Prashant Johri

We are grateful to Dr. Pastore for his thoughtful comments

The prognosis and severity of kidney cancer significantly impact the chances of recovery, necessitating accurate and timely diagnostic methods. However, manual segmentation remains a challenging and time-consuming task. In order to overcome these challenges, a novel Deep Learning (DL)-based segmentation framework, which integrates pre-processing and segmentation stages. Initially, the quality of the images is improved by the probabilistic Wiener filter and statistical HU windowing mechanism. A novel Bidirectional Recurrent Gated Vision Transformer (Bi-ReGaViT) approach is introduced for precise kidney and tumor segmentation. Finally, the hyperparameters in the classifier models are fine-tuned using the Enhanced Elk Herd Optimization Algorithm (EEHOA), which improves model accuracy significantly. The effectiveness of the proposed approach is validated using the KiTS19 dataset, which demonstrates a superior segmentation performance with a Dice Similarity Coefficient (DSC) of 94.89%, accuracy of 97.4% and sensitivity of 96.0%. For the CT kidney dataset, the proposed model has obtained an accuracy of 98.3%. The experimental results confirm that the proposed model enhances segmentation accuracy, robustness and computational efficiency, making it a promising tool for clinical kidney cancer diagnosis. The proposed model can be integrated into a Computer-Aided Diagnosis (CAD) system to assist radiologists in real-time kidney tumor detection, reducing manual efforts and improving diagnostic accuracy. This approach can also be deployed in automated surgical planning systems to improve precision in robotic-assisted kidney surgeries.

Medical image segmentation plays a critical role in the field of medical image processing. Precisely delineating brain tumor areas from multimodal MRI scans is crucial for clinical diagnosis and predicting patient outcomes. However, challenges arise from similar intensity patterns, varying tumor shapes, and indistinct boundaries, which complicate brain tumor segmentation. Traditional segmentation networks like UNet face difficulties in capturing comprehensive long-range dependencies within the feature space due to the limitations of CNN receptive fields. This limitation is particularly significant in tasks requiring detailed predictions such as brain tumor segmentation. Inspired by these constraints, this study suggests incorporating EfficientNet as an encoder within UNet, with a thorough reassessment of its fundamental components: the encoder, bottleneck, and skip connections. EfficientNet replaces UNet’s encoder, initially frozen to retain learned features from pre-trained weights, adept at extracting detailed features crucial for precise segmentation like brain tumors from MRI scans. Preserving UNet’s bottleneck compresses EfficientNet’s outputs, while skip connections maintain spatial integrity during decoder upsampling. The decoder reconstructs the original image size by merging encoder-decoder features, refining boundaries with convolutional layers for accurate clinical insights.The study conducted multiclass operations on the Brain-Tumor.npy dataset from Kaggle, consisting of 3064 T1-weighted contrast-enhanced images from 233 patients with meningioma (708 slices), glioma (1426 slices), and pituitary tumor (930 slices). Experimental findings in brain tumor segmentation tasks show that the proposed model achieves performance on par with or better than recent CNN or Transformer models. Specifically, the model achieves an accuracy of 0.9925 and a loss of 0.2991 on the dataset.

This paper proposes a combined framework of CNN+RFC to brain tumor categorization/classification using MRI (Magnetic-Resonance Imaging) images, which combines both CNN (Convolution Neural Networks) and RFC (Random Forest Classification). Preprocessing, Feature bring-out, and Categorization are the three phases of the proposed framework. In the first step, we use the Gaussian Filter Method on the data set then we combine the original data set with processed data in parallel. The feature extraction of magnetic resonance imaging was performed automatically by CNN in the second step. We also called such a type of process in this paper as non-hand-crafted feature extraction. Several classification algorithms, including RFC (Random Forest Classifier), KNN (K-Nearest Neighbor Classifier), DT (Decision Tree Classifier), SVM (Support Vector Machine Classifier), and NB (Naïve Bayes Classifier), are used in the final step. The extracted features from the CNN model are then given to the classifier algorithms, which predict Glioma tumor, Pituitary tumor, Meningioma tumor, and no tumor as a result of the testing data set. Experiments are carried out on an open data set of images selected for classification from the Kaggle databases. This data set is very complex since it contains images of brain tumor with different angles and different depths. We don't alter this data set at all. We make a separate CSV file that contains testing images' name and their specification. Using this proposed approach, we were able to achieve 99.61% accuracy on the training data set, 92.16% on the validation data, and 71.2% on the CSV/testing data.

