multi-scale segmentation for detecting mass in mammograms using deep learning techniques

  Seema Saknure,  Dr. Deepa Deshpande

This paper tends to the issue of fragmenting an image into the segment. We characterize a predicate for estimating the proof for a limit between two districts utilizing a diagram based portrayal of the picture. We at that point build up an efficient division calculation dependent on this predicate and demonstrate that in spite of the fact that this calculation settles on ravenous choices it produces divisions that fulfill worldwide properties. We apply the calculation to picture division utilizing two different sorts of nearby neighborhoods in building the chart and show the outcomes with both genuine and engineered pictures. The calculation keeps running in time about straight in the number of chart edges and is additionally quick by and by. A significant normal for the strategy is its capacity to safeguard detail in low-changeability picture districts while overlooking points of interest in high-fluctuation locales. Convolution Neural Networks (CNNs) are investigated in the context of computer-aided diagnosis (CADx) of breast cancer. State-of-the-art CNNs are trained and evaluated on two mammographic datasets, consisting of ROIs depicting benign or malignant mass lesions. The performance evaluation of each examined network is addressed in two training scenarios: the first involves initializing the network with pre-trained weights, while for the second the networks are initialized in a random fashion. Extensive experimental results show the superior performance achieved in the case of fine-tuning a pre trained network compared to training from initial stages respectively. Our purpose is to develop a mammography-based DL breast cancer risk model that is more accurate than established clinical breast cancer risk models. We propose a novel approach for detecting and segmenting breast masses in mammography based on multi-scale morphological filtering and a self-adaptive cascade of random forests (CasRFs). CasRFs can cope with severe class imbalance by adding layers to the cascade until a minimum number of false-positives (FPs) is reached.

Keywords- cancer,mammogram,machine learning ,svm

Unique Identification Number - IJEDR2002067
Page Number(s) - 395-401
Pubished in - Volume 8 | Issue 2 | April 2020
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Seema Saknure,  Dr. Deepa Deshpande,   "multi-scale segmentation for detecting mass in mammograms using deep learning techniques", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.8, Issue 2, pp.395-401, April 2020, Available at :http://www.ijedr.org/papers/IJEDR2002067.pdf