BITS Pilani

  • Page last updated on Monday, September 12, 2022

Research

banner
Research

Detection and Classification of Diabetic Retinopathy using Digital Fundus Images

Diabetic retinopathy (DR) is caused by damage to the small blood vessels of the retina in the posterior part of the eye of the diabetic patient. The main stages of diabetic retinopathy are non-proliferate diabetes retinopathy (NPDR) and proliferate diabetes retinopathy (PDR). The retinal fundus photographs are widely used in the diagnosis and treatment of various eye diseases in clinics. It is also one of the main resources for mass screening of diabetic retinopathy
 
 
 
 
 
 
 
 
 

Steganography and Watermarking in Bio Medicine

Simultaneous storage of medical images in the spatial and frequency domain: A comparative study
Digital watermarking is a technique of hiding specific identification data for copyright authentication. This technique is adapted here for interleaving patient information with medical images, to reduce storage and transmission overheads. 
 
Efficient Storage and Transmission of Digital Fundus Images with Patient Information Using Reversible Watermarking Technique and Error Control Codes 
Abstract Handling of patient records is increasing overhead costs for most of the hospitals in this digital age. In most hospitals and health care centers, the patient text information and corresponding medical images are stored separately as different files. There is a possibility of mishandling the text file containing patient history. We are proposing a novel method for the compact storage and transmission of patient information with the medical images. In this technique, we are using a reversible watermarking technique to hide the patient information within the retinal fundus image. There is a possibility that these medical images, which carry patient information, can get corrupted by the noise during the storage or transmission. The safe recovery of patient information is important in this situation. So, to recover the maximum amount of text information in the noisy environment, the encrypted patient information is coded with error control coding (ECC) techniques. The performance of three types of ECC for various levels of salt & pepper (S &P) noise is tabulated for a specific example. The proposed system is more reliable even in a noisy environment and saves memory.
 
 

Early Detection of Glaucoma using Digital Fundus Images

Glaucoma is a disease of the optic nerve caused by the increase in the intraocular pressure of the eye. Glaucoma mainly affects the optic disc by increasing the cup size. It can lead to the blindness if it is not detected and treated in proper time. The detection of glaucoma through Optical Coherence Tomography (OCT) and Heidelberg Retinal Tomography (HRT) is very expensive. This paper presents a novel method for glaucoma detection using digital fundus images. Digital image processing techniques, such as preprocessing, morphological operations and thresholding, are widely used for the automatic detection of optic disc, blood vessels and computation of the features. We have extracted features such as cup to disc (c/d) ratio, ratio of the distance between optic disc center and optic nerve head to diameter of the optic disc, and the ratio of blood vessels area in inferior-superior side to area of blood vessel in the nasal-temporal side. These features are validated by classifying the normal and glaucoma images using neural network classifier. The results presented in this paper indicate that the features are clinically significant in the detection of glaucoma. Our system is able to classify the glaucoma automatically with a sensitivity and specificity of 100% and 80% respectively.
 
 
 
 

Quick Links

    An Institution Deemed to be University estd. vide Sec.3 of the UGC Act,1956 under notification # F.12-23/63.U-2 of Jun 18,1964

    © 2025 Centre for Software Development,SDET Unit, BITS-Pilani, India.

    Designed and developed by fractal | ink design studios