Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
Item Coupled PDE for Ultrasound Despeckling Using ENI Classification(Elsevier B.V., 2016) Soorajkumar, R.; Krishnakumar, P.; Girish, D.; Rajan, J.Speckle is a type of noise which is often present in ultrasound images. Speckle is formed due to constructive or destructive interference of ultrasound waves. Due to the granular pattern of speckle noise, it hides important details in ultrasound images. Many despeckling techniques are proposed in the literature, but most of them fail to reach a balance between the removal of speckle noise and preservation of the fine details in the image. In this work, an improved coupled PDE model is proposed which combines second order selective degenerate diffusion (SDD) model and fourth order PDE model based on the assumption that speckle in ultrasound image follows Gamma distribution. An edge noise interior (ENI) method is used to control the diffusion. With the help of ENI controlling function, the diffusion at edge pixels and noisy pixels are selectively accomplished with varying speed. Thus, the proposed model preserves the edges and fine texture details in the image. The model is tested on simulated images after corrupting the images with various levels of Gamma noise. Further, we have tested it on real ultrasound images also. The performance of the proposed model is compared with other similar techniques and the proposed method outperforms other state-of-the-art methods, both in terms of qualitative and quantitative measures. © 2016 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license.Item Fourth order PDE based ultrasound despeckling using ENI classification(Institute of Electrical and Electronics Engineers Inc., 2016) Soorajkumar, R.; Krishna Kumar, P.; Girish, D.; Rajan, J.Medical ultrasound images are generally corrupted with a type of signal dependent noise called speckle. The major reason for the speckle in ultrasound images is the constructive or destructive interference of ultrasound waves. The granular pattern of the speckle noise degrades the image and hinders the information present in it. In this work, we developed an improved speckle denoising method using a fourth order partial differential equation (PDE) model by integrating Edge Noise Interior method in it. Edge Noise Interior (ENI) method preserves the edges and counts the number of homogeneous pixels in the neighbourhood to classify the edges. Furthermore, a maximum likelihood technique is used to estimate and remove the bias in the denoised images. The proposed method is compared against other existing methods and validated for both simulated as well as real ultrasound images. The proposed method outperforms other state-of-the-art methods in terms of qualitative and quantitative analysis. © 2016 IEEE.Item Sonochemical synthesis of cetyl trimethylammonium bromide modified halloysite nanotubes-polystyrene nanocomposites by solution casting method(Chemical Publishing Co., 2017) Buruga, B.; Kalathi, T.K.This paper reports the surface modification of halloysite nanotubes (HNTs) using cetyl trimethylammonium bromide (CTAB) and propitious incorporation of CTAB-HNTs into polystyrene matrix by ultrasound-assisted solution casting method. The effect of surface modification and sonication on the structure, morphology and thermal behaviour of the modified halloysite nanotubes and synthesized nanocomposites was also investigated. X-ray diffraction data stipulated increase in d-spacing on surface modification and revealed complete exfoliation as a result of sonication. Scanning electron microscopy portrayed uniform distribution of clay in the polymer matrix due to combined effect of surface modification as well as sonication. Fourier transform and infrared results manifested halloysite nanotubes, cetyl trimethylammonium bromides and polystyrene major peaks in the synthesized nanocomposites confirming intercalation of cetyl trimethylammonium bromide in halloysite nanotubes interlayers and encapsulation of CTAB-HNT into the polymer, DSC analysis displayed enhancement in glass transition temperature (Tg) indicating increase in thermal stability, hence these can improved properties with potential applications. © 2017, Chemical Publishing Co. All rights reserved.Item Highlighting Nerves in Images for Ultrasound Guided Regional Anesthesia(Institute of Electrical and Electronics Engineers Inc., 2020) Akkasaligar, P.T.; Koolagudi, S.G.; Biradar, S.; Hotagi, P.; Badiger, S.Surgery is a treatment given to the patient, when patient is having injuries in the body parts. While doing the surgery the patient will undergo pain and discomfort, to reduce the pain of patient anesthesia is given before surgery. There are many types of anesthesia procedure called local, regional and general. Local anesthesia is given to specific part of the body; general anesthesia is where the patient is completely senseless. Regional anesthesia is procedure, where anesthetist does injection near a class of nerves to numb the area of human body that requires surgery. There is difference in structure of every person. This makes doctor hard to detect nerve in internal organ. Ultrasound image provide information about structure of body which can be used for regional anesthesia. Ultrasonography is the safest method compared to the other imaging techniques like Xray, CT, and MRI; because it is not based on ionizing radiation. In this paper, we simplify the issue of detection of nerve in ultrasound image. For input, image such as ultrasound images of brachial plexus are used. Initially in preprocessing, filtering technique is used to remove noise from ultrasound image and then segmentation is carried out using active contour model. Performance of segmentation is evaluated using dice coefficient and Jaccard coefficient. The nerve location in ultrasound image is detected to help the doctors in giving regional anesthesia. © 2020 IEEE.