scholarly journals Classification of Monocytes, Promonocytes and Monoblasts Using Deep Neural Network Models: An Area of Unmet Need in Diagnostic Hematopathology

2021 ◽  
Vol 10 (11) ◽  
pp. 2264
Author(s):  
Mazen Osman ◽  
Zeynettin Akkus ◽  
Dragan Jevremovic ◽  
Phuong L. Nguyen ◽  
Dana Roh ◽  
...  
Keyword(s):  
Unmet Need ◽  
Network Models ◽  
Ground Truth ◽  
Monocytic Differentiation ◽  
Neural Network Models ◽  
Monocytic Cell ◽  
Monocytic Cells ◽  
Blast Cells ◽  
Single Category ◽  
Improved Accuracy

The accurate diagnosis of chronic myelomonocytic leukemia (CMML) and acute myeloid leukemia (AML) subtypes with monocytic differentiation relies on the proper identification and quantitation of blast cells and blast-equivalent cells, including promonocytes. This distinction can be quite challenging given the cytomorphologic and immunophenotypic similarities among the monocytic cell precursors. The aim of this study was to assess the performance of convolutional neural networks (CNN) in separating monocytes from their precursors (i.e., promonocytes and monoblasts). We collected digital images of 935 monocytic cells that were blindly reviewed by five experienced morphologists and assigned into three subtypes: monocyte, promonocyte, and blast. The consensus between reviewers was considered as a ground truth reference label for each cell. In order to assess the performance of CNN models, we divided our data into training (70%), validation (10%), and test (20%) datasets, as well as applied fivefold cross validation. The CNN models did not perform well for predicting three monocytic subtypes, but their performance was significantly improved for two subtypes (monocyte vs. promonocytes + blasts). Our findings (1) support the concept that morphologic distinction between monocytic cells of various differentiation level is difficult; (2) suggest that combining blasts and promonocytes into a single category is desirable for improved accuracy; and (3) show that CNN models can reach accuracy comparable to human reviewers (0.78 ± 0.10 vs. 0.86 ± 0.05). As far as we know, this is the first study to separate monocytes from their precursors using CNN.

Models of Artificial Multi-Polynomial Higher Order Neural Networks

2021 ◽  
pp. 97-136
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real World ◽  
Network Models ◽  
Higher Order ◽  
Neural Network Models ◽  
Real World Data ◽  
World Data ◽  
Higher Order Neural Networks ◽  
Improved Accuracy

This chapter introduces multi-polynomial higher order neural network models (MPHONN) with higher accuracy. Using Sun workstation, C++, and Motif, a MPHONN simulator has been built. Real-world data cannot always be modeled simply and simulated with high accuracy by a single polynomial function. Thus, ordinary higher order neural networks could fail to simulate complicated real-world data. But MPHONN model can simulate multi-polynomial functions and can produce results with improved accuracy through experiments. By using MPHONN for financial modeling and simulation, experimental results show that MPHONN can always have 0.5051% to 0.8661% more accuracy than ordinary higher order neural network models.

scholarly journals Computation of the electroencephalogram (EEG) from network models of point neurons

2020 ◽  
Author(s):  
Pablo Martínez-Cañada ◽  
Torbjørn V. Ness ◽  
Gaute T. Einevoll ◽  
Tommaso Fellin ◽  
Stefano Panzeri
Keyword(s):  
Neural Network ◽  
Brain Function ◽  
Network Models ◽  
Ground Truth ◽  
Recording Electrode ◽  
Neuron Network ◽  
Neural Network Models ◽  
Synaptic Currents ◽  
Wide Range ◽  
Electroencephalogram Eeg

