International Journal of Image and Graphics

The five-year survival rate for pancreatic cancer (PC) is the lowest of any cancer kind, and it is the fourth greatest cause of cancer-related death, with a growing death rate. When it comes to cancer invasion, the most significant risk factors are: smoking; alcohol usage; diabetes; and prior pancreatitis. By using this method, we will be able to detect our PC, which is equipped with picture handling technology. Researchers used CT images as input in this study and preprocessed them to remove any noise in the images that had been learned using an adaptive Weiner filter. Preprocessing is followed by the use of a region grow ideal to segment the noise-free image. Scale Invariant Feature Transform (SIFT) is utilized once more to extract the tumor limits and principal component analysis (PCA) is used to enhance the retrieved structures to improve the types of pancreatic CT images. In order to activate the picture parameters, a convolutional neural network (CNN) classifier is used. In order to categorize an image as nonpancreatic cancer or pancreatic cancer, the test data were compared to the training data and the classified image was compared. MATLAB then initiates the entire process, and the most recent performance estimation approach is utilized, resulting in outstanding accuracy.

The active theme for exploration is currently the potential for visual gaze tracking and visual human–machine interactions in contemporary user devices. Eye views were used as an input tool to extract human behavioral knowledge and to achieve immersive user interactions in augmented and amplified reality systems. However, implementations of gaze on consumer devices operating under controlled circumstances face tough precision and reliability challenges. For evolving automotive electronic systems such as driver surveillance systems and new touch screens, accurate and successful gaze estimates are significant. Such systems have to work efficiently and at minimum cost in demanding unregulated, low-power conditions. Deep learning is omnipresent for most computer vision tasks, but it is still common to estimate the eye gaze. The realistic account of all challenges and opportunities of eye gaze tracking requires a complete study of available deep learning methods. In this chapter, huge potential efforts are made to study the background of eye gaze tracking with the detail of how deep learning made a contribution to computer vision-based tracking. In the end, this chapter also highlights a generic system model and comparison of various algorithms for deep learning-driven eye gaze direction diagnosis.

Skin cancer is one of the critical diseases that occurs in different age groups of the population. Early detection and prevention can save many lives. Melanoma is one of the fundamental skin cancer types. The traditional approaches for skin lesion detection and classification (SLDC) failed to distinguish between melanoma and non-melanoma skin malignancies, resulting in low classification accuracy. Thus, this article is focused on the implementation of computer aided detection method for SLDC using iterative random forest (IRF) algorithm, hereafter named as IRFNet. The proposed IRFNet acts as a decision-making tool for the dermatologists. Initially, the first level consists of five intuitive classifiers (ICs) named as perceptron coupled with color local binary patterns (PC-CLBP), histograms of oriented gradients (HOGs), the generative adversarial network coupled with ABCD rule (GAN-ABCD), ResNet, and AlexNet are used to extract the texture, shape, color, size, and convolutional pixel connections-based features from given skin lesion images. Then, IRF algorithm is used to select the optimal features and finally the object classifier called deep learning convolutional neural network (DLCNN) is employed to classify the type of lesion as either melanoma or non-melanoma based on back-propagation perceptron that provides the final decision. The extensive simulation outcome performed on ISIC-2019 and PH2 datasets discloses the superiority of the proposed IRFNet in terms of precision, recall, sensitivity, specificity, and f1-score. In addition, it also achieved the trade-off between classification accuracy and execution time as compared to the existing SLDC approaches.

