Automated Detection of Retinal Detachment from Ocular Ultrasound using Image Thresholding

This paper presents a new method for automated detection of retinal detachment from ocular ultrasound (USG) image using digital image processing techniques. Retinal detachment (RD) is an ocular emergency in which retina gets detached from the tissues lying underneath it and often requires immediate intervention to prevent rapid, irreversible vision loss. For the detection of RD, manual methods like direct fundoscopy and visual field testing are difficult to perform and they do not completely rule out retinal detachment. Ophthalmologists use ocular ultrasound image to enhance their clinical acumen in detecting retinal detachment. Sometimes it is difficult to extract diagnostic features from ultrasound image due to its poor quality. Also, noise present in the image would cause misinterpretation during an eye examination; this demands pre-processing of the image followed by automated detection technique for detection of retinal detachment. A new technique for automatic detection of retinal detachment using ocular ultrasound image is presented here through appropriate image thresholding and segmentation methods. In this paper, enhancement of the ultrasound image is done initially and then region of interest (ROI) is fixed to locate vitreous region. In next stage, thresholding (Binarization) and inversion of ROI are performed. In last stage, morphological operations are performed for computing percentage of detached retina (PDR) and identification of the nature of detached retina (NDR).