Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
7 results
Search Results
Item Enhancement and bias removal of optical coherence tomography images: An iterative approach with adaptive bilateral filtering(Elsevier Ltd, 2016) Sudeep, P.V.; Issac Niwas, S.; Ponnusamy, P.; Rajan, J.; Xiaojun, Y.; Wang, X.; Luo, Y.; Liu, L.Optical coherence tomography (OCT) has continually evolved and expanded as one of the most valuable routine tests in ophthalmology. However, noise (speckle) in the acquired images causes quality degradation of OCT images and makes it difficult to analyze the acquired images. In this paper, an iterative approach based on bilateral filtering is proposed for speckle reduction in multiframe OCT data. Gamma noise model is assumed for the observed OCT image. First, the adaptive version of the conventional bilateral filter is applied to enhance the multiframe OCT data and then the bias due to noise is reduced from each of the filtered frames. These unbiased filtered frames are then refined using an iterative approach. Finally, these refined frames are averaged to produce the denoised OCT image. Experimental results on phantom images and real OCT retinal images demonstrate the effectiveness of the proposed filter. © 2016 Elsevier Ltd.Item Non-local means image denoising using shapiro-wilk similarity measure(Institute of Electrical and Electronics Engineers Inc., 2018) Yamanappa, W.; Sudeep, P.V.; Sabu, M.K.; Rajan, J.Most of the real-time image acquisitions produce noisy measurements of the unknown true images. Image denoising is the post-acquisition technique to improve the signal-to-noise ratio of the acquired images. Denoising is an essential pre-processing step for different image processing applications such as image segmentation, feature extraction, registration, and other quantitative measurements. Among different denoising methods proposed in the literature, the non-local means method is a preferred choice for images corrupted with an additive Gaussian noise. A conventional non-local means filter (CNLM) suppresses noise in a given image with minimum loss of structural information. In this paper, we propose modifications to the CNLM algorithm where the samples are selected statistically using Shapiro-Wilk test. The experiments on standard test images demonstrate the effectiveness of the proposed method. © 2013 IEEE.Item Automatic detection and localization of Focal Cortical Dysplasia lesions in MRI using fully convolutional neural network(Elsevier Ltd, 2019) Bijay Dev, K.M.; Pawan, P.S.; Niyas, S.; Vinayagamani, S.; Kesavadas, C.; Rajan, J.Focal cortical dysplasia (FCD) is the leading cause of drug-resistant epilepsy in both children and adults. At present, the only therapeutic approach in patients with drug-resistant epilepsy is surgery. Hence, the quantification of FCD via non-invasive imaging techniques helps physicians to decide on surgical interventions. The properties like non-invasiveness and capability to produce high-resolution images makes magnetic resonance imaging an ideal tool for detecting the FCD to an extent. The FCD lesions vary in size, shape, and location for different patients and make the manual detection time consuming and sensitive to the experience of the observer. Automatic segmentation of FCD lesions is challenging due to the difference in signal strength in images acquired with different machines, noise, and other kinds of distortions such as motion artifacts. Most of the methods proposed in the literature use conventional machine learning and image processing techniques in which their accuracy relies on the trained features. Hence, feature extraction should be done more precisely which requires human expertise. The ability to learn the appropriate features/representations from the training data without any human interventions makes the convolutional neural network (CNN) the suitable method for addressing these drawbacks. As far as we are aware, this work is the first one to use a CNN based model to solve the aforementioned problem using only MRI FLAIR images. We customized the popular U-Net architecture and trained the proposed model from scratch (using MRI images acquired with 1.5T and 3T scanners). FCD detection rate (recall) of the proposed model is 82.5 (33/40 patients detected correctly). © 2019Item A Conceptual Investigation at the Interface between Wireless Power Devices and CMOS Neuron IC for Retinal Image Acquisition(MDPI, 2020) Al-Shidaifat, A.; Kumar, S.; Chakrabartty, S.; Song, H.In this paper, a conceptual investigation of the interface between wireless power devices and a retina complementary metal oxide semiconductor (CMOS) neuron integrated circuit (IC) have been presented. The proposed investigation consists of three designs: design-I, design-II, and design-III. Design-I involves a slotted loop monopole antenna as per American National Standards Institute (ANSI) guidelines, which achieve an ultra-wide band ranging from 3.1 GHz to 10.6 GHz. The biocompatible antenna is made on silicon-nitride substrate using on-wafer packaging technology and it is used as a receiver device. The performance of antenna provides a wideband, sufficient power to receive, and low losses due to the avoidance of printed circuit board (PCB) fabrication. A CMOS based multi-stack power harvesting circuit achieves the output power ranging from 4 mW to 2.7 W and corresponds from the selected Radio Frequency (RF) bands of loop antenna is exhibited in design-II. The power efficiency of 40% to 82%, with respect to output powers of 4 mW to 2.7 W, is achieved. Design-III includes a CMOS based retina neuron circuit that employs a dynamic feedback technique and support to achieve the number of read-out spikes. At the end of the interface between wireless power devices and a CMOS retina neuron IC, 50 mV read-out spikes are achieved, with varying light intensity, from 0 mW/cm2 to 2 mW/cm2. The proposed design-II and design-III are implemented and fabricated using commercial CMOS 0.065 µm, Samsung process. The antenna and RF power harvesting IC could be placed on a contact lens platform while retina neuron IC can be implanted after ganglions cells inside the eye. The antenna and harvesting IC are physically connected to the retina circuit in the form of light. This conceptual investigation could support medical professionals in achieving an interfacing approach to restore the image visualization. