Degnbak1335

Spreadsheet-based tools provide a simple yet effective way of calculating values, which makes them the number-one choice for building and formalizing simple models for budget planning and many other applications. A cell in a spreadsheet holds one specific value and gives a discrete, overprecise view of the underlying model. Therefore, spreadsheets are of limited use when investigating the inherent uncertainties of such models and answering what-if questions. Existing extensions typically require a complex modeling process that cannot easily be embedded in a tabular layout. In Fuzzy Spreadsheet, a cell can hold and display a distribution of values. This integrated uncertainty-handling immediately conveys sensitivity and robustness information. The fuzzification of the cells enables calculations not only with precise values but also with distributions, and probabilities. We conservatively added and carefully crafted visuals to maintain the look and feel of a traditional spreadsheet while facilitating what-if analyses. Given a user-specified reference cell, Fuzzy Spreadsheet automatically extracts and visualizes contextually relevant information, such as impact, uncertainty, and degree of neighborhood, for the selected and related cells. To evaluate its usability and the perceived mental effort required, we conducted a user study. The results show that our approach outperforms traditional spreadsheets in terms of answer correctness, response time, and perceived mental effort in almost all tasks tested.Given a target grayscale image and a reference color image, exemplar-based image colorization aims to generate a visually natural-looking color image by transforming meaningful color information from the reference image to the target image. It remains a challenging problem due to the differences in semantic content between the target image and the reference image. In this paper, we present a novel globally and locally semantic colorization method called exemplar-based conditional broad-GAN, a broad generative adversarial network (GAN) framework, to deal with this limitation. Our colorization framework is composed of two sub-networks the match sub-net and the colorization sub-net. We reconstruct the target image with a dictionary-based sparse representation in the match sub-net, where the dictionary consists of features extracted from the reference image. To enforce global-semantic and local-structure self-similarity constraints, global-local affinity energy is explored to constrain the sparse representation for matching consistency. Then, the matching information of the match sub-net is fed into the colorization sub-net as the perceptual information of the conditional broad-GAN to facilitate the personalized results. Finally, inspired by the observation that a broad learning system is able to extract semantic features efficiently, we further introduce a broad learning system into the conditional GAN and propose a novel loss, which substantially improves the training stability and the semantic similarity between the target image and the ground truth. Extensive experiments have shown that our colorization approach outperforms the state-of-the-art methods, both perceptually and semantically.Although accurate detection of breast cancer still poses significant challenges, deep learning (DL) can support more accurate image interpretation. In this study, we develop a highly robust DL model that is based on combined B-mode ultrasound (B-mode) and strain elastography ultrasound (SE) images for classifying benign and malignant breast tumors. This study retrospectively included 85 patients, including 42 with benign lesions and 43 with malignancies, all confirmed by biopsy. Two deep neural network models, AlexNet and ResNet, were separately trained on combined 205 B-mode and 205 SE images (80% for training and 20% for validation) from 67 patients with benign and malignant lesions. These two models were then configured to work as an ensemble using both image-wise and layer-wise and tested on a dataset of 56 images from the remaining 18 patients. The ensemble model captures the diverse features present in the B-mode and SE images and also combines semantic features from AlexNet & ResNet models to classify the benign from the malignant tumors. The experimental results demonstrate that the accuracy of the proposed ensemble model is 90%, which is better than the individual models and the model trained using B-mode or SE images alone. Moreover, some patients that were misclassified by the traditional methods were correctly classified by the proposed ensemble method. The proposed ensemble DL model will enable radiologists to achieve superior detection efficiency owing to enhance classification accuracy for breast cancers in US images.Multimodal learning usually requires a complete set of modalities during inference to maintain performance. Although training data can be well-prepared with high-quality multiple modalities, in many cases of clinical practice, only one modality can be acquired and important clinical evaluations have to be made based on the limited single modality information. In this work, we propose a privileged knowledge learning framework with the 'Teacher-Student' architecture, in which the complete multimodal knowledge that is only available in the training data (called privileged information) is transferred from a multimodal teacher network to a unimodal student network, via both a pixel-level and an image-level distillation scheme. Specifically, for the pixel-level distillation, we introduce a regularized knowledge distillation loss which encourages the student to mimic the teacher's softened outputs in a pixel-wise manner and incorporates a regularization factor to reduce the effect of incorrect predictions from the teacher. For the image-level distillation, we propose a contrastive knowledge distillation loss which encodes image-level structured information to enrich the knowledge encoding in combination with the pixel-level distillation. We extensively evaluate our method on two different multi-class segmentation tasks, i.e., cardiac substructure segmentation and brain tumor segmentation. Experimental results on both tasks demonstrate that our privileged knowledge learning is effective in improving unimodal segmentation and outperforms previous methods.

