Quantitative Structure-Property Relationship on Prediction of Surface Tension of Nonionic Surfactants

A quantitative structure-property relationship (QSPR) study has been made for the prediction of the surface tension of nonionic surfactants in aqueous solution. The regressed model includes a topological descriptor, the Kier & Hall index of zero order (KH0) of the hydrophobic segment of surfactant and a quantum chemical one, the heat of formation (fHD) of surfactant molecules. The established general QSPR between the surface tension and the descriptors produces a correlation coefficient of multiple determination, 2r=0.9877, for 30 studied nonionic surfactants.

Estimation of surface tension of organic compounds using quantitative structure-property relationship

A novel quantitative structure-property relationship(QSPR) model for estimating the solution surface tension of 92 organic compounds at 20 °C was developed based on newly introduced atom-type topological indices.The data set contained non-polar and polar liquids,and saturated and unsaturated compounds.The regression analysis shows that excellent result is obtained with multiple linear regression.The predictive power of the proposed model was discussed using the leave-one-out(LOO) cross-validated(CV) method.The correlation coefficient(R) and the leave-one-out cross-validation correlation coefficient(RCV) of multiple linear regression model are 0.991 4 and 0.991 3,respectively.The new model gives the average absolute relative deviation of 1.81% for 92 substances.The result demonstrates that novel topological indices based on the equilibrium electro-negativity of atom and the relative bond length are useful model parameters for QSPR analysis of compounds.

Accurate method based on data filtering for quantitative multi-element analysis of soils using CF-LIBS

To obtain more stable spectral data for accurate quantitative analysis of multi-element,especially for the large-area in-situ elements detection of soils, we propose a method for a multielement quantitative analysis of soils using calibration-free laser-induced breakdown spectroscopy(CF-LIBS) based on data filtering. In this study, we analyze a standard soil sample doped with two heavy metal elements, Cu and Cd, with a specific focus on the line of Cu I324.75 nm for filtering the experimental data of multiple sample sets. Pre-and post-data filtering,the relative standard deviation for Cu decreased from 30% to 10%, The limits of detection(LOD)values for Cu and Cd decreased by 5% and 4%, respectively. Through CF-LIBS, a quantitative analysis was conducted to determine the relative content of elements in soils. Using Cu as a reference, the concentration of Cd was accurately calculated. The results show that post-data filtering, the average relative error of the Cd decreases from 11% to 5%, indicating the effectiveness of data filtering in improving the accuracy of quantitative analysis. Moreover, the content of Si, Fe and other elements can be accurately calculated using this method. To further correct the calculation, the results for Cd was used to provide a more precise calculation. This approach is of great importance for the large-area in-situ heavy metals and trace elements detection in soil, as well as for rapid and accurate quantitative analysis.

Study on Quantitative Precipitation Estimation by Polarimetric Radar Using Deep Learning

Accurate radar quantitative precipitation estimation(QPE)plays an essential role in disaster prevention and mitigation.In this paper,two deep learning-based QPE networks including a single-parameter network and a multi-parameter network are designed.Meanwhile,a self-defined loss function(SLF)is proposed during modeling.The dataset includes Shijiazhuang S-band dual polarimetric radar(CINRAD/SAD)data and rain gauge data within the radar’s 100-km detection range during the flood season of 2021 in North China.Considering that the specific propagation phase shift(KDP)has a roughly linear relationship with the precipitation intensity,KDP is set to 0.5°km^(-1 )as a threshold value to divide all the rain data(AR)into a heavy rain(HR)and light rain(LR)dataset.Subsequently,12 deep learning-based QPE models are trained according to the input radar parameters,the precipitation datasets,and whether an SLF was adopted,respectively.The results suggest that the effects of QPE after distinguishing rainfall intensity are better than those without distinguishing,and the effects of using SLF are better than those that used MSE as a loss function.A Z-R relationship and a ZH-KDP-R synthesis method are compared with deep learning-based QPE.The mean relative errors(MRE)of AR models using SLF are improved by 61.90%,51.21%,and 56.34%compared with the Z-R relational method,and by 38.63%,42.55%,and 47.49%compared with the synthesis method.Finally,the models are further evaluated in three precipitation processes,which manifest that the deep learning-based models have significant advantages over the traditional empirical formula methods.

