A multi-task fusion model based on a residual-Multi-layer perceptron network for mammographic breast cancer screening.

BACKGROUND AND OBJECTIVE: Deep learning approaches are being increasingly applied for medical computer-aided diagnosis (CAD). However, these methods generally target only specific image-processing tasks, such as lesion segmentation or benign state prediction. For the breast cancer screening task, single feature extraction models are generally used, which directly extract only those potential features from the input mammogram that are relevant to the target task. This can lead to the neglect of other important morphological features of the lesion as well as other auxiliary information from the internal breast tissue. To obtain more comprehensive and objective diagnostic results, in this study, we developed a multi-task fusion model that combines multiple specific tasks for CAD of mammograms. METHODS: We first trained a set of separate, task-specific models, including a density classification model, a mass segmentation model, and a lesion benignity-malignancy classification model, and then developed a multi-task fusion model that incorporates all of the mammographic features from these different tasks to yield comprehensive and refined prediction results for breast cancer diagnosis. RESULTS: The experimental results showed that our proposed multi-task fusion model outperformed other related state-of-the-art models in both breast cancer screening tasks in the publicly available datasets CBIS-DDSM and INbreast, achieving a competitive screening performance with area-under-the-curve scores of 0.92 and 0.95, respectively. CONCLUSIONS: Our model not only allows an overall assessment of lesion types in mammography but also provides intermediate results related to radiological features and potential cancer risk factors, indicating its potential to offer comprehensive workflow support to radiologists.

Seizure prediction based on improved vision transformer model for EEG channel optimization.

Epileptic seizures are unpredictable events caused by abnormal discharges of a patient's brain cells. Extensive research has been conducted to develop seizure prediction algorithms based on long-term continuous electroencephalogram (EEG) signals. This paper describes a patient-specific seizure prediction method that can serve as a basis for the design of lightweight, wearable and effective seizure-prediction devices. We aim to achieve two objectives using this method. The first aim is to extract robust feature representations from multichannel EEG signals, and the second aim is to reduce the number of channels used for prediction by selecting an optimal set of channels from multichannel EEG signals while ensuring good prediction performance. We design a seizure-prediction algorithm based on a vision transformer (ViT) model. The algorithm selects channels that play a key role in seizure prediction from 22 channels of EEG signals. First, we perform a time-frequency analysis of processed time-series signals to obtain EEG spectrograms. We then segment the spectrograms of multiple channels into many non-overlapping patches of the same size, which are input into the channel selection layer of the proposed model, named Sel-JPM-ViT, enabling it to select channels. Application of the Sel-JPM-ViT model to the Boston Children's Hospital-Massachusetts Institute of Technology scalp EEG dataset yields results using only three to six channels of EEG signals that are slightly better that the results obtained using 22 channels of EEG signals. Overall, the Sel-JPM-ViT model exhibits an average classification accuracy of 93.65%, an average sensitivity of 94.70% and an average specificity of 92.78%.

Microstructure Formation and Characterization of Long-Acting Injectable Microspheres: The Gateway to Fully Controlled Drug Release Pattern.

Long-acting injectable microspheres have been on the market for more than three decades, but if calculated on the brand name, only 12 products have been approved by the FDA due to numerous challenges in achieving a fully controllable drug release pattern. Recently, more and more researches on the critical factors that determine the release kinetics of microspheres shifted from evaluating the typical physicochemical properties to exploring the microstructure. The microstructure of microspheres mainly includes the spatial distribution and the dispersed state of drug, PLGA and pores, which has been considered as one of the most important characteristics of microspheres, especially when comparative characterization of the microstructure (Q3) has been recommended by the FDA for the bioequivalence assessment. This review extracted the main variables affecting the microstructure formation from microsphere formulation compositions and preparation processes and highlighted the latest advances in microstructure characterization techniques. The further understanding of the microsphere microstructure has significant reference value for the development of long-acting injectable microspheres, particularly for the development of the generic microspheres.

Multi-view fusion-based local-global dynamic pyramid convolutional cross-tansformer network for density classification in mammography.

