Yazar "Aljanabi, Mohanad" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    A new and effective method for human retina optic disc segmentation with fuzzy clustering method based on active contour model
    (Springer Heidelberg, 2020) Abdullah, Ahmad S.; Rahebi, Javad; Özok, Yasa Ekşioğlu; Aljanabi, Mohanad
    In this paper, a new approach is proposed for localization and segmentation of the optic disc in human retina images. This new approach can find the boundary of the optic disc by an initial fuzzy clustering means algorithm. The proposed approach uses active contour model evolution based on a fuzzy clustering algorithm. The robustness of the proposed approach was evaluated with retinal imaging medical databases, such as DRIVE, STARE, DIARETDB1, and DRIONS. These bases contained images affected by different abnormalities, for example, diabetes, retinitis pigmentosa, and age-related macular degeneration AMD. A success detection rate with 100% accuracy was achieved for the DRIVE, DIRATEDB1, and DRIONS-DB databases, and 97.53% for the STARE database. For the optic disc segmentation, the method achieved an average accuracy and overlap in the range of 97.01-99.46% and 78.35-84.56% in these four databases. The result was compared with various methods in the literature, and it was concluded that the proposed method is more accurate than the other existing methods.
  • [ X ]
    Öğe
    An investigation of update information equations by using the artificial bee colony method for skin cancer detection
    (Int Journal Computer Science & Network Security-Ijcsns, 2018) Aljanabi, Mohanad; Javad, Rahebi; Özok, Yasa Ekşiğlu
    In Artificial Bee Colony, the one design coefficient of the improvement problem is updated by artificial bees at the Artificial Bee Colony phases by making use of mutual influence of the bees. This updating increased the slow convergence and thus helped to find the best solution for the algorithm. The convergence was set apart by means of a direct and indirect method, and the Artificial Bee Colony was proposed to be used in the Artificial Bee Colony equations. However, more than one design parameters were taken into consideration in this approach to updating. The updating depended on the orders the scout bees were given to find a better solution position after searching more in this area. By varying the new updated information (numbers of iterations) and training the algorithms of random and direct Artificial Bee Colony, the accuracy of this system was enhanced and the parameters were compared. In this study, we used the formal equations to find new positions, new update information, and an optimal solution for good food and behavior of the bees by using both the direct and random Artificial Bee Colony method used in detecting the diseases in the medical system. The proposed method provides the highest accuracy and specificity in the detection of melanoma of all other art methods. The comparison showed that the direct method was very efficient in solving skin cancer detection and successful in terms of the best solution quality and durability. The Artificial Bee Colony algorithm gives the best results in segmenting (melanoma and benign) skin cancer images.
  • [ X ]
    Öğe
    A new and effective method for human retina optic disc segmentation with fuzzy clustering method based on active contour model (December, 10.1007/S11517-019-02032-8, 2019)
    (Springer Heidelberg, 2020) Abdullah, Ahmad S.; Rahebi, Javad; Ozok, Yasa Eksioglu; Aljanabi, Mohanad
    [No abstract available]
  • Küçük Resim
    Öğe
    Skin lesion segmentation method for dermoscopy images using artificial bee colony algorithm
    (Mdpi, 2018) Aljanabi, Mohanad; Özok, Yasa Ekşioğlu; Rahebi, Javad; Abdullah, Ahmad S.
    The occurrence rates of melanoma are rising rapidly, which are resulting in higher death rates. However, if the melanoma is diagnosed in Phase I, the survival rates increase. The segmentation of the melanoma is one of the largest tasks to undertake and achieve when considering both beneath and over the segmentation. In this work, a new approach based on the artificial bee colony (ABC) algorithm is proposed for the detection of melanoma from digital images. This method is simple, fast, flexible, and requires fewer parameters compared with other algorithms. The proposed approach is applied on the PH2, ISBI 2016 challenge, the ISBI 2017 challenge, and Dermis datasets. These bases contained images are affected by different abnormalities. The formation of the databases consists of images collected from different sources; they are bases with different types of resolution, lighting, etc., so in the first step, the noise was removed from the images by using morphological filtering. In the next step, the ABC algorithm is used to find the optimum threshold value for the melanoma detection. The proposed approach achieved good results in the conditions of high specificity. The experimental results suggest that the proposed method accomplished higher performance compared to the ground truth images supported by a Dermatologist. For the melanoma detection, the method achieved an average accuracy and Jaccard's coefficient in the range of 95.24-97.61%, and 83.56-85.25% in these four databases. To show the robustness of this work, the results were compared to existing methods in the literature for melanoma detection. High values for estimation performance confirmed that the proposed melanoma detection is better than other algorithms, which demonstrates the highly differential power of the newly introduced features.