Nuclei Segmentation for Quantification of Brain Tumors in Digital Pathology Images

2018 ◽  
Vol 10 (2) ◽  
pp. 36-49 ◽  
Author(s):  
Peifang Guo ◽  
Alan Evans ◽  
Prabir Bhattacharya
Keyword(s):  
Brain Tumors ◽  
Real Time ◽  
Level Set ◽  
Average Rate ◽  
Digital Pathology ◽  
Similarity Index ◽  
Threshold Level ◽  
Problem Space ◽  
Nuclei Segmentation ◽  
Validation Stage

In this article, based on image transformation of HSV (Hue, Saturation, Value), the authors propose a method for cancer nuclei segmentation when such conflicts of cancer nuclei involve ‘omics' indicative of brain tumors pathologically. To constrain the problem space in the region of color information, i.e. cancer nuclei, they convert the images into the V component of HSV first, and then apply the threshold level-set segmentation and the sparsity technique (VTLS-ST) in segmentation. The combined technique of the proposed VTLS-ST is implemented using the real-time CBTC dataset in the validation stage. The proposed method exhibits an improved capability of searching recursively for the optimal threshold level-set in the working subsets via the sparsity representation in segmentation. The experimental results show the reliability and efficiency of the proposed approach in real-time applications with an average rate of 0.932 in terms of similarity index for segmentation of cancer nuclei in brain tumor detection.

scholarly journals Real-Time Runway Detection for Infrared Aerial Image Using Synthetic Vision and an ROI Based Level Set Method

2018 ◽  
Vol 10 (10) ◽  
pp. 1544 ◽  
Author(s):  
Changjiang Liu ◽  
Irene Cheng ◽  
Anup Basu
Keyword(s):  
Real Time ◽  
Level Set Method ◽  
Level Set ◽  
Infrared Image ◽  
Region Of Interest ◽  
Aerial Image ◽  
Real Time Processing ◽  
Synthetic Vision ◽  
Level Set Function ◽  
Rough Region

We present a new method for real-time runway detection embedded in synthetic vision and an ROI (Region of Interest) based level set method. A virtual runway from synthetic vision provides a rough region of an infrared runway. A three-thresholding segmentation is proposed following Otsu’s binarization method to extract a runway subset from this region, which is used to construct an initial level set function. The virtual runway also gives a reference area of the actual runway in an infrared image, which helps us design a stopping criterion for the level set method. In order to meet the needs of real-time processing, the ROI based level set evolution framework is implemented in this paper. Experimental results show that the proposed algorithm is efficient and accurate.

scholarly journals Implementation of Iterative bilateral filtering for removal of Rician noise in MR images using FPGA

2020 ◽  
Vol 9 (3) ◽  
pp. 279-284
Keyword(s):  
Magnetic Resonance ◽  
Real Time ◽  
Visual Analysis ◽  
Similarity Index ◽  
Structural Similarity ◽  
Bilateral Filter ◽  
Magnetic Resonance Images ◽  
Rician Noise ◽  
Diagnostic Quality ◽  
Index Matrix

Magnetic resonance image noise reduction is important to process further and visual analysis. Bilateral filter is denoises image and also preserves edge. It proposes Iterative bilateral filter which reduces Rician noise in the magnitude magnetic resonance images and retains the fine structures, edges and it also reduces the bias caused by Rician noise. The visual and diagnostic quality of the image is retained. The quantitative analysis is based on analysis of standard quality metrics parameters like peak signal-to-noise ratio and mean structural similarity index matrix reveals that these methods yields better results than the other proposed denoising methods for MRI. Problem associated with the method is that it is computationally complex hence time consuming. It is not recommended for real time applications. To use in real time application a parallel implantation of the same using FPGA is proposed.

scholarly journals A statistical approach for identifying the ionospheric footprint of magnetospheric boundaries from SuperDARN observations

2008 ◽  
Vol 26 (2) ◽  
pp. 305-314 ◽  
Author(s):  
G. Lointier ◽  
T. Dudok de Wit ◽  
C. Hanuise ◽  
X. Vallières ◽  
J.-P. Villain
Keyword(s):  
Real Time ◽  
Statistical Approach ◽  
Spectral Width ◽  
Threshold Level ◽  
Strongly Correlated ◽  
Spatial Coverage ◽  
First Results ◽  
High Latitude Ionosphere ◽  
Value Decomposition ◽  
Magnetospheric Boundaries

Abstract. Identifying and tracking the projection of magnetospheric regions on the high-latitude ionosphere is of primary importance for studying the Solar Wind-Magnetosphere-Ionosphere system and for space weather applications. By its unique spatial coverage and temporal resolution, the Super Dual Auroral Radar Network (SuperDARN) provides key parameters, such as the Doppler spectral width, which allows the monitoring of the ionospheric footprint of some magnetospheric boundaries in near real-time. In this study, we present the first results of a statistical approach for monitoring these magnetospheric boundaries. The singular value decomposition is used as a data reduction tool to describe the backscattered echoes with a small set of parameters. One of these is strongly correlated with the Doppler spectral width, and can thus be used as a proxy for it. Based on this, we propose a Bayesian classifier for identifying the spectral width boundary, which is classically associated with the Polar Cap boundary. The results are in good agreement with previous studies. Two advantages of the method are: the possibility to apply it in near real-time, and its capacity to select the appropriate threshold level for the boundary detection.

