Background: Several studies have reported that benzimidazole-based structures are used in the diagnosis of Alzheimer's disease. Various modified benzimidazole-based structures serve as radiotracers. Among them, 2-(4-(2-(fluoro-18F)ethyl)piperidin-1-yl)benzo[4,5]imidazo[1,2-a]pyrimidine or [18F]T808 is a prominent radiotracer for tau PET tracer. The synthesis was started with trichloroacetyl chloride and ethyl vinyl ether, the precursor synthesis was completed in 9 steps. The precursor facilitated the radiosynthesis of [18F]T808 in excellent yield with higher purity. Objective: We explored a radiotracer for diagnosing Alzheimer's disease, specifically a benzimidazole-based tau PET precursor. The goal was to synthesise and develop a semi-automated radiolabelling protocol of 2-(4-(2-(fluoro-18F)ethyl)piperidin-1-yl)benzo[4,5] imidazo[1,2-a] pyrimidine, resulting in a higher yield with shorter radiosynthesis time. Methods: The synthesis of the precursor started with Ethyl vinyl ether and trichloroacetyl chloride. All chemically synthesised compounds were characterised by 1H-NMR, 13C-NMR, and mass spectrometry. The synthesised precursor was used for the radiosynthesis of tau PET tracer [18F]T808 by the nucleophilic [18F]fluorination with K[18F]F/Kryptofix 2.2.2 in DMSO at 140 degrees C. This transformative process resulted in a crude radiolabeled product being purified through semipreparative high-performance liquid chromatography (HPLC) and solid phase extraction (SPE) in an isolated desired product. The synthesised radiotracer was analysed using analytical tools such as radio TLC, HPLC, pH, endotoxin, and half-life. Results: The precursor was successfully synthesised in 9 crucial steps with 80% yields, and '97% chemical purity. The synthesised precursor was used in the semi-automated radiosynthesis of [18F]T808. The radiolabelled desired product [18F]T808 was successfully achieved. The decaycorrected yield for [18F]T808 was approximately 45-50% at the end of synthesis, 40-45 min Conclusion: Our method resulted in tau PET tracer precursor synthesis of 65% yield with 97% chemical purity. The tau tracer was radiolabeled with 45-50% radiochemical purity of '98%. The analytical data match regulatory standards for being used as a PET tracer for clinical studies.

Glioma is a primary brain tumor type that is very aggressive and that necessitates proper timely detection so as to be handled effectively by the clinical practice. Our proposed approach is a deep learning-based object detection and classification system of detecting as well as classifying Glioma with automated localization and binary grading via multi-modal magnetic Resonance imaging (MRI) sequence. The proposed approach utilizes the experimentation done with the fusion combination of four MRI modalities, which include T1, T1 contrast-enhanced (T1CE), T2, and Fluid Attenuated Inversion Recovery (FLAIR) to take advantage of their respective anatomical and pathological properties of tumor regions. Modality-aware preprocessing and augmentation strategy is utilized and a YOLOv8 object detector model is trained using transfer learning to localize and classify tumours simultaneously achieving an accuracy of more than 99% with (T1C + T2 + Flair). Another test is a qualitative single-image test of inference, which also proves to be reliable in the localization of tumors and predicting tumor grades. The findings suggest that multimodal MRI fusion along with YOLOv8 can be an efficient and reliable computer-aided diagnosis (CAD) system to detect and grade glioma through automatic detection and grading of glioma and could be used with real-time clinical decision support.

A novel hybrid transfer learning approach called as "CovVoxTrada" was proposed for the COVID-19 positive patient's detection utilizing X-rays of Chest and CT scans. The CovVoxTrada is a hybrid model/approach which uses Voxnet and TraDaBoost models. Besides chest X-rays, this study also uses CT scans since CT's proved to be more reliable and accurate in identifying COVID-19 positive patients globally. The CT scan dataset was collected locally at Sanya MRI and CT scan center in Jabalpur, MP, India, while global chest X-rays dataset are also used. This hybrid approach, initially trains VoxNet model for feature extraction and then these features are employed for the training of the TraDaBoost model for performing binary classification. This study also illustrates the brief performance comparison in between the proposed model and additional widely used deep transfer learning models such as InceptionV3, VGG19, ResNet50 VGG16, YoloV9, which are trained on both the datasets. The CovVoxTrada yields 97% and 94.55% accuracy across the two datasets outperforming other hybrid and transfer learning architectures.