Super-resolution ultrasound localization microscopy (ULM) has unprecedented vascular resolution at clinically relevant imaging penetration depths. This technology can potentially screen for the transient microvascular changes that are thought to be critical to the synergistic effect(s) of combined chemotherapy-antiangiogenic agent regimens for cancer.

In this paper, we apply this technology to a high-throughput colorectal carcinoma xenograft model treated with either the antiangiogenic agent sorafenib, FOLFOX-6 chemotherapy, a combination of the two treatments, or vehicle control.

Longitudinal ULM demonstrated morphological changes in the antiangiogenic treated cohorts, and evidence of vascular disruption caused by chemotherapy. Gold-standard histological measurements revealed reduced levels of hypoxia in the sorafenib treated cohort for both of the human cell lines tested (HCT-116 and HT-29). Therapy resistance was associated with an increase in tumor vascular fractal dimension as measured by a box-counting technique on ULM images.

These results imply that the morphological changes evident on ULM signify a functional change in the tumor microvasculature, which may be indicative of chemo-sensitivity.

ULM provides additional utility for tumor therapy response evaluation by offering a myriad of morphological and functional quantitative indices for gauging treatment effect(s).

ULM provides additional utility for tumor therapy response evaluation by offering a myriad of morphological and functional quantitative indices for gauging treatment effect(s).

Fractional Flow Reserve (FFR) is regarded as a fundamental index to assess pulmonary artery stenosis. The application of FFR can increase the accuracy of detection of pulmonary artery stenosis. However, the invasive examination may carry a number of physiological risks for patients. Therefore, we propose a personalized pulmonary circulation model to non- invasively calculate FFR of pulmonary artery stenosis. Method- ology We employed a personalized pulmonary circulation model to non-invasively calculate FFR using only computed tomography angiogram (CTA) data. This model combined boundary conditions estimation and 3D pulmonary artery morphology reconstruction for CFD simulation. First, we obtained patient-specific boundary conditions by adapting the right ventricle stroke volume and main pulmonary artery pressure feature points (systolic, diastolic, and mean pressure). Secondly, the 3D pulmonary artery morphology was reconstructed by threshold segmentation. The CFD simulation was then performed to obtain pressure distribution in the entire pulmonary artery. Finally, the FFR in pulmonary artery stenoses was calculated as the ratio of distal pressure and proximal pres- sure.

To validate our model, we compared the calculated FFR with measured FFR by pressure guide wires examination of 8 patients. The FFR calculated by our model showed a good agreement with measured FFR by pressure guide wires exami- nation. The average accuracy rate was 91.41%.

The proposed personalized pulmonary model is capable of reasonably non-invasively calculating FFR with sufficient accuracy.

FFR calculated in our model may contribute to non-invasive detection of pulmonary artery stenosis and to the assessment of invasive interventions.

FFR calculated in our model may contribute to non-invasive detection of pulmonary artery stenosis and to the assessment of invasive interventions.Through this study, we established the taxonomic status of seven strains belonging to the genus Pectobacterium (A477-S1-J17T, A398-S21-F17, A535-S3-A17, A411-S4-F17, A113-S21-F16, FL63-S17 and FL60-S17) collected from four different river streams and an artificial lake in south-east France between 2016 and 2017. Ecological surveys in rivers and lakes pointed out different repartition of strains belonging to this clade compared to the closest species, Pectobacterium aquaticum. The main phenotypic difference observed between these strains and the P. aquaticum type strain was strongly impaired growth with rhamnose as the sole carbon source. This correlates with three different forms of pseudogenization of the l-rhamnose/proton symporter gene rhaT in the genomes of strains belonging to this clade. Phylogenetic analysis using gapA gene sequences and multi locus sequence analysis of the core genome showed that these strains formed a distinct clade within the genus Pectobacterium closely related to P. aquaticum. Digital DNA-DNA hybridization (dDDH) and average nucleotide identity (ANI) values showed a clear discontinuity between the new clade and P. aquaticum. However, the calculated values are potentially consistent with either splitting or merging of this new clade with P. aquaticum. In support of the split, ANI coverages were higher within this new clade than between this new clade and P. aquaticum. selleckchem The split is also consistent with the range of observed ANI or dDDH values that currently separate several accepted species within the genus Pectobacterium. On the basis of these data,strains A477-S1-J17T, A398-S21-F17, A535-S3-A17, A411-S4-F17, A113-S21-F16, FL63-S17 and FL60-S17 represent a novel species of the genus Pectobacterium, for which the name Pectobacterium quasiaquaticum sp. nov. is proposed. The type strain is A477-S1-J17T (=CFBP 8805T=LMG 32181T).