Simplified quantitative analysis method and its application in the insitu synthesized copper-based azide chips

Copper-based azide(Cu(N_(3))2 or CuN_(3),CA)chips synthesized by in-situ azide reaction and utilized in miniaturized explosive systems has become a hot research topic in recent years.However,the advantages of in-situ synthesis method,including small size and low dosage,bring about difficulties in quantitative analysis and differences in ignition capabilities of CA chips.The aim of present work is to develop a simplified quantitative analysis method for accurate and safe analysis of components in CA chips to evaluate and investigate the corresponding ignition ability.In this work,Cu(N_(3))2 and CuN_(3)components in CA chips were separated through dissolution and distillation by utilizing the difference in solubility and corresponding content was obtained by measuring N_(3)-concentration through spectrophotometry.The spectrophotometry method was optimized by studying influencing factors and the recovery rate of different separation methods was studied,ensuring the accuracy and reproducibility of test results.The optimized method is linear in range from 1.0-25.0 mg/L,with a correlation coefficient R^(2)=0.9998,which meets the requirements of CA chips with a milligram-level content test.Compared with the existing ICP method,component analysis results of CA chips obtained by spectrophotometry are closer to real component content in samples and have satisfactory accuracy.Moreover,as its application in miniaturized explosive systems,the ignition ability of CA chips with different component contents for direct ink writing CL-20 and the corresponding mechanism was studied.This study provided a basis and idea for the design and performance evaluation of CA chips in miniaturized explosive systems.

Quantitative analysis and prediction of the sound field convergence zone in mesoscale eddy environment based on data mining methods

The mesoscale eddy(ME)has a significant influence on the convergence effect in deep-sea acoustic propagation.This paper use statistical approaches to express quantitative relationships between the ME conditions and convergence zone(CZ)characteristics.Based on the Gaussian vortex model,we construct various sound propagation scenarios under different eddy conditions,and carry out sound propagation experiments to obtain simulation samples.With a large number of samples,we first adopt the unified regression to set up analytic relationships between eddy conditions and CZ parameters.The sensitivity of eddy indicators to the CZ is quantitatively analyzed.Then,we adopt the machine learning(ML)algorithms to establish prediction models of CZ parameters by exploring the nonlinear relationships between multiple ME indicators and CZ parameters.Through the research,we can express the influence of ME on the CZ quantitatively,and achieve the rapid prediction of CZ parameters in ocean eddies.The prediction accuracy(R)of the CZ distance(mean R:0.9815)is obviously better than that of the CZ width(mean R:0.8728).Among the three ML algorithms,Gradient Boosting Decision Tree has the best prediction ability(root mean square error(RMSE):0.136),followed by Random Forest(RMSE:0.441)and Extreme Learning Machine(RMSE:0.518).

Artificial Immune Detection for Network Intrusion Data Based on Quantitative Matching Method

Artificial immune detection can be used to detect network intrusions in an adaptive approach and proper matching methods can improve the accuracy of immune detection methods.This paper proposes an artificial immune detection model for network intrusion data based on a quantitative matching method.The proposed model defines the detection process by using network data and decimal values to express features and artificial immune mechanisms are simulated to define immune elements.Then,to improve the accuracy of similarity calculation,a quantitative matching method is proposed.The model uses mathematical methods to train and evolve immune elements,increasing the diversity of immune recognition and allowing for the successful detection of unknown intrusions.The proposed model’s objective is to accurately identify known intrusions and expand the identification of unknown intrusions through signature detection and immune detection,overcoming the disadvantages of traditional methods.The experiment results show that the proposed model can detect intrusions effectively.It has a detection rate of more than 99.6%on average and a false alarm rate of 0.0264%.It outperforms existing immune intrusion detection methods in terms of comprehensive detection performance.