X-ray computed tomography (CT) is extensively used in medicine and research, often requiring iodine-based contrast agents which can cause adverse effects in iodine-intolerant patients. Considering safer alternatives, we have biosynthesized and comprehensively characterized highly fluorescent tin tungstate nanoparticles (SnWO₄ NPs) with a size of 40 nm, and compared their effectiveness as contrast agents in CT imaging with that of the commercially available OMNIPAQUETM Iohexol injection. The comparative analysis at 80 kVp showed that the highest CT numbers at 10 mg/ml were 2106 ± 101 for iodine and 1477 ± 40 for SnWO₄ NPs, while the lowest at 1 mg/ml were 63 ± 10 and 45 ± 13, respectively. The in vitro cytotoxicity of SnWO₄ NPs against HEK-293 cells, splenocytes, and thymocytes together with their biodistribution in healthy Wistar rats was evaluated revealing minimal toxicity. These findings indicate that SnWO₄ NPs hold significant promise for biomedical imaging applications, demonstrating excellent contrast performance and positioning them as strong candidates for future use as contrast agents.

Image processing is the recent trend in the computing, images play very crucial role in the field of engineering and technology. Many real-world applications used images as computation purpose. To find the high-resolution images still very challenging, due the capacity of the various acquisition devices, it is difficult to obtain the high-resolution images, still noise also present in the images. Various techniques for the image enhancement proposes by the various researchers to remove the noise present in the image. In this work generative adversarial network-based model is use here to improve image resolution. Adversarial network is the deep learning-based model which comprises various convolution layers, ReLU functions and normalization layers. GAN consists of discriminator and generator functions which is dedicated to perform different tasks. Single image super resolution-based GAN pretrained model used here to upscaling the images. This work upscale the different medical images with good PSNR values. All simulation performed in python environment with tensor flow and keras. The model training performs of colab with virtual GPU support.

Underwater crack classification is a crucial task in the maintenance and repair of submerged structures, such as pipelines, bridges, and offshore platforms. Finding and classifying cracks correctly prevent catastrophic failure and ensure the longevity of these structures. In the past few years, techniques like image processing and deep learning algorithms have been suggested to automate classifying the cracks on different structures such as buildings, pavements, and bridges. But there is still a scope to automate the process of underwater crack detection. presence of water can cause cracks to appear differently than they would in air, which can make it more challenging to accurately identify and classify them. The goal of these methods is to make it easier and more accurate to find and classify cracks while reducing the need for human intervention. This paper proposed improved EfficientNet-based lightweight crack classification model and a novel image dataset for underwater crack detection. Model performance evaluated by the performance metrics which gives 99

A novel two-dimensional (2D) multilayered material Ti 3 C 2 T x MXene has been synthesized for the first time in 2011 using hydrofluoric acid (HF) as an etchant. Since the discovery of Ti 3 C 2 T x , a variety of novel synthetic routes using different etching agents and intercalants have been developed for the fabrication of myriad new MXenes. Endowed with hydrophilic nature, easy large-scale synthesis in water, and low capacitance in turn high electrical conductivity, MXenes have shown a bright aspect for applications ranging from electrocatalysis, to energy storage, to electromagnetic shielding. Bulk of the MXenes have been synthesized by top-down approach including etching and exfoliation of parental layered compounds. The etching methods including HF as an etchants, in situ HF forming methods, molten salt method, alkali etching methods, and electrochemical methods were discussed in detail. In addition to this, few of the bottom-up approaches, namely chemical vapor deposition and plasma-enhanced pulsed laser deposition methods, have also gained substantial interest for synthesis of MXenes, which were also explained herein. Thus, in the present book chapter, development of various synthetic protocols along with reaction conditions over a certain time scale has been well summarized.