The security of data in an IoT network is of utmost importance. The medical IoT devices need to implement the security protocols in the devices to safeguard the crucial information. This paper proposes a novel high-speed data encryption scheme using elliptic curve cryptography (ECC) for key generation, key length reduction, Diffie–Hellman key exchange, SHA-256 and advance encryption standard (AES). The proposed hybrid data encryption scheme begins with elliptic curve key generation. Each authorized user in the broadcast range generated a private key using ECC. The proposed key reduction algorithm reduces the size of the secret key generated. This key is exchanged efficiently between the broadcast members using Diffie–Hellman key exchange. Each user then generates their final encryption keys. These keys are encoded using SHA-256 algorithm for further security. These keys are then used to encrypt the data using AES algorithm and sent to the cloud. The intended receivers can check the identity of the sender and decrypt the data using their own keys. The proposed method also includes user identity authentication. The origin of the message is verified to authenticate the sender of the message. This implementation is apt for home automation applications where data collected by medical devices like Fitbit and watches need to be shared among multiple users. The proposed method is at par in providing security to the data in much less time. The throughput, key generation time, key length, encryption time, decryption time and memory usage, Avalanche effect are efficient in comparison to existing methods.

Medical imaging fusion is the process of combining pictures from various imaging modalities to create a single image that may be used in clinical settings. Robust methods for merging image data from several modalities are being developed in the field of multimodal medical imaging. Deep learning (DL) has been widely researched in two areas: pattern recognition and image processing. We will demonstrate a multimodal image fusion with DL implementation that considers the characteristics of medical diagnostic imaging as well as the demands of clinical practice. For the past three years, pixel-level picture fusion has been a hot topic. This paper proposes a new multimodal medical picture fusion technique for a wide range of medical diagnostic challenges. Image fusion is crucial in biomedical research and clinical diagnostics for biomedical image processing and therapy planning. The most convincing argument for fusion is obtaining a significant amount of critical information from the input photographs. We show how a well-organized multimodal medical image fusion technique can be utilized to integrate computed tomography (CT) and magnetic resonance imaging (MRI) data in this study. Using convolutional neural networks (CNNs), the quantum-behaved particle swarm optimization (QPSO) algorithm was used to create a method for integrating multimodal medical pictures. In order to improve the overall quality and efficiency of QPSO, it was chosen to add the metrics of image entropy, standard deviation, average gradient (AG), spatial frequency (SF), and visual information fidelity (VIF). In experiments, multimodal medical images are utilized to evaluate a variety of parameters, including performance and algorithm stability. When compared to the other possibilities, the recommended technique outperformed them in the evaluations. On a range of quantitative metrics, this method outperforms the alternatives.

Diabetic retinopathy (DR) is stated as a disease in the eyes that affects the retina blood vessels and causes blindness. The early diagnosis and detection of the DR in patients preserve the patient’s vision. In general, for the diagnosis of eye diseases, retinal fundus images are employed. The advancement in the automatic diagnosis of diseases attained higher significance for rapid advancement in computing technology in the medical field. Besides, for the diagnosis of the diseases, fundus image automatic detection is involved in the recognition of blood vessels evaluated based on the length, branching pattern, and width. However, fundus images have low contrast and it is difficult to evaluate the identification of the disease in blood vessels. As a result, it is necessary to adopt a consistent automated method to extract blood vessels in the fundus images for DR. The conventional automated localization of the macula and optic disk in the retinal fundus images needs to be improved for DR disease diagnosis. But existing methods are not sufficient for the early identification and detection of DR. This paper proposed an entropy distributed matching global and local clustering (EDMGL) for fundus images. The developed EDMGL comprises the different uncertainties for the evaluation of the classes based on local and global entropy. The fundus image local entropy is evaluated based on the spatial likelihood fuzzifier membership function estimation for segmentation. The final proposed algorithm membership function is estimated using the addition of weighted parameters through membership estimation based on the global and local entropy. The classification performance of the proposed EDMGL is evaluated based on the dice coefficient, segmentation accuracy, and partition entropy. The performance of the proposed EDMGL is comparatively examined with the conventional technique. The comparative analysis expressed that the performance of the proposed EDMGL exhibits ∼5% improved performance in terms of accuracy, precision, recall, and F1-score.

Diabetic Retinopathy (DR) refers to a micro-vascular complication causing vision problems in diabetic patients. It is a serious global public health issue that damages the retinal blood vessels and leaves a large number of patients with loss of vision. Micro-aneurysms, hemorrhages, macular edema, and exudates are some of the lesions used to diagnose it. When detected early, Diabetic Retinopathy can be treated well with precise identification of lesions. Computer-aided diagnosis refers to the approaches used to extract specific features associated with the disease by using image processing filters. Some Machine Learning tools, especially the ones well-suited to data analysis applications are particularly useful. This paper primarily focuses on a comparative performance evaluation of many machine learning and deep learning-based techniques applied for the diagnosis of this vision ailment in diabetic patients.

