A Study on the Effectiveness of Deep Learning-Based Anomaly Detection Methods for Breast Ultrasonography.

In the medical field, it is delicate to anticipate good performance in using deep learning due to the lack of large-scale training data and class imbalance. In particular, ultrasound, which is a key breast cancer diagnosis method, is delicate to diagnose accurately as the quality and interpretation of images can vary depending on the operator's experience and proficiency. Therefore, computer-aided diagnosis technology can facilitate diagnosis by visualizing abnormal information such as tumors and masses in ultrasound images. In this study, we implemented deep learning-based anomaly detection methods for breast ultrasound images and validated their effectiveness in detecting abnormal regions. Herein, we specifically compared the sliced-Wasserstein autoencoder with two representative unsupervised learning models autoencoder and variational autoencoder. The anomalous region detection performance is estimated with the normal region labels. Our experimental results showed that the sliced-Wasserstein autoencoder model outperformed the anomaly detection performance of others. However, anomaly detection using the reconstruction-based approach may not be effective because of the occurrence of numerous false-positive values. In the following studies, reducing these false positives becomes an important challenge.

Fabrication of 1,4-alpha-D-glucan glucanohydrolase holding Gel-Scaffolds using Agar-Agar, a natural polysaccharide and Polyacrylamide, a synthetic organic polymer for continuous liquefaction of starch

1,4-alpha-D-glucan glucanohydrolase is among the most widely used commercial hydrolytic enzymes acting randomly on the glycosidic linkages of starch resulting in its saccharification and liquefaction. Its applicability in different industries can be improved by enhancing its stability and reusability. Therefore, in the present study attempts have been made to enhance the industrial applicability of 1,4-alpha-D-glucan glucanohydrolase from Bacillus subtilis KIBGE-HAR by adapting immobilization technology. The study developed mechanically stable, enzyme containing gel-frameworks using two support matrices including agar-agar, a natural polysaccharide and polyacrylamide gel, a synthetic organic polymer. These catalytic gel-scaffolds were compared with each other in terms of kinetics and stability of entrapped 1,4-α-D-glucan glucanohydrolase. In case of polyacrylamide gel, Km value for immobilized enzyme increased to 7.95 mg/mL, while immobilization in agar-agar resulted in decreased Km value i.e 0.277 mg/mL as compared to free enzyme. It was found that immobilized enzyme showed maximum activity at 70 °C in both the supports as compared to free enzyme having maximum activity at 60 °C. Immobilized 1,4-α-D-glucan glucanohydrolase exhibited no change in optimal pH 7.0 before and after entrapment in polyacrylamide gel and agar-agar. The enzyme containing gel-scaffold was found suitable for repeated batches of starch liquefaction in industrial processes. Agar-agar entrapped 1,4-α-D-glucanglucanohydrolase was capable to degrade starch up to seven repeated operational cycles whereas polyacrylamide entrapped enzyme conserved its activity up to sixth operational cycle.

Robust Fourier transformed infrared spectroscopy coupled with multivariate methods for detection and quantification of urea adulteration in fresh milk samples.

Urea is added as an adulterant to give milk whiteness and increase its consistency for improving the solid not fat percentage, but the excessive amount of urea in milk causes overburden and kidney damages. Here, an innovative sensitive methodology based on near-infrared spectroscopy coupled with multivariate analysis has been proposed for the robust detection and quantification of urea adulteration in fresh milk samples. In this study, 162 fresh milk samples were used, those consisting 20 nonadulterated samples (without urea) and 142 with urea adulterant. Eight different percentage levels of urea adulterant, that is, 0.10%, 0.30%, 0.50%, 0.70%, 0.90%, 1.10%, 1.30%, and 1.70%, were prepared, each of them prepared in triplicates. A Frontier NIR spectrophotometer (BSEN60825-1:2007) by Perkin Elmer was used for scanning the absorption of each sample in the wavenumber range of 10,000-4,000 cm-1, using 0.2 mm path length CaF2 sealed cell at resolution of 2 cm-1. Principal components analysis (PCA), partial least-squares discriminant analysis (PLS-DA), and partial least-squares regressions (PLSR) methods were applied for the multivariate analysis of the NIR spectral data collected. PCA was used to reduce the dimensionality of the spectral data and to explore the similarities and differences among the fresh milk samples and the adulterated ones. PLS-DA also showed the discrimination between the nonadulterated and adulterated milk samples. The R-square and root mean square error (RMSE) values obtained for the PLS-DA model were 0.9680 and 0.08%, respectively. Furthermore, PLSR model was also built using the training set of NIR spectral data to make a regression model. For this PLSR model, leave-one-out cross-validation procedure was used as an internal cross-validation criteria and the R-square and the root mean square error (RMSE) values for the PLSR model were found as 0.9800 and 0.56%, respectively. The PLSR model was then externally validated using a test set. The root means square error of prediction (RMSEP) obtained was 0.48%. The present proposed study was intended to contribute toward the development of a robust, sensitive, and reproducible method to detect and determine the urea adulterant concentration in fresh milk samples.

