Search

In the field of pathology, whole slide image (WSI) has become the major carrier of visual and diagnostic information. Content-based image retrieval among WSIs can aid the diagnosis of an unknown pathological image by finding its similar regions in WSIs with diagnostic information. However, the huge size and complex content of WSI pose several challenges for retrieval. In this paper, we propose an unsupervised, accurate, and fast retrieval method for a breast histopathological image. Specifically, the method presents a local statistical feature of nuclei for morphology and distribution of nuclei, and employs the Gabor feature to describe the texture information. The latent Dirichlet allocation model is utilized for high-level semantic mining. Locality-sensitive hashing is used to speed up the search. Experiments on a WSI database with more than 8000 images from 15 types of breast histopathology demonstrate that our method achieves about 0.9 retrieval precision as well as promising efficiency. Based on the proposed framework, we are developing a search engine for an online digital slide browsing and retrieval platform, which can be applied in computer-aided diagnosis, pathology education, and WSI archiving and management. [ABSTRACT FROM AUTHOR]

In this paper, a novel 3D reconstruction framework is proposed to recover the 3D structural model of a space object from its multi-view images captured by a visible sensor. Given an image sequence, this framework first estimates the relative camera poses and recovers the depths of the surface points by the structure from motion (SFM) method, then the patch-based multi-view stereo (PMVS) algorithm is utilized to generate a dense 3D point cloud. To resolve the wrong matches arising from the symmetric structure and repeated textures of space objects, a new strategy is introduced, in which images are added to SFM in imaging order. Meanwhile, a refining process exploiting the structural prior knowledge that most sub-components of artificial space objects are composed of basic geometric shapes is proposed and applied to the recovered point cloud. The proposed reconstruction framework is tested on both simulated image datasets and real image datasets. Experimental results illustrate that the recovered point cloud models of space objects are accurate and have a complete coverage of the surface. Moreover, outliers and points with severe noise are effectively filtered out by the refinement, resulting in an distinct improvement of the structure and visualization of the recovered points. [ABSTRACT FROM AUTHOR]

Loss of dopaminergic (DA) neurons leads to Parkinson's disease; however, themechanism(s) for the vulnerability of DA neurons is(are) not fully understood.We demonstrate that TRPC1 regulates the L-type Ca2+channel that contributes to the rhythmic activity of adult DA neurons in the substantia nigra region. Store depletion that activates TRPC1, via STIM1, inhibits the frequency and amplitude of the rhythmic activity in DA neurons of wild-type, but not in TRPC1-/-, mice. Similarly, TRPC1-/- substantia nigra neurons showed increased L-type Ca2+ currents, decreased stimulation-dependent STIM1-Cav1.3 interaction, and decreased DA neurons. L-type Ca2+ currents and the open channel probability of Cav1.3 channels were also reduced upon TRPC1 activation, whereas increased Cav1.3 currents were observed upon STIM1 or TRPC1 silencing. Increased interaction between Cav1.3-TRPC1-STIM1 was observed upon store depletion and the loss of either TRPC1 or STIM1 led to DA cell death, which was prevented by inhibiting L-type Ca2+ channels. Neurotoxins that mimic Parkinson's disease increased Cav1.3 function, decreased TRPC1 expression, inhibited Tg-mediated STIM1-Cav1.3 interaction, and induced caspase activation. Importantly, restoration of TRPC1 expression not only inhibited Cav1.3 function but increased cell survival. Together, we provide evidence that TRPC1 suppresses Cav1.3 activity by providing an STIM1-based scaffold, which is essential for DA neuron survival. [ABSTRACT FROM AUTHOR]

How to obtain accurate difference map remains an open challenge in change detection. To tackle this problem, we propose a change detection method based on saliency detection and wavelet transformation. We do frequency-tuned saliency detection in initial difference image (IDI) obtained by logarithm ratio to get a salient difference image (SDI). Then, we calculate local entropy of SDI to obtain an entropic salient difference image (ESDI). The final difference image (FDI) is the wavelet fusion of IDI and ESDI, and Otsu thresholding is used to extract difference map from FDI. Experimental results validate the effectiveness and feasibility. [ABSTRACT FROM AUTHOR]

