Deep Learning Mechanism for Predicting the Axillary Lymph Node Metastasis in Patients with Primary Breast Cancer

The second largest cause of mortality worldwide is breast cancer, and it mostly occurs in women. Early diagnosis has improved further treatments and reduced the level of mortality. A unique deep learning algorithm is presented for predicting breast cancer in its early stages. This method utilizes numerous layers to retrieve significantly greater amounts of information from the source inputs. It could perform automatic quantitative evaluation of complicated image properties in the medical field and give greater precision and reliability during the diagnosis. The dataset of axillary lymph nodes from the breast cancer patients was collected from Erasmus Medical Center. A total of 1050 images were studied from the 850 patients during the years 2018 to 2021. For the independent test, data samples were collected for 100 images from 95 patients at national cancer institute. The existence of axillary lymph nodes was confirmed by pathologic examination. The feed forward, radial basis function, and Kohonen self-organizing are the artificial neural networks (ANNs) which are used to train 84% of the Erasmus Medical Center dataset and test the remaining 16% of the independent dataset. The proposed model performance was determined in terms of accuracy (Ac), sensitivity (Sn), specificity (Sf), and the outcome of the receiver operating curve (Roc), which was compared to the other four radiologists' mechanism. The result of the study shows that the proposed mechanism achieves 95% sensitivity, 96% specificity, and 98% accuracy, which is higher than the radiologists' models (90% sensitivity, 92% specificity, and 94% accuracy). Deep learning algorithms could accurately predict the clinical negativity of axillary lymph node metastases by utilizing images of initial breast cancer patients. This method provides an earlier diagnostic technique for axillary lymph node metastases in patients with medically negative changes in axillary lymph nodes.

Detection of fetal arrhythmia by adaptive single channel electrocardiogram extraction

Fetal arrhythmia, the abnormal heartbeat of a fetus is broadly classified as tachy arrhythmia (too fast > 160 beats/min) and brady arrhythmia (too slow < 120 beats/min). Detection of this irregular heart beat rhythm of the fetus during pregnancy is still a challenging task for the clinicians. Heart rate detection through electrocardiography has always been accurate for identifying cardiac defect in humans. Adult ECG has achieved several developments in the modern medicine whereas noninvasive fetal ECG (FECG) continues to be a big challenge. Automatic detection of fetal heart rate is vital for monitoring the unborn infant during pregnancy. The non-invasive placement of electrodes over the abdomen region of pregnant women records the ECG signal of both mother and fetus. The arrhythmia affected FECG signals (n = 14) are processed from the physionet database. This raw ECG signal is preprocessed using a Savitzky-Golay filter and symlet wavelet transform to remove the basic noises. Adaptive recursive least square filter is preferably chosen for extracting the FECG, using mother's thorax ECG as a reference. An accurate PQRST wave-shape of the FECG is required for the proper diagnosis of fetal cardiac defects. Using a single channel abdominal ECG signal, the proposed work generates extracted fetal ECG and an automated visual display of fetal heart rate. The presence of arrhythmia and fetal distress can be analyzed through fetal heart rate display and abnormal conductivity of PQRST wave respectively. We have analyzed fetal arrhythmias through ECG extraction and the same was compared with the echocardiograph results given by pediatric cardiologist. This study helps to identify the fetal distress at early gestational age that helps the obstetricians to make quick decisions before or immediately after delivery.

A New Meta Heuristic Based Segmentation for MRI Image

An automated brain tumor segmentation and detection have huge importance in the diagnostics of medical field as it renders information about functional structures in addition to the probable abnormal tissue required for surgical planning. However, it is still a problem due to low contrast and poorly-specified boundaries and accuracy issue. Hence, Refined Migrating Birds Optimization (RMBO) algorithm is introduced for automatic tumor segmentation that gets over the disadvantage of classical metaheuristic segmentation techniques. The RMBO helps in improving both migration and position update steps which includes three phases. First phase starts from Preprocessing, film artifacts and unnecessary areas (skull) of MRI images are eliminated with the help of enhanced tracking algorithm. Next and second phase being the procedure of eliminating the noises employing Anisotropic Filtering and contrast enhancement is carried out with the help of histogram equalization. Finally segmentation is performed employing RMBO. The novel algorithm operates on the image pixels information along with regions/neighborhood map to generate a contextual area where the merging is possible. With the RMBO algorithm, MRI of brain images are segmented and the results are analyzed through the comparison of the existing techniques viz., Particle Swarm Optimization (PSO), Genetic algorithms.