Clinical Value of the Quantitative Flow Ratio to Predict Long-term Target Vessel Failure in Patients with In-stent Restenosis after Drug-coated Balloon Angioplasty

Objective The study sought to investigate the clinical predictive value of quantitative flow ratio(QFR)for the long-term target vessel failure(TVF)outcome in patients with in-stent restenosis(ISR)by using drug-coated balloon(DCB)treatment after a long-term follow-up.Methods This was a retrospective study.A total of 186 patients who underwent DCB angioplasty for ISR in two hospitals from March 2014 to September 2019 were enrolled.The QFR of the entire target vessel was measured offline.The primary endpoint was TVF,including target vessel-cardiac death(TV-CD),target vessel-myocardial infarction(TV-MI),and clinically driven-target vessel revascularization(CD-TVR).Results The follow-up time was 3.09±1.53 years,and 50 patients had TVF.The QFR immediately after percutaneous coronary intervention(PCI)was significantly lower in the TVF group than in the no-TVF group.Multivariable Cox regression analysis indicated that the QFR immediately after PCI was an excellent predictor for TVF after the long-term follow-up[hazard ratio(HR):5.15×10−5(6.13×10−8−0.043);P<0.01].Receiver-operating characteristic(ROC)curve analysis demonstrated that the optimal cut-off value of the QFR immediately after PCI for predicting the long-term TVF was 0.925(area under the curve:0.886,95%confidence interval:0.834–0.938;sensitivity:83.40%,specificity:88.00;P<0.01).In addition,QFR≤0.925 post-PCI was strongly correlated with the TVF,including TV-MI and CD-TVR(P<0.01).Conclusion The QFR immediately after PCI showed a high predictive value of TVF after a long-term follow-up in ISR patients who underwent DCB angioplasty.A lower QFR immediately after PCI was associated with a worse TVF outcome.

Quantitative hepatitis B core antibody and quantitative hepatitis B surface antigen:Novel viral biomarkers for chronic hepatitis B management

The management of hepatitis B virus(HBV)infection now involves regular and appropriate monitoring of viral activity,disease progression,and treatment response.Traditional HBV infection biomarkers are limited in their ability to predict clinical outcomes or therapeutic effectiveness.Quantitation of HBV core antibodies(qAnti-HBc)is a novel non-invasive biomarker that may help with a variety of diagnostic issues.It was shown to correlate strongly with infection stages,hepatic inflammation and fibrosis,chronic infection exacerbations,and the presence of occult infection.Furthermore,qAnti-HBc levels were shown to be predictive of spontaneous or treatment-induced HBeAg and HBsAg seroclearance,relapse after medication termination,re-infection following liver transplantation,and viral reactivation in the presence of immunosuppression.qAnti-HBc,on the other hand,cannot be relied on as a single diagnostic test to address all problems,and its diagnostic and prognostic potential may be greatly increased when paired with qHBsAg.Commercial qAnti-HBc diagnostic kits are currently not widely available.Because many methodologies are only semi-quantitative,comparing data from various studies and defining universal cut-off values remains difficult.This review focuses on the clinical utility of qAnti-HBc and qHBsAg in chronic hepatitis B management.

Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy(LIBS)has become a widely used atomic spectroscopic technique for rapid coal analysis.However,the vast amount of spectral information in LIBS contains signal uncertainty,which can affect its quantification performance.In this work,we propose a hybrid variable selection method to improve the performance of LIBS quantification.Important variables are first identified using Pearson's correlation coefficient,mutual information,least absolute shrinkage and selection operator(LASSO)and random forest,and then filtered and combined with empirical variables related to fingerprint elements of coal ash content.Subsequently,these variables are fed into a partial least squares regression(PLSR).Additionally,in some models,certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance.The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method.It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method.The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction(RMSEP)values of 1.605,3.478 and 1.647,respectively,which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables,which are 1.959,3.718 and 2.181,respectively.The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection,with RMSEP values dropping from 1.635,3.962 and 1.647 to 1.483,3.086 and 1.567,respectively.Such results demonstrate that using empirical knowledge as a support for datadriven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.

Solubility study of hydrogen in direct coal liquefaction solvent based on quantitative structure–property relationships model

Direct coal liquefaction(DCL)is an important and effective method of converting coal into high-valueadded chemicals and fuel oil.In DCL,heating the direct coal liquefaction solvent(DCLS)from low to high temperature and pre-hydrogenation of the DCLS are critical steps.Therefore,studying the dissolution of hydrogen in DCLS under liquefaction conditions gains importance.However,it is difficult to precisely determine hydrogen solubility only by experiments,especially under the actual DCL conditions.To address this issue,we developed a prediction model of hydrogen solubility in a single solvent based on the machine-learning quantitative structure–property relationship(ML-QSPR)methods.The results showed that the squared correlation coefficient R^(2)=0.92 and root mean square error RMSE=0.095,indicating the model’s good statistical performance.The external validation of the model also reveals excellent accuracy and predictive ability.Molecular polarization(a)is the main factor affecting the dissolution of hydrogen in DCLS.The hydrogen solubility in acyclic alkanes increases with increasing carbon number.Whereas in polycyclic aromatics,it decreases with increasing ring number,and in hydrogenated aromatics,it increases with hydrogenation degree.This work provides a new reference for the selection and proportioning of DCLS,i.e.,a solvent with higher hydrogen solubility can be added to provide active hydrogen for the reaction and thus reduce the hydrogen pressure.Besides,it brings important insight into the theoretical significance and practical value of the DCL.