Objective:Biochemical recurrence (BCR) after initial management of Prostate Carcinoma (PC) is frequent. Subsequent interventions rely on disease burden and metastasis distribution. 68Ga prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) is an excellent imaging modality in BCR. However, 68Ga is radionuclide generator produced and has restricted availability. 99mTc-labeled PSMA could be a potential cost-effective alternative. We compared the performance of 99mTc-PSMA single-photon emission CT (SPECT)/CT and 68Ga-PSMA PET/CT in BCR with a serum prostate surface antigen (PSA) level of <20 ng/mL. Materials and Methods:The prospective study included 25 patients with BCR and at least one lesion on a 68Ga-PSMA PET/CT. All patients underwent 99 mTc-PSMA SPECT/CT, and disease distribution and metastatic burden were compared with 68Ga-PSMA PET/CT. The maximum standard uptake value (SUVmax) and the tumor-to-background ratio (TBR) were computed and analyzed. Results:The mean age and serum PSA (SPSA) were 69.72 ± 6.69 years and 5.65 ± 6.07 ng/mL. Eleven patients (44%) had SPSA ≤2 ng/mL. Recurrent sites were noted in the prostate (19, 76%), prostatic bed (3, 12%), and pelvis lymph nodes (LNs) (13, 52%). Distant metastasis to bones (13, 52%), lungs (5, 20%), and retroperitoneal LNs (2, 8%) were noted. Both modalities were concordant for the recurrent disease at the prostate, prostatic bed, bone, and lung lesions. 99mTc-PSMA could localize pelvis LNs in most patients (10/13, 76.9%). The site-specific sensitivity and specificity between the two modalities were not significantly different (P > 0.05). TBR shows excellent correlation with SUVmax (0.783, P < 0.001). Four (16%) patients were understaged with 99mTc-PSMA due to the nonvisualization of the subcentimeter size LNs. No patient with systemic metastases was understaged. Conclusions:99mTc-PSMA SPECT/CT has good concordance with 68Ga-PSMA PET/CT in BCR, even at low PSA levels. However, it may miss a few subcentimeter LNs due to lower resolution. 99mTc-PSMA SPECT/CT could be a simple, cost-effective, and readily available imaging alternative to PET/CT.

In today’s digital epoch, the notion of the Internet of Things (IoT) is widely engaged in delivering a variety of services. Internet technologies are highly used for online communication. Hence, the validity of digital media and copyright safeguard techniques are extremely required. For authenticity and to protect copyright data from unlawful access, an entropy-based watermarking technique is proposed here. The Y section of the color space is employed to place secret digital information. Y channel block having the highest entropy belonging to the host image is employed to embed the watermark using scaling factor (α). The dual scrambling method is used for watermark security. To judge the effectiveness of the projected technique, various image quality and security assessment parameters like PSNR, SSIM, and NCC are used.

Herein, we have synthesized an ESIPT inbuilt novel tripodal gelator TH-AIL, which upon dissolution in DMSO followed by the addition of water (1 : 1) leads to the formation of a unique orange fluorescent organohydrogel (0.35% w/v, OHG). The obtained OHG reveals responses towards base NH3 and acid HCl by way of reversible change in fluorescence colour from orange to green along with restorable conversion from gel to sol phase.

Li+-enriched metallohydrogel (MG-Co) has been synthesized via in situ LiOH deprotonation of the pre-gelator (H9SAL) followed by coordination with Co2+ to develop a pure gel electrolyte and electrode material without adding any external dopant to the gel matrix. The electrochemical performance of MG-Co as an electrolyte and electrode material has shown promising features to be utilized in supercapacitor applications.

