Peripapillary Atrophy Detection by Sparse Biologically Inspired Feature Manifold
| Autor: | Damon Wing Kee Wong, Seang-Mei Saw, Dacheng Tao, Tien Yin Wong, Jiang Liu, Ngan Meng Tan, Jun Cheng |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Databases
Factual genetic structures Computer science Optic Disk Feature extraction Optic disk Glaucoma Image processing Diagnostic Techniques Ophthalmological Retina chemistry.chemical_compound Atrophy Retinal Diseases Image Processing Computer-Assisted medicine Humans Computer vision Peripapillary atrophy Electrical and Electronic Engineering Child Radiological and Ultrasound Technology business.industry fungi Retinal Image segmentation Linear discriminant analysis medicine.disease eye diseases Computer Science Applications Euclidean distance Optic Atrophy medicine.anatomical_structure chemistry Feature (computer vision) Artificial intelligence Transfer of learning business Algorithms Software Curse of dimensionality |
| Zdroj: | IEEE Transactions on Medical Imaging. 31:2355-2365 |
| ISSN: | 1558-254X 0278-0062 |
| DOI: | 10.1109/tmi.2012.2218118 |
| Popis: | Peripapillary atrophy (PPA) is an atrophy of pre-existing retina tissue. Because of its association with eye diseases such as myopia and glaucoma, PPA is an important indicator for diagnosis of these diseases. Experienced ophthalmologists are able to determine the presence of PPA using visual information from the retinal images. However, it is tedious, time consuming and subjective to examine all images especially in a screening program. This paper presents biologically inspired feature (BIF) for the automatic detection of PPA. BIF mimics the process of cortex for visual perception. In the proposed method, a focal region is segmented from the retinal image and the BIF is extracted. As BIF is an intrinsically low dimensional feature embedded in a high dimensional space, it is not suitable to measure the similarity between two BIFs directly based on the Euclidean distance. Therefore, it is necessary to obtain a suitable mapping to reduce the dimensionality. In this paper, we explore sparse transfer learning to transfer the label information from ophthalmologists to the sample distribution knowledge contained in all samples. Selective pair-wise discriminant analysis is used to define two strategies of sparse transfer learning: negative and positive sparse transfer learning. Experimental results show that negative sparse transfer learning is superior to the positive one for this task. The proposed BIF based approach achieves an accuracy of more than 90% in detecting PPA, much better than previous methods. It can be used to save the workload of ophthalmologists and thus reduce the diagnosis costs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|