Enhancement and De-Noising of OCT Image by Adaptive Wavelet Thresholding Method

Sahu, Sima; Singh, Harsh Vikram; Kumar, Basant; Singh, Amit Kumar; Kumar, Prabhat

doi:10.1007/978-3-030-15887-3_22

Cited by 8 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dong et al developed a custom generative adversarial network (GAN) to denoise OCT images [ 15 ]. Sahu et al applied an adaptive wavelet thresholding method for the enhancement and denoising of OCT images [ 16 ]. Hojjatoleslami and Avanaki proposed an OCT skin image enhancement through the attenuation compensation algorithm [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

A Joint Model for Macular Edema Analysis in Optical Coherence Tomography Images Based on Image Enhancement and Segmentation

Tao

Zhang

Yao

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Optical coherence tomography (OCT) provides the visualization of macular edema which can assist ophthalmologists in the diagnosis of ocular diseases. Macular edema is a major cause of vision loss in patients with retinal vein occlusion (RVO). However, manual delineation of macular edema is a laborious and time-consuming task. This study proposes a joint model for automatic delineation of macular edema in OCT images. This model consists of two steps: image enhancement using a bioinspired algorithm and macular edema segmentation using a Gaussian-filtering regularized level set (SBGFRLS) algorithm. We then evaluated the delineation efficiency using the following parameters: accuracy, precision, sensitivity, specificity, Dice’s similarity coefficient, IOU, and kappa coefficient. Compared with the traditional level set algorithms, including C-V and GAC, the proposed model had higher efficiency in macular edema delineation as shown by reduced processing time and iteration times. Moreover, the accuracy, precision, sensitivity, specificity, Dice’s similarity coefficient, IOU, and kappa coefficient for macular edema delineation could reach 99.7%, 97.8%, 96.0%, 99.0%, 96.9%, 94.0%, and 96.8%, respectively. More importantly, the proposed model had comparable precision but shorter processing time compared with manual delineation. Collectively, this study provides a novel model for the delineation of macular edema in OCT images, which can assist the ophthalmologists for the screening and diagnosis of retinal diseases.

show abstract

Section: Introductionmentioning

confidence: 99%

A Joint Model for Macular Edema Analysis in Optical Coherence Tomography Images Based on Image Enhancement and Segmentation

Tao

Zhang

Yao

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…The developers have utilized average and maximum selection rules with complex wavelet transform. A guided channel‐based methodology with wavelet transform is shown by References 23,24. In Reference 25, an adaptive sparse representation‐ (SR) based multimodal image fusion method is utilized for fusion.…”

Section: Introductionmentioning

confidence: 99%

A novel approach for multimodality medical image fusion over secure environment

Kumar

Diwakar

2020

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Summary An emerging trend to deal with the issue of multimodality medical image fusion over the secure communication environment is required. Hence, this paper presents a human visual fusion algorithm for medical images such as computed tomography and magnetic resonance imaging which is based on the nonsubsampled shearlet transform (NSST) over the secure environment. Initially, the images are decayed through NSST into low and detailed highlights. The neighborhood aggregate of correlation‐based movement measures is proposed to intertwine the low frequency and sum‐modified‐Laplacian‐based fusion is utilized on detail subbands of NSST. After getting a fused image, a method noise thresholding approach is utilized to improve the accuracy of the proposed method. As a result, more accurate fused images is received. To measure the proposed method accuracy, the results of the fused images are also tested over the secure environment where encrypted/decrypted fused images are obtained using the random generator method. These decrypted fused images are also analyzed with original fused images with the proposed method as well as existing methods. From result analysis, it is observed that the proposed technique is better in holding a bone, calcification, cerebrospinal liquid, edema, and tumor subtleties of the source images and is more accurate than other existing fusion methods.

show abstract