Automated blob detection using iterative Laplacian of Gaussian filtering and unilateral second-order Gaussian kernels

Wang, Gang; López-Molina, Carlos; Baets, Bernard De

doi:10.1016/j.dsp.2019.102592

Cited by 42 publications

(19 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LoG kernel was then convoluted with the blob-like structures to return a fitting score. This process was performed in an iterative manner with increasing σ LoG kernels, where the best fit scale of σ 0 was determined when the fitting score converges to a local maximum, the radius of particle was then obtained as r ¼ ffiffi ffi 2 p s 0 [37]. This algorithm was applied to each blob-like structure in the image with an adaptive threshold to filter out the unfocused outliers allowing accurate particle size distribution from the PIV images; see the example in electronic supplementary material, figure S4d.…”

Section: Particle Size Analysismentioning

confidence: 99%

On the design of particle filters inspired by animal noses

Yuk

Chakraborty

Cheng

et al. 2022

J. R. Soc. Interface.

View full text Add to dashboard Cite

Passive filtering is a common strategy to reduce airborne disease transmission and particulate contaminants across scales spanning orders of magnitude. The engineering of high-performance filters with relatively low flow resistance but high virus- or particle-blocking efficiency is a non-trivial problem of paramount relevance, as evidenced in the variety of industrial filtration systems and face masks. Next-generation industrial filters and masks should retain sufficiently small droplets and aerosols while having low resistance. We introduce a novel 3D-printable particle filter inspired by animals’ complex nasal anatomy. Unlike standard random-media-based filters, the proposed concept relies on equally spaced channels with tortuous airflow paths. These two strategies induce distinct effects: a reduced resistance and a high likelihood of particle trapping by altering their trajectories with tortuous paths and induced local flow instability. The structures are tested for pressure drop and particle filtering efficiency over different airflow rates. We have also cross-validated the observed efficiency through numerical simulations. We found that the designed filters exhibit a lower pressure drop, compared to commercial masks and filters, while capturing particles bigger than approximately 10 μm. Our findings could facilitate a novel and scalable filter concept inspired by animal noses.

show abstract

Section: Particle Size Analysismentioning

confidence: 99%

On the design of particle filters inspired by animal noses

Yuk

Chakraborty

Cheng

et al. 2022

J. R. Soc. Interface.

View full text Add to dashboard Cite

show abstract

“…Another recurrent problem in cell screening is the presence of colliding or overlapping cells, which are not trivially discriminated by automatic methods. A primary alternative in these cases is the use of object detection methods designed for blob-like structures [30]. A secondary alternative, not based on filtering, is the use of superpixel maps [31] as the initial oversegmentation.…”

Section: Object Segmentation Phasementioning

confidence: 99%

Unsupervised Cell Segmentation and Labelling in Neural Tissue Images

et al. 2021

Self Cite

View full text Add to dashboard Cite

Neurodegenerative diseases are a group of largely incurable disorders characterised by the progressive loss of neurons and for which often the molecular mechanisms are poorly understood. To bridge this gap, researchers employ a range of techniques. A very prominent and useful technique adopted across many different fields is imaging and the analysis of histopathological and fluorescent label tissue samples. Although image acquisition has been efficiently automated recently, automated analysis still presents a bottleneck. Although various methods have been developed to automate this task, they tend to make use of single-purpose machine learning models that require extensive training, imposing a significant workload on the experts and introducing variability in the analysis. Moreover, these methods are impractical to audit and adapt, as their internal parameters are difficult to interpret and change. Here, we present a novel unsupervised automated schema for object segmentation of images, exemplified on a dataset of tissue images. Our schema does not require training data, can be fully audited and is based on a series of understandable biological decisions. In order to evaluate and validate our schema, we compared it with a state-of-the-art automated segmentation method for post-mortem tissues of ALS patients.

show abstract

“…However, appropriate segmentation and OS time prediction remain unresolved issues due to the diagnosis limitations and difficulty for the radiologists to view the tumorous regions with intra-tumoral structures. 12 For this, multi-scale (MS) features of texture type have been derived from tumour regions in the axial view of MRI images using a filter named Laplacian of Gaussian (LOG) 13 for the OS time prediction. 14 In a recent study, segmentation was performed using the convolutional neural network (CNN)-based methods.…”

Section: Introductionmentioning

confidence: 99%

Multi‐level dilated convolutional neural network for brain tumour segmentation and multi‐view‐based radiomics for overall survival prediction

Rafi

Madni

Janjua

et al. 2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Glioblastoma (GBM) is the most high-risk and grievous tumour in the brain that causes the death of more than 50% of the patients within one to 2 years after diagnosis. Accurate detection and prognosis of this disease are critical to provide essential guidelines for treatment planning. This study proposed using a deep learning-based network for the GBM segmentation and radiomic features for the patient's overall survival (OS) time prediction. The segmentation model used in this study was a modified U-Net-based deep 3D multi-level dilated convolutional neural network. It uses multiple kernels of altered sizes to capture contextual information at different levels. The proposed scheme for OS time prediction overcomes the problem of information loss caused by the derivation of features in a single view due to the variation in the neighbouring pixels of the tumorous region. The selected features were based on texture, shape, and volume. These features were computed from the segmented components of tumour in axial, coronal, and sagittal views of magnetic resonance imaging slices. The proposed models were trained and evaluated on the BraTS 2019 dataset. Experimental results of OS time prediction on the validation data have showed an accuracy of 48.3%, with the mean squared error of 92 599.598. On the validation data, the segmentation model achieved a mean dice similarity coefficient of 0.75, 0.89, and 0.80 for enhancing tumour, whole tumour, and tumour core, respectively. Future work is warranted to improve the overall performance of OS time prediction based on the findings in this study.

show abstract

Automated blob detection using iterative Laplacian of Gaussian filtering and unilateral second-order Gaussian kernels

Cited by 42 publications

References 39 publications

On the design of particle filters inspired by animal noses

On the design of particle filters inspired by animal noses

Unsupervised Cell Segmentation and Labelling in Neural Tissue Images

Multi‐level dilated convolutional neural network for brain tumour segmentation and multi‐view‐based radiomics for overall survival prediction

Contact Info

Product

Resources

About