An efficient method for automatic morphological abnormality detection from human sperm images

Ghasemian, Fatemeh; Mirroshandel, Seyed Abolghasem; Monji-Azad, Sara; Azarnia, Mahnaz; Zahiri, Ziba

doi:10.1016/j.cmpb.2015.08.013

Cited by 65 publications

(40 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 (c), (g) and (k) respectively. The results produced by Ghasemian, et al [24] shows that the unwanted small particles were completely removed from the median filtering process that were applied before the sperms are segmented. However for the occlusion case as shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…In addition, we applied proposed technique published by Ghasemian, et al [24] for comparison since the published work focuses on the segmentation algorithm in detecting morphological of the sperm. Although Ghasemian, et al's technique mainly design for morphological analysis, their algorithm able to detect the whole body of the sperm which is relevant to be compared with our method.…”

Section: Resultsmentioning

confidence: 99%

“…The proposed method and segmentation technique by Ravanfar, et al [12] and Ghasemian, et al [24] were tested on 20 sperm motility video samples where each sample consists of different number of sperms (a total of 327 sperms) as tabulated in Table 2. Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Although the authors demonstrated the ability of their developed system in producing useful information on motility percentage, their focus is more on the tracking of the motile sperm rather than producing an efficient segmentation tool. Another recent technique published by Ghasemian, et al [24] presented an effective method in segmenting the human sperm head. Although it is designed for morphology analysis, their published work is heavily focuses on the segmenting the sperm (i.e.…”

Section: Related Workmentioning

confidence: 99%

“…Other authors such as Abbiramy and Shanthi [21], Bijar, et al [9] and Carrillo, et al [10] also proposed segmentation algorithms but their focuses are more on sperm morphological analysis. Alias, et al [16] Template matching √ X X X Bijar, et al [9] Bayesian classifier with entropy based expectation maximization and Markov random field √ √ √ √ Carrillo, et al [10] Thresholding & morphological mask √ √ X √ Park, et al [25] Strategic Hough transform √ X X X Abbiramy and Shanthi [21] Gradient image & Watershed algorithm √ √ √ √ Rahatabad, et al [19] Morphological processing √ X X √ Alegre, et al [18] Otsu thresholding technique √ X X X Sánchez, et al [20] Morphological processing & Otsu thresholding √ X X √ Chang, et al [7] k-means clustering & histogram statistical analysis techniques √ X X √ Elsayed, et al [22] Maximum entropy technique √ √ √ X Ghasemian, et al [24] Sobel edge detection & skeleton finding…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

A New Region-Based Adaptive Thresholding For Sperm Motility Segmentation

Hasikin‬

Isa

Mohamed

et al. 2017

MJCS

View full text Add to dashboard Cite

Infertility cases have shown increasing growth in recent years where approximately 40% of root causes of infertility cases are related to men. Researchers have shown that the sperm motility has significantly contributed towards infertility as compared to its concentration and morphology. However, existing technique has faced difficulties in segmenting motile sperm in the low contrast regions. The movements of the motile sperms that are normally fast further complicate the automated segmentation. In this paper, we present a new region-based adaptive thresholding technique that consists of four main stages. Pixels of the images are classified based on the intensity distribution and those pixels are grouped and processed separately. Multiple thresholds are generated based on the classified group to ensure objects in low contrast regions are segmented. In addition, the proposed method does not require external pre-processing tool or phase contrast accessories prior to the sperm segmentation. Our experimental evaluations show that the proposed method produces significant improvement from the existing technique with the average accuracy of 95.74%. The qualitative results also indicate that the proposed method is able to segment the motile sperms in the low contrast region. These results of sperm segmentation are in agreement with the quantitative measurement of non-uniformity where the proposed method attains lower non-uniformity with respect to the results achieved by the other method.Keywords: sperm motility, segmentation, thresholding, sperm detection, semen analysis. INTRODUCTIONMale factor infertility cases caused by defective sperm parameter had increased in recent years. Infertility evaluation plays a major role in identifying the underlying cause of this issue. Semen analysis is an intial and most essential step of male factor infertility evaluation. It provides prognostic information for fertility potential. The evaluation included a physical examination, hormonal evaluation, sperm parameter testing and genetic analysis. The seminal concentration, sperm motility and morphology have been used as biomarkers of male infertility since the middle of the 20th century [1]. However several studies have concluded that the sperm motility is highly contributed to the fertilization rate either in vivo or in vitro than relying only on the sperm count or morphology of the sperm [2][3][4]. The identification of sperm motility has potential importance in sperm function tests and in reproductive toxicology investigation. Sperm motility is a critical indicator of semen quality and fertility potential since it is required for the penetration of cervical mucus. It becomes critical during fertilization since it allows and facilitates the passage of the sperm through the egg membrane. The advancement in imaging technology has enabled the analysis of sperm behavior through microscopic imaging. In this approach, images which have been acquired from semen specimens are analyzed manually by an expert person. An automated metho...

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%