Object.Breast density is an important indicator of breast cancer risk. However, existing methods for breast density classification do not fully utilise the multi-view information produced by mammography and thus have limited classification accuracy.Method.In this paper, we propose a multi-view fusion network, denoted local-global dynamic pyramidal-convolution transformer network (LG-DPTNet), for breast density classification in mammography. First, for single-view feature extraction, we develop a dynamic pyramid convolutional network to enable the network to adaptively learn global and local features. Second, we address the problem exhibited by traditional multi-view fusion methods, this is based on a cross-transformer that integrates fine-grained information and global contextual information from different views and thereby provides accurate predictions for the network. Finally, we use an asymmetric focal loss function instead of traditional cross-entropy loss during network training to solve the problem of class imbalance in public datasets, thereby further improving the performance of the model.Results.We evaluated the effectiveness of our method on two publicly available mammography datasets, CBIS-DDSM and INbreast, and achieved areas under the curve (AUC) of 96.73% and 91.12%, respectively.Conclusion.Our experiments demonstrated that the devised fusion model can more effectively utilise the information contained in multiple views than existing models and exhibits classification performance that is superior to that of baseline and state-of-the-art methods.

Integral imaging reconstruction system based on the human eye viewing mechanism.

For integral stereo imaging systems based on lens arrays, the cross-mixing of erroneous light rays between adjacent lenses seriously affects the quality of the reconstructed light field. In this paper, we proposed a light field reconstruction method based on the human eye viewing mechanism, which incorporates simplified human eye imaging into the integral imaging system. First, the light field model for specified viewpoint is established, and the distribution of the light source for each viewpoint is accurately calculated for the EIA generation algorithm of fixed viewpoint. Second, according to the ray tracing algorithm in this paper, non-overlapping EIA based on the human eye viewing mechanism is designed to suppress the amount of crosstalk rays fundamentally. The actual viewing clarity is improved with the same reconstructed resolution. Experimental results verify the effectiveness of the proposed method. The SSIM value is higher than 0.93, which verifies that the viewing angle range is increased to 62°.

Predicting epileptic seizures based on EEG signals using spatial depth features of a 3D-2D hybrid CNN.

Epilepsy is a recurrent chronic brain disease that affects nearly 75 million people around the world. Therefore, the ability to reliably predict epileptic seizures would be instrumental for implementing interventions to reduce brain injury and improve patients' quality of life. In addition to classical machine learning algorithms and feature engineering methods, the use of electroencephalography (EEG) to predict seizures has gradually become a mainstream trend. Here, we propose a patient-specific method to predict epileptic seizures based on EEG data acquired using spatial depth features of a three-dimensional-two-dimensional hybrid convolutional neural network (3D-2D HyCNN) model. This method facilitates the acquisition of abundant and reliable deep features from multi-channel EEG signals. We first developed a reliable data preprocessing method to reconstruct time-series EEG signals into 3D feature images. Then, the 3D-2D HyCNN model was used to extract correlation features between multiple channels of EEG signals, which are automatically exploited by the network to improve seizure prediction. The method achieved accuracy of 98.43% and 93.11%, sensitivity of 98.58% and 90.98%, and specificity of 96.86% and 92.39% on the CHB-MIT Scalp EEG dataset and the American Epilepsy Society Epilepsy Prediction Challenge dataset, respectively. The results revealed that the new algorithm is reliable. Graphical Abstract A new patient-specific epilepsy prediction approach.

Anti-Toxoplasma gondii agent isolated from Orostachys malacophylla (Pallas) Fischer.

Botanical medicinal plants have aroused our interest to deal with Toxoplasmosis which can causes serious public health problems. Nipagic acid, gallic acid, ethyl gallate, phloretic acid, protocatechuic acid, methyl p-coumarate, arbutin, and homoprotocatechuic acid are first isolated from Orostachys malacophylla (Pallas) Fischer, their inhibition rate, survival rate, biochemical and viscera index are evaluated using gastric epithelia strain-1(GES-1). Among them, arbutin can effectively prolong the survival time of mice acutely infected with T. gondii, and exhibit the same curative effect as Spiramycin (Spi) group in terms of the glutathione (GSH) and malondialdehyde (MDA) content, alleviate hepatomegaly and splenomegaly. Structure-activity relationship (SAR) and molecular docking implies that phenolic hydroxyl group would be preferred for improvement of activity. In a summary, arbutin is a potential anti-T. gondii candidate for clinical application.

