Breast cancer is a crucial reason for death in females. Early recognition of this disease with the assistance of mammography reduces the death rate. Deep learning (DL) is an approach being utilized ...and requested by radiologist that assists them in making an accurate diagnosis and helps to improve outcome predictions. This paper includes a new approach, applied on the Mini-MIAS dataset of 322 images, involving a pre-processing method and inbuilt feature extraction using K-mean clustering for Speed-Up Robust Features (SURF) selection. A new layer is added at the classification level, which carries out a ratio of 70% training to30% testing of the deep neural network and Multiclass Support Vector Machine (MSVM). The outcome described here demonstrates that the accuracy rate of the proposed automated DL method using K-mean clustering with MSVM is better than using a decision tree model. Experimental results show that the average accuracy (ACC) rates of the three classes, i.e., normal, benign and malignant cancer, using the proposed method are95%, 94% and 98%, respectively. The increased sensitivity rate is 3%, specificity is 2%, and Receiver Operating Characteristics (ROC) area is 0.99 using SVM compared to the Multi-Layer Perception (MLP) and J48+K-mean clustering WEKA manual approach. A 10-fold cross validation was used, and the obtained results for the Support Vector Machine (SVM), K-nearest neighbour (KNN), linear discriminant analysis (LDA) and Decision Tree were 96.9%, 93.8%, 89.7% and 88.7%, respectively.
From the month of December-19, the outbreak of Coronavirus (COVID-19) triggered several deaths and overstated every aspect of individual health. COVID-19 has been designated as a pandemic by World ...Health Organization. The circumstances placed serious trouble on every country worldwide, particularly with health arrangements and time-consuming responses. The increase in the positive cases of COVID-19 globally spread every day. The quantity of accessible diagnosing kits is restricted because of complications in detecting the existence of the illness. Fast and correct diagnosis of COVID-19 is a timely requirement for the prevention and controlling of the pandemic through suitable isolation and medicinal treatment. The significance of the present work is to discuss the outline of the deep learning techniques with medical imaging such as outburst prediction, virus transmitted indications, detection and treatment aspects, vaccine availability with remedy research. Abundant image resources of medical imaging as X-rays, Computed Tomography Scans, Magnetic Resonance imaging, formulate deep learning high-quality methods to fight against the pandemic COVID-19. The review presents a comprehensive idea of deep learning and its related applications in healthcare received over the past decade. At the last, some issues and confrontations to control the health crisis and outbreaks have been introduced. The progress in technology has contributed to developing individual’s lives. The problems faced by the radiologists during medical imaging techniques and deep learning approaches for diagnosing the COVID-19 infections have been also discussed.
Lung abnormality is becoming the most widespread illness in individuals of the entire age group. This ailment can occur because of several causes. Recently, the novel disease, widely known as ...COVID-19, originated from the severe acute respiratory syndrome coronavirus-2, that can be stated as an outbreak by the World Health Organization. Detecting COVID-19 in its early stage becomes crucial for suppressing the epidemic it has triggered. In this proposed work, a CNN-based transfer learning approach for the screening of the outbreak of COVID-19. The central principle of this approach is to develop a computerized framework to help medical organizations, mainly in regions where fewer skilled employees are available. The proposed work explores the potential of pre-trained model architectures for the automatic identification of COVID-19 infection from lung CT images. First, in the data preparation, discrete wavelet transform is applied for three-level image decomposition, and then wavelet-based denoising is implemented on the training data sample using the VisuShrink algorithm. Second, data augmentation is done by applying zoom, change in brightness, height-width shifting, shearing, and rotation operations. Thirdly, the work is implemented by implementing the fine-tuned modified MobileNetV2 model in which 80% of CT images have been preferred for model training purpose, and 20% of images are selected for validation purposes. The overall performance of the pre-trained models is estimated by calculating several parametric outcomes. The outcome of the investigational analysis proves that the MobileNetV2 pre-trained CNN model obtained improved classification outcomes with 93.59% accuracy, 100% sensitivity, 87.25% specificity, 88.59% precision, 93.95% F1-score, 100% NPV, and AUC of 93.62%. In addition, the comparison of various CNN models such as Xception, NASNetLarge, NASNetMobile, DenseNet121, DenseNet169, DenseNet201, InceptionV3, and InceptionResNetV2 have been considered for experimentation analysis.