AIM:Efficient synthesis of precursor from commercially available starting materials and automated radiosynthesis of [11C]PiB using commercially available dedicated [11C]- Chemistry module from the synthesized precursor. BACKGROUND:[11C]PiB is a promising radiotracer for PET imaging of β-Amyloid, advancing Alzheimer's disease research. The availability of precursors and protocols for efficient radiolabelling foster the applications of any radiotracer. Efficient synthesis of PiB precursor was performed using anisidine and 4-nitrobenzoyl chloride as starting materials in 5 steps, having addition, substitutions, and cyclization chemical methodologies. This precursor was used for fully automated radiosynthesis of [11C]PiB in a commercially available synthesizer, MPS-100 (SHI, Japan). The synthesized [11C]PiB was purified via solid-phase methodology, and its quality control was performed by the quality and safety criteria required for clinical use. METHODS:The synthesis of desired precursors and standard authentic compounds started with commercially available materials with 70-80% yields. The standard analytical methods were characterized all synthesized compounds. The fully automated [11C]-chemistry synthesizer (MPS-100) used for radiosynthesis of [11C]PiB with [11C]CH3OTf acts as a methylating agent. For radiolabelling, varied amounts of precursor and time of reaction were explored. The resulting crude product underwent purification through solid-phase cartridges. The synthesized radiotracer was analyzed using analytical tools such as radio TLC, HPLC, pH endo-toxicity, and half-life. RESULTS:The precursor for radiosynthesis of [11C]PiB was achieved in excellent yield using simple and feasible chemistry. A protocol for radiolabelling of precursor to synthesized [11C]PiB was developed using an automated synthesizer. The crude radiotracer was purified by solid-phase cartridge, with a decay-corrected radiochemical yield of 40±5% and radiochemical purity of more than 97% in approx 20 minutes (EOB). The specific activity was calculated and found in a 110-121 mCi/μmol range. CONCLUSION:A reliable methodology was developed for preparing precursor followed by fully automated radiolabeling using [11C]MeOTf as a methylating agent to synthesize [11C]PiB. The final HPLC-free purification yielded more than 97% radiochemical purity tracer within one radionuclide half-life. The method was reproducible and efficient for any clinical center.

This paper compares the time complexity of various sorting algorithms for the logic, code and time complexity of each algorithm. The sorting algorithms that this paper discusses are Selection sort, Bubble sort, Insertion sort, Quick sort and Merge sort. The algorithms execution times are calculated using the C++ chrono library. Each algorithms have different formats and their own pros and cons. This paper presents a study of how these different algorithms work and compares them on the basis of their execution time in different input size to reach a conclusion.

Computer vision enables to detect many objects in any scenario which helps in various real time application but still face recognition and detection remains a tedious process due to the low resolution, blurriness, noise, diverse pose and expression and occlusions. This proposal develops a novel scrupulous Standardized Convolute Generative Adversarial Network (SCGAN) framework for performing accurate face recognition automatically by restoring the occluded region including blind face restoration. Initially, a scrupulous image refining technique is utilised to offer the appropriate input to the network in the subsequent process. Following the pre-processing stage, a Caffe based Principle Component Analysis (PCA) filtration is conducted which uses convolutional architecture for fast feature embedding that collects spatial information and significant differentiating characteristics to counteract the loss of information existing in pooling operations. Then a filtration method identifies the specific match of the face based on the extracted features, creating uncorrelated variables that optimise variance across time while minimising information loss. To handle all the diversification occurring in the image and accurately recognise the face with occlusion in any part of the face, a novel Standardized Convolute GAN network is used to restore the image and recognise the face using novel Generative Adversarial Network (GAN) networks are modelled. This GAN ensures the normal distribution along with parametric optimization contributing to the high performance with accuracy of 96.05% and Peak Signal to Noise Ratio (PSNR) of 18 and Structural Similarity Index Metric (SSIM) of 98% for restored face recognition. Thus, the performance of the framework based on properly recognizing the face from the generated images is evaluated and discussed.

This is the Era where no. of customers are increases day by day in every business [1] and Customer have more than one choice in each and every aspect whether it is financial, governmental, organizational etc. In this project we are mainly discuss about the customer churn prediction in Banking sector. Customer churn is one of the problem of banking sector where industries are not able to hold their customers due to several fluctuating reasons such as better services at lower cost, bank location etc [2]. Hence Maintaining a good relationship with customers is crucial because it costs more to attract new ones than it does to retain existing ones in today's market[3]. Through this Research we want to proposed the solution of this problem using Machine learning (ML) approach. In Our Research work we applied many ML or DL algorithms such as Linear Regression, Logistic Regression, SVM, Artificial Neural Network, Random Forest classifier etc on Churn Modelling Bank dataset to predict the Probability of customer who are going to be Exited. This prediction helps the banking sector to identify the factors that leads the customer to be Exited so that they are able to improve the relationship with the customers. At the end of our research work we finally reach to the conclusion that Random Forest classifier predicts more accurate result compared to other ML or DL algorithms. Random Forest Classifier predicts the result with the test accuracy of 86.05 % without handling imbalanced data, 95.16% after oversampling with duplicate data, 89.548% after SMOTE oversampling, 74.69% after under sampling. A significant limitation of our model is its lack of training on real-time data. Instead, it relies solely on the Kaggle Bank churn dataset for its learning. Real-time data often presents dynamic and evolving patterns that might differ from those captured in the static dataset. The result and performance of the models may be further improved by using some other algorithms or by increasing the no. of hidden layers in ANN or by using Real Time Dataset.

