Search

This paper attempts to estimate diagnostically relevant measure, i.e., Arteriovenous Ratio with an improved retinal vessel classification using feature ranking strategies and multiple classifiers decision-combination scheme. The features exploited for retinal vessel characterization are based on statistical measures of histogram, different filter responses of images and local gradient information. The feature selection process is based on two feature ranking approaches (Pearson Correlation Coefficient technique and Relief-F method) to rank the features followed by use of maximum classification accuracy of three supervised classifiers (k-Nearest Neighbor, Support Vector Machine and Naïve Bayes) as a threshold for feature subset selection. Retinal vessels are labeled using the selected feature subset and proposed hybrid classification scheme, i.e., decision fusion of multiple classifiers. The comparative analysis shows an increase in vessel classification accuracy as well as Arteriovenous Ratio calculation performance. The system is tested on three databases, a local dataset of 44 images and two publically available databases, INSPIRE-AVR containing 40 images and VICAVR containing 58 images. The local database also contains images with pathologically diseased structures. The performance of the proposed system is assessed by comparing the experimental results with the gold standard estimations as well as with the results of previous methodologies. Overall, an accuracy of 90.45%, 93.90% and 87.82% is achieved in retinal blood vessel separation with 0.0565, 0.0650 and 0.0849 mean error in Arteriovenous Ratio calculation for Local, INSPIRE-AVR and VICAVR dataset, respectively. [ABSTRACT FROM AUTHOR]

Unfavorable lighting conditions pose significant challenges to imaging devices. Use of multiple sensor fusion and false colorization has been demonstrated by many recent works. However, semi-automatic nature of these approaches make them less attractive. To address these shortcomings, we present a color night vision system, named FACE (Fully Automated Context Enhancement). It uses enhanced multi-spectral video fusion and fully automated color transform based color morphing to process multiple video streams captured by infrared (IR) and low light visible (VIS) sensors. At first, we introduce glare-suppressed inter-channel fusion in RGB color space to negate the ghost-like effect produced by IR channel. We then introduce color value imputation with deep KNN framework for joint classification of grayscale and color imagery. A suitable color transform is then sought to give a day-like color appearance to night vision imagery. Objective quality evaluation indicates the effectiveness of our framework for context enhancement at nighttime. [ABSTRACT FROM AUTHOR]

Neurological electrophysiology has revealed that both dopamine and stimulation tend to affect the formation of memory. This study aimed to investigate the regulatory effect of dopamine and stimulation on long-term and short-term memories using an integrated striatal dopamine and neuronal network model. The robustness of the model was verified by applying interference stimulation. The results showed that the duration of network firing response was associated with the value of dopamine and the duration of stimulation, and the network firing peak was not affected by the interference stimulation, suggesting that the model was strongly robust. [ABSTRACT FROM AUTHOR]

This work provides a performance comparison of four different machine learning classifiers: multinomial logistic regression with ridge estimators (MLR) classifier, k -nearest neighbours (KNN), support vector machine (SVM) and naïve Bayes (NB) as applied to terahertz (THz) transient time domain sequences associated with pixelated images of different powder samples. The six substances considered, although have similar optical properties, their complex insertion loss at the THz part of the spectrum is significantly different because of differences in both their frequency dependent THz extinction coefficient as well as differences in their refractive index and scattering properties. As scattering can be unquantifiable in many spectroscopic experiments, classification solely on differences in complex insertion loss can be inconclusive. The problem is addressed using two-dimensional (2-D) cross-correlations between background and sample interferograms, these ensure good noise suppression of the datasets and provide a range of statistical features that are subsequently used as inputs to the above classifiers. A cross-validation procedure is adopted to assess the performance of the classifiers. Firstly the measurements related to samples that had thicknesses of 2 mm were classified, then samples at thicknesses of 4 mm, and after that 3 mm were classified and the success rate and consistency of each classifier was recorded. In addition, mixtures having thicknesses of 2 and 4 mm as well as mixtures of 2, 3 and 4 mm were presented simultaneously to all classifiers. This approach provided further cross-validation of the classification consistency of each algorithm. The results confirm the superiority in classification accuracy and robustness of the MLR (least accuracy 88.24%) and KNN (least accuracy 90.19%) algorithms which consistently outperformed the SVM (least accuracy 74.51%) and NB (least accuracy 56.86%) classifiers for the same number of feature vectors across all studies. The work establishes a general methodology for assessing the performance of other hyperspectral dataset classifiers on the basis of 2-D cross-correlations in far-infrared spectroscopy or other parts of the electromagnetic spectrum. It also advances the wider proliferation of automated THz imaging systems across new application areas e.g., biomedical imaging, industrial processing and quality control where interpretation of hyperspectral images is still under development. [ABSTRACT FROM AUTHOR]