Magnesium aluminate spinel (MgAl
2
O
4
) (MAO) was fabricated by sol–gel process and sintered at a temperature ranging from 700 to 1400 °C. The phase development of MAO was confirmed by X-ray ...diffraction (XRD), Fourier transfer infrared spectroscopy (FTIR), and scanning electron microscopy. The XRD data confirms the formation of MAO spinel. FTIR analysis matches well with XRD data. The obtained results show that the optimized phase and morphology of the prepared nanoparticles were achieved at 1100 °C. The optical behavior of MAO was investigated using UV–Vis spectroscopy (UV–Vis) and fluorescence spectroscopy. Down-conversion energy transition from UV to visible light had been studied with three different excitations, 351 nm, 395 nm, and 405 nm. The material's color purity and CIE coordinates indicate that it is ideal for optoelectronic applications.
Cellulases convert lignocellulosic biomass into fermentable sugars which further act as substrate for ethanol production. Our previous research was focused on enzymatic hydrolysis of rice straw by ...free cellulases for production of fermentable sugars. Immobilization is a powerful tool to increase the stability and reusability of cellulases besides improving the economy of ethanol production process from rice straw. In the present study, cellulase produced from
Aspergillus fumigatus
was immobilized on magnetic nanoparticles by using glutaraldehyde cross linker with a binding efficiency of 65.55%. The electron microscopy and spectroscopy tools confirmed the enzyme immobilization process on magnetic nanoparticles. The immobilized cellulase exhibited filter paper, carboxymethyl cellulase and cellobiase activities of 11.82, 21.36 and 10.81 IU, respectively. The free and immobilized cellulase exhibited identical pH optima (pH 5.0) while different temperature optima of 50 °C and 60 °C, respectively. The immobilized enzyme retained 56.87% of its maximal activity after 6 h of pre-incubation at 60 °C. K
m
(Michaelis constant) and V
max
(maximum velocity) of immobilized enzyme were 11.76 mM and 1.17 μmol min
−1
ml
−1
, respectively. The immobilized cellulase hydrolysed pre-treated rice straw with saccharification efficiency of 52.67%. Further, it could be reutilized for up to four saccharification cycles with retention of 50.34% activity. Therefore, the improved properties of magnetic nanoparticle-immobilized cellulase and its reusability benefits offer a promising potential for industrial production of fermentable sugars and ethanol from rice straw.
Graphical abstract
The growing environmental concerns due to the excessive use of non-renewable petroleum based products have raised interest for the sustainable synthesis of bio-based value added products and ...chemicals. Recently, nanocellulose has attracted wide attention because of its unique properties such as high surface area, tunable surface chemistry, excellent mechanical strength, biodegradability and renewable nature. It serves wide range of applications in paper making, biosensor, hydrogel and aerogel synthesis, water purification, biomedical industry and food industry. Variations in selection of source, processing technique and subsequent chemical modifications influence the size, morphology, and other characteristics of nanocellulose and ultimately their area of application. The current review is focused on extraction/synthesis of nanocellulose from different sources such as bacteria and lignocellulosic biomass, by using various production techniques ranging from traditional harsh chemicals to green methods. Further, the challenges in nanocellulose production, physio-chemical properties and applications are discussed with future opportunities. Finally, the sustainability of nanocellulose product as well as processes is reviewed by taking a systems view. The impact of chemicals, energy use, and waste generated can often negate the benefit of a bio-based product. These issues are evaluated and future research needs are identified.