Medical image processing has a significant role in clinical investigation and recent medical research. An appropriate image-based medical assessment helps to analyze or detect critical diseases early, as it has a high value of medical information. In this study, medical imaging is reviewed for the diagnosis of eye diseases using computational intelligence. However, the identification of these diseases using traditional image processing is quite complicated. Nowadays, various machine learning and deep learning approaches are developed for the detection of different eye diseases which are helpful for the detection of the diseases at an early stage. Research showed that eye disorders are more serious in emerging or underdeveloped nations due to inadequate healthcare facilities and skilled health workers. An estimate of 45 million people around the world are blind and the tragic fact is that only 75% of these cases are curable. Moreover, the doctor-patient ratio around the globe is about 1: 10,000. Therefore, it takes an hour to create a screening system for the identification of these illnesses. Ophthalmology is close to making breakthroughs in evaluating, diagnosing, and treating eye diseases. Additionally, many eye and vision problems show no obvious signs. As a consequence, people are often unaware that problems exist. Early detection of diseases is a primary concern as they could be easily cured before leading to severity. This research paper focuses on detecting eye illnesses, such as Diabetic retinopathy, Diabetic Macular Edema, Glaucoma, Age macular Degeneration, Retinal Vascular Occlusions, and Retinal Detachment. The authors explore various algorithms, imaging modalities, and challenges in this context. The study aims to raise awareness about eye disorders leading to blindness using computer vision, image processing, and deep learning techniques. It also investigates how these machine learning and deep learning approaches can aid in early disease diagnoses for effective treatment before vision loss occurs.

Touchless fingerprint recognition is becoming increasingly popular as biometric authentication in terms of both ease and cleanliness. Furthermore, they offer advantages in terms of speed, robustness, and flexibility in challenging circumstances while also meeting the increasing need for touchless technologies in a post-COVID-19 era. These touchless fingerprint images have a unique quality that sets them apart from traditional ink-based and live-scan fingerprints. Existing touch-based fingerprint matchers often struggle to extract reliable minutiae features due to differences in contrast, illumination, and magnification. In contrast to touch-based systems, which have their own set of problems, such as the existence of latent fingerprints or deformation brought about by pressing fingers over a sensor surface, touchless acquisition processes have none of these problems. In this paper, a novel Dual-Cross Generative Adversarial Networks framework with Capsule Networks-based PCA filtration is proposed to accurately recognize the touchless fingerprint. In the proposed model, Capsule network-based PCA filtration is utilized for fast feature embedding with a convolutional architecture to collect spatial information. To handle all the diversification, Dual-Cross Generative Adversarial Networks is modeled to restore and recognize the fingerprint . The performance of the proposed system is assessed using two widely recognized datasets (the PolyU Cross dataset and the Benchmark 2D/3D dataset). The experimental results show that the proposed system achieves an accuracy of 99.51% and 99.13%, respectively, and significantly reduces the Equal Error Rate compared to the baseline.

Diabetes affected millions of individuals till now, up from 108 million in past years, and the ratio is increasing daily. Age-specific diabetes mortality rates increased exponentially. Blindness is frequently brought on by diabetes. With medication, routine screening problems, and treatment for any that arise, diabetes can be controlled and its effects postponed or averted. Therefore, for earlier detection of diabetes-based disease, Diabetic Macular Edema is diagnosed using transfer learning deep models. The transfer learning is used on the pre- trained EfficientNetBO and ResNet50 models. The CNN layer and hyperparameters are added to these models to combat overfitting. Moreover, the dataset is well pre-processed and augmented using specific parameters to avoid misclassification and better model training. The work in this paper does categorical classification instead of binary classification, which makes the patient clearer about the severity of the disease. The models are trained and evaluated on MESSIDOR and IDRID diabetic macular edema publicly available datasets. This work has been observed to be more effective than other published work on this disease.