An Insight Framework for Content based Medical Image Retrieval using Deep Convolutional Neural Network
Hari Priya P1, Porkodi R2
1Hari Priya P, Department of Computer Science, Bharathiar University, (Tamil Nadu), India.
2Porkodi R, Department of Computer Science, Bharathiar University, (Tamil Nadu), India.
Manuscript received on 26 November 2019 | Revised Manuscript received on 08 December 2019 | Manuscript Published on 14 December 2019 | PP: 172-179 | Volume-9 Issue-1S October 2019 | Retrieval Number: A10431091S19/19©BEIESP | DOI: 10.35940/ijeat.A1043.1091S19
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: Content Based Image Retrieval system is essentially proven techniques for retrieving the DICOM based images. DICOM format is use to acquire, store and shared medical images. Typically, retrieval of image under query upon the medical image databases is performed by fusing the low-level and high-level descriptors along with DCNN features. In this paper, DICOM image meta data are extracted by using dicom function and create the local database for reserve the information. To accomplish the initial search and retrieve the images by using extraction of Semantic information. The DICOM tags are extracted from the DICOM images and use DCNN feature to build a feature vector database. Subsequently prediction is done based on the by leveraging the convolution layers based on the meta data along with DCNN image features. This paper attempts to implement pre filter method to all DICOM images which further decrease the searching no of images, searching time and ultimately gives fast processing. DCNN based prediction model was constructed and finest results are accomplished. Average accuracy of precision and recall up to0.80 and 0.87 respectively is achieved based on precision value which would be suitable for high quality image retrieval based on semantic information confined in the image.
Keywords: CBMIR, DICOM, DCNN, Semantic Gap.
Scope of the Article: Deep Learning