Heavy Metal Ions Trigger a Fluorescent Quenching in DNA-Organic Semiconductor Hybrid Assemblies.

The significance of DNA is no longer limited to its role as a biological information carrier; as a natural polymer, it also become in the field of materials. Single-stranded DNA (ssDNA) molecules with specific sequences can form a G-quadruplex or hairpin-shaped conformation with specific heavy metal ions through coordination bonds. In this study, ssDNA molecules of the four sequences were prepared into hybrid assemblies with one of the famous display materials, the tris-(8-hydroxyquinoline)aluminum (Alq3) semiconductor. Based on these hybrid assemblies, heavy metal ions, namely Pb2+, Hg2+, Cd2+ and As3+, were detected individually at the ppb level. Apart from this, in practical application, many samples containing heavy metal ions are digested with acid. By introducing MES buffer solution, the influence of acidity on the fluorescent signal of Alq3 was excluded. This strategy showed promising results in the practical application of detecting heavy metal ions in shrub branches and leaves.

DNA Methylation Profiles of the DRD2 and NR3C1 Genes in Patients with Recent-Onset Psychosis.

Objectives: Dopamine receptor D2 gene (DRD2) and glucocorticoid receptor gene (NR3C1) are implicated in the development of psychosis. We investigated methylation levels of DRD2 and NR3C1 in peripheral blood of patients with recent-onset (RO) psychosis using bisulfite pyrosequencing as well as its association with childhood trauma and rumination. Methods: In all, 51 individuals with RO psychosis and 47 healthy controls were recruited. DNA methylation levels in the targeted regions of two genes were analyzed and compared. Childhood trauma and rumination were evaluated using the Early Trauma Inventory Self-Report Short Form (ETI-SF) and Brooding Scale (BS), respectively. Correlations between the scores of the ETI-SF and BS and methylation levels were explored. Results: For DRD2, we found no significant differences between groups in terms of methylation level or association with childhood trauma or rumination. For NR3C1, we found a trend level significance for average value of all CpG sites and significant hypermethylation or hypomethylation at specific sites. There was also a significant positive correlation between the methylation level at the CpG8 site of NR3C1 exon 1F and negative symptom subscale score of the PANSS (PANSS-N). Conclusion: Epigenetic alterations of NR3C1 are associated with the pathophysiology of psychosis. Further epigenetic studies will elucidate the molecular mechanisms underpinning the pathophysiology of psychosis.

Methylome-wide Association Study of Patients with Recent-onset Psychosis.

Objective: Dysregulation of gene expression through epigenetic mechanisms may have a vital role in the pathogenesis of schizophrenia (SZ). In this study, we investigated the association of altered methylation patterns with SZ symptoms and early trauma in patients and healthy controls. Methods: The present study was conducted to identify methylation changes in CpG sites in peripheral blood associated with recent-onset (RO) psychosis using methylome-wide analysis. Lifestyle factors, such as smoking, alcohol, exercise, and diet, were controlled. Results: We identified 2,912 differentially methylated CpG sites in patients with RO psychosis compared to controls. Most of the genes associated with the top 20 differentially methylated sites had not been reported in previous methylation studies and were involved in apoptosis, autophagy, axonal growth, neuroinflammation, protein folding, etc. The top 15 significantly enriched Kyoto Encyclopedia of Genes and Genomes pathways included the oxytocin signaling pathway, long-term depression pathway, axon guidance, endometrial cancer, long-term potentiation, mitogen-activated protein kinase signaling pathway, and glutamatergic pathway, among others. In the patient group, significant associations of novel methylated genes with early trauma and psychopathology were observed. Conclusion: Our results suggest an association of differential DNA methylation with the pathophysiology of psychosis and early trauma. Blood DNA methylation signatures show promise as biomarkers of future psychosis.

