Marker controlled superpixel nuclei segmentation and automatic counting on immunohistochemistry staining images.

MOTIVATION: For the diagnosis of cancer, manually counting nuclei on massive histopathological images is tedious and the counting results might vary due to the subjective nature of the operation. RESULTS: This paper presents a new segmentation and counting method for nuclei, which can automatically provide nucleus counting results. This method segments nuclei with detected nuclei seed markers through a modified simple one-pass superpixel segmentation method. Rather than using a single pixel as a seed, we created a superseed for each nucleus to involve more information for improved segmentation results. Nucleus pixels are extracted by a newly proposed fusing method to reduce stain variations and preserve nucleus contour information. By evaluating segmentation results, the proposed method was compared to five existing methods on a dataset with 52 immunohistochemically (IHC) stained images. Our proposed method produced the highest mean F1-score of 0.668. By evaluating the counting results, another dataset with more than 30 000 IHC stained nuclei in 88 images were prepared. The correlation between automatically generated nucleus counting results and manual nucleus counting results was up to R2 = 0.901 (P < 0.001). By evaluating segmentation results of proposed method-based tool, we tested on a 2018 Data Science Bowl (DSB) competition dataset, three users obtained DSB score of 0.331 ± 0.006. AVAILABILITY AND IMPLEMENTATION: The proposed method has been implemented as a plugin tool in ImageJ and the source code can be freely downloaded. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Both endoplasmic reticulum and mitochondrial pathways are involved in oligodendrocyte apoptosis induced by capsular hemorrhage.

OBJECTIVE: The white matter injury caused by intracerebral hemorrhage (ICH) includes demyelination and axonal injury. Oligodendrocyte apoptosis is reported to be involved in triggering demyelination. Experimental observations indicate that both endoplasmic reticulum and mitochondrial pathways could mediate cell apoptosis. The purpose of this study was to investigate the demyelination and the possible mechanisms in an autologous blood-injected rat model of internal capsule hemorrhage. METHODS: Transmission electron microscope was applied to examine the pathological changes of myelinated nerve fibers in internal capsule. Western blotting was used to detect the myelin basic protein (MBP) which was an important component of myelin sheath. Double immunofluorescence and Western blotting were used to determine the apoptosis and apoptotic pathways. The levels of caspase-12 (a representative protein of endoplasmic reticulum stress) and cytochrome c (an apoptosis factor released from mitochondria) were assessed in this study. RESULTS: Demyelination occurred on day 1, 3, and 7 after ICH onset. Myelin sheaths of internal capsule nerve fibers were swollen and broken down in ICH groups. MBP expression showed a downregulation after ICH with its minimum value occurred on day 7 post-ICH. Besides, neuron and oligodendrocyte apoptosis were observed at different time intervals post-ICH accompanied with an upregulated caspase-12 expression and enhanced cytochrome c release. CONCLUSIONS: These results suggested that oligodendrocyte and neuron apoptosis may contribute to the demyelination induced by internal capsule hemorrhage and oligodendrocyte apoptosis is positively mediated through both endoplasmic reticulum and mitochondrial pathways.

Statistical colour models: an automated digital image analysis method for quantification of histological biomarkers.

BACKGROUND: Colour is the most important feature used in quantitative immunohistochemistry (IHC) image analysis; IHC is used to provide information relating to aetiology and to confirm malignancy. METHODS: Statistical modelling is a technique widely used for colour detection in computer vision. We have developed a statistical model of colour detection applicable to detection of stain colour in digital IHC images. Model was first trained by massive colour pixels collected semi-automatically. To speed up the training and detection processes, we removed luminance channel, Y channel of YCbCr colour space and chose 128 histogram bins which is the optimal number. A maximum likelihood classifier is used to classify pixels in digital slides into positively or negatively stained pixels automatically. The model-based tool was developed within ImageJ to quantify targets identified using IHC and histochemistry. RESULTS: The purpose of evaluation was to compare the computer model with human evaluation. Several large datasets were prepared and obtained from human oesophageal cancer, colon cancer and liver cirrhosis with different colour stains. Experimental results have demonstrated the model-based tool achieves more accurate results than colour deconvolution and CMYK model in the detection of brown colour, and is comparable to colour deconvolution in the detection of pink colour. We have also demostrated the proposed model has little inter-dataset variations. CONCLUSIONS: A robust and effective statistical model is introduced in this paper. The model-based interactive tool in ImageJ, which can create a visual representation of the statistical model and detect a specified colour automatically, is easy to use and available freely at http://rsb.info.nih.gov/ij/plugins/ihc-toolbox/index.html . Testing to the tool by different users showed only minor inter-observer variations in results.