AbstractThe electroencephalogram (EEG) is one of the main tools for non-invasively studying brain function and dysfunction. To better interpret EEGs in terms of neural mechanisms, it is important to compare experimentally recorded EEGs with the output of neural network models. Most current neural network models use networks of simple point neurons. They capture important properties of cortical dynamics, and are numerically or analytically tractable. However, point neuron networks cannot directly generate an EEG, since EEGs are generated by spatially separated transmembrane currents. Here, we explored how to compute an accurate approximation of the EEG with a combination of quantities defined in point-neuron network models. We constructed several different candidate approximations (or proxies) of the EEG that can be computed from networks of leaky integrate-and-fire (LIF) point neurons, such as firing rates, membrane potentials, and specific combinations of synaptic currents. We then evaluated how well each proxy reconstructed a realistic ground-truth EEG obtained when the synaptic input currents of the LIF network were fed into a three-dimensional (3D) network model of multi-compartmental neurons with realistic cell morphologies. We found that a new class of proxies, based on an optimized linear combination of time-shifted AMPA and GABA currents, provided the most accurate estimate of the EEG over a wide range of network states of the LIF point-neuron network. The new linear proxies explained most of the variance (85-95%) of the ground-truth EEG for a wide range of cell morphologies, distributions of presynaptic inputs, and position of the recording electrode. Non-linear proxies, obtained using a convolutional neural network (CNN) to predict the EEG from synaptic currents, increased proxy performance by a further 2-8%. Our proxies can be used to easily calculate a biologically realistic EEG signal directly from point-neuron simulations and thereby allow a quantitative comparison between computational models and experimental EEG recordings.Author summaryNetworks of point neurons are widely used to model neural dynamics. Their output, however, cannot be directly compared to the electroencephalogram (EEG), which is one of the most used tools to non-invasively measure brain activity. To allow a direct integration between neural network theory and empirical EEG data, here we derived a new mathematical expression, termed EEG proxy, which estimates with high accuracy the EEG based simply on the variables available from simulations of point-neuron network models. To compare and validate these EEG proxies, we computed a realistic ground-truth EEG produced by a network of simulated neurons with realistic 3D morphologies that receive the same spikes of the simpler network of point neurons. The new obtained EEG proxies outperformed previous approaches and worked well under a wide range of simulated configurations of cell morphologies, distribution of presynaptic inputs, and position of the recording electrode. The new proxies approximated well both EEG spectra and EEG evoked potentials. Our work provides important mathematical tools that allow a better interpretation of experimentally measured EEGs in terms of neural models of brain function.

Artificial Multi-Polynomial Higher Order Neural Network Models

2013 ◽  
pp. 1-29 ◽  
Author(s):  
Ming Zhang
Keyword(s):  
Neural Network ◽  
Real World ◽  
Network Models ◽  
Higher Order ◽  
Polynomial Functions ◽  
Neural Network Models ◽  
Real World Data ◽  
World Data ◽  
Higher Order Neural Networks ◽  
Improved Accuracy

This chapter introduces Multi-Polynomial Higher Order Neural Network (MPHONN) models with higher accuracy. Using Sun workstation, C++, and Motif, a MPHONN Simulator has been built. Real world data cannot always be modeled simply and simulated with high accuracy by a single polynomial function. Thus, ordinary higher order neural networks could fail to simulate complicated real world data. However, the MPHONN model can simulate multi-polynomial functions, and can produce results with improved accuracy through experiments. By using MPHONN for financial modeling and simulation, experimental results show that MPHONN can always have 0.5051% to 0.8661% more accuracy than ordinary higher order neural network models.

scholarly journals Altered Immunophenotypes on Leukemic and/or Monocytic Cells from Acute Myeloid Leukemia Highly Predict for Nucleophosmin Gene Mutation

Blood ◽  
2019 ◽  
Vol 134 (Supplement_1) ◽  
pp. 2687-2687
Author(s):  
Sergio Matarraz ◽  
Pilar Leoz ◽  
Xavier Calvo ◽  
Luis García Alonso ◽  
Rosa Ayala Bueno ◽  
...  
Keyword(s):  
Board Of Directors ◽  
Myeloid Leukemia ◽  
Research Funding ◽  
Blast Cell ◽  
Monocytic Differentiation ◽  
Advisory Committees ◽  
Monocytic Cells ◽  
Blast Cells ◽  
Cell Expression ◽  
Acute Myeloid

