Region Of Interest Estimation Research Articles

LATENT FINGERPRINT IMAGE ENHANCEMENT BASED ON OPTIMIZED BENT IDENTITY BASED CONVOLUTIONAL NEURAL NETWORK

Fingerprints are unique biometric systems (BSs) in which none of the human possesses similar fingerprint structures. It is one of the most significant biometric processes used in the identification of criminals. Latent fingerprints or latents are generated mainly by the finger sweat or oil deposits which is left by the suspects unintentionally. The impressions of latents are blurred or smudgy in nature and not viewed by naked eye. These fingerprints are of low quality, corrupted by noise, degraded by technological factors and exhibit minor details. Latents display consistent structural info when observed as an image. Image Enhancement is necessary in latents, to transform the latent (noisy) image into fine-quality (enhanced) image. In this work, a new image enhancement approach named BI-CNN (Bent Identity-Convolution Neural Network) with Spatial Pyramid Max Pooling (SPMP) model optimized using TSOA (Tunicate Swarm Optimization Algorithm) is presented to produce an enhanced latent at the output. This procedure involves the integration of ROI (Region Of Interest) Estimation, Anisotropic Gaussian Filter (AGF) based Pre-filtering, Fingerprint alignment using Sobel Filter, Intrinsic Feature patch extraction using Optimized BI-CNN, GAT (Graph Attention) network based Similarity Estimation followed by image reconstruction and feedback module. The implementation tool used in this work is PYTHON platform. The proposed optimized BI-CNN framework tested on dual public datasets namely IIITD-latent finger print and IIITD-MOLF have shown enhanced outcomes. Thus, the IIITD -latent fingerprint database obtained 83.33% on Rank-10 accuracy and 39.33% on Rank-25 accuracy.

Boundary Extraction Enhanced Distorted Born Iterative Method for Microwave Mammography

This letter focuses on improving the accuracy of the distorted Born iterative method (DBIM)-based inverse scattering algorithm, using accurate boundary extraction in microwave mammography. It is well known that the accuracy of inverse scattering algorithms depends on the initial estimate of the region of interest (ROI). The Envelope algorithm is one of the promising algorithms for accurate ROI estimation. However, in the near-field breast imaging scenario, the coupling effect between an antenna and the breast surface incurs a nonnegligible error for Envelope-based boundary extraction, which is mainly caused by the mismatching between the reference and measured waveforms. To address this problem, this letter introduces the finite-difference time-domain-based waveform reconstruction for improving the accuracy of DBIM-based microwave imaging. The two-dimensional numerical simulations, using realistic breast phantoms derived from magnetic resonance images, demonstrate that our proposed algorithm remarkably enhances the accuracy of the DBIM, even in highly heterogeneous cases.

Accurate retrieval of region of interest for estimating point spread function and image deblurring

ABSTRACTExtraction of an optimal region of interest (ROI) is crucial in many image processing applications, such as estimation of the point spread function (PSF) and blind deconvolution (BD). Although the amount of publications on PSF and BD is quite extensive; however, the work on ROI estimation has not received much attention. Existing methods which used heuristic models are not only time-consuming but also computationally expensive. In this paper, we proposed a new ROI retrieval scheme based on image partitioning and entropy measurement feedback. This method has low computation cost since it contains no matrix operations. Comprehensive experiments on real and synthetic datasets revealed that the proposed method is competitive when compared with existing search techniques, averaging at 26.1 dB, 0.46 and 1.44 on peak signal-to-noise ratio, universal image quality index and error ratio scales, respectively. On average, the proposed method takes less than 10 s to retrieve the ROI which is significantly faster compared to established solution.

A Bayesian particle filtering method for brain source localisation

In this paper, we explore the multiple source localisation problem in the cerebral cortex using magnetoencephalography (MEG) data. We model neural currents as point-wise dipolar sources which dynamically evolve over time, then model dipole dynamics using a probabilistic state space model in which dipole locations are strictly constrained to lie within the cortex. Based on the proposed models, we develop a Bayesian particle filtering algorithm for localisation of both known and unknown numbers of dipoles. The algorithm consists of a region of interest (ROI) estimation step for initial dipole number estimation, a Gibbs multiple particle filter (GMPF) step for individual dipole state estimation, and a selection criterion step for selecting the final estimates. The estimated results from the ROI estimation are used to adaptively adjust particle filter's sample size to reduce the overall computational cost. The proposed models and the algorithm are tested in numerical experiments. Results are compared with existing particle filtering methods. The numerical results show that the proposed methods can achieve improved performance metrics in terms of dipole number estimation and dipole localisation.