Altered expression of long non-coding RNAs during genotoxic stress-induced cell death in human glioma cells.

Long non-coding RNAs (lncRNAs), a recently discovered class of non-coding genes, are transcribed throughout the genome. Emerging evidence suggests that lncRNAs may be involved in modulating various aspects of tumor biology, including regulating gene activity in response to external stimuli or DNA damage. No data are available regarding the expression of lncRNAs during genotoxic stress-induced apoptosis and/or necrosis in human glioma cells. In this study, we detected a change in the expression of specific candidate lncRNAs (neat1, GAS5, TUG1, BC200, Malat1, MEG3, MIR155HG, PAR5, and ST7OT1) during DNA damage-induced apoptosis in human glioma cell lines (U251 and U87) using doxorubicin (DOX) and resveratrol (RES). We also detected the expression pattern of these lncRNAs in human glioma cell lines under necrosis induced using an increased dose of DOX. Our results reveal that the lncRNA expression patterns are distinct between genotoxic stress-induced apoptosis and necrosis in human glioma cells. The sets of lncRNA expressed during genotoxic stress-induced apoptosis were DNA-damaging agent-specific. Generally, MEG3 and ST7OT1 are up-regulated in both cell lines under apoptosis induced using both agents. The induction of GAS5 is only clearly detected during DOX-induced apoptosis, whereas the up-regulation of neat1 and MIR155HG is only found during RES-induced apoptosis in both cell lines. However, TUG1, BC200 and MIR155HG are down regulated when necrosis is induced using a high dose of DOX in both cell lines. In conclusion, our findings suggest that the distinct regulation of lncRNAs may possibly involve in the process of cellular defense against genotoxic agents.

A Dataset and Model for the Visual Quality Assessment of Inversely Tone-Mapped HDR Videos.

To enhance the viewer experience of standard dynamic range (SDR) video content on high dynamic range (HDR) displays, inverse tone mapping (ITM) is employed. Objective visual quality assessment (VQA) models are needed for effective evaluation of ITM algorithms. However, there is a lack of specialized VQA models for assessing the visual quality of inversely tone-mapped HDR videos (ITM-HDR-Videos). This paper addresses both an algorithmic and a dataset gap by introducing a novel SDR referenced HDR (SD-R-HD) VQA model tailored for ITM-HDR-Videos, along with the first public dataset specifically constructed for this purpose. The innovations of the SD-R-HD VQA model include 1) utilizing available SDR video as a reference signal, 2) extracting features that characterize standard ITM operations such as global mapping and local compensation, and 3) directly modeling interframe inconsistencies introduced by ITM operations. The newly created ITM-HDR-VQA dataset comprises 200 ITM-HDR-Videos annotated with mean opinion scores, gathered over 320 man-hours of psychovisual experiments. Experimental results demonstrate that the SD-R-HD VQA model significantly outperforms existing state-of-the-art VQA models.

Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning.

Anomaly detection has wide applications in machine intelligence but is still a difficult unsolved problem. Major challenges include the rarity of labeled anomalies and it is a class highly imbalanced problem. Traditional unsupervised anomaly detectors are suboptimal while supervised models can easily make biased predictions towards normal data. In this paper, we present a new supervised anomaly detector through introducing the novel Ensemble Active Learning Generative Adversarial Network (EAL-GAN). EAL-GAN is a conditional GAN having a unique one generator versus multiple discriminators architecture where anomaly detection is implemented by an auxiliary classifier of the discriminator. In addition to using the conditional GAN to generate class balanced supplementary training data, an innovative ensemble learning loss function ensuring each discriminator makes up for the deficiencies of the others is designed to overcome the class imbalanced problem, and an active learning algorithm is introduced to significantly reduce the cost of labeling real-world data. We present extensive experimental results to demonstrate that the new anomaly detector consistently outperforms a variety of SOTA methods by significant margins.

