Cycle [J].
Brahim Belhaouari, Djamal ;
Fontanini, Anthony ;
Baudoin, Jean-Pierre ;
Haddad, Gabriel ;
Le Bideau, Marion ;
Bou Khalil, Jacques Yaacoub ;
Raoult, Didier ;
La Scola, Bernard .
FRONTIERS IN MICROBIOLOGY, 2020, 11
[8]   Swarm Intelligence Algorithms for Feature Selection: A Review [J].
Brezocnik, Lucija ;
Fister, Iztok, Jr. ;
Podgorelec, Vili .
APPLIED SCIENCES-BASEL, 2018, 8 (09)
[9]   Pervasiveness of UVC254-resistant Geobacillus strains in extreme environments [J].
Carlson, Courtney ;
Singh, Nitin K. ;
Bibra, Mohit ;
Sani, Rajesh K. ;
Venkateswaran, Kasthuri .
APPLIED MICROBIOLOGY AND BIOTECHNOLOGY, 2018, 102 (04) :1869-1887
[10]   Invariant Delineation of Nuclear Architecture in Glioblastoma Multiforme for Clinical and Molecular Association [J].
Chang, Hang ;
Han, Ju ;
Borowsky, Alexander ;
Loss, Leandro ;
Gray, Joe W. ;
Spellman, Paul T. ;
Parvin, Bahram .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2013, 32 (04) :670-682