Fast detection and quantification of pork meat in other meats by reflectance FT-NIR spectroscopy and multivariate analysis.

This study aimed to develop a fast analytical method, combining near infrared reflectance spectroscopy and multivariate analysis, for detection and quantification of pork meat in other meat samples. A total of 5952 mixture samples from 39 types of meat were prepared in triplicate, with the inclusion of pork at 0%, 1%, 5%, 10%, 30%, 50%, 70%, 90% and 100%. Each sample was scanned using an FT-NIR spectrophotometer in the reflection mode. Spectra were collected in the wavenumber range from 10,000 to 4000 cm-1, at a resolution of 2 cm-1 and a total path length of 0.5 mm. Principal Component Analysis (PCA) revealed the similarities and differences among the various types of meat samples and Partial Least-Squares Discriminant Analysis (PLS-DA) showed a good discrimination between pure and pork-spiked meat samples. A Partial Least-Squares Regression (PLSR) model was built to predict the pork meat contents in other meats, which provided the R2 value of 0.9774 and RMSECV value of 1.08%. Additionally, an external validation was carried out using a test set, providing a rather good prediction error, with an RMSEP value of 1.84%.

Applications of FT-NIRS combined with PLS multivariate methods for the detection & quantification of saccharin adulteration in commercial fruit juices.

Detection of adulteration in carbohydrate-rich foods like fruit juices is particularly difficult because of the variety of the commercial sweeteners available that match the concentration profiles of the major carbohydrates in the foods. In present study, a new sensitive and robust assay using Fourier Transform Near-Infrared Spectroscopy (FT-NIRS) combined with partial least square (PLS) multivariate methods has been developed for detection and quantification of saccharin adulteration in different commercial fruit juice samples. For this investigation, six different commercially available fruit juice samples were intentionally adulterated with saccharin at the following percentage levels: 0%, 0.10%, 0.30%, 0.50%, 0.70%, 0.90%, 1.10%, 1.30%, 1.50%, 1.70% and 2.00% (weight/volume). Altogether, 198 samples were used including 18 pure juice samples (unadulterated) and 180 juice samples adulterated with saccharin. PLS multivariate methods including partial least-squares discriminant analysis (PLS-DA) and partial least-squares regressions (PLSR) were applied to the obtained spectral data to build models. The PLS-DA model was employed to differentiate between pure fruit juice samples and those adulterated with saccharin. The R2 value obtained for the PLS-DA model was 97.90% with an RMSE error of 0.67%. Similarly, a PLS regression model was also developed to quantify the amount of saccharin adulterant in juice samples. The R2 value obtained for the PLSR model was 97.04% with RMSECV error of 0.88%. The employed model was then cross-validated by using a test set which included 30% of the total adulterated juice samples. The excellent performance of the model was proved by the low root mean squared error of prediction value of 0.92% and the high correlation factor of 0.97. This newly developed method is robust, nondestructive, highly sensitive and economical.

Application of reflectance spectroscopies (FTIR-ATR & FT-NIR) coupled with multivariate methods for robust in vivo detection of begomovirus infection in papaya leaves.

Nucleic acid & serology based methods have revolutionized plant disease detection, however, they are not very reliable at asymptomatic stage, especially in case of pathogen with systemic infection, in addition, they need at least 1-2days for sample harvesting, processing, and analysis. In this study, two reflectance spectroscopies i.e. Near Infrared reflectance spectroscopy (NIR) and Fourier-Transform-Infrared spectroscopy with Attenuated Total Reflection (FT-IR, ATR) coupled with multivariate exploratory methods like Principle Component Analysis (PCA) and Partial least square discriminant analysis (PLS-DA) have been deployed to detect begomovirus infection in papaya leaves. The application of those techniques demonstrates that they are very useful for robust in vivo detection of plant begomovirus infection. These methods are simple, sensitive, reproducible, precise, and do not require any lengthy samples preparation procedures.

