Rice production has faced numerous challenges in recent years, and traditional methods are still being used to detect rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The public dataset consists of 2000 images; about 1200 images belong to the leaf blast class, and 800 to the healthy leaf class. The modified connection-skipping ResNet 50 had the highest accuracy of 99.75% with a loss rate of 0.33, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. Furthermore, ResNet 50 achieved a validation accuracy of 99.69%, precision of 99.50%, F1-score of 99.70, and AUC of 99.83%. In conclusion, the study demonstrated a superior performance and disease prediction using the Gradio web application.

CT vertebral segmentation plays an essential role in various clinical applications, such as computer‐assisted surgical interventions, assessment of spinal abnormalities, and vertebral compression fractures. Automatic CT vertebral segmentation is challenging due to the overlapping shadows of thoracoabdominal structures such as the lungs, bony structures such as the ribs, and other issues such as ambiguous object borders, complicated spine architecture, patient variability, and fluctuations in image contrast. Deep learning is an emerging technique for disease diagnosis in the medical field. This study proposes a patch‐based deep learning approach to extract the discriminative features from unlabeled data using a stacked sparse autoencoder (SSAE). 2D slices from a CT volume are divided into overlapping patches fed into the model for training. A random under sampling (RUS)‐module is applied to balance the training data by selecting a subset of the majority class. SSAE uses pixel intensities alone to learn high‐level features to recognize distinctive features from image patches. Each image is subjected to a sliding window operation to express image patches using autoencoder high‐level features, which are then fed into a sigmoid layer to classify whether each patch is a vertebra or not. We validate our approach on three diverse publicly available datasets: VerSe, CSI‐Seg, and the Lumbar CT dataset. Our proposed method outperformed other models after configuration optimization by achieving 89.9% in precision, 90.2% in recall, 98.9% in accuracy, 90.4% in F‐score, 82.6% in intersection over union (IoU), and 90.2% in Dice coefficient (DC). The results of this study demonstrate that our model’s performance consistency using a variety of validation strategies is flexible, fast, and generalizable, making it suited for clinical application.

The purpose of this research is to demonstrate the ability of machine-learning (ML) methods for liver cancer classification using a fused dataset of two-dimensional (2D) computed tomography (CT) scans and magnetic resonance imaging (MRI). Datasets of benign (hepatocellular adenoma, hemangioma, cyst) and malignant (hepatocellular carcinoma, hepatoblastoma, metastasis) liver cancer were acquired at Bahawal Victoria Hospital (BVH), Bahawalpur, Pakistan. The final dataset was generated by fusion of 1200 (100 × 6 × 2) MR and CT-scan images, 200 (100 MRI and 100 CT-scan) images size 512 × 512 for each class of cancer. The acquired dataset was preprocessed by employing the Gabor filters to reduce the noise and taking an automated region of interest (ROIs) using an Otsu thresholding-based segmentation approach. The preprocessed dataset was used to acquire 254 hybrid-feature data for each ROI, which is the combination of the histogram, wavelet, co-occurrence, and run-length features, while 10 optimized hybrid features were selected by employing (probability of error plus average correlation) feature selection technique. For classification, we deployed this optimized hybrid-feature dataset to four ML classifiers: multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), and J48, using a ten fold cross-validation method. MLP showed an overall accuracy of (95.78% on MRI and 97.44% on CT). Unfortunately, the obtained results were not promising, and there were some limitations due to the different modalities of the dataset. Thereafter, a fusion of MRI and CT-scan datasets generated the fused optimized hybrid-feature dataset. The MLP has shown a promising accuracy of 99% among