Twenty-one intracranial hemorrhagic lesions were imaged at 0.15 and 0.6 T using inversion recovery (IR), spin echo (SE), and multiple SE (Carr-Purcell-Meiboom-Gill, CPMG) pulse sequences. Two subarachnoid hemorrhages (SAH), nine acute intraparenchymal hemorrhages (IPH), ten chronic IPH, and one subdural hematoma were studied. Acute SAH could not be identified on the T1-weighted, IR images but was clearly seen on a T2-weighted, CPMG image. Acute (7 days or less) intraparenchymal hematoma showed signal intensity on IR and CPMG images similar to white matter. The T1 and T2 times of acute intraparenchymal hematoma were also similar to white matter. Some small acute hematomas could not be distinguished from white matter on IR and CPMG images. Acute hemorrhagic tissue showed image intensities and relaxation times similar to gray matter. All acute hemorrhages were identified on CT. Chronic IPH lesions (14 days or more) showed high signal intensity, greater than white matter, on IR, SE, and CPMG images. The T1 of the chronic lesions was similar to the acute lesions but T2 was significantly longer (p less than 0.05). Available evidence suggests that the nonspecificity of acute IPH signal and relaxation times may not be restricted to our pulse sequences or magnetic field strengths.

NMR imaging of intracranial hemorrhage

With time, AI technologies have matured well and resonated in various domains of applied sciences and engineering. The sub-domains of AI, machine learning (ML), deep learning (DL), and associated statistical tools are getting more attention. Therefore, various machine learning models are being created to take advantage of the data available and accomplish tasks, such as automatic prediction, classification, clustering, segmentation and anomaly detection, etc. Tasks like classification need labeled data used to train the models to achieve a reliable accuracy. This study shows the systematic review of promising research areas and applications of DL models in medical diagnosis and medical healthcare systems. The prevalent DL models, their architectures, and related pros, cons are discussed to clarify their prospects. Many deep learning networks have been useful in the field of medical image processing for prognosis and diagnosis of life-threatening ailments (e.g., breast cancer, lung cancer, and brain tumor, etc.), which stand as an error-prone and tedious task for doctors and specialists when performed manually. Medical images are processed using these DL methods to solve various tasks like prediction, segmentation, and classification with accuracy bypassing human abilities. However, the current DL models have some limitations that encourage the researchers to seek further improvement.

The state of the art of deep learning models in medical science and their challenges

This paper proposed an enhanced system for securing sensitive text-data on personal computer benefitting from the combination of both techniques: cryptography and steganography. The system security is generated by involving RSA cryptography followed by video based steganography as two sequential layers to insure best possible security gaining the advantages from both. The study modeled the system and implemented it to be tested to explore the relation between security, capacity and data dependency. The experimentations covered testing securing data within 15 different size videos showing interesting results. The research gave enhancement to capacity vs. security, as enforced unavoidable tradeoff. The work uniqueness is presented in showing different measures allowing the user and application to be the decision maker to choose. The tests provided all possibilities of accepting security of 1-LSB, 2-LSB, and 3-LSB methods detailing their effects on the cover video. The main outcome proved applicability to be adopting 3-LSB approach to give acceptable security with practical capacity preferred making 3-LSB winning among 1-LSB and 2-LSB techniques.

/pdf/enhancing-pc-data-security-via-combining-rsa-cryptography-4jqjxkzt91.pdf

Enhancing PC Data Security via Combining RSA Cryptography and Video Based Steganography

The food processing and handling industry is the most significant business among the various manufacturing industries in the entire world that subsidize the highest employability. The human workforce plays an essential role in the smooth execution of the production and packaging of food products. Due to the involvement of humans, the food industries are failing to maintain the demand-supply chain and also lacking in food safety. To overcome these issues of food industries, industrial automation is the best possible solution. Automation is completely based on artificial intelligence (AI) or machine learning (ML) or deep learning (DL) algorithms. By using the AI-based system, food production and delivery processes can be efficiently handled and also enhance the operational competence. This article is going to explain the AI applications in the food industry which recommends a huge amount of capital saving with maximizing resource utilization by reducing human error. Artificial intelligence with data science can improve the quality of restaurants, cafes, online delivery food chains, hotels, and food outlets by increasing production utilizing different fitting algorithms for sales prediction. AI could significantly improve packaging, increasing shelf life, a combination of the menu by using AI algorithms, and food safety by making a more transparent supply chain management system. With the help of AI and ML, the future of food industries is completely based on smart farming, robotic farming, and drones.