New robust sensitive fluorescence spectroscopy coupled with PLSR for estimation of quercetin in Ziziphus mucronata and Ziziphus sativa.

Flavonoids are natural antioxidants derived from plants and commonly found in a variety of foods to sequester free radicals. Quercetin, belonging to flavonol subclass of flavonoids, has received considerable attention because of its wide uses as a nutritional supplement as well as a phytochemical remedy for a number of diseases. In the current study, quantification of quercetin was carried out in two medicinally important flavonoid rich plant Ziziphus mucronata and Ziziphus sativa. Emission spectroscopy was utilized as a new method coupled with Partial Least Squares Regression (PLSR) and the cross validation was done by UV-Visible spectroscopy. The results indicated the higher quercetin content in Z. mucronata (1.50±0.034%) than Z. sativa (1.21±0.052%), and were further verified through Folin-Ciocalteu Colorimetric method (Z. mucronata; 1.41±0.26% and Z. sativa; 1.13±0.136%). In this study the sensitivity was explained in term of slope i.e. Slope=0.9973.

Robust new NIRS coupled with multivariate methods for the detection and quantification of tallow adulteration in clarified butter samples.

Cows' butterfat may be adulterated with animal fat materials like tallow which causes increased serum cholesterol and triglycerides levels upon consumption. There is no reliable technique to detect and quantify tallow adulteration in butter samples in a feasible way. In this study a highly sensitive near-infrared (NIR) spectroscopy combined with chemometric methods was developed to detect as well as quantify the level of tallow adulterant in clarified butter samples. For this investigation the pure clarified butter samples were intentionally adulterated with tallow at the following percentage levels: 1%, 3%, 5%, 7%, 9%, 11%, 13%, 15%, 17% and 20% (wt/wt). Altogether 99 clarified butter samples were used including nine pure samples (un-adulterated clarified butter) and 90 clarified butter samples adulterated with tallow. Each sample was analysed by using NIR spectroscopy in the reflection mode in the range 10,000-4000 cm-1, at 2 cm-1 resolution and using the transflectance sample accessory which provided a total path length of 0.5 mm. Chemometric models including principal components analysis (PCA), partial least-squares discriminant analysis (PLSDA), and partial least-squares regressions (PLSR) were applied for statistical treatment of the obtained NIR spectral data. The PLSDA model was employed to differentiate pure butter samples from those adulterated with tallow. The employed model was then externally cross-validated by using a test set which included 30% of the total butter samples. The excellent performance of the model was proved by the low RMSEP value of 1.537% and the high correlation factor of 0.95. This newly developed method is robust, non-destructive, highly sensitive, and economical with very minor sample preparation and good ability to quantify less than 1.5% of tallow adulteration in clarified butter samples.

Application of NIR Spectroscopy Coupled with PLS Regression for Quantification of Total Polyphenol Contents from the Fruit and Aerial Parts of Citrullus colocynthis.

INTRODUCTION: Citrullus colocynthis (L.) Schrad is extensively used to treat diabetes, obesity, fever, cancer, amenorrhea, jaundice, leukemia, rheumatism, and respiratory diseases. Chemical studies have indicated the presence of several cucurbitacins, flavones, and other polyphenols in this plant. These phytochemical constituents are responsible for the interesting antioxidant and other biological activities of C. colocynthis. OBJECTIVE: In the present study, for the first time, near infrared (NIR) spectroscopy coupled with partial least square (PLS) regression analysis was used to quantify the polyphenolic phytochemicals of C. colocynthis. METHODOLOGY: The fruit and aerial parts of the C. colocynthis were extracted individually in methanol followed by fractionation in n-hexane, chloroform, ethyl acetate, n-butanol, and water. Near infrared (NIR) spectra were obtained in absorption mode in the wavelength range 700-2500 nm. The PLS regression model was then built from the obtained spectral data to quantify the total polyphenol contents in the selected plant samples. RESULTS: The PLS regression model obtained had a R2 value of 99% with a 0.98 correlationship value and a good prediction with a root mean square error of prediction (RMSEP) value of 1.89% and correlation of 0.98. These results were further confirmed through UV-vis spectroscopy and it is found that the ethyl acetate fraction has the maximum value for polyphenol contents (101.7 mg/100 g; NIR, 100.4 mg/100 g; UV-vis). CONCLUSIONS: The polyphenolic phytochemicals of the fruit and aerial parts of C. colocynthis have been quantified successfully by using multivariate analysis in a non-destructive, economical, precise, and highly sensitive method, which uses very simple sample preparation. Copyright © 2017 John Wiley & Sons, Ltd.