A computational toolbox for molecular property prediction based on quantum mechanics and quantitative structure-property relationship

Chemical industry is always seeking opportunities to efficiently and economically convert raw materials to commodity chemicals and higher value-added chemicalbased products.The life cycles of chemical products involve the procedures of conceptual product designs,experimental investigations,sustainable manufactures through appropriate chemical processes and waste disposals.During these periods,one of the most important keys is the molecular property prediction models associating molecular structures with product properties.In this paper,a framework combining quantum mechanics and quantitative structure-property relationship is established for fast molecular property predictions,such as activity coefficient,and so forth.The workflow of framework consists of three steps.In the first step,a database is created for collections of basic molecular information;in the second step,quantum mechanics-based calculations are performed to predict quantum mechanics-based/derived molecular properties(pseudo experimental data),which are stored in a database and further provided for the developments of quantitative structure-property relationship methods for fast predictions of properties in the third step.The whole framework has been carried out within a molecular property prediction toolbox.Two case studies highlighting different aspects of the toolbox involving the predictions of heats of reaction and solid-liquid phase equilibriums are presented.

Application of quantum chemical descriptors into quantitative structure-property relationship models for prediction of the photolysis half-life of PCBs in water

Quantitative structure-property relationship(QSPR)models were developed for prediction of photolysis half-life(t_(1/2))of polychlorinated biphenyls(PCBs)in water under ultraviolet(UV)radiation.Quantum chemical descriptors computed by the PM3 Hamiltonian software were used as independent variables.The cross-validated Q^(2)_(cum)value for the optimal QSPR model is 0.966,indicating good prediction capability for lg t_(1/2)values of PCBs in water.The QSPR results show that the largest negative atomic charge on a carbon atom(Q-C)and the standard heat of formation(ΔH_(f))have a dominant effect on t_(1/2)values of PCBs.Higher Q_(C)^(-)values or lowerΔHf values of the PCBs leads to higher lg t_(1/2)values.In addition,the lg t_(1/2)values of PCBs increase with the increase in the energy of the highest occupied molecular orbital values.Increasing the largest positive atomic charge on a chlorine atom and the most positive net atomic charge on a hydrogen atom in PCBs leads to the decrease of lg t_(1/2)values.

Estimation of photolysis half-lives of dyes in a continuous-flow system with the aid of quantitative structure-property relationship

In this paper the photolysis half-lives of the model dyes in water solutions and under ultraviolet （UV） radiation were determined by using a continuous-flow spectrophotometric method. A quantitative structure- property relationship （QSPR） study was carried out using 21 descriptors based on different chemometric tools including stepwise multiple linear regression （MLR） and partial least squares （PLS） for the prediction of the photolysis half-life （t1/2） of dyes. For the selection of test set compounds, a K-means clustering technique was used to classify the entire data set, so that all clusters were properly represented in both training and test sets. The QSPR results obtained with these models show that in MLR-derived model, photolysis half-lives of dyes depended strongly on energy of the highest occupied molecular orbital （EHoMO）, largest electron density of an atom in the molecule （ED^＋） and lipophilicity （logP）. While in the model derived from PLS, besides aforementioned EHOMO and ED^＋ descriptors, the molecular surface area （Sm）, molecular weight （M-W）, electronegativity （X）, energy of the second highest occupied molecular orbital （EHoMO- 1） and dipole moment （μ） had dominant effects on logt1/2 values of dyes. These were applicable for all classes of studied dyes （including monoazo, disazo, oxazine, sulfo- nephthaleins and derivatives of fluorescein）. The results were also assessed for their consistency with findings from other similar studies.