Introduction. Nucleophosmin gene mutation (NPM1mut) occurs in around 30% of acute myeloid leukemia (AML) patients, frequently linked with favourable prognosis in the absence of FLT3-ITDmut, which occurs in around 40% of NPM1mutAML. Therefore, more expeditious diagnostic approaches may contribute to early diagnosis and prognostic stratification of these patients. Herein, we investigated the association of immunophenotypic features of leukemic and monocytic cells with the presence of NPM1mut in AML. Methods. A total of 404 bone marrow (BM) samples from newly-diagnosed AML patients according to WHO 2017 classification were retrospectively studied by 8-color flow cytometry, including 225 AML with NPM1mut and 179 cases wild type gene (NPM1wt). Information on FLT3-ITD could be obtained from 397/404 cases. Thus, FLT3-ITDmut was present in 85/397 (21%), being concomitant with NPM1mutin 62/85 AML cases (73%). Logistic regression analysis was used to identify predictive phenotypes for the presence of NPM1mut. Results. Overall, blast cell with immunophenotypic features of monocytic differentiation (corresponding to FAB M4 and M5 AML subtypes) were observed among 135/225 (60%) and 69/179 (38.5%) AML patients with NPM1mutand NPM1wt, respectively (p<0.001). In the remaining AML cases without monocytic differentiation (FAB M0, M1 and M2; n=200), both immature/myeloid blasts and remaining monocytic cells were immunophenotypically characterized. Among AML with monocytic blast cell differentiation, altered monocytic phenotypes were more frequent among NPM1mut vs. NPM1wtcases (98% vs. 36%) (p<0.001). In detail, these phenotypic alterations consisted of asynchronous expression of CD300e prior CD14 (79% vs. 5% NPM1wtcases, respectively; p<0.001) and/or CD35 prior CD14 (84% vs. 30%), which were observed independently of FLT3-ITD. Of note, coexistence of the latter two asynchronous monocytic patterns (CD300e prior CD14 and CD35 prior CD14) on monocytic blast cells was specific for NPM1mut (64% vs. 0% NPM1wtpatients; p<0.001). Noteworthy, in AML cases without blast cell monocytic differentiation, remaining monocytic cells showed similar asynchronous phenotypic patterns, which were also more frequent among NPM1mut cases (78% vs. 23% of NPM1wtcases, respectively; p <0.001). Thus, remaining monocytic cells from NPM1mut AML cases also showed a higher frequency of asynchronous CD300e prior CD14 (64% vs. 8% of NPM1wt cases; p<0.001) and CD35 prior CD14 expression (58% vs. 20% of NPM1wt cases, respectively; p<0.001). In addition, aberrant CD9 blast cell expression was found in a significant proportion of all AML cases studied (124/222, 56%). However, altered CD9 was more frequent on (either monocytic or immature/myeloid) blast cells from AML cases with NPM1mut (76% vs. 46% NPM1wtcases; p<0.001), but not in AML with only-FLT3-ITDmut(39% vs. 46% of NPM1wtFLT3-ITDwt; p>0.05). In turn, aberrant CD25 expression on blast cells was otherwise linked to FLT3-ITDmut (61% vs. 20% of FLT3-ITDwtcases; p<0.001), being more frequent in AML with FLT3-ITDmutNPM1wt and double mutated AML cases vs. AML with FLT3-ITDwtNPM1mut and FLT3-ITDwtNPM1wt (79% and 47% vs. 20% and 20% of cases, respectively; p<0.001). In addition, overall, FLT3-ITDmut was associated with a significantly higher proportion of immature (i.e. CD34+) blasts, as compared to FLT3-ITDwt cases (median of 10% vs. 0.3% CD34+ blasts; p<0.001). In multivariate analysis, baseline detection of monocytic-lineage blast cells with asynchronous expression of CD300 prior CD14 -C-index= 0.954, odds ratio (OR), 78.8; 95% confidence interval (CI), 13.1-471; p<0.001- and CD35 prior CD14 (OR, 24.5; 95% CI, 4.8-123; p<0.001) and detection of these asynchronous patterns on remaining monocytic cells from AML without monocytic differentiation (C-index= 0.816, OR, 14.7; 95% CI, 6.4-34; p<0.001 and, OR, 2.5; 95% CI, 1.2-5.3; p=0.01, respectively) showed the highest predictive value for NPM1mut in AML. In turn, CD25 aberrant blast cell expression was the only immunophenotypic parameter with predictive value for FLT3-ITDmut (OR, 6.4; 95% CI, 2.9-14.5; p<0.001). Conclusions. Detection of specific aberrant immunophenotypic patterns among blast cells and/or remaining monocytic cells from AML patients is highly predictive for NPM1mut, which may contribute to early diagnosis and follow-up of these patients. Disclosures Díez-Campelo: Celgene Corporation: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Novartis: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding.

scholarly journals Computation of the electroencephalogram (EEG) from network models of point neurons

2021 ◽  
Vol 17 (4) ◽  
pp. e1008893
Author(s):  
Pablo Martínez-Cañada ◽  
Torbjørn V. Ness ◽  
Gaute T. Einevoll ◽  
Tommaso Fellin ◽  
Stefano Panzeri
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Ground Truth ◽  
Membrane Potentials ◽  
Eeg Signal ◽  
Neural Network Models ◽  
Synaptic Currents ◽  
Firing Rates ◽  
Wide Range ◽  
Electroencephalogram Eeg