Bumetanide Rescues Aquaporin-4 Depolarization via Suppressing ß-Dystroglycan Cleavage and Provides Neuroprotection in Rat Retinal Ischemia-Reperfusion Injury.

Aquaporin-4 (AQP4) regulates retinal water homeostasis and participates in retinal oedema pathophysiology. ß-dystroglycan (ß-DG) is responsible for AQP4 polarization and can be cleaved by matrix metalloproteinase-9 (MMP9). Retinal oedema induced by ischemia-reperfusion (I/R) injury is an early complication. Bumetanide (BU) has potential efficacy against cytotoxic oedema. Our study investigated the effects of ß-DG cleavage on AQP4 and the roles of BU in a rat retinal I/R injury model. The model was induced by applying 110 mm Hg intraocular pressure to the anterior eye chamber. BU and U0126 (a selective ERK inhibitor) were intraperitoneally administered 15 and 30 min, respectively, before I/R induction. Rhodamine isothiocyanate extravasation detection, quantitative real-time PCR, transmission electron microscopy, hematoxylin-eosin staining, immunofluorescence staining, western blotting, and TUNEL staining were performed. AQP4 lost its polarization in the retinal perivascular domain as a result of ß-DG cleavage. BU rescued AQP4 depolarization, suppressed AQP4 protein expression, attenuated retinal cytotoxic oedema, and downregulated ß-DG and AQP4 mRNA expression. BU suppressed glial responses and mitochondria-mediated apoptotic protein expression, including that of Caspase-3 and Cyto C, raised the Bcl-2/Bax ratio, and lowered the number of apoptotic cells in the retina. Both BU and U0126 downregulated p-ERK and MMP9 expression. Thus, BU treatment suppressed ß-DG cleavage, recovered AQP4 polarization partially via inhibiting ERK/MMP9 signaling pathway, and possess potential neuroprotective efficacy in the rat retinal ischemia-reperfusion injury model.

Perfusion preparation of the rat bladder decellularized scaffold.

Introduction: Bladder reconstruction is a huge challenge in the field of urology. In recent years, perfusion methods have brought promising results in the field of tissue engineering. We prepared bladder decellularized scaffolds by improved perfusion, which may be suitable for bladder reconstruction. Methods: We prepared decellularized scaffolds of rat bladder by perfusion of SDS (0.5% sodium dodecyl sulfate), SDS-SDC (0.5% sodium dodecyl sulfate +0.5% sodium deoxycholate). Histological characteristics of bladder decellularized scaffolds were assessed by Hematoxylin and eosin, Masson, and DAPI staining. Moreover, we also prepared a murine bladder transplantation model to evaluate the regenerative potential of scaffolds. Results: Hematoxylin and eosin, Masson, and DAPI staining indicated almost no cellular component residues in the SDS-SDC group. Histological analysis (hematoxylin and eosin staining, Masson staining), CD31 and F4/80 staining analysis, one month after implantation, revealed that the decellularized scaffolds had regenerative characteristics, and the SDS-SDC scaffold had better regenerative properties than the SDS scaffold. Conclusions: We successfully prepared the decellularized scaffold for the rat bladder by perfusion. Our results showed that the SDS-SDC scaffold had better decellularization efficiency and reconstruction ability than the SDS scaffold, which provides a new perspective on bladder reconstruction materials.

Class-Imbalanced Deep Learning via a Class-Balanced Ensemble.