In this paper, we demonstrate a comprehensive method for segmenting the retinal vasculature in camera images of the fundus. This is of interest in the area of diagnostics for eye diseases that affect the blood vessels in the eye. In a departure from other state-of-the-art methods, vessels are first pre-grouped together with graph partitioning, using a spectral clustering technique based on morphological features. Local curvature is estimated over the whole image using eigenvalues of Hessian matrix in order to enhance the vessels, which appear as ridges in images of the retina. The result is combined with a binarized image, obtained using a threshold that maximizes entropy, to extract the retinal vessels from the background. Speckle type noise is reduced by applying a connectivity constraint on the extracted curvature based enhanced image. This constraint is varied over the image according to each region's predominant blood vessel size. The resultant image exhibits the central light reflex of retinal arteries and veins, which prevents the segmentation of whole vessels. To address this, the earlier entropy-based binarization technique is repeated on the original image, but crucially, with a different threshold to incorporate the central reflex vessels. The final segmentation is achieved by combining the segmented vessels with and without central light reflex. We carry out our approach on DRIVE and REVIEW, two publicly available collections of retinal images for research purposes. The obtained results are compared with state-of-the-art methods in the literature using metrics such as sensitivity (true positive rate), selectivity (false positive rate) and accuracy rates for the DRIVE images and measured vessel widths for the REVIEW images. Our approach out-performs the methods in the literature. [ABSTRACT FROM AUTHOR]

In previous research, a thiamine-auxotrophic yeast for alpha-ketoglutaric acid (KGA) overproduction was screened in our laboratory and named Yarrowia lipolytica WSH-Z06 (CCTCC no. M207143). However, the high concentration of by-products (mainly pyruvate) limited its application on an industrial scale. To enhance KGA production and reduce pyruvate (PA) accumulation, the pyruvate carboxylation pathway was regulated. By overexpressing the pyruvate carboxylase genes ScPYC1 from Saccharomyces cerevisiae and RoPYC2 from Rhizopus oryzae in Y. lipolytica WSH-Z06, the yields of KGA in Y. lipolytica-ScPYC1 and Y. lipolytica-RoPYC2 increased by 24.5 and 35.3 %, and the yields of PA decreased by 51.9 and 69.8 % in shake flasks, respectively. These changes in the expression levels and activities of key intracellular enzymes showed that enhancing the pyruvate carboxylation pathway had successfully redistributed the carbon flux from PA to KGA. Finally, by controlling the pH in a 3-L fermenter, the maximum concentration of KGA in Y. lipolytica-RoPYC2 reached 62.5 g L with an evident decrease in PA yield from 35.2 to 13.5 g L. [ABSTRACT FROM AUTHOR]

Abstract: α-Ketoglutarate (α-KG) is an important intermediate in the tricarboxylic acid (TCA) cycle and has an important role in the regulation of the balance between carbon and nitrogen metabolism in most microorganisms. In previous research, a thiamine-auxotrophic yeast for α-KG overproduction was screened and named as Yarrowia lipolytica WSH-Z06. To enhance α-KG production and reduce by-product (mainly pyruvate) accumulation, the cofactor metabolism was regulated to redistribute the carbon flux from pyruvate to α-KG. The acetyl-CoA synthetase gene, ACS1, from Saccharomyces cerevisiae and the ATP-citrate lyase gene, ACL, from Mus musculus were expressed to regulate the acetyl-CoA metabolism in Y. lipolytica WSH-Z06. The resultant strains were designated as Y. lipolytica-ACS1 and Y. lipolytica-ACL, respectively. Both of the ACS1 and ACL genes could increase the level of acetyl-CoA and enhance the α-KG production. In a 3-L jar fermenter, the highest yield of α-KG in Y. lipolytica-ACL reached up to 56.5gL−1 with an obvious decrease of pyruvate accumulation from 35.1gL−1 to 20.2gL−1. This study demonstrated that enhancing the acetyl-CoA availability could effectively increase the α-KG production in Y. lipolytica. [Copyright &y& Elsevier]