New design of experiment combined with UV-Vis spectroscopy for extraction and estimation of polyphenols from Basil seeds, Red seeds, Sesame seeds and Ajwan seeds.

New experimental designs for the extraction of polyphenols from different seeds including Basil seed, Red seed, Sesame seeds and Ajwan seeds were investigated. Four variables the concentration and volume of methanol and NaOH solutions as well as the temperature and time of extraction were varied to see their effect on total phenol extraction. The temperature was varied in the range from 25°C to 200°C while the time in the range from 30 to 200minutes. Response surface methodology was used to optimize the extraction parameters. The estimation of polyphenols was measured through phenols reduction UV-Vis spectroscopic method of phosphotungstic-phosphomolybdic acids (Folin-Ciocalteu's reagent). Calibration curve was made by using tannic acid as a polyphenols standard in the concentration range from 0.1 to 10ppm. The regression line obtained shows the value of correlation coefficient i.e. R=0.930 and Root mean square error of cross validation (RMSEC) value of 0.0654. The Basil seeds were found containing the highest amount of total phenols i.e. 785.76mg/100g. While the Sesame seeds having the least amount i.e. 33.08mg/100g. The Ajwan seeds and the Red seeds are containing the medium amounts i.e. 379mg/100g and 220.54mg/100g respectively.

Development of new NIR-spectroscopy method combined with multivariate analysis for detection of adulteration in camel milk with goat milk.

New NIR spectroscopy combined with multivariate analysis for detection and quantification of camel milk adulteration with goat milk was investigated. Camel milk samples were collected from Aldhahira and Sharqia regions of Sultanate of Oman and were measured using NIR spectroscopy in absorption mode in the wavelength range from 700 to 2500nm, at 2cm-1 resolution and using a 0.2mm path length CaF2 sealed cell. The multivariate methods like PCA, PLS-DA and PLS regression were used for interpretation of NIR spectral data. PLS-DA was used to detect the discrimination between the pure and adulterated milk samples. For PLSDA model the R-square value obtained was 0.974 with 0.08 RMSE. Furthermore, PLS regression model was used to quantify the levels of adulteration from, 0%, 2%, 5%, 10%, 15% and 20%. The PLS model showed the RMSEC=1.10% with R2=94%. This method is simple, reproducible, having excellent sensitivity. The limit of detection was found 0.5%, while the limit of quantification was 2%.

Determination of sucrose in date fruits (Phoenix dactylifera L.) growing in the Sultanate of Oman by NIR spectroscopy and multivariate calibration.

A Near Infrared (NIR) spectroscopic method combined with multivariate calibration was developed for the determination of the amount of sucrose in date fruits growing in the Sultanate of Oman. In this study two groups of samples were used: one group of 48 sucrose standard solutions in the concentration range from 0.01% to 50% (w/v) and another group of 54 date fruit samples of 18 different varieties. The sucrose standard samples were split in two sets, i.e. one training set of 31 samples and one test set of 17 samples. All samples were measured with a NIR spectrophotometer in the wavelength range from 700 to 2500 nm. The spectra collected were preprocessed using baseline correction and Savitzky-Golay 1st derivative. Partial least-squares regression (PLSR) was used to build the regression model with the training set of 31 samples. This model was then validated by using random leave-one-out cross-validation. Later, the PLS regression model was externally validated by using the test set of 17 samples of known sucrose concentration. The root mean squared error of prediction (RMSEP) was found to be of 1.5%, which shows a good prediction ability of the model. Finally, the PLS model was applied to the spectra of 54 date fruit samples to quantify their sucrose amount. It was found that the Khalas, Barnia Nizwi, Ajwa Almadina, Maan, and Khunizi varieties contain high amounts of sucrose, i.e. ranging from 36% to 60%, while Naghal, Fardh, Nashu and Qash Tabaq varieties contain the least amount of sucrose, ranging from 3.5% to 8.1%.

Microsphaerol and seimatorone: two new compounds isolated from the endophytic fungi, Microsphaeropsis sp. and Seimatosporium sp.