Class imbalance is a prevalent phenomenon in various real-world applications and it presents significant challenges to model learning, including deep learning. In this work, we embed ensemble learning into the deep convolutional neural networks (CNNs) to tackle the class-imbalanced learning problem. An ensemble of auxiliary classifiers branching out from various hidden layers of a CNN is trained together with the CNN in an end-to-end manner. To that end, we designed a new loss function that can rectify the bias toward the majority classes by forcing the CNN's hidden layers and its associated auxiliary classifiers to focus on the samples that have been misclassified by previous layers, thus enabling subsequent layers to develop diverse behavior and fix the errors of previous layers in a batch-wise manner. A unique feature of the new method is that the ensemble of auxiliary classifiers can work together with the main CNN to form a more powerful combined classifier, or can be removed after finished training the CNN and thus only acting the role of assisting class imbalance learning of the CNN to enhance the neural network's capability in dealing with class-imbalanced data. Comprehensive experiments are conducted on four benchmark data sets of increasing complexity (CIFAR-10, CIFAR-100, iNaturalist, and CelebA) and the results demonstrate significant performance improvements over the state-of-the-art deep imbalance learning methods.

Towards Disentangling Latent Space for Unsupervised Semantic Face Editing.

Facial attributes in StyleGAN generated images are entangled in the latent space which makes it very difficult to independently control a specific attribute without affecting the others. Supervised attribute editing requires annotated training data which is difficult to obtain and limits the editable attributes to those with labels. Therefore, unsupervised attribute editing in an disentangled latent space is key to performing neat and versatile semantic face editing. In this paper, we present a new technique termed Structure-Texture Independent Architecture with Weight Decomposition and Orthogonal Regularization (STIA-WO) to disentangle the latent space for unsupervised semantic face editing. By applying STIA-WO to GAN, we have developed a StyleGAN termed STGAN-WO which performs weight decomposition through utilizing the style vector to construct a fully controllable weight matrix to regulate image synthesis, and employs orthogonal regularization to ensure each entry of the style vector only controls one independent feature matrix. To further disentangle the facial attributes, STGAN-WO introduces a structure-texture independent architecture which utilizes two independently and identically distributed (i.i.d.) latent vectors to control the synthesis of the texture and structure components in a disentangled way. Unsupervised semantic editing is achieved by moving the latent code in the coarse layers along its orthogonal directions to change texture related attributes or changing the latent code in the fine layers to manipulate structure related ones. We present experimental results which show that our new STGAN-WO can achieve better attribute editing than state of the art methods.

Hypotonic induction of aquaporin5 expression in rat astrocytes through p38 MAPK pathway.

Brain oedema is a common pathological phenomenon following many diseases and may lead to severe secondary damage. Astrocytes are the most numerous cells in the brain. Five aquaporins (AQPs) have been found in mature astrocytes, which play crucial roles in water transportation. However, most studies have focused on AQP4 or AQP9 and whether another aquaporin such as AQP5 involved in brain oedema is unclear. Here, we addressed the issue that the expression pattern of AQP5 in rat astrocytes in vitro was altered in the hypotonic condition through some mitogen-activated protein kinases (MAPK) pathways. Primary astrocytes were randomly divided into the control group and the hypotonic group. Cell viability was evaluated by MTT test. Immunofluorescence, Western blotting and real-time PCR were used to detect the expression of AQP5. Western blotting was used to detect the variation of MAPK pathway. The present study demonstrated that incubation of astrocytes in the hypotonic medium produced an increase inAQP5 expression, and AQP5 peaked at 6-12 h after hypotension solution exposure. In addition, MAPK pathways were set in motion under hypotension, but not all branches. Only the p38 inhibitor can inhibit AQP5 expression in cultured astrocytes. AQP5 is directly related to the extracellular hypotonic stimuli in astrocytes, which could be regulated through the p38 MAPK pathway.

Main Pathological Changes of Benign Ureteral Strictures.