Red blood cells flows in rectilinear microfluidic chip

The red blood cells flow in a controlled environment as a microfluidic chip with a rectilinear geometry was investigated. The optical monitoring performed by an automatic Particle Image Velocimetry procedure has allowed a quantitative analysis on flow features. Various parameters such as velocity, shear rate, strain rate, vorticity, divergence were extracted. The comparisons of the results obtained from the different experiments was used for the overall understanding of the RBC movements in different conditions and the establishment of the analysis procedure.

Studies on visible light photocatalytic and antibacterial activities of nanostructured cobalt doped ZnO thin films prepared by sol-gel spin coating method

Nanostructured cobalt doped ZnO thin films were deposited on glass substrate by sol-gel spin coating technique and characterized by X-ray diffraction, X-ray photoelectron spectroscopy, field-emission scanning electron microscopy, energy-dispersive X-ray spectroscopy and UV-Vis spectroscopy. The XRD results showed that the thin films were well crystalline with hexagonal wurtzite structure. The results of EDAX and XPS revealed that Co was doped into ZnO structure. FESEM images revealed that the films possess granular morphology without any crack and confirm that Co doping decreases the grain size. UV-Vis transmission spectra show that the substitution of Co in ZnO leads to band gap narrowing. The Co doped ZnO films were found to exhibit improved photocatalytic activity for the degradation of methylene blue dye under visible light in comparison with the undoped ZnO film. The decrease in grain size and extending light absorption towards the visible region by Co doping in ZnO film contribute equally to the improved photocatalytic activity. The bactericidal efficiency of Co doped ZnO films were investigated against a Gram negative (Escherichia coli) and a Gram positive (Staphylococcus aureus) bacteria. The optical density (OD) measurement showed better bactericidal activity at higher level of Co doping in ZnO.

Facile synthesis of graphene-CeO2 nanocomposites with enhanced electrochemical properties for supercapacitors

Graphene-ceria (CeO2G) nanocomposites were prepared by using a low-temperature solution process with different weight percentages of graphene, and their electrochemical properties were investigated. Structural properties of the nanocomposites were studied by X-ray diffraction, Raman spectroscopy, and FTIR spectral analyses. FE-SEM and HRTEM images revealed a "wrinkled paper"-like morphology of the prepared composites. Elemental mapping images were recorded by using the FE-EPMA technique. XPS analyses revealed the binding states of different elements present in the composites. The composite with 5% graphene displayed a specific capacitance of 110 F g(-1), according to cyclic voltammetric studies, which is higher than that observed for pure CeO2 (75 F g(-1)). The significant increase in the specific capacitance suggests that the CeO2G is a promising material for supercapacitor applications.

Effect of solvents on the bulk growth of 4-aminobenzophenone single crystals: a potential material for blue and green lasers

Although 4-aminobenzophenone (4-ABP) is the best derivative of benzophenone with 260 times higher second harmonic generation (SHG) efficiency than potassium dihydrogen phosphate (KDP), growth of high quality bulk crystal still remains a difficult task. In the present work, the effect of solvents on solubility and growth aspects of 4-ABP was investigated to grow inclusion free 4-ABP crystals. The growth processes were discussed based on solute-solvent interaction in two different growth media of ethyl acetate and ethanol. The growth rate and thereby solvent inclusions are relatively higher in ethyl acetate grown crystal than the crystal grown from ethanol. The structural, thermal and optical properties of 4-ABP crystals were studied. The enthalpy of 4-ABP melting process was estimated from differential thermal analysis. The optical transmission study shows that 4-ABP crystals grown from ethanol has high transparency compared to ethyl acetate grown sample due to solvent inclusion in the later crystal.

Crystal growth, structural, thermal and mechanical behavior of l-arginine 4-nitrophenolate 4-nitrophenol dihydrate (LAPP) single crystals

Single crystals of l-arginine 4-nitrophenolate 4-nitrophenol dihydrate (LAPP) have been grown successfully from the solution of l-arginine and 4-nitrophenol. Slow evaporation of solvent technique was adopted to grow the bulk single crystals. Single crystal X-ray diffraction analysis confirms the grown crystal has monoclinic crystal system with space group of P21. Powder X-ray diffraction analysis shows the good crystalline nature. The crystalline perfection of the grown single crystals was analyzed by HRXRD by employing a multicrystal X-ray diffractometer. The functional groups were identified from proton NMR spectroscopic analysis. Linear and nonlinear optical properties were determined by UV-Vis spectrophotometer and Kurtz powder technique respectively. It is found that the grown crystal has no absorption in the green wavelength region and the SHG efficiency was found to be 2.66 times that of the standard KDP. The Thermal stability of the crystal was found by obtaining TG/DTA curve. The mechanical behavior of the grown crystal has been studied by Vicker's microhardness method.

