Applying dual models on optimized LSTM with U-net segmentation for breast cancer diagnosis using mammogram images.

BACKGROUND OF THE STUDY: Breast cancer is the most fatal disease that widely affects women. When the cancerous lumps grow from the cells of the breast, it causes breast cancer. Self-analysis and regular medical check-ups help for detecting the disease earlier and enhance the survival rate. Hence, an automated breast cancer detection system in mammograms can assist clinicians in the patient's treatment. In medical techniques, the categorization of breast cancer becomes challenging for investigators and researchers. The advancement in deep learning approaches has established more attention to their advantages to medical imaging issues, especially for breast cancer detection. AIM: The research work plans to develop a novel hybrid model for breast cancer diagnosis with the support of optimized deep-learning architecture. METHODS: The required images are gathered from the benchmark datasets. These collected datasets are used in three pre-processing approaches like "Median Filtering, Histogram Equalization, and morphological operation", which helps to remove unwanted regions from the images. Then, the pre-processed images are applied to the Optimized U-net-based tumor segmentation phase for obtaining accurate segmented results along with the optimization of certain parameters in U-Net by employing "Adapted-Black Widow Optimization (A-BWO)". Further, the detection is performed in two different ways that is given as model 1 and model 2. In model 1, the segmented tumors are used to extract the significant patterns with the help of the "Gray-Level Co-occurrence Matrix (GLCM) and Local Gradient pattern (LGP)". Further, these extracted patterns are utilized in the "Dual Model accessed Optimized Long Short-Term Memory (DM-OLSTM)" for performing breast cancer detection and the detected score 1 is obtained. In model 2, the same segmented tumors are given into the different variants of CNN, such as "VGG19, Resnet150, and Inception". The extracted deep features from three CNN-based approaches are fused to form a single set of deep features. These fused deep features are inserted into the developed DM-OLSTM for getting the detected score 2 for breast cancer diagnosis. In the final phase of the hybrid model, the score 1 and score 2 obtained from model 1 and model 2 are averaged to get the final detection output. RESULTS: The accuracy and F1-score of the offered DM-OLSTM model are achieved at 96 % and 95 %. CONCLUSION: Experimental analysis proves that the recommended methodology achieves better performance by analyzing with the benchmark dataset. Hence, the designed model is helpful for detecting breast cancer in real-time applications.

Intracellular pH responses of hybridoma and yeast to substrate addition and acid challenge.

The pHi responses of hybridoma and yeast cells to substrate and external acid additions were measured using the fluorescent pHi indicator, 9-aminoacridine. The pHi change, following CCCP addition, indicated by 9AA, compared very well with that indicated by BCECF. No change in pHi was observed following glucose or glutamine additions to hybridoma cells under glucose- and glutamine-absent conditions. Also, no change in pHi was observed when glucose was added in the presence of low glutamine and when glutamine was added in the presence of low glucose. However, in the presence of amiloride, the pHi of hybridoma cells decreased following glucose addition. Intracellular pH responses of hybridoma and yeast cells to decreases in external pH, effected by acid addition, were dependent on the cellular energy state and acid type. Cells controlled their pHi more tightly under energy-poor conditions compared to energy-rich conditions, and sulfuric acid (strong acid) caused larger changes in pHi compared to pyruvic acid (weak acid). In response to acid addition under energy-rich conditions, the magnitudes of pHi increases in hybridoma were smaller in the presence of amiloride compared to that in the absence of amiloride. Further, pHi responses to a decrease in external pH were slower at submetabolic temperatures.

Improvement in enzyme productivities from mold cultivations using the liquid-phase oxygen supply strategy.

Cultivations of Aspergillus niger cells in which oxygen was provided through the liquid-phase oxygen supply strategy (which involves the need-based decomposition of H2O2 pulses to yield the necessary oxygen) were studied. Concentrations of H2O2 in the range of 1 to 5 mM were found to be suitable for use in cultivations. The growth rate constant of 0.17 h(-1) obtained in the H2O2-based cultivation, was comparable to that obtained in the cultivation with aeration; however, the maximum cell concentration in the H2O2-based cultivation was 124% of that obtained in cultivation with aeration. Maximum concentrations of catalase, protease and glucose oxidase obtained in the H2O2-based cultivation, were 240%, 172%, and 124% respectively, of those obtained in the cultivation with aeration. Further, the specific enzyme levels (units per gram cell) of catalase and protease obtained in the H2O2-based cultivation were 172% and 156% of those obtained in the cultivation with aeration, whereas, the specific glucose oxidase levels were comparable. In addition, the oxygen profiles inside the pellets ofA. niger during both the modes of oxygen supply were described using mathematical models. Studies to elucidate the mechanism of oxygen availability showed that the decomposition of the H2O2 supplied in the extracellular space occurred intracellularly, as well as extracellularly, to yield oxygen. Also, the proton motive force (PMF) was found to be involved in the process of oxygen availability from H2O2 to A. niger cells.

Improvement in bioreactor productivities using free radicals: HOCl-induced overproduction of xanthan gum from Xanthomonas campestris and its mechanism.

Free-radical induction has been employed as a novel strategy to improve bioreactor productivity and, more specifically, the quality and productivity of xanthan gum from Xanthomonas campestris cultures. A 210% increase in xanthan yield and a 20% increase in viscosity (quality) resulted from HOCl (oxidant) treatment. The acetate mass fraction in xanthan gum decreased by 42% and its pyruvate mass fraction increased by 63% as a result of HOCl treatment. The growth rate was almost unaffected by HOCl treatment. A hypothesis to explain the mechanism of xanthan gum overproduction by free-radical induction has been formulated. The significant aspects of the hypothesis, such as SoxS protein binding to the promoter region of the gum gene and the consequent increase in mRNA concentrations, have been experimentally verified.