/pdf/opportunities-of-artificial-intelligence-and-machine-10pj5tg3np.pdf

Opportunities of Artificial Intelligence and Machine Learning in the Food Industry

Intracerebral hemorrhage (ICH) is the most serious type of stroke, which results in a high disability or mortality rate. Therefore, accurate and rapid ICH region segmentation is of great significance for clinical diagnosis and treatment of ICH. In this paper, we focus on deep neural networks to automatically segment ICH regions. Firstly, we propose an encoder-decoder convolutional neural network (ED-Net) architecture to comprehensively utilizing both the low-level and high-level semantic information. Specifically, the encoder is used to extract multi-scale semantic feature information, while the decoder integrates them to form a unified ICH feature representation. Secondly, we introduce a synthetic loss function by paying more attention to the small ICH regions to overcome the data imbalanced problem. Thirdly, to improve the clinical adaptability of the proposed model, we collect 480 patient cases with ICH from four hospitals to construct a multi-center dataset, in which each case contains the first and review CT scans. In particular, CT scans of different patients are diverse, which greatly increases the difficulty of segmentation. Finally, we evaluate ED-Net on the multi-center ICH clinical dataset from different model parameters and different loss functions. We also compare the results of ED-Net with nine state-of-the-art methods in the literature. Both quantitative and visual results have shown that ED-Net outperforms other methods by providing more accurate and stable performance.

Automatic segmentation of intracerebral hemorrhage in CT images using encoder–decoder convolutional neural network

Steganography is an important technique for information hiding in any digital object. Steganography technique is the science that includes communicating secret information in an appropriate digital multimedia cover objects such as audio, video and image files. The main objective of steganography is to hide the existence of the embedded data. Steganography technique has improved the security of existing data hiding techniques by the outstanding development in computational power. Objectives of steganography are Undetectability, robustness and capacity of the concealed data, these key factors that separate it from related techniques like cryptography and watermarking. This paper delivers a survey on digital images steganography and covering its fundamental concepts. The development of image steganographic methods in spatial representation, in JPEG format and also discuss the recent development in the field of image steganography. Specific generally used approaches for increasing steganographic security are summarized and significant research developments are also discussed.

/pdf/a-survey-on-image-steganography-techniques-2s51ydzv51.pdf

A Survey on Image Steganography Techniques

https://www.techscience.com/cmc/v70n2/44633/pdf

Secure Watermarking Scheme for Color DICOM Images in Telemedicine Applications

Entropy based Automatic Unsupervised Brain Intracranial Hemorrhage Segmentation using CT images

Planning of location area (LA) in cellular networks plays a vital role in utilizing the resources efficiently and economically. Location update and paging costs directly affect the cost to the service provider. When the size of the Mobile Switching Centre (MSC) is large, the paging cost becomes maximum. Though, no location update is required for this case. On the contrary, paging cost shoots high if each cell forms individual LA, but in this case, location update cost shoots to the maximum value. Therefore, deducing the network to the optimal amount of LA's is an intractable combinatorial optimization problem. In this paper, we intend to optimize the partitions of the MSC service area into an optimal number of LA, to curtail the total location management cost. We propose a novel scheme bearing in mind cell attributes of the network to deduce an optimum number of location areas, leading to minimum cost per call. It is revealed by the results of this work, attained after simulating the scenario on MATLAB 2018a that Cell Attributes Based Algorithm is a very promising scheme for cellular networks, and it outperforms the existing algorithms in a practical scenario.

Kamred Udham Singh

Papers

The state of the art of deep learning models in medical science and their challenges

A Survey on Image Steganography Techniques

Secure Watermarking Scheme for Color DICOM Images in Telemedicine Applications

Entropy based Automatic Unsupervised Brain Intracranial Hemorrhage Segmentation using CT images

Artificial intelligence‐based novel scheme for location area planning in cellular networks