Objective • The differential gene analysis of ferroptosis inreating allergic rhinitis with Bu-Zhong-Yi-Qi-Decoction based on GEO using network pharmacology and molecular docking . Method • This study used databases such as TCMSP to search for traditional Chinese herbal medicine’s active ingredients and targets in Bu-Zhong-Yi-Qi-Decoction in treating allergic rhinitis. GeneCards, OMIM, TTD, and PharmaGkb were used to obtain disease targets for allergic rhinitis, and R language was used to screen Bu-Zhong-Yi- Qi-Decoction as the main target for treating allergic rhinitis. Retrieve the gene dataset of allergic rhinitis using the GEO database, analyze ferroptosis-related genes, and select the intersection of effective targets of Bu-Zhong-Yi- Qi-Decoction for treating allergic rhinitis and ferroptosisrelated genes of allergic rhinitis, draw protein interaction networks using the STRING database, use Cytoscape software to construct the target regulatory network of Bu-Zhong-Yi-Qi-Decoction for treating allergic rhinitis and ferroptosis related genes, and then use the CytoNCA plugin to screen key targets. Using R language, Gene ontology, and the biological pathway enrichment analysis were performed on the predicted targets related to the treatment of allergic rhinitis and ferroptosis with Bu-Zhong-Yi-Qi-Decoction. Selecting key targets and active ingredients for molecular docking to explore the potential mechanism of Bu-Zhong-Yi-Qi-Decoction in treating ferroptosis in allergic rhinitis. Result • After searching the TCMSP database, a total of 182 active ingredients were obtained from 8 traditional Chinese medicines of Bu-Zhong-Yi-Qi-Decoction, such as naringenin, kaempferol, Isorhamnetin, corresponding to 3023 targets and 2025 targets related to allergic rhinitis. There are 30 remarkably enriched Go analyses for biological function of potential target genes of Bu-Zhong- Yi-Qi-Decoction in allergic rhinitis, such as regulation of apoptotic signaling pathway, cellular response to peptide, wound healing, etc. Among them, there are 7 key genes related to the treatment of allergic rhinitis and ferroptosis with Bu-Zhong-Yi-Qi-Decoction, namely TP53, MAPK1, MAPK14, HIF1A, AR, CAV1, GSK3B. Conclusion • The treatment of allergic rhinitis with Bu-Zhong-Yi-Qi-Decoction is a process involving multiple divisions, targets, and pathways. These results indicated that oral Bu-Zhong-Yi-Qi-Decoction may effectively treat allergic rhinitis in clinical practice. [ABSTRACT FROM AUTHOR]

Abstract: In the process of car license plate location, the camera can’t obtain the high quality images easily due to illumination conditions, viewpoint and distance changes, vehicle motion, complex background, etc. In order to alleviate these problems to impact future car license plate location algorithm, a new algorithm using intensity variance and edge density in license plate region is proposed. The license plate region had the properties that the intensity variance is approximately equal and edge density also is approximately equal and within a certain range, then the license plate region is enhanced using these natures. In order to locate the license plate region, a matched filter based on the nature of edge density is designed. The filter can effectively extract all possible candidates. Then, the object authenticity confirmation using morphological operation and priori knowledge is done. In the morphological operation, a selfadaptive method is used to set the structuring element; it can effectively improve the flexibility of the proposed algorithm. An experiment about 700 actual images from different environments is done, and the experimental results show that the proposed algorithm can effectively improve the image quality of license plate region and the object location accuracy is 98.4 percent, which proves the proposed location method is effective and robust. [Copyright &y& Elsevier]

The problem of classifying a remote-sensing image by specifically labelling each pixel in the image is addressed. A novel method, named composite kernels conditional random field (CKCRF), which embeds multiple kernels into a classical CRFs model is proposed. Rather than manually selecting kernel-like KCRF, CKCRFs chooses the appropriate kernel by training. Moreover, a genetic programming-based decision-level fusion framework is proposed to tackle the problem of feature selection. It can select the appropriate features suitable to each category. Evaluations show that CKCRFs outperform CRFs and KCRFs, and CKCRFs with the fusion scheme is better than that without the fusion step. [ABSTRACT FROM AUTHOR]

Content-based image retrieval (CBIR) has been widely researched for histopathological images. It is challenging to retrieve contently similar regions from histopathological whole slide images (WSIs) for regions of interest (ROIs) in different size. In this paper, we propose a novel CBIR framework for database that consists of WSIs and size-scalable query ROIs. Each WSI in the database is encoded into a matrix of binary codes. When retrieving, a group of region proposals that have similar size with the query ROI are firstly located in the database through an efficient table-lookup approach. Then, these regions are ranked by a designed multi-binary-code-based similarity measurement. Finally, the top relevant regions and their locations in the WSIs as well as the corresponding diagnostic information are returned to assist pathologists. The effectiveness of the proposed framework is evaluated on a fine-annotated WSI database of epithelial breast tumors. The experimental results have proved that the proposed framework is effective for retrieval from database that consists of WSIs. Specifically, for query ROIs of 4096 4096 pixels, the retrieval precision of the top 20 return has reached 96% and the retrieval time is less than 1.5 s.