The electroencephalogram (EEG) is a major tool for non-invasively studying brain function and dysfunction. Comparing experimentally recorded EEGs with neural network models is important to better interpret EEGs in terms of neural mechanisms. Most current neural network models use networks of simple point neurons. They capture important properties of cortical dynamics, and are numerically or analytically tractable. However, point neurons cannot generate an EEG, as EEG generation requires spatially separated transmembrane currents. Here, we explored how to compute an accurate approximation of a rodent’s EEG with quantities defined in point-neuron network models. We constructed different approximations (or proxies) of the EEG signal that can be computed from networks of leaky integrate-and-fire (LIF) point neurons, such as firing rates, membrane potentials, and combinations of synaptic currents. We then evaluated how well each proxy reconstructed a ground-truth EEG obtained when the synaptic currents of the LIF model network were fed into a three-dimensional network model of multicompartmental neurons with realistic morphologies. Proxies based on linear combinations of AMPA and GABA currents performed better than proxies based on firing rates or membrane potentials. A new class of proxies, based on an optimized linear combination of time-shifted AMPA and GABA currents, provided the most accurate estimate of the EEG over a wide range of network states. The new linear proxies explained 85–95% of the variance of the ground-truth EEG for a wide range of network configurations including different cell morphologies, distributions of presynaptic inputs, positions of the recording electrode, and spatial extensions of the network. Non-linear EEG proxies using a convolutional neural network (CNN) on synaptic currents increased proxy performance by a further 2–8%. Our proxies can be used to easily calculate a biologically realistic EEG signal directly from point-neuron simulations thus facilitating a quantitative comparison between computational models and experimental EEG recordings.

scholarly journals Time Classification Algorithm Based on Windowed-Color Histogram Matching

2021 ◽  
Vol 11 (24) ◽  
pp. 11997
Author(s):  
Hye-Jin Park ◽  
Jung-In Jang ◽  
Byung-Gyu Kim
Keyword(s):  
Web Search ◽  
Search Time ◽  
Network Models ◽  
Ground Truth ◽  
Color Histogram ◽  
Neural Network Models ◽  
Search System ◽  
User Interests ◽  
Time Period ◽  
Color Histograms

A web-based search system recommends and gives results such as customized image or video contents using information such as user interests, search time, and place. Time information extracted from images can be used as a important metadata in the web search system. We present an efficient algorithm to classify time period into day, dawn, and night when the input is a single image with a sky region. We employ the Mask R-CNN to extract a sky region. Based on the extracted sky region, reference color histograms are generated, which can be considered as the ground-truth. To compare the histograms effectively, we design the windowed-color histograms (for RGB bands) to compare each time period from the sky region of the reference data with one of the input images. Also, we use a weighting approach to reflect a more separable feature on the windowed-color histogram. With the proposed windowed-color histogram, we verify about 91% of the recognition accuracy in the test data. Compared with the existing deep neural network models, we verify that the proposed algorithm achieves better performance in the test dataset.

Method of complex copper-zinc ore typification using neural network models

2020 ◽  
Vol 5 ◽  
pp. 140-147 ◽  
Author(s):  
T.N. Aleksandrova ◽  
◽  
E.K. Ushakov ◽  
A.V. Orlova ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Neural Network Models ◽  
Copper Zinc ◽  
Complex Copper

Digital twin of equipment as a basis for the consumer in digital production

2020 ◽  
Keyword(s):  
Neural Network ◽  
Tool Wear ◽  
Chip Formation ◽  
Network Models ◽  
Machining Accuracy ◽  
Neural Network Models ◽  
Digital Twin ◽  
The Neural Network ◽  
Digital Production ◽  
Cyberphysical System

The neural network models series used in the development of an aggregated digital twin of equipment as a cyber-physical system are presented. The twins of machining accuracy, chip formation and tool wear are examined in detail. On their basis, systems for stabilization of the chip formation process during cutting and diagnose of the cutting too wear are developed. Keywords cyberphysical system; neural network model of equipment; big data, digital twin of the chip formation; digital twin of the tool wear; digital twin of nanostructured coating choice

Measuring the World

2018 ◽  
Author(s):  
Ann-Sophie Barwich
Keyword(s):  
Sensory Information ◽  
Network Models ◽  
Model System ◽  
Stimulus Input ◽  
Expectancy Effects ◽  
Neural Network Models ◽  
Perceptual Object ◽  
External Objects ◽  
The Common ◽  
The Brain

How much does stimulus input shape perception? The common-sense view is that our perceptions are representations of objects and their features and that the stimulus structures the perceptual object. The problem for this view concerns perceptual biases as responsible for distortions and the subjectivity of perceptual experience. These biases are increasingly studied as constitutive factors of brain processes in recent neuroscience. In neural network models the brain is said to cope with the plethora of sensory information by predicting stimulus regularities on the basis of previous experiences. Drawing on this development, this chapter analyses perceptions as processes. Looking at olfaction as a model system, it argues for the need to abandon a stimulus-centred perspective, where smells are thought of as stable percepts, computationally linked to external objects such as odorous molecules. Perception here is presented as a measure of changing signal ratios in an environment informed by expectancy effects from top-down processes.

Sign in / Sign up

Export Citation Format

Share Document