Tumors are most dangerous to humans and cause death when patient not noticed it in the early stages. Edema is one type of brain swelling that consists of toxic particles in the human brain. Especially in the brain, the tumors are identified with magnetic resonance imaging (MRI) scanning. This scanning plays a major role in detecting the area of the affected area in the given input image. Tumors may contain cancer or non-cancerous cells. Many experts have used this MRI report as the primary confirmation of the tumors or edemas as cancer cells. Brain tumor segmentation is a significant task that is used to classify the normal and tumor tissues. In this paper, a hybrid segmentation approach (HSA) is introduced to detect the accurate regions of tumors and edemas to the given brain input image. HSA is the combination of an advanced segmentation model and edge detection technique used to find the state of the tumors or edemas. HSA is applied on the Kaggle brain image dataset consisting of MRI scanning images. Edge detection technique improves the detection of tumor or edema region. The performance of the HSA is compared with various algorithms such as Fully Automatic Heterogeneous Segmentation using support vector machine (FAHS-SVM), SVM with Normal Segmentation, etc. Performance of proposed work is calculated using mean square error (MSE), peak signal noise ratio (PSNR), and accuracy. The proposed approach achieved better performance by improving accuracy.

Diabetic retinopathy (DR) refers to a diabetes complexity that immensely impacts the eyes. This is classified into 5 various stages of the severity in accordance with the international convention. Despite that, optimization of a grading model to have a robust generalizability needs a huge number of balanced training data that is very complicated to gather, especially for greater levels of severity. A vast amount of medical data is complex and has a very high-priced method which requires cooperation between the clinics and researchers. The issue is usually attempted to be figured out with the usage of the traditional methods of data augmentation by making certain changes to images of retina dataset for instance rotation, cropping, size and zooming. In this suggested paper, the latest methods or techniques of data augmentation is exhibited which is called as deep convolutional generative adversial network (DC-GAN) and variational auto encoders (VAE). This is a particular method which is responsible for the production of artificial medical images. In addition to this, to improve DR, we can also take the aid of the classification models which are resnet50, densenet201, InceptionV3 and VGG19 for the purpose of classification of the eye related diseases. The proposed method is depicted on the Asia Pacific Tele-Ophthalmology Society (APTOS)-Blindness dataset. First, the present-day online data augmentation techniques have been utilized, and the artificial images of retina are produced by the ease of DCGAN. Then, a method of classifying is used for both techniques. Ultimately, after the method training which is done by using the real & synthetic clinical images and the outcome exhibits which the proposed model determines every stage or phase of DR and achieve the accuracy of 98.66% with using of ResNet-50 which is contrary to the current existing techniques.

The leaves of plants often display signs of nutritional shortages. Therefore, to identify the nutrient shortages in plants, the color as well as the shape of the leaves can be wielded. Image classification is a quick and efficient methodology for this diagnosis task. In image classification, even though Deep Convolutional Neural Networks (DCNNs) are successful, little emphasis has been paid to their use in detecting plant nutrient deficits. Thus, to classify rice plant nutrient deficits, a DenseNet121 model is proposed in this paper. This proposed technique includes inserting additional new layers, early stopping criteria, model checkpoints, and five-fold cross-validation to enhance the model’s accuracy. After that, the model’s efficacy has been assessed utilizing specific performance metrics like accuracy, F1 score, precision, and recall. The performance of the suggested model is also analogized with the newer deep learning algorithms. From experimental results, the modified DenseNet121 attained 99.98% of accuracy, 99.99% of Precision, 99.98% of Recall, and 99.97% of F1-score. Lastly, to classify nutrient deficiencies in rice plants automatically on the web and mobile devices, an application was created for the farmers.