scholarly journals Collection of Garbage using Internet of Things

2019 ◽  
Vol 8 (6) ◽  
pp. 3481-3483
Keyword(s):  
Internet Of Things ◽  
Real Time ◽  
Threshold Level ◽  
Pond Water ◽  
Conveyor Belt ◽  
Human Intervention ◽  
Practical Application ◽  
Electric Oven ◽  
Plastic Wastes ◽  
Opening And Closing

Due to rise in population, the waste disposed by human has become enormous. This paper deals with a real time practical application of designing and building a prototype for an automatic opening and closing of dustbin on the detection of the human intervention who wish to throw out their trash. In this system the level of garbage in the bin can be known by the use of sensors. Each dustbin has a unique ID. If the garbage in the bin reaches the threshold level, the garbage collectors are given information based on which they can collect the garbage. In case the dustbins reach threshold level, user will not be able to access the bin. In order to avoid the decaying smell around the bin the harmless chemical sprinklers are used. Further, the garbage is segregated into bio degradable and non-biodegradable wet and dry waste using a conveyor belt. Internally electric oven burns the dry waste and the ashes are used for certain applications such as in cleaning the pond and in preventing the growth of algae in the pond water. The wet wastes are made to decompose and it acts as a fertilizer to the fields. The plastic wastes collected are used in building plastic tar roads

scholarly journals Simulation of a Real-Time Bus Arrival Predictor using RFID and LabVIEW

2012 ◽  
pp. 207-211
Author(s):  
Aritra Paul ◽  
Nischit Bharadwaj ◽  
Jagriti R ◽  
Sameera S
Keyword(s):  
Real Time ◽  
The Public ◽  
Bus Network ◽  
Bus Stops ◽  
Concept Validation ◽  
Validation Stage

Most college and office goers in India use the public buses for daily commuting. The bus network caters to the need of thousands who find it an affordable means of transport. However, the absence of real-time updates in the system poses some very serious problems during the exit period. Large cohorts leave the workplace at one time, leading to over-crowding, chaos and accidents at local bus stops. To address this issue, we have designed an RFID based system that alerts the commuter at periodic intervals as his desired bus approaches the stop. This paper documents the preliminaries, concept validation stage, and the development of a scaled-down prototype. The objective is to notify commuters of the approach of their desired bus (on request) by SMS.

Computational Nuclei Segmentation Methods in Digital Pathology: A Survey

2019 ◽  
Vol 28 (1) ◽  
pp. 1-13
Author(s):  
Tomohiro Hayakawa ◽  
V. B. Surya Prasath ◽  
Hiroharu Kawanaka ◽  
Bruce J. Aronow ◽  
Shinji Tsuruoka
Keyword(s):  
Digital Pathology ◽  
Nuclei Segmentation ◽  
Segmentation Methods

scholarly journals Pathogenicity and a TaqMan Real-Time PCR for Specific Detection of Pantoea allii, a Bacterial Pathogen of Onions

Plant Disease ◽  
2019 ◽  
Vol 103 (12) ◽  
pp. 3031-3040 ◽  
Author(s):  
Shabnam Rahimi-Khameneh ◽  
Sanni Hsieh ◽  
Renlin Xu ◽  
Tyler J. Avis ◽  
Sean Li ◽  
...  
Keyword(s):  
Real Time ◽  
Real Time Pcr ◽  
Phylogenetic Analyses ◽  
Similarity Index ◽  
Taqman Probe ◽  
Economic Losses ◽  
In Planta ◽  
Pcr Assay ◽  
Blind Test ◽  
Reliable Detection

Bacterial diseases of onion are reported to cause significant economic losses. Pantoea allii Brady, one of the pathogens causing the center rot on onions, has not yet been reported in Canada. We report the pathogenicity of P. allii on commercially available Canadian green onions (scallions). All P. allii-inoculated plants, irrespective of the inoculum concentration, exhibited typical leaf chlorotic discoloration on green onion leaves, which can reduce their marketability. Reisolation of P. allii from infected scallion tissues and reidentification by sequencing and phylogenetic analyses of the leuS gene suggest that the pathogen can survive in infected tissues 21 days after inoculation. This is the first report of P. allii as a potential pathogen of green onions. This study also reports the development and validation of a TaqMan real-time PCR assay targeting the leuS gene for reliable detection of P. allii in pure cultures and in planta. A 642-bp leuS gene fragment was targeted because it showed high nucleotide diversity and positively correlated with genome-based average nucleotide identity with respect to percent similarity index and identity of Pantoea species. The assay specificity was validated using 61 bacterial and fungal strains. Under optimal conditions, the selected primers and FAM-labeled TaqMan probe were specific for the detection of nine reference P. allii strains by real-time PCR. The 52 strains of other Pantoea spp. (n = 25), non-Pantoea spp. (n = 20), and fungi/oomycetes (n = 7) tested negative (no detectable fluorescence). Onion tissues spiked with P. allii, naturally infested onion bulbs, greenhouse infected green onion leaf samples, as well as an interlaboratory blind test were used to validate the assay specificity. The sensitivities of a 1-pg DNA concentration and 30 CFU are comparable to previously reported real-time PCR assays of other bacterial pathogens. The TaqMan real-time PCR assay developed in this study will facilitate reliable detection of P. allii and could be a useful tool for screening onion imports or exports for the presence of this pathogen.

Sign in / Sign up

Export Citation Format

Share Document