Quantitative Structure-property Relationship Studies on Amino Acid Conjugates of Jasmonic Acid as Defense Signaling Molecules

Jasmonates and related compounds, including amino acid conjugates of jasmonic acid, have regulatory functions in the signaling pathway for plant developmental processes and responses to the complex equilibrium of biotic and abiotic stress. But the molecular details of the signaling mechanism are still poorly understood. Statistically significant quantitative structure-property relationship models （r^2 〉 0.990） constructed by genetic function approximation and molecular field analysis were generated for the purpose of deriving structural requirements for lipophilicity of amino acid conjugates of jasmonic acid. The best models derived in the present study provide some valuable academic information in terms of the 2/3D-descriptors influencing the lipophilicity, which may contribute to further understanding the mechanism of exogenous application ofjasmonates in their signaling pathway and designing novel analogs of jasmonic acid as ecological pesticides.

Prediction on Critical Micelle Concentration of Nonionic Surfactants in Aqueous Solution:Quantitative Structure-Property Relationship Approach

In order to predict the critical micelle concentration (cmc) of nonionic surfactants in aqueous solution,a quantitative structure-property relationship (QSPR) was found for 77 nonionic surfactants belonging to eight series. The best-regressed model contained four quantum-chemical descriptors,the heat of formation (ΔH),the molecular dipole moment (D),the energy of the lowest unoccupied molecular orbital (E_ LUMO ) and the energy of the highest occupied molecular orbital (E_ HOMO ) of the surfactant molecule; two constitutional descriptors,the molecular weight of surfactant (M) and the number of oxygen and nitrogen atoms (n_ ON ) of the hydrophilic fragment of surfactant molecule; and one topological descriptor,the Kier & Hall index of zero order (KH0) of the hydrophobic fragment of the surfactant. The established general QSPR between lg(cmc) and the descriptors produced a relevant coefficient of multiple determination:R 2=0.986. When cross terms were considered,the corresponding best model contained five descriptors E_ LUMO ,D,KH0,M and a cross term n_ ON ·KH0,which also produced the same coefficient as the seven-parameter model.

Evaluation of Reference Genes for Quantitative Real-Time PCR Analysis in Manila Clam Ruditapes philippinarum Under Hypoxic Stress

Quantitative real-time PCR(qRT-PCR)has been widely used for gene expression analysis,and selection of reference genes is a key point to obtain accurate results.To find out optimal reference genes for qRT-PCR in Manila clam Ruditapes philippinarum in response to hypoxia,different tissues were used and compared to evaluate the stability of candidate reference genes under low oxygen stress(DO 0.5mgL^(−1) and DO 2.0mgL^(−1))and normal condition(DO 7.5mgL^(−1)).Seven candidate reference genes were selected to evaluate the stability of their expression levels.The reference genes were evaluated by Delta Ct,BestKeeper,NormFinder and geNorm,and then screened by RefFinder calculation.Under hypoxic stress of 0.5mgL^(−1),the most suitable reference gene for gill and hepatopancreas was RPL31,and the optimal reference genes for axe foot and adductor muscle were TUB and HIS,respectively.For hypoxic stress of 2.0mgL^(−1),the most stable reference gene for gill and hepatopancreas was RPL31,and the optimal reference genes for axe foot and adductor muscle were RPS23 and EF1A,respectively.At the normal condition,HIS and EF1A were identified as the optimal internal reference genes in gill and hepatopancreas respectively,and GFRP2 was the best internal reference gene for axe foot and adductor muscle.The present findings will provide important basis for the selection of reference genes for qRT-PCR analysis of gene expression level in bivalves under hypoxic stress,which might be helpful for the analysis of other molluscs too.

Radar Quantitative Precipitation Estimation Based on the Gated Recurrent Unit Neural Network and Echo-Top Data