Objective: To identify the pathological classification of benign ureteral strictures according to the histological features and explore the relationship between various pathological types and inflammatory cells, fibroblasts, and collagen. Patients and Methods: Thirty one specimens from patients diagnosed with ureteral strictures between 2013 and 2021 were included and classified according to the histopathological characteristics. The number of fibroblasts and inflammatory cells was counted, and the proportion of type I and type III collagen in ureteral stricture tissues was detected by picrosirius red staining. Results: We identified three types of benign ureteral strictures in 31 specimens: inflammatory cell infiltration (n = 10, 32%), fibroplasia (n = 14, 45%), and hyalinization (n = 7, 23%), with significant differences in obstruction history and hydronephrosis grades among the three types. The number of inflammatory cells (lymphocytes, neutrophils and eosinophils) was significantly lower in hyalinization ureteral strictures than in the other two types (p < 0.05). The number of foreign-body giant cells associated with foreign-body reactions increased significantly in suture-induced ureteral strictures (p < 0.05). Fibroplasia type had the largest number of fibroblasts, whereas the other two types had smaller numbers. The results of type I and III collagen analysis showed that type I and III collagen were the most abundant in hyalinization among all ureteral stricture types (p < 0.05). Compared to ureteral strictures, the content of type I and III collagen in atresia increased significantly (p < 0.05). Conclusion: Common pathological types of benign ureteral strictures include inflammatory cell infiltration, fibroplasia, and hyalinization. Changes in type I and III collagen, inflammatory cells, and fibroblasts in different pathological types may be related to the progression of ureteral strictures.

Iopromide and Iodixanol in the Development of Postoperative Contrast Nephropathy in Patients with Renal Insufficiency: A Meta-Analysis.

In order to compare the effects of iopromide and isoxazole on postoperative contrast-induced nephropathy in patients with renal insufficiency, the paper searches for randomized controlled trials and retrospective cohort studies comparing the effects of iopromide and iodixanol on renal function in patients with renal insufficiency after surgery. The data are extracted from eligible studies. We tried to assess the incidence of contrast-agent nephropathy, preoperative and postoperative serum creatinine indicators, and mortality. This paper includes 8 studies with a total of 1243 patients. The incidence of contrast-induced nephropathy in the iopromide group is higher than that in the iodixanol group, and there is no significant difference between the two groups in postoperative mortality and preoperative serum creatinine expression. Sensitivity analysis and funnel chart show that our research is robust and has low publication bias. Our research shows that in patients with renal insufficiency, the incidence of contrast-medium nephropathy in the iopromide group is higher than that in the iodixanol group. Iodixanol is safer and has less effect on patients' serum creatinine levels.

Neuroglobin expression and function in the temporal cortex of bilirubin encephalopathy rats.

Bilirubin encephalopathy (BE) is a neurological syndrome in newborns, mainly caused by neuronal injury due to excessive oxidative stress produced by unconjugated bilirubin (UCB). Neuroglobin (NGB) can protect the brain by removing oxidative stress species, but its expression and significance in BE are not clear. To address this question, the neonatal BE model was established by injecting UCB into the cerebellomedullary cistern of 7-day-old SD rats. Rats were divided into a sham and BE 6 hr group, BE 12 hr group, BE 24 hr group, and BE 7 d group according to UCB action times. Hematoxylin/eosin and Nissl staining, and electron microscopy were employed to observe the pathological and ultrastructural changes of nerve cells in each group. Immunofluorescence staining was used to detect NGB expression sites and cell types. Western blotting and quantitative PCR served to detect NGB expression and test the mitochondrial apoptosis signal pathway. The results confirm that UCB can lead to pathological damage and ultrastructural changes in rats' temporal cortex, increasing the expression of apoptosis-related proteins Bax, Bcl-2, Cyt c, Caspase-3, and neuronal NGB. UCB promotes NGB expression with an increase in action time and reach a peak at 12 hr. In summary, brain damage induced by UCB will cause an increase in NGB expression, the increasing NGB can inhibit neuron apoptosis in early BE phases. Therefore, promoting the expression of endogenous NGB, to act as a neuroprotective agent may be a potential treatment strategy for BE.

Silencing Akt1 enhances the resistance of prostate cancer cells to starvation and inhibits starvation-induced lung metastasis through epithelial-mesenchymal transition in prostate cancer.

