Segmentation Approach Towards PCM Images 1131


Figure 1. Flocs and filaments in a phase-contrast microscopic image.


procedures require skillful preparation of samples. Alter- natively, the sample preparation for bright-field and PCMs is simple, and requires a micropipette, slide, and coverslip (Khan et al., 2015a,2015b). Themain advantage of PCMover bright-field and fluorescence microscopies, with reference to AS, is that the filamentous bacteria can be observed at lower objective magnification, without requiring staining. There- fore, PCM requires less time to acquire images of an AS sample. However, the PCM has inherent artifacts, known as shade-off and halos, affecting the accuracy of the image seg- mentation. In this work, we have explored different segmen- tation approaches for their robustness in avoiding artifacts. The resultant segmentation can be used as initialization for more sophisticated segmentation techniques (Cai et al., 2014; Pang et al., 2015). In the context of AS, Mesquita et al. compared bright-


field and PCMs on the basis of floc area and filament length determined by image analysis (Mesquita et al., 2010). Jenné et al. (2007) and Cenens et al. (2002) suggested the seg- mentation of PCM images of AS. However, they do not address the artifacts associated with the PCM. Consequently, their method of segmentation over-estimated the floc area and under-estimated the filament length. Based on the lim- itation of their algorithm, Mesquita et al. recommended bright-field microscopy. Due to the shortcomings of their


algorithms, and the recommendations in favor of the bright field by Mesquita et al., their algorithmcould not be used for benchmarking. However, we have customized the algorithm of Jenné et al. to segment the filaments only, as a top-bottom- hat filtering-based segmentation. In addition, we observe that if segmentation of flocs and filaments in the phase- contrast image is accurate enough, it can give results com- parable with or better than the bright-field microscopy. Several segmentation algorithms have been reported to


segment the PCM images (Das et al., 2011; Topman et al., 2011; Juneau et al., 2013; Su et al., 2013; Jaccard et al., 2014; Pang et al., 2015; Yin et al., 2016). However, the algorithms were either meant to measure cell confluency (Topman et al., 2011; Juneau et al., 2013) or particularly segment bone marrow cell or neuron images (Das et al., 2011; Su et al., 2013; Jaccard et al., 2014; Pang et al., 2015; Yin et al., 2016). The two approaches cannot be adopted in the case of AS images because the flocs and filaments are morphologically


Figure 2. Flow chart for segmentation of phase-contrast images of activated sludge (AS) and its assessment.


different from bone marrow cells or neurons. On one hand, the flocs are three-dimensional (3D) structures of arbitrary shapes, with some compactness and porosity. The filaments,


on the other hand, can be free or attached to the flocs. Some filaments are long enough to be captured by image stitching (Khan et al., 2015a, 2015b). Some filaments overlap with themselves or other filaments making closed paths. Most importantly, we are interested in preserving the morphology of the flocs and filaments in the segmented images, in the presence of artifacts of the PCM. The algorithms that are meant to count cells do not consider the morphological variations. Hence, the techniques, reported in the literature, cannot be directly applied to AS images for benchmarking. However, we have customized the previously reported techniques based on range filtering (Juneau et al., 2013), and watershed (Debeir et al., 2008), for PCM images of AS. The customization is explained in the following Methods section. We have compared different approaches and assessed with specific reference to AS. The comparison will establish which segmentation approach is suitable for PCM images of AS. The flow chart of the work reported in this paper is shown in Figure 2.


METHODS


Sample Preparation and Image Acquisition In total, 61 PCM images, used for the assessment of the proposed segmentation algorithms, were selected randomly from a database of AS images. The database was constructed using samples from eight municipal wastewater treatment plants and one experimental setup. The experimental setup


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92  |  Page 93  |  Page 94  |  Page 95  |  Page 96  |  Page 97  |  Page 98  |  Page 99  |  Page 100  |  Page 101  |  Page 102  |  Page 103  |  Page 104  |  Page 105  |  Page 106  |  Page 107  |  Page 108  |  Page 109  |  Page 110  |  Page 111  |  Page 112  |  Page 113  |  Page 114  |  Page 115  |  Page 116  |  Page 117  |  Page 118  |  Page 119  |  Page 120  |  Page 121  |  Page 122  |  Page 123  |  Page 124  |  Page 125  |  Page 126  |  Page 127  |  Page 128  |  Page 129  |  Page 130  |  Page 131  |  Page 132  |  Page 133  |  Page 134  |  Page 135  |  Page 136  |  Page 137  |  Page 138  |  Page 139  |  Page 140  |  Page 141  |  Page 142  |  Page 143  |  Page 144  |  Page 145  |  Page 146  |  Page 147  |  Page 148  |  Page 149  |  Page 150  |  Page 151  |  Page 152  |  Page 153  |  Page 154  |  Page 155  |  Page 156  |  Page 157  |  Page 158  |  Page 159  |  Page 160  |  Page 161  |  Page 162  |  Page 163  |  Page 164  |  Page 165  |  Page 166  |  Page 167  |  Page 168  |  Page 169  |  Page 170  |  Page 171  |  Page 172  |  Page 173  |  Page 174  |  Page 175  |  Page 176  |  Page 177  |  Page 178  |  Page 179  |  Page 180