Ovarian Cancer Detection in MRI Images using Feature Space and Classification Method (ABC-CNN)
Uroosa Shafi1, Sugandha Sharma2
1Uroosa Shafi, College of Engineering, Chandigarh University, Mohali (Punjab), India.
2Sugandha Sharma, College of Engineering, Chandigarh University, Mohali (Punjab), India.
Manuscript received on 20 August 2019 | Revised Manuscript received on 30 August 2019 | Manuscript Published on 16 September 2019 | PP: 545-551 | Volume-8 Issue-2S6 July 2019 | Retrieval Number: B11730782S619/2019©BEIESP | DOI: 10.35940/ijrte.B1173.0782S619
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The most common disease has an adverse effect on women is ovarian cancer. The female generative organ that is placed in the pelvis is similar to the size of the almond. The production of eggs for the reproduction is the part of the ovaries. Ovarian cancer mainly started from the ovaries, ovaries are the reproductive glands that mainly found in the women. The main aim of this paper is detection of the ovarian cancer and is done in stage wise manner. At every stage the cancer images are trained and cancer is detected using ABC- Convolutional Neural Network. The quality of the MRI cancer images are enhanced and selected in accordance to the performance parameters which are accuracy, error rate and processing time. The images are selected by extracting the features to increase the accuracy rate and reduce the cost and the time of the processing. The MRI cancer images are used for detection, classification and extraction algorithms. The selection of the extracted features of the medical images is done through the optimized ABC algorithm. After the extracting features in medicinal images using kernel PCA method. The selected features removes zero values and then optimized the feature vector .The classification process based on the convolutional neural network for training and testing the cancer images in each stage also detecting the quality of the cancer images. The method is evaluated using performance parameter which is signaling to noise ratio. The dataset is created by collecting the medical images from skims (sher-i-kashmir institute of Medical sciences) and Hospital Kashmir. The number of cancer images used 250. There is two kind of images used. Individual is normal image means without or cancer free images the 2nd one are malignant cancer images. Complete number of images used 250 which have 50 medical images of each dataset (Normal, Stage I, Stage II, Stage II and Stage III). The dataset pictures usually include the MRI scan image of PELVIS. The detection and selection of the images through MRI cancer images is in stage wise approach. The quality of the cancer images is improved with peak signal to noise ratio. The evaluated parameters used to increase the accuracy rate and decrease the time of processing.
Keywords: Ovarian Cancer, Extracting Features, Convolutional Neural Network, Detection and Classification.
Scope of the Article: Image Security