Nutritional starvation (NST) is the basis of tumor anti-angiogenesis and metabolic therapy strategy. Silencing Akt1 inhibits prostate cancer (PCa) cells growing; slow-growing cells tend to consume less nutrition. It is suggested that Akt1-silenced cancer cells will have a more substantial tolerance to NST. Clarify this critical question is vital for tumor treatment strategies based on Akt1 and NST. The Akt1 gene of PC3 and DU145 cells was silenced by lent-virus. NST model was established by serum stripping. Cell viability was detected by MTT assay and cell counting method. Apoptosis was detected by TUNEL and flow cytometry, and cell invasion was determined by transwells and ECIS. The markers of epithelial-mesenchymal transition (EMT) were detected by western blotting. PCa lung metastasis model was established by tail vein injection and quantified by Indian ink and GFP fluorescence. Silencing Akt1 slowed down the decrease of cell number and increase of apoptosis caused by NST. Silencing Akt1 with NST exposure in PCa cells could down-regulate epithelial markers (E-cadherin, claudin-5, and ZO-1) and up-regulate mesenchymal markers N-cadherin and EMT regulators Snail. Although silencing Akt1 enhanced the invasion of PCa cells induced by NST in vitro, silencing Akt1 inhibited the PCa lung metastasis induced by NST in vivo. Silencing Akt1 gene enhances the resistance of PCa cells to NST. The invasion results in vitro were inconsistent with those metastases in vivo, which may be related to a combination of NST with silencing Akt1 to maintain the mesenchymal state of PCa cells through EMT.

Image Defogging Quality Assessment: Real-World Database and Method.

Fog removal from an image is an active research topic in computer vision. However, current literature is weak in the following two areas which in many ways are hindering progress for developing defogging algorithms. First, there is no true real-world and naturally occurring foggy image datasets suitable for developing defogging models. Second, there is no suitable mathematically simple and easy to use image quality assessment (IQA) methods for evaluating the visual quality of defogged images. We address these two aspects in this paper. We first introduce a new foggy image dataset called multiple real-world foggy image dataset (MRFID). MRFID contains foggy and clear images of 200 outdoor scenes. For each scene, one clear image and 4 foggy images of different densities defined as slightly foggy, moderately foggy, highly foggy, and extremely foggy, are manually selected from images taken from these scenes over the course of one calendar year. We then process the foggy images of MRFID using 16 defogging methods to obtain 12,800 defogged images (DFIs) and perform a comprehensive subjective evaluation of the visual quality of the DFIs. Through collecting the mean opinion score (MOS) of 120 subjects and evaluating a variety of fog-relevant image features, we have developed a new Fog-relevant Feature based SIMilarity index (FRFSIM) for assessing the visual quality of DFIs. We present extensive experimental results to show that our new visual quality assessment measure, the FRFSIM, is more consistent with the MOS than other IQA methods and is therefore more suitable for evaluating defogged images than other state-of-the-art IQA methods. Our dataset and relevant code are available at http://www.vistalab.ac.cn/MRFID-for-defogging/.

End-to-End Fovea Localisation in Colour Fundus Images With a Hierarchical Deep Regression Network.

Accurately locating the fovea is a prerequisite for developing computer aided diagnosis (CAD) of retinal diseases. In colour fundus images of the retina, the fovea is a fuzzy region lacking prominent visual features and this makes it difficult to directly locate the fovea. While traditional methods rely on explicitly extracting image features from the surrounding structures such as the optic disc and various vessels to infer the position of the fovea, deep learning based regression technique can implicitly model the relation between the fovea and other nearby anatomical structures to determine the location of the fovea in an end-to-end fashion. Although promising, using deep learning for fovea localisation also has many unsolved challenges. In this paper, we present a new end-to-end fovea localisation method based on a hierarchical coarse-to-fine deep regression neural network. The innovative features of the new method include a multi-scale feature fusion technique and a self-attention technique to exploit location, semantic, and contextual information in an integrated framework, a multi-field-of-view (multi-FOV) feature fusion technique for context-aware feature learning and a Gaussian-shift-cropping method for augmenting effective training data. We present extensive experimental results on two public databases and show that our new method achieved state-of-the-art performances. We also present a comprehensive ablation study and analysis to demonstrate the technical soundness and effectiveness of the overall framework and its various constituent components.

