Retinal image processing and classification using convolutional neural networks (Record no. 6116)
[ view plain ]
000 -LEADER | |
---|---|
fixed length control field | 02321nam a22001937a 4500 |
003 - CONTROL NUMBER IDENTIFIER | |
control field | OSt |
005 - DATE AND TIME OF LATEST TRANSACTION | |
control field | 20220107122841.0 |
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
fixed length control field | 180605b xxu||||| |||| 00| 0 eng d |
040 ## - CATALOGING SOURCE | |
Transcribing agency | IIITMK |
100 ## - MAIN ENTRY--PERSONAL NAME | |
Personal name | Karuna Rajan (91616008) |
9 (RLIN) | 14312 |
245 ## - TITLE STATEMENT | |
Title | Retinal image processing and classification using convolutional neural networks |
300 ## - PHYSICAL DESCRIPTION | |
Extent | MSC MI 2016-2018 |
500 ## - GENERAL NOTE | |
General note | In the field of medical image processing, deep learning approaches is emerging out as powerful<br/>tool for analysis and disease detection. The project aims to develop a system to distinguish<br/>retinal diseases from fundus images. Precise and programmed analysis of retinal images has been<br/>considered as an effective tool for the determination of retinal diseases such as diabetic<br/>retinopathy, hypertension, arteriosclerosis, etc. In this study, we extracted different retinal<br/>features such as blood vessels, optic disc, lesions, etc., and applied Convolutional Neural<br/>network based models to detect various disease from fundus images involved in the STructured<br/>Analysis of REtina. Augmentation techniques like translations and rotations were done for<br/>increasing the number of images. The blood vessel extraction was done with the help of<br/>morphological operations like dilation and erosion, and enhancement operations like CLAHE,<br/>AHE. The bright lesions (exudates) inside the retina can be detected by the filtering operations<br/>and contrast enhancement after the removal of the optic disc. The optic disc can be localised by<br/>the methods such as opening, closing, Canny’s edge detection, and finally thresholding the image<br/>after filling the holes. At the end of the stage of classification, we will get the disease classes<br/>with the probabilities. We used the Convolutional Neural Networks for this grouping purpose.<br/>The convolutional model for 10 classes with the RGB images as input, got 42% as the accuracy.<br/>The model with the green channel images are expected to have the highest accuracy. Due to the<br/>small size of datasets, the deep learning techniques in this study were ineffective to be applied<br/>for the detection of the disease. <br/> |
502 ## - DISSERTATION NOTE | |
Degree type | MSC MI |
Name of granting institution | 2016-2018 |
Year degree granted | INT |
-- | Mr. Pradeep Kumar K |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name entry element | CONVOLUTIONAL NEURAL NETWORK |
9 (RLIN) | 14313 |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name entry element | RETINAL IMAGE PROCESSING |
9 (RLIN) | 14314 |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name entry element | DEEP LEARNING |
9 (RLIN) | 14315 |
942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
Source of classification or shelving scheme | Dewey Decimal Classification |
Koha item type |
Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Collection code | Home library | Current library | Shelving location | Date acquired | Total Checkouts | Barcode | Date last seen | Price effective from | Koha item type |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dewey Decimal Classification | Non Fiction | IIITM-K | Kerala University of Digital Sciences, Innovation and Technology Knowledge Centre | 05/06/2018 | R-1410 | 05/06/2018 | 05/06/2018 | Project Reports |