This paper presents an approach for automatic classification of pulsed Terahertz (THz), or T-ray, signals highlighting their potential in biomedical, pharmaceutical and security applications. T-ray classification systems supply a wealth of information about test samples and make possible the discrimination of heterogeneous layers within an object. In this paper, a novel technique involving the use of Auto Regressive (AR) and Auto Regressive Moving Average (ARMA) models on the wavelet transforms of measured T-ray pulse data is presented. Two example applications are examined — the classification of normal human bone (NHB) osteoblasts against human osteosarcoma (HOS) cells and the identification of six different powder samples. A variety of model types and orders are used to generate descriptive features for subsequent classification. Wavelet-based de-noising with soft threshold shrinkage is applied to the measured T-ray signals prior to modeling. For classification, a simple Mahalanobis distance classifier is used. After feature extraction, classification accuracy for cancerous and normal cell types is 93%, whereas for powders, it is 98%. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) has been a prevalence technique for breast cancer diagnosis. Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis. There are two main issues of the existing breast lesion segmentation techniques: requiring manual delineation of Regions of Interests (ROIs) as a step of initialization; and requiring a large amount of labeled images for model construction or parameter learning, while in real clinical or experimental settings, it is highly challenging to get sufficient labeled MRIs. To resolve these issues, this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies. After image segmentation with advanced cluster techniques, we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI. To obtain the optimal performance of tumor extraction, we take extensive experiments to learn parameters for tumor segmentation and classification, and design 225 classifiers corresponding to different parameter settings. We call the proposed method as Semi-supervised Tumor Segmentation (SSTS), and apply it to both mass and nonmass lesions. Experimental results show better performance of SSTS compared with five state-of-the-art methods. [ABSTRACT FROM AUTHOR]

PURPOSE: Neoadjuvant chemotherapy (NAC) has been widely used in patients with breast cancer to minish tumor burden and increase resection rate of cancer. T-cell repertoire has been believed to be able to monitor antitumor immune responses. This study aimed to explore the dynamic change of T-cell repertoire and its clinical value in evaluating the tumor response in patients with breast cancer receiving NAC. MATERIALS AND METHODS: Ninety-four patients who underwent NAC before surgery were recruited, and peripheral blood samples were collected at multiple time points during NAC. High-throughput T-cell receptor (TCR)-β sequencing was used to characterize the T-cell repertoire of every sample and analyzed the changes in circulating T-cell repertoire during NAC. RESULTS: We found that the diversity of TCR repertoires was associated with age and clinical stage of the patients with breast cancer. The distribution of Vβ and Jβ genes in TCR repertoires was skewed in patients with human epidermal growth factor receptor 2–positive (HER2+) breast cancer. Vβ20.1 and Vβ30 expression levels before NAC correlate with tumor response after all cycles of NAC in HER2– and HER2+ patients, respectively. Some CDR3 motifs that correlated with clinical response in either HER2+ or HER2– patients were identified. Besides, TCR repertoire evolved during NAC and the diversity of TCR repertoire decreased more after two cycles of NAC in patients with good tumor response after all cycles of NAC (P =.0061). CONCLUSION: Our results demonstrated that TCR repertoire correlated with the characteristics of the tumor, such as the expression status of HER2. Moreover, some characteristics of TCR repertoires that correlated with clinical response were identified and they might provide useful information to tailor therapeutic regimens at the early cycle of NAC. This study identified T-cell repertoires that correlated with clinical response in patients with breast cancer. [ABSTRACT FROM AUTHOR]