Changes in the prefrontal cortex after the hippocampus was injected with Aß25-35 via the P35/P25-CDK5-Tau hyperphosphorylation signaling pathway.

Alzheimer's disease (AD) is one of the common neurodegenerative illnesses in aging populations around the world. Recently, psychiatric symptoms are becoming increasingly important in recognizing the manifestations of AD in addition to cognitive impairment. Some studies suggest that the prefrontal cortex (PFC) is closely related to apathy/depression, and a network may exist between the CA1 of hippocampus and PFC. However, whether the injection of Aß2535 into hippocampi may result in PFC abnormalities in AD model rats is unclear. In this study, it was investigated the changes in the PFCs after the hippocampal injection via the P35/P25 - Cyclin-dependent kinase5 (CDK5) - Tau hyperphosphorylation signaling pathway. Our results demonstrated that rats injected with Aß25-35 showed decreased learning and memory ability, and increased depression-like behaviors compared with uninjected controls and saline-injected shams. P35/P25, CDK5, Tau[pS199], and Tau[pS202] are significantly elevated in the PFCs and hippocampi after Aß25-35 was injected into the hippocampi. Furthermore, P35/P25-CDK5 complexes were detected in vivo by immunofluorescence and co-immunoprecipitation. Therefore, the relative expression of proteins associated with the P35/P25-CDK5 pathway showed the same changes in the hippocampi and PFCs after Aß25-35 injection. These findings demonstrate a potential mechanism for prefrontal-mediated cognitive impairment and the psychiatric symptoms of AD.

Visual Saliency via Embedding Hierarchical Knowledge in a Deep Neural Network.

Deep neural networks (DNNs) have been extensively applied in image processing, including visual saliency map pre-diction of images. A major difficulty in using a DNN for visual saliency prediction is the lack of labeled ground truth of visual saliency. A powerful DNN usually contains a large number of trainable parameters. This condition can easily lead to model over-fitting. In this study, we develop a novel method that over-comes such difficulty by embedding hierarchical knowledge of existing visual saliency models in a DNN. We achieve the objective of exploiting the knowledge contained in the existing visual sali-ency models by using saliency maps generated by local, global, and semantic models to tune and fix about 92.5% of the parame-ters in our network in a hierarchical manner. As a result, the number of trainable parameters that need to be tuned by the ground truth is considerably reduced. This reduction enables us to fully utilize the power of a large DNN and overcome the issue of over-fitting at the same time. Furthermore, we introduce a simple but very effective center prior in designing the learning cost function of the DNN by attaching high importance to the errors around the image center. We also present extensive experimental results on four commonly used public databases to demonstrate the superiority of the proposed method over classical and state-of-the-art methods on various evaluation metrics.

Attention by Selection: A Deep Selective Attention Approach to Breast Cancer Classification.

Deep learning approaches are widely applied to histopathological image analysis due to the impressive levels of performance achieved. However, when dealing with high-resolution histopathological images, utilizing the original image as input to the deep learning model is computationally expensive, while resizing the original image to achieve low resolution incurs information loss. Some hard-attention based approaches have emerged to select possible lesion regions from images to avoid processing the original image. However, these hard-attention based approaches usually take a long time to converge with weak guidance, and valueless patches may be trained by the classifier. To overcome this problem, we propose a deep selective attention approach that aims to select valuable regions in the original images for classification. In our approach, a decision network is developed to decide where to crop and whether the cropped patch is necessary for classification. These selected patches are then trained by the classification network, which then provides feedback to the decision network to update its selection policy. With such a co-evolution training strategy, we show that our approach can achieve a fast convergence rate and high classification accuracy. Our approach is evaluated on a public breast cancer histopathological image database, where it demonstrates superior performance compared to state-of-the-art deep learning approaches, achieving approximately 98% classification accuracy while only taking 50% of the training time of the previous hard-attention approach.