Display omitted
Acquisition of the standard plane is the prerequisite of biometric measurement and diagnosis during the ultrasound (US) examination. Based upon the analysis of existing algorithms for ...the automatic fetal development measurement, a new algorithm known as Neuro-Fuzzy based on genetic algorithm is developed. Firstly, the fetal ultrasound benchmark image is auto-pre-processed using Normal Shrink Homomorphic technique. Secondly, the features are extracted using Gray Level Co-occurrence Matrix (GLCM), Grey Level Run Length Matrix (GLRLM), Intensity Histogram (IH) and Rotation Invariant Moments (IM). Thirdly, Neuro-Fuzzy using Genetic approach is used to distinguish among the fetus growth as abnormal or normal. Experimental results using benchmark and live dataset demonstrate that the developed method achieves an accuracy of 97% as compared to the state-of- art methods in terms of parameters such as Sensitivity, Specificity, Recall, F-Measure &Precision Rate. The use of area under the receiver of characteristics(AUC) and confusion matrix as assessment indicators is also cross-validated using various classification methods by achieving best accuracy rate of Support Vector Machine (SVM) i.e. 98.7% as compare to other classification methods such as KNN, Ensemble methods, Linear Discriminant Analysis(LDA) and Decision Tree whereas ROC curve covers 0.9992 SVM.
In the fields of medico-legal matters and bio-archaeological settings, gender evaluation plays a pivotal role in the initial stages of human identification. Approximately half of the population at ...risk is excluded when gender is determined, making it the most essential factor for identification. When it comes to medico-legal matters and bio-archaeological settings, gender evaluation is a crucial initial step in human identification. Traditional gender determination procedures, such as skull and pelvic analysis, may be hindered by fragmentary human remains that have been degraded by various forms of inhumation or physical assaults.
To investigate sexual dimorphism, this study examined the ratio of index finger length to ring finger length.
The lengths of the index and ring fingers were measured and the ratios between them were calculated for both hands separately. Applications of IBM SPSS Statistics for Windows, Version 16.0 (Released 2007; IBM Corp., Armonk, New York, United States) included Student's t-test and Levene's test.
According to the study, women's index finger-to-ring finger length ratios were much longer than men's. The ratio of index finger to ring finger length was significantly different between the sexes on both sides of the hand (p<0.001). In terms of the right hand, the threshold value was 0.9666 for men and 0.9952 for females, while in terms of the left hand, the values were 0.9638 and 0.9920, respectively.
With an advancing front in this arena on gender determination, the use of digits has become an additional source of support to physical anthropologists for bio-archaeological surveys and to forensic experts for use in medico-legal investigations for fragmentary remains received during investigatory trials.
Cancer is becoming the most toxic ailment identified among individuals worldwide. The mortality rate has been increasing rapidly every year, which causes progression in the various diagnostic ...technologies to handle this illness. The manual procedure for segmentation and classification with a large set of data modalities can be a challenging task. Therefore, a crucial requirement is to significantly develop the computer-assisted diagnostic system intended for the initial cancer identification. This article offers a systematic review of Deep Learning approaches using various image modalities to detect multi-organ cancers from 2012 to 2023. It emphasizes the detection of five supreme predominant tumors, i.e., breast, brain, lung, skin, and liver. Extensive review has been carried out by collecting research and conference articles and book chapters from reputed international databases, i.e., Springer Link, IEEE Xplore, Science Direct, PubMed, and Wiley that fulfill the criteria for quality evaluation. This systematic review summarizes the overview of convolutional neural network model architectures and datasets used for identifying and classifying the diverse categories of cancer. This study accomplishes an inclusive idea of ensemble deep learning models that have achieved better evaluation results for classifying the different images into cancer or healthy cases. This paper will provide a broad understanding to the research scientists within the domain of medical imaging procedures of which deep learning technique perform best over which type of dataset, extraction of features, different confrontations, and their anticipated solutions for the complex problems. Lastly, some challenges and issues which control the health emergency have been discussed.
•In the systematic survey, the contribution is to examine the five types of cancer by applying deep learning-based segmentation and classification techniques utilized for diagnostic purposes.•It focusses on the inclusion and exclusion criteria to be performed by Preferred Reporting Items for Systematic Reviews and Meta-analysis technique.•This technique can be widely used by utilization of several pre-trained CNN models along with different benchmark datasets for each cancer type.•Several research questions (RQs) have taken under considerations to identify the different applications for multi-organ cancer and their state-of-the-art outcomes, which obtained by CNN pre-trained models.•At last, it will allow to assemble the results by comparing different outcomes related to the CNN techniques. Moreover, several challenges and future directions have been considered for the better outcome.