Intracellular pH based controlled cultivation of yeast cells: I. Measurement methodology.

A method has been developed to continuously measure the intracellular pH (pH(i)) of cells cultivated in a bioreactor in an on-line fashion over extend time periods. The methods is attractive in its simplicity and involves the use of a fluorescent pH(i) indicator 9-aminoacridine (9A A) which is a week base. An expression has been derived to calculate changes in pH(i) from measured 9AA-fluorescence changes. The indicator 9AA was found t be nontoxic to yeast cells at concentrations used to measure pH(i) (7 microM). The fluorescence of nicotinamide adenine dinucleotide (NADH) molecules did not interfere significantly with the measurement of 9AA-fluorescence. The pH(i) change in yeast cell following the addition of a proton ionophore carbonyl cyanide m-chlorophenyl hydrazone (CCCP) measured by 9AA compared favorably with that measured by the well-established pH(i), indicator (which is however unsuitable for on-line applications in a bioreactor) bis-carboxyethyl carboxy fluorescein (BCECF). The pH(i) of yeast under substrate starved conditions was 6.4 units. The responses of pH(i) of yeast cells to induced metabolic transitions were studied. Under aerobic condition, pH(i) increased by 0.12 unit following a 100-ppm glucose pulse addition and by 0.25 unit following a 300-ppm ethanol pulse addition. Under anaerobic condition, pH(i) increased by 0.1 unit following a 500-ppm glucose pulse addition. Comparison of pH(i) with other indicators of cellular metabolic state suggests that pH(i) is a cellular metabolic state indicator.

Intracellular pH-based controlled cultivation of yeast cells: II. cultivation methodology.

Intracellular pH (pH(i)) was measured on-line in a bioreactor using a fluorescent pH(i) indicator, 9-aminoacridine, and controlled fed-batch cultivations of yeast cells based on pH(i) (FB-pH(i)) were performed. In FB-pH(i) cultivations, automated glucose additions were made to the culture in response to culture pH(i). The average ethanol (an-aerobic product) yield was significantly lower [0.12 g g(-1) glucose in fed-batch pH(i) cultivations with 100 ppm glucose additions (FB-pH(i)-100 cultivation) vs. 0.48 g g(-1) glucose in batch] and cell yield was higher (0.54 g g(-1) glucose in FB-pH(i)-100 cultivation vs. 0.3 g g(-1) glucose in batch) compared to batch cultivation. An expression has been derived to calculate changes in pH(i) from measured fluorescence values when the cell concentration increases during growth. Cultivations based on pH(i), performed with different magnitudes of glucose addition (100, 50, and 10 ppm additions), showed that lower magnitudes of glucose addition resulted in lower ethanol yields while cell yield remained unaffected. The ratio of specific oxygen uptake rate to specific glucose uptake rate (OUR/GUR) increased with decreased in magnitude of glucose additions in FB-pH(i) cultivations, suggesting that the culture aerobic state was higher when the magnitude of glucose addition was lower. The average cell productivity in FB-pH(i) cultivations was 29% higher than in batch cultivation. Cells were also cultivated at high OUR conditions, and the results are compared with other cultivations.

Mechanism of oxygen availability from hydrogen peroxide to aerobic cultures of Xanthomonas campestris.

Fundamental studies on the availability of oxygen from the decomposition of H(2)O(2), in vivo, by Xanthomonas campestris, when H(2)O(2) is used as an oxygen source are presented. It was found that the H(2)O(2) added extracellularly (0.1-6 mM) was decomposed intracellularly. Further, when H(2)O(2) was added, the flux of H(2)O(2) into the cell, is regulated by the cell. The steady-state H(2)O(2) flux into the cell was estimated to be 9.7 x 10(-8) mol m(-2) s(-1). In addition, it was proved that the regulation of H(2)O(2) flux was coupled to the protonmotive force (PMF) using experiments with the protonophore carbonyl cyanide m-chlorophenylhydrazone (CCCP), which disrupts PMF. The coupling constant between the rate of free energy availability from PMF and the rate of reduction of H(2)O(2) flux, was found to be 46.4 mol m(-2) s(-1) J(-1) from simulations using a developed model. Also, the estimated periplasmic catalase concentration was 1.4 x 10(-9) M.

Bovine colostrum or milk as a serum substitute for the cultivation of a mouse hybridoma.

A mouse-mouse hybridoma was grown in serum-free medium supplemented with bovine milk or colostrum. Bovine colostrum supported growth of the hybridoma whereas bovine milk alone did not support cellular proliferation. For growth in medium supplemented with colostrum, the maximum cell concentration achieved was 1.4 x 10(6) cells/mL in 2.2% colostrum, which is 44% of that obtained in 9% serum. When cells were grown in media containing milk and low amounts of serum (<1%) the maximum cell concentration in 2.2% milk with 0.4% serum was 2 x 10(6) cells/ml, whereas it was only 0.2 x 10(6) cells/ml and 1.3 x 10(6) cells/ml in 2.2% milk alone and 0.4% serum alone, respectively. Similar behavior was observed for growth in media containing colostrum and low amounts of serum. The monoclonal antibody production in media containing combinations of serum and milk or colostrum was comparable to that obtained in media with higher serum concentrations. Experiments performed with conditioned media suggest that the rapid decrease in viability, after the maximum cell concentration has been reached, is partially due to the presence of some inhibitory components generated during the cell culture rather than due to depletion of some serum components.