Bhupendra Deshmukh - Academia.edu (original) (raw)
Uploads
Papers by Bhupendra Deshmukh
ABSTRACT Screening of microscopic slides is a manual process which involves its subjectivity. A s... more ABSTRACT Screening of microscopic slides is a manual process which involves its subjectivity. A semi-automated computer based system can contribute to the detection of screening error by the way of greater reliability. The objective of segmentation in microscopic image is to extract cellular, nuclear and tissue components. This problem is challenging because accurate segmentation of each cell is a difficult task and there is large variations in feature of each component. In this paper an attempt is made to overview various segmentation methods for microscopic images. The existing methods are grouped by their application in one of the following pathologist field: Cytology and Histology. This analysis is helpful for the better use of existing method and for improving their performance as well as designing new one.
The proposed system efficiently predicts breast tumour from microscopic cytology images through i... more The proposed system efficiently predicts breast tumour from microscopic cytology images through image processing techniques coupled with support vector machine (SVM) classifier as either benign or malignant. The breast cytology image is denoised using non-linear Anisotropic diffusion method to remove random noise prevalent in cytology images. In the cytology images only nucleus is the region of interest for the detection of breast cancer. Hence, all the nuclei in the cytology image are segmented using seeded region growing (SRG) method. Geometric features of every cell nuclei are extracted. These features are then used in conjunction with SVMs that classifies breast tumour as cancerous or non-cancerous. The proposed system implemented on MATLAB takes less than 1 minutes of processing time and has yielded promising results that would supplement in the diagnosis of breast cancer.
2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies, 2014
ABSTRACT Screening of microscopic slides is a manual process which involves its subjectivity. A s... more ABSTRACT Screening of microscopic slides is a manual process which involves its subjectivity. A semi-automated computer based system can contribute to the detection of screening error by the way of greater reliability. The objective of segmentation in microscopic image is to extract cellular, nuclear and tissue components. This problem is challenging because accurate segmentation of each cell is a difficult task and there is large variations in feature of each component. In this paper an attempt is made to overview various segmentation methods for microscopic images. The existing methods are grouped by their application in one of the following pathologist field: Cytology and Histology. This analysis is helpful for the better use of existing method and for improving their performance as well as designing new one.
The proposed system efficiently predicts breast tumour from microscopic cytology images through i... more The proposed system efficiently predicts breast tumour from microscopic cytology images through image processing techniques coupled with support vector machine (SVM) classifier as either benign or malignant. The breast cytology image is denoised using non-linear Anisotropic diffusion method to remove random noise prevalent in cytology images. In the cytology images only nucleus is the region of interest for the detection of breast cancer. Hence, all the nuclei in the cytology image are segmented using seeded region growing (SRG) method. Geometric features of every cell nuclei are extracted. These features are then used in conjunction with SVMs that classifies breast tumour as cancerous or non-cancerous. The proposed system implemented on MATLAB takes less than 1 minutes of processing time and has yielded promising results that would supplement in the diagnosis of breast cancer.
2014 International Conference on Electronic Systems, Signal Processing and Computing Technologies, 2014