Video Person Re-Identification with Frame Sampling-Random Erasure and Mutual Information-Temporal Weight Aggregation.

Partial occlusion and background clutter in camera video surveillance affect the accuracy of video-based person re-identification (re-ID). To address these problems, we propose a person re-ID method based on random erasure of frame sampling and temporal weight aggregation of mutual information of partial and global features. First, for the case in which the target person is interfered or partially occluded, the frame sampling-random erasure (FSE) method is used for data enhancement to effectively alleviate the occlusion problem, improve the generalization ability of the model, and match persons more accurately. Second, to further improve the re-ID accuracy of video-based persons and learn more discriminative feature representations, we use a ResNet-50 network to extract global and partial features and fuse these features to obtain frame-level features. In the time dimension, based on a mutual information-temporal weight aggregation (MI-TWA) module, the partial features are added according to different weights and the global features are added according to equal weights and connected to output sequence features. The proposed method is extensively experimented on three public video datasets, MARS, DukeMTMC-VideoReID, and PRID-2011; the mean average precision (mAP) values are 82.4%, 94.1%, and 95.3% and Rank-1 values are 86.4%, 94.8%, and 95.2%, respectively.

Development of the Korea-Polyenvironmental Risk Score for Psychosis.

OBJECTIVE: Comprehensive understanding of polyenvironmental risk factors for the development of psychosis is important. Based on a review of related evidence, we developed the Korea Polyenvironmental Risk Score (K-PERS) for psychosis. We investigated whether the K-PERS can differentiate patients with schizophrenia spectrum disorders (SSDs) from healthy controls (HCs). METHODS: We reviewed existing tools for measuring polyenvironmental risk factors for psychosis, including the Maudsley Environmental Risk Score (ERS), polyenviromic risk score (PERS), and Psychosis Polyrisk Score (PPS). Using odds ratios and relative risks for Western studies and the "population proportion" (PP) of risk factors for Korean data, we developed the K-PERS, and compared the scores thereon between patients with SSDs and HCs. In addition, correlation was performed between the K-PERS and Positive and Negative Syndrome Scale (PANSS). RESULTS: We first constructed the "K-PERS-I," comprising five factors based on the PPS, and then the "K-PERS-II" comprising six factors based on the ERS. The instruments accurately predicted participants' status (case vs. control). In addition, the K-PERS-I and -II scores exhibited significant negative correlations with the negative symptom factor score of the PANSS. CONCLUSION: The K-PERS is the first comprehensive tool developed based on PP data obtained from Korean studies that measures polyenvironmental risk factors for psychosis. Using pilot data, the K-PERS predicted patient status (SSD vs. HC). Further research is warranted to examine the relationship of K-PERS scores with clinical outcomes of psychosis and schizophrenia.

Comparison of clinical features and 1-year outcomes between patients with psychotic disorder not otherwise specified and those with schizophrenia.

AIM: Research on psychotic disorder not otherwise specified (PNOS) that clearly mentions its subgroups is very rare. This study was conducted to identify the demographic and clinical features, cognitive function, and 1-year outcomes of patients with early stage PNOS compared with those with early stage schizophrenia (SZ). METHODS: The study subjects were 54 and 321 patients with PNOS and SZ, respectively, who were registered at least more than 1 year ago. Due to drop out, only 37 and 210 patients with PNOS and SZ were evaluated at the 1-year follow-up. We compared clinical variables (duration of untreated psychosis, symptom severity, self-rating scales, and so on), cognitive function, and short-term outcomes (treatment response, remission, compliance, drop out, relapse) between the two groups. RESULTS: The patients with PNOS were associated with higher diagnostic stability (53.7%) compared with those in previous studies. They had lower symptom severity, better treatment response at 2 months and higher remission rates at 12 months, but poorer compliance at 6 months compared with patients with SZ. Level of cognitive impairment in PNOS was intermediate between those of SZ patients and healthy controls. CONCLUSIONS: These findings indicate that PNOS has unique clinical features, suggesting that it should be treated as a distinct clinical syndrome. At the same time, however, prevention of its possible progression to other psychotic disorders in some patients with PNOS is also important.

