Spark Machine Learning Pipelines to Predict Brain Tumor using Deep Learning
Abhishek Sawant1, Naveen Kumar N2
1Abhishek Sawant, Pursuing MTech, School of Computer Science and Engineering, VIT, Vellore (Tamil Nadu), India.
2Naveen Kumar N, Professor, VIT, Vellore (Tamil Nadu), India.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 1444-1448 | Volume-8 Issue-7, May 2019 | Retrieval Number: G562805871/19©BEIESP
Open Access | Ethics and 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: One of the challenging points in the field of Healthcare and Medicine is to detect cancer cells from a brain image generated in terms of MRI, CT-Scan etc. For efficiently determining the cancer cells in an image first the background of the image must be eliminated, Background check verification of patients is necessary. As multiple CT-Scan images show multiple cancer cells, sometimes though there are multiple cancer cells found in an image, yet we forget the root cancer cell and focus upon every cancer cells visualizable. The main target must be to visualize the number of cancer cells which are the root cause for child cancer cells and a re-verification on images which has multiple cancer cells detected. During such observation we ought to lack the cancer cell differentiation such kind of cancer and its type. In this paper we present the solution for the stated problem by processing an Image Dataset of Brain Tumor of various Patients using Tensor flow. The Image are contrasted based on features analyzed from the Dataset. Modelling is carried out using Deep Neural Featurizer which utilizes Inception V3 and Image Classification based on Logistic Regression. HealthCare’s, Govt Agencies and Corporate companies working for Healthcare are looking for ways to assist patients, customers, staff and assets to tackle the cancer during the initial stage, provide solutions to help detect cancer at early stages. In this paper we introduce to deep learning models, Large-scale computing platform and combined altogether to learn powerful feature representations within image classification and retrieval.
Keyword: Brain Tumor, Deep Learning, DCNN, Image Classification, Inception, Logistic Regression.
Scope of the Article: Deep Learning.