Brain tumor diagnosis is a complex task due to the intricate anatomy of the brain and the heterogeneity of tumors. While magnetic resonance imaging (MRI) is commonly used for brain imaging, accurately detecting brain tumors remains challenging. This study aims to enhance brain tumor classification via deep transfer learning architectures using fine-tuned transfer learning, an advanced approach within artificial intelligence. Deep learning methods facilitate the analysis of high-dimensional MRI data, automating the feature extraction process crucial for precise diagnoses. In this research, several transfer learning models, including InceptionResNetV2, VGG19, Xception, and MobileNetV2, were employed to improve the accuracy of tumor detection. The dataset, sourced from Kaggle, contains tumor and non-tumor images. To mitigate class imbalance, image augmentation techniques were applied. The models were pre-trained on extensive datasets and fine-tuned to recognize specific features in MRI brain images, allowing for improved classification of tumor versus non-tumor images. The experimental results show that the Xception model outperformed other architectures, achieving an accuracy of 96.11%. This result underscores its capability in high-precision brain tumor detection. The study concludes that fine-tuned deep transfer learning architectures, particularly Xception, significantly improve the accuracy and efficiency of brain tumor diagnosis. These findings demonstrate the potential of using advanced AI models to support clinical decision making, leading to more reliable diagnoses and improved patient outcomes.

Software has emerged as an indispensable part of everyday existence in the increasingly digital age, impacting everything from healthcare to finance to transportation to industries. Given the increasing reliance on software, ensuring it is reliable and safe is crucial. Discovering and fixing vulnerabilities is crucial for sustaining the security and dependability of software. Numerous issues, including illegal accessibility, data breaches, and service interruptions, may result from these vulnerabilities. Software updates are applied by patching to address vulnerabilities, increase functionality, or improve performance. Adopting best practices for patching and vulnerability management can significantly lower security risks and improve the overall resilience of software environments despite certain limitations. Very few attempts have been made to model vulnerability Patch models (VPMs), even though Vulnerability Discovery Modeling (VDM) has been modeled based on the impact of vulnerabilities discovered over time, which help software vendors identify security trends, forecast security investments, and plan patches. The proposed modeling framework, which includes vulnerability discovery modeling and vulnerability Patch modeling, is designed to provide a comprehensive understanding of the patch management workflow. This paper also introduces a new modeling framework in the context of Patch. A statistical analysis has been conducted utilizing patch datasets to demonstrate the proposed systematic layout, providing a solid foundation for the research findings.

The critical role of wireless communication in the context of the Internet of Things (IoT) and its impact on modern sensor networks. As the world becomes increasingly interconnected, the proliferation of IoT devices and sensors has revolutionized various industries, enabling unprecedented data collection and analysis for smarter decision-making. This chapter delves into the fundamental principles and challenges of wireless communication in IoT sensor networks. It presents an overview of various wireless technologies employed in IoT, such as Wi-Fi, Bluetooth, Zigbee, LoRa, and NB-IoT, comparing their strengths and weaknesses to optimize sensor communication. Furthermore, the chapter highlights the importance of security and privacy in IoT sensor communication, providing insights into encryption techniques and authentication protocols to safeguard sensitive data from potential threats and breaches. Through an exploration of real-world applications, this chapter highlights the practical implementation of IoT sensor communication using wireless technology in domains like smart cities, healthcare, agriculture, and industrial automation. Overall, this chapter provides a comprehensive understanding of how wireless technology serves as a backbone for efficient and scalable communication among IoT sensors, unlocking the full potential of the Internet of Things in the modern era.

Throughout this work, an apparatus that uses machine learning, image manufacturing, or Connectivity to track riverbed water levels is given. By using the processing of images, wherein boundary detection technology is used to analyze both pictures acquired using a television camera, such an approach is designed to determine the level of a shoreline and the level of the stream. The stream's water grade plus the shoreline rating are compared to calculate the flood intensity rating. The storm's intensity was then uploaded to an Internet of Things system. Once the water's intensity exceeded a specific critical level, a notice was delivered to the public via the popular social networking site Telegram. Within the aforementioned architecture gadget, a Banana Pi 3 B variant is employed as both a controlling device and a camera using the Banana Pi 5MP cameras package. Ubidots is an Internet of Things system that is employed, and it allows for user notification. Our work's major contributions focus on integrating image processing using Internet of things clouds to create an advanced flood tracking device in response to warming temperatures by identifying the flooding extent and warning individuals about the flooding harshness condition. According to experimental findings, combining machine vision using machine learning for image analysis using the Internet of Things Cloud infrastructure is a realistic strategy. In order to determine the liquid level versus bank straight, the paper compares the creepy-edge detection approach and reaching the point technique. To determine whether this device might function in the real world, it was additionally tested in both lab (indoor) as well as outdoor environments.