Evaluation of bone involvement in patients with Gaucher disease: a semi-quantitative magnetic resonance imaging method (using ROI estimation of bone lesion) as an alternative method to semi-quantitative methods used so far.

The aim of this study was to evaluate bone involvement in patients with Gaucher disease (GD) and to propose a novel semi-quantitative magnetic resonance imaging (MRI) staging. MRI of the lumbar spine, femur, and tibia was performed in 24 patients with GD and 24 healthy controls. We also measured circulating levels of C-C motif ligand-3 (CCL-3) chemokine, C-telopeptide of collagen type-1 (CTX), and tartrate-resistant acid phosphatase isoform type-b (TRACP-5b). We used the following staging based on MRI data: stage I: region of interest (ROI) 1/2 of normal values and bone infiltration up to 30%; stage II: ROI 1/3 of normal values and bone infiltration from 30 to 60%; stage III: ROI 1/4 of normal values and bone infiltration from 60% to 80%; and stage IV: detection of epiphyseal infiltration, osteonecrosis and deformity regardless of the ROI's values. All but two patients had abnormal MRI findings: 9 (37.5%), 6 (25%), 3 (12.5%), and 4 (16.7%) had stages I-IV, respectively. Patients with GD had elevated chitotriosidase, serum TRACP-5b, and CCL-3 levels (P<0.001). We propose an easily reproducible semi-quantitative scoring system and confirm that patients with GD have abnormal MRI bone findings and enhanced osteoclast activity possibly due to elevated CCL-3.

A SEGMENTATION FRAMEWORK FOR PHASE CONTRAST AND FLUORESCENCE MICROSCOPY IMAGES

The noninvasive imaging of unstained living cells is a widely used technique in biotechnology for determining biological and biochemical role of proteins, since it allows studying living specimens without altering them. Usually, fluorescence and contrast (or transmission) images are both used complementarily, as their combination allows possible better outcomes. However, segmentation of contrast images is particularly difficult due to the presence of defocused scans, lighting/shade-off artifacts and cells overlapping. In this work, we investigate the optical properties intervening during the image formation process, and propose different segmentation strategies that can benefit from these properties. The proposed scheme (i) combines the estimated phase and the fluorescence information in order to obtain initial markers for a latter segmentation stage; and (ii) use the shear oriented polar snakes, an active contour model that implicitly involves phase information on its energy functional. The obtained contour can be used as region of interest estimation, as data for a latter shape-fitting process, or as smart markers for a more detailed segmentation process (i.e. watershed). Experimental results provide a comparison of the different segmentation schemes, and confirm the suitability of the proposed strategy and model for cell images segmentation.

Impact of Filtering on Region of Interest Estimation from Diffusion Weighted Brain Images

Article Impact of Filtering on Region of Interest Estimation from Diffusion Weighted Brain Images was published on September 7, 2013 in the journal Biomedical Engineering / Biomedizinische Technik (volume 58, issue SI-1-Track-L).

Fully Automatic Region of Interest Selection in Glomerular Filtration Rate Estimation from 99mTc-DTPA Renogram

Glomerular filtration rate (GFR) is a common accepted standard estimation of renal function. Gamma camera-based methods for estimating renal uptake of (99m)Tc-diethylenetriaminepentaacetic acid (DTPA) without blood or urine sampling have been widely used. Of these, the method introduced by Gates has been the most common method. Currently, most of gamma cameras are equipped with a commercial program for GFR determination, a semi-quantitative analysis by manually drawing region of interest (ROI) over each kidney. Then, the GFR value can be computed from the scintigraphic determination of (99m)Tc-DTPA uptake within the kidney automatically. Delineating the kidney area is difficult when applying a fixed threshold value. Moreover, hand-drawn ROIs are tedious, time consuming, and dependent highly on operator skill. Thus, we developed a fully automatic renal ROI estimation system based on the temporal changes in intensity counts, intensity-pair distribution image contrast enhancement method, adaptive thresholding, and morphological operations that can locate the kidney area and obtain the GFR value from a (99m)Tc-DTPA renogram. To evaluate the performance of the proposed approach, 30 clinical dynamic renograms were introduced. The fully automatic approach failed in one patient with very poor renal function. Four patients had a unilateral kidney, and the others had bilateral kidneys. The automatic contours from the remaining 54 kidneys were compared with the contours of manual drawing. The 54 kidneys were included for area error and boundary error analyses. There was high correlation between two physicians' manual contours and the contours obtained by our approach. For area error analysis, the mean true positive area overlap is 91%, the mean false negative is 13.4%, and the mean false positive is 9.3%. The boundary error is 1.6 pixels. The GFR calculated using this automatic computer-aided approach is reproducible and may be applied to help nuclear medicine physicians in clinical practice.