• Radiomic features can identify multiple actionable gene mutations in NSCLC. • Radiomic features predict PD-1/PD-L1 expression in NSCLC. • Integrating multi-regional information is crucial for understanding the molecular signature of NSCLC. • Non-invasive, comprehensive biomarkers hold promise for the longitudinal monitoring of therapeutic processes. • Radiographic phenotyping identifies NSCLC patients responsive to targeted or immunotherapy. Selecting therapeutic strategies for cancer patients is typically based on key target-molecule biomarkers that play an important role in cancer onset, progression, and prognosis. Thus, there is a pressing need for novel biomarkers that can be utilized longitudinally to guide treatment selection. Using data from 508 non-small cell lung cancer (NSCLC) patients across three institutions, we developed and validated a comprehensive predictive biomarker that distinguishes six genotypes and infiltrative immune phenotypes. These features were analyzed to establish the association between radiological phenotypes and tumor genotypes/immune phenotypes and to create a radiological interpretation of molecular features. In addition, we assessed the sensitivity of the models by evaluating their performance at five different voxel intervals, resulting in improved generalizability of the proposed approach. Findings: The radiomics model we developed, which integrates clinical factors and multi-regional features, outperformed the conventional model that only uses clinical and intratumoral features. Our combined model showed significant performance for EGFR, KRAS, ALK, TP53, PIK3CA, and ROS1 mutation status with AUCs of 0.866, 0.874, 0.902, 0.850, 0.860, and 0.900, respectively. Additionally, the predictive performance for PD-1/PD-L1 was 0.852. Although the performance of all models decreased to different degrees at five different voxel space resolutions, the performance advantage of the combined model did not change. We validated multiscale radiomic signatures across tumor genotypes and immunophenotypes in a multi-institutional cohort. This imaging-based biomarker offers a non-invasive approach to select patients with NSCLC who are sensitive to targeted therapies or immunotherapy, which is promising for developing personalized treatment strategies during therapy. [ABSTRACT FROM AUTHOR]

Radiomics and deep learning (DL) hold transformative promise and substantial and significant advances in oncology; however, most methods have been tested in retrospective or simulated settings. There is considerable interest in the biomarker validation, clinical utility, and methodological robustness of these studies and their deployment in real-world settings. This review summarizes the characteristics of studies, the level of prospective validation, and the overview of research on different clinical endpoints. The discussion of methodological robustness shows the potential for independent external replication of prospectively reported results. These in-depth analyses further describe the barriers limiting the translation of radiomics and DL into primary care options and provide specific recommendations regarding clinical deployment. Finally, we propose solutions for integrating novel approaches into the treatment environment to unravel the critical process of translating AI models into the clinical routine and explore strategies to improve personalized medicine. • Revisiting prospective clinical research of radiomics and deep learning in oncology. • Visual analysis of prospective validation levels and methodological robustness. • Propose clinical deployment endpoints based on application overview and challenges. • Build an implementation framework to integrate AI models into the clinical process. • Unveiling the translation of academic results in related fields to clinical routines. [ABSTRACT FROM AUTHOR]

Arrhythmia is a common class of Cardiovascular disease which is the cause for over 31% of all death over the world, according to WHOs' report. Automatic detection and classification of arrhythmia, as an effective tool of early warning, has recently been received more and more attention, especially in the applications of wearable devices for data capturing. However, different from traditional application scenarios, wearable electrocardiogram (ECG) devices have some drawbacks, such as being subject to multiple abnormal interferences, thus making accurate ventricular contraction (PVC) and supraventricular premature beat (SPB) detection to be more challenging. The traditional models for heartbeat classification suffer from the problem of large-scale parameters and the performance in dynamic ECG heartbeat classification is not satisfactory. In this paper, we propose a novel light model Lightweight Fussing Transformer to address these problems. We developed a more lightweight structure named LightConv Attention (LCA) to replace the self-attention of Fussing Transformer. LCA has reached remarkable performance level equal to or higher than self-attention with fewer parameters. In particular, we designed a stronger embedding structure (Convolutional Neural Network with attention mechanism) to enhance the weight of features of internal morphology of the heartbeat. Furthermore, we have implemented the proposed methods on real datasets and experimental results have demonstrated outstanding accuracy of detecting PVC and SPB. [ABSTRACT FROM AUTHOR]