Synthesis, growth, crystal structure and characterization of a new organic NLO crystal: L-lysine 4-nitrophenolate monohydrate (LLPNP)

L-lysine 4-nitrophenolate monohydrate (LLPNP) has been synthesized and grown by solution growth method at room temperature using deionised water as a solvent. The crystal structure of the materials was solved by single crystal X-ray diffraction analysis and it was found that the material has orthorhombic system. The crystallinity of the grown crystals was studied by the powder X-ray diffraction analysis. Molecular structure of the grown crystal was investigated by 1H NMR spectroscopy. The various functional groups of the sample were identified by Fourier transform infrared and Fourier transform-Raman spectroscopic analyses. Thermal stability of the grown crystal has been studied by Thermogravimetric and Differential thermal (TG&DTA) analysis. The optical absorption of the grown crystals has been ascertained by UV-Vis-NIR absorption studies. Second harmonic generation (SHG) efficiency of the material has been determined by Kurtz and Perry technique and the efficiency was found to be 4.45 and 1.4 times greater than that of standard KDP and urea samples, respectively.

Tailoring bismuth telluride nanostructures using a scalable sintering process and their thermoelectric properties

The size and phase of bismuth telluride nanocrystals were tailored using a sintering process, to enhance their thermoelectric properties.

Structural and optical properties of sol-gel synthesised Zn(1-x)Mg(x)O nanocrystals

Zn(1-x)Mg(x)O nanocrystals with various compositions (x = 0-0.1) were synthesised by sol-gel process using tri ethanol amine (TEA) as a capping agent. The structural properties of the prepared materials were studied by X-ray diffraction analysis. Un-agglomerated nanocrystals with spherical morphology were observed by scanning electron microscope (SEM). The presence of Mg in the Zn(1-x)Mg(x)O was confirmed by X-ray photoelectron spectroscopy (XPS). Moreover, the Mg composition relatively increases in the synthesised nanocrystals as it increases in the precursor solution. The optical absorption studies of the Zn(1-x)Mg(x)O samples show the blue shift from the pure ZnO due to the incorporation of Mg in ZnO lattice. The photoluminescence studies demonstrated that the intensity of defect related deep level emission increases drastically with increasing the x value from 0.02 to 0.08 and decreases sharply on further increase of Mg from 0.08 to 0.1. The mechanism for the enhanced green emission was explained based on the structural properties of the Zn(1-x)Mg(x)O samples.

Investigations on the growth aspects and characterization of semiorganic nonlinear optical single crystals of L-histidine and its hydrochloride derivative

Semiorganic single crystals of l-histidine and l-histidine hydrochloride monohydrate have been obtained in a single solution prepared from the mixture of l-histidine and hydrochloric acid in 1:2M ratio. Growth aspects of the single crystals have been discussed along with characterization studies. Crystal system and lattice parameters have been identified by X-ray diffraction analyses. It has been observed that the grown crystals possess orthorhombic system but with different set of lattice parameters. Presence of various functional groups has been identified and formation of two different crystals has been confirmed by Fourier transform infrared spectral analyses and FT-Raman studies. Linear and nonlinear optical properties have been studied by UV-Vis spectral analyses and Kurtz-Perry powder technique respectively. The thermal stability of the grown crystals was determined by thermal analyses. From the characterization studies it is found that both the crystals are useful for second harmonic generation applications.

Effect of zinc chloride on the growth and characterization of L-proline cadmium chloride monohydrate semiorganic NLO single crystals

Single crystals of zinc doped L-proline cadmium chloride monohydrate were successfully grown from aqueous solution by slow evaporation method at room temperature for different molar concentration of zinc chloride. The structural properties of grown crystals have been studied by single crystal X-ray diffraction, powder X-ray diffraction studies and Fourier transform infrared spectral analysis. The incorporation of the dopant (zinc chloride) into L-proline cadmium chloride monohydrate crystal lattice has been confirmed by EDAX analysis. UV-Vis spectral analyses showed that the doped crystals have lower UV cut-off wavelength at 200 nm combined with very good transparency about 85% in a very wide range. The second harmonic generation efficiency test has been carried out and results are discussed. The 0.2 and 0.4 mol Zinc chloride doped crystals were thermally stable up to 208.9 °C and 211.9 °C respectively. The electrical properties have been studied by dielectric constant studies. All results are compared with the results of pure L-PCCM crystals.

Optimization in Model Matching and Perceptual Organization

We introduce an optimization approach for solving problems in computer vision that involve multiple levels of abstraction. Our objective functions include compositional and specialization hierarchies. We cast vision problems as inexact graph matching problems, formulate graph matching in terms of constrained optimization, and use analog neural networks to perform the optimization. The method is applicable to perceptual grouping and model matching. Preliminary experimental results are shown.