The Gated Recurrent Unit(GRU) neural network has great potential in estimating and predicting a variable. In addition to radar reflectivity(Z), radar echo-top height(ET) is also a good indicator of rainfall rate(R). In this study, we propose a new method, GRU_Z-ET, by introducing Z and ET as two independent variables into the GRU neural network to conduct the quantitative single-polarization radar precipitation estimation. The performance of GRU_Z-ET is compared with that of the other three methods in three heavy rainfall cases in China during 2018, namely, the traditional Z-R relationship(Z=300R1.4), the optimal Z-R relationship(Z=79R1.68) and the GRU neural network with only Z as the independent input variable(GRU_Z). The results indicate that the GRU_Z-ET performs the best, while the traditional Z-R relationship performs the worst. The performances of the rest two methods are similar.To further evaluate the performance of the GRU_Z-ET, 200 rainfall events with 21882 total samples during May–July of 2018 are used for statistical analysis. Results demonstrate that the spatial correlation coefficients, threat scores and probability of detection between the observed and estimated precipitation are the largest for the GRU_Z-ET and the smallest for the traditional Z-R relationship, and the root mean square error is just the opposite. In addition, these statistics of GRU_Z are similar to those of optimal Z-R relationship. Thus, it can be concluded that the performance of the GRU_ZET is the best in the four methods for the quantitative precipitation estimation.

Quantitative parameters in novel spectral computed tomography:Assessment of Ki-67 expression in patients with gastric adenocarcinoma

BACKGROUND The level of Ki-67 expression has served as a prognostic factor in gastric cancer.The quantitative parameters based on the novel dual-layer spectral detector computed tomography(DLSDCT)in discriminating the Ki-67 expression status are unclear.AIM To investigate the diagnostic ability of DLSDCT-derived parameters for Ki-67 expression status in gastric carcinoma(GC).METHODS Dual-phase enhanced abdominal DLSDCT was performed preoperatively in 108 patients with gastric adenocarcinoma.Primary tumor monoenergetic CT attenuation value at 40-100 kilo electron volt(kev),the slope of the spectral curve(λ_(HU)),iodine concentration(IC),normalized IC(nIC),effective atomic number(Z^(eff))and normalized Z^(eff)(nZ^(eff))in the arterial phase(AP)and venous phase(VP)were retrospectively compared between patients with low and high Ki-67 expression in gastric adenocarcinoma.Spearman’s correlation coefficient was used to analyze the association between the above parameters and Ki-67 expression status.Receiver operating characteristic(ROC)curve analysis was performed to compare the diagnostic efficacy of the statistically significant parameters between two groups.RESULTS Thirty-seven and 71 patients were classified as having low and high Ki-67 expression,respectively.CT_(40 kev-VP),CT_(70 kev-VP),CT_(100 kev-VP),and Z^(eff)-related parameters were significantly higher,but IC-related parameters were lower in the group with low Ki-67 expression status than the group with high Ki-67 expression status,and other analyzed parameters showed no statistical difference between the two groups.Spearman’s correlation analysis showed that CT_(40 kev-VP),CT_(70 kev-VP),CT_(100 kev-VP),Z^(eff),and n Z^(eff) exhibited a negative correlation with Ki-67 status,whereas IC and nIC had positive correlation with Ki-67 status.The ROC analysis demonstrated that the multi-variable model of spectral parameters performed well in identifying the Ki-67 status[area under the curve(AUC)=0.967;sensitivity 95.77%;specificity 91.89%)].Nevertheless,the differentiating capabilities of singlevariable model were moderate(AUC value 0.630-0.835).In addition,the nZ_(VP)^(eff) and nIC_(VP)(AUC 0.835 and 0.805)showed better performance than CT_(40 kev-VP),CT_(70 kev-VP) and CT_(100 kev-VP)(AUC 0.630,0.631 and 0.662)in discriminating the Ki-67 status.CONCLUSION Quantitative spectral parameters are feasible to distinguish low and high Ki-67 expression in gastric adenocarcinoma.Z^(eff) and IC may be useful parameters for evaluating the Ki-67 expression.

Deep learning assisted variational Hilbert quantitative phase imaging

We propose a high-accuracy artifacts-free single-frame digital holographic phase demodulation scheme for relatively lowcarrier frequency holograms-deep learning assisted variational Hilbert quantitative phase imaging(DL-VHQPI).The method,incorporating a conventional deep neural network into a complete physical model utilizing the idea of residual compensation,reliably and robustly recovers the quantitative phase information of the test objects.It can significantly alleviate spectrum-overlapping-caused phase artifacts under the slightly off-axis digital holographic system.Compared to the conventional end-to-end networks(without a physical model),the proposed method can reduce the dataset size dramatically while maintaining the imaging quality and model generalization.The DL-VHQPI is quantitatively studied by numerical simulation.The live-cell experiment is designed to demonstrate the method's practicality in biological research.The proposed idea of the deep learning-assisted physical model might be extended to diverse computational imaging techniques.