A new polychlorinated triphenyl diether named microsphaerol (1), has been isolated from the endophtic fungus Microsphaeropsis sp. An intensive phytochemical investigation of the endophytic fungus Seimatosporium sp., led to the isolation of a new naphthalene derivative named seimatorone (2) and eight known compounds, i.e., 1-(2,6-dihydroxyphenyl)-3-hydroxybutan-1-one (3), 1-(2,6-dihydroxyphenyl)butan-1-one (4), 1-(2-hydroxy-6-methoxyphenyl)butan-1-one (5), 5-hydroxy-2-methyl-4H-chromen-4-one (6), 2,3-dihydro-5-hydroxy-2-methyl-4H-chromen-4-one (7), 8-methoxynaphthalen-1-ol (8), nodulisporins A and B (9 and 10, resp.), and daldinol (11). The structures of 1 and 2 were elucidated by detailed spectroscopic analysis including (1) H- and (13) C-NMR, COSY, HMQC, HMBC, and HR-EI-MS, while the structures of the known compounds were deduced from comparison of their spectral data with those in the literature. Preliminary studies revealed that microsphaerol (1) showed good antibacterial activities against B. Megaterium and E. coli, and good antilagal and antifungal activities against C. fusca, M. violaceum, respectively. On the other hand, seimatorone (2) exhibited moderate antibacterial, antialgal, and antifungal activities.

Seimisochromenes A and B: two new dihydroisochromenes from the endophytic fungus, Seimatosporium sp.

Two new dihydroisochromenes, named seimisochromenes A and B (1 and 2), were isolated from an endophytic fungus, Seimatosporium sp. The structures of seimisochromenes A and B have been determined from 1D ((1)H and (13)C NMR spectra) and 2D (COSY, HMQC, HMBC, and NOESY) NMR experiments.

Isolation and bioactivities of the flavonoids morin and morin-3-O-ß-D-glucopyranoside from Acridocarpus orientalis-A wild Arabian medicinal plant.

Acridocarpus orientalis is an important medicinal plant for some of the locals of Arabian region. Very little is known about its phytochemical constituents. In the present study, we aimed to isolate bioactive chemicals from the crude methanolic extract of the aerial parts of A. orientalis. The extraction and isolation resulted in the purification of two flavonoids: morin (1) and morin-3-O-ß-D-glucopyranoside (2). The structure elucidation was carried out by extensive analysis of spectroscopic data and comparison with the reported data for the known constituents. The pure isolates were subjected to various biological assays for their bioactivities. The compounds 1 and 2 were significantly active against the growth of various pathogenic fungi and phytotoxic against lettuce seed at higher concentrations. Furthermore, the free radical scavenging activities, anti-lipid peroxidation, and cytotoxic effects against HepG2, HT29, and HCT116 cancer cell lines were also assayed and the results are presented in this paper.

Role of platelet indices, glycemic control and hs-CRP in pathogenesis of vascular complications in type-2 diabetic patients.

OBJECTIVES: Alteration in platelet morphology and functions are associated with pathological processes and increased risk of vascular complications in patients with diabetes. The purpose of the study was to find the correlation between platelet indices with fasting blood glucose, HbA1c and hs-CRP level in pathogenesis of vascular complications in type 2 diabetic patients. METHODOLOGY: The study has been carried out on 51 Type 2 Diabetics and 55 age and sex matched healthy control subjects. Fasting blood glucose (FBG), Glycosylated hemoglobin (HbA1c), high sensitivity C- reactive protein (hs-CRP) level and platelet indices including Platelet count (PLT), Plateletcrit (PCT), Mean platelet volume (MPV), Platelet distribution width (PDW) were estimated and compared with normal subjects. The results were evaluated statistically. RESULTS: The study demonstrated that FBG, HbA1c, MPV, PDW and hs-CRP were statistically higher in diabetics in comparison with control subjects (P is less than 0.05). Positive correlation of FBG with HbA1c (r is equal to 0.993, P is equal to 0.0001), PLT with PCT (r is equal to 0.922, P is equal to 0.0001) and MPV with PDW (r is equal to 0.332, P is equal to 0.024) was found in diabetics. CONCLUSION: The poor glycemic control is positively correlated with high HbA1c level. The increased values of MPV, PDW and elevated hs-CRP level may also serve as confirmatory test in finding risk of developing complications.