Deep Multi-Feature Transfer Network for Fourier Ptychographic Microscopy Imaging Reconstruction.

Fourier ptychographic microscopy (FPM) is a potential imaging technique, which is used to achieve wide field-of-view (FOV), high-resolution and quantitative phase information. The LED array is used to irradiate the samples from different angles to obtain the corresponding low-resolution intensity images. However, the performance of reconstruction still suffers from noise and image data redundancy, which needs to be considered. In this paper, we present a novel Fourier ptychographic microscopy imaging reconstruction method based on a deep multi-feature transfer network, which can achieve good anti-noise performance and realize high-resolution reconstruction with reduced image data. First, in this paper, the image features are deeply extracted through transfer learning ResNet50, Xception and DenseNet121 networks, and utilize the complementarity of deep multiple features and adopt cascaded feature fusion strategy for channel merging to improve the quality of image reconstruction; then the pre-upsampling is used to reconstruct the network to improve the texture details of the high-resolution reconstructed image. We validate the performance of the reported method via both simulation and experiment. The model has good robustness to noise and blurred images. Better reconstruction results are obtained under the conditions of short time and low resolution. We hope that the end-to-end mapping method of neural network can provide a neural-network perspective to solve the FPM reconstruction.

Symptomatic and full remission rates in first-episode psychosis: A 12-month follow-up study in Korea.

AIM: In the present study, the prevalence and predictors of symptomatic and full remission were investigated in patients with first-episode psychosis (FEP) at the 12-month follow-up. METHODS: A total of 308 participants aged 18-45 years fulfilled the study inclusion criteria and 214 completed the 12-month follow-up. RESULTS: At the 12-month follow-up, 67.3% (142) and 25.9% (55) of the FEP patients met the criteria for symptomatic and full remission, respectively. Stepwise logistic regression analysis showed a shorter duration of untreated psychosis (DUP), no family history, lower Positive and Negative Syndrome Scale (PANSS) negative symptom scores at baseline and higher familial support predicted symptomatic remission at the 12-month follow-up. A higher educational level, shorter DUP, lower PANSS general symptoms scores at baseline and higher subjective well-being under neuroleptics emotional regulation scores predicted full remission. CONCLUSIONS: Our findings regarding the rates of symptomatic and full remission are consistent with previous studies. The results indicate a large discrepancy between symptomatic versus full remission rates at a 12-month follow-up in patients with FEP. Effective psychosocial interventions are necessary to improve the outcomes of FEP patients.

Longitudinal symptom network structure in first-episode psychosis: a possible marker for remission.

BACKGROUND: Network approach has been applied to a wide variety of psychiatric disorders. The aim of the present study was to identify network structures of remitters and non-remitters in patients with first-episode psychosis (FEP) at baseline and the 6-month follow-up. METHODS: Participants (n = 252) from the Korean Early Psychosis Study (KEPS) were enrolled. They were classified as remitters or non-remitters using Andreasen's criteria. We estimated network structure with 10 symptoms (three symptoms from the Positive and Negative Syndrome Scale, one depressive symptom, and six symptoms related to schema and rumination) as nodes using a Gaussian graphical model. Global and local network metrics were compared within and between the networks over time. RESULTS: Global network metrics did not differ between the remitters and non-remitters at baseline or 6 months. However, the network structure and nodal strengths associated with positive-self and positive-others scores changed significantly in the remitters over time. Unique central symptoms for remitters and non-remitters were cognitive brooding and negative-self, respectively. The correlation stability coefficients for nodal strength were within the acceptable range. CONCLUSION: Our findings indicate that network structure and some nodal strengths were more flexible in remitters. Negative-self could be an important target for therapeutic intervention.

Dilated and soft attention-guided convolutional neural network for breast cancer histology images classification.