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.Item A cascaded convolutional neural network architecture for despeckling OCT images(Elsevier Ltd, 2021) Anoop, B.N.; Kalmady, K.S.; Udathu, A.; Siddharth, V.; Girish, G.N.; Kothari, A.R.; Rajan, J.Optical Coherence Tomography (OCT) is an imaging technique widely used for medical imaging. Noise in an OCT image generally degrades its quality, thereby obscuring clinical features and making the automated segmentation task suboptimal. Obtaining higher quality images requires sophisticated equipment and technology, available only in selected research settings, and is expensive to acquire. Developing effective denoising methods to improve the quality of the images acquired on systems currently in use has potential for vastly improving image quality and automated quantitative analysis. Noise characteristics in images acquired from machines of different makes and models may vary. Our experiments show that any single state-of-the-art method for noise reduction fails to perform equally well on images from various sources. Therefore, detailed analysis is required to determine the exact noise type in images acquired using different OCT machines. In this work we studied noise characteristics in the publicly available DUKE and OPTIMA datasets to build a more efficient model for noise reduction. These datasets have OCT images acquired using machines of different manufacturers. We further propose a patch-wise training methodology to build a system to effectively denoise OCT images. We have performed an extensive range of experiments to show that the proposed method performs superior to other state-of-the-art-methods. © 2021 Elsevier LtdItem Analyzing data incompleteness for MRI Data for quality enhancement(Institute of Electrical and Electronics Engineers Inc., 2024) Shanbhag, S.; Raju, S.; Gurupur, V.P.; Kamath, S.S.; Kandala, R.N.V.P.S.; Trader, A.E.; Lal, S.Magnetic resonance imaging (MRI) is a powerful medical imaging technique widely used for diagnosing various conditions because it provides detailed images of internal structures within the body. However, like any imaging modality, MRI images can be susceptible to artifacts that may arise from various sources, including hardware imperfections, patient motion, and image acquisition techniques. Detecting and mitigating these artifacts are crucial steps in ensuring MRI scans' reliability and clinical utility. In this paper, we present algorithms specifically designed to address the challenges of undersampling and motion artifacts in MR images. Our approach involves leveraging advanced image processing techniques, including line detection algorithms for undersampling detection and blur parameter estimation for motion artifact analysis. By accurately identifying and quantifying these artifacts, our algorithms aim to improve MRI data's overall quality and completeness, ultimately enhancing diagnostic accuracy and patient care. © 2024 The Authors.Item A retinex inspired deep image prior model for despeckling and deblurring of aerial and satellite images using proximal gradient method(Taylor and Francis Ltd., 2025) Shastry, A.; Bini, A.A.; Padikkal, J.Unsupervised learning models, particularly in the remote sensing domain, have gained significant attention in recent years. Various degradations in the satellite images, primarily occurring during acquisition, pose a substantial hurdle in obtaining reliable ground truth and extensive training data. The Deep Image Prior model (DIP) addresses these issues by performing restoration tasks using a single image, relying on the implicit regularization inherent in the network architecture. In this paper, we propose a novel approach, integrating the DIP model within the retinex framework to restore aerial and satellite images from the Gamma distributed speckles and linear shift-invariant Gaussian blur along with contrast enhancement using the alternating proximal gradient descent ascent (PGDA) method. Our proposed methodology combines implicit regularization with explicit total variational (TV) regularization, incorporating automated estimation of local regularization parameters. The data-fidelity component in the optimization function is formulated using the Bayesian Maximum A posteriori (MAP) estimate, assuming the speckles follow the Gamma distribution. Demonstration of despeckling and deblurring alone and in addition as a combined task is carried out on aerial and Synthetic Aperture Radar (SAR) images with different resolutions and polarization from various sources. Results obtained are compared with various state-of-the-art despeckling and deblurring models using distinct image quality metrics such as Equivalent Number of Looks (ENL), Contrast to Noise Ratio (CNR), Edge Preserving Index (EPI), Entropy, Global Contrast Factor (GCF), Natural Image Quality Evaluator (NIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Bradley-Terry (B-T) score based on the various factors. The quality of restored images depicted superior performance of the proposed method over the existing models under study. © 2024 Informa UK Limited, trading as Taylor & Francis Group.