Breast cancer is one of the most common types of cancer in women, and histopathological imaging is considered the gold standard for its diagnosis. However, the great complexity of histopathological images and the considerable workload make this work extremely time-consuming, and the results may be affected by the subjectivity of the pathologist. Therefore, the development of an accurate, automated method for analysis of histopathological images is critical to this field. In this article, we propose a deep learning method guided by the attention mechanism for fast and effective classification of haematoxylin and eosin-stained breast biopsy images. First, this method takes advantage of DenseNet and uses the feature map's information. Second, we introduce dilated convolution to produce a larger receptive field. Finally, spatial attention and channel attention are used to guide the extraction of the most useful visual features. With the use of fivefold cross-validation, the best model obtained an accuracy of 96.47% on the BACH2018 dataset. We also evaluated our method on other datasets, and the experimental results demonstrated that our model has reliable performance. This study indicates that our histopathological image classifier with a soft attention-guided deep learning model for breast cancer shows significantly better results than the latest methods. It has great potential as an effective tool for automatic evaluation of digital histopathological microscopic images for computer-aided diagnosis.

Network analysis of trauma in patients with early-stage psychosis.

Childhood trauma (ChT) is a risk factor for psychosis. Negative lifestyle factors such as rumination, negative schemas, and poor diet and exercise are common in psychosis. The present study aimed to perform a network analysis of interactions between ChT and negative lifestyle in patients and controls. We used data of patients with early-stage psychosis (n = 500) and healthy controls (n = 202). Networks were constructed using 12 nodes from five scales: the Brief Core Schema Scale (BCSS), Brooding Scale (BS), Dietary Habits Questionnaire, Physical Activity Rating, and Early Trauma Inventory Self Report-Short Form (ETI). Graph metrics were calculated. The nodes with the highest predictability and expected influence in both patients and controls were cognitive and emotional components of the BS and emotional abuse of the ETI. The emotional abuse was a mediator in the shortest pathway connecting the ETI and negative lifestyle for both groups. The negative others and negative self of the BCSS mediated emotional abuse to other BCSS or BS for patients and controls, respectively. Our findings suggest that rumination and emotional abuse were central symptoms in both groups and that negative others and negative self played important mediating roles for patients and controls, respectively.Trial Registration: ClinicalTrials.gov identifier: CUH201411002.

Simplified digital content generation based on an inverse-directed propagation algorithm for holographic stereogram printing.

Holographic stereogram (HS) printing requires extensive memory capacity and long computation time during perspective acquisition and implementation of the pixel re-arrangement algorithm. Hogels contain very weak depth information of the object. We propose a HS printing system that uses simplified digital content generation based on the inverse-directed propagation (IDP) algorithm for hogel generation. Specifically, the IDP algorithm generates an array of hogels using a simple process that acquires the full three-dimensional (3D) information of the object, including parallax, depth, color, and shading, via a computer-generated integral imaging technique. This technique requires a short computation time and is capable of accounting for occlusion and accommodation effects of the object points via the IDP algorithm. Parallel computing is utilized to produce a high-resolution hologram based on the properties of independent hogels. To demonstrate the proposed approach, optical experiments are conducted in which the natural 3D visualizations of real and virtual objects are printed on holographic material. Experimental results demonstrate the simplified computation involved in content generation using the proposed IDP-based HS printing system and the improved image quality of the holograms.

Diffraction efficiency enhancement and optimization in full-color HOE using the inhibition characteristics of the photopolymer.

A novel and effective simultaneous recording method, to the best of our knowledge, is proposed for improving the diffraction efficiency and uniformity of full-color holographic optical elements (HOE) using the Bayfol HX102 photopolymer. To improve the diffraction efficiency of a full-color HOE, it is important to find the optimal recording beam intensity taking into account the initial and late responses of the medium. The range of optimal beam intensity for recording full-color HOE can be found experimentally by analyzing the inhibition period and response characteristics of the recording medium for three wavelengths. Through this method, a full-color HOE with an average diffraction efficiency of about 56.81% and a standard deviation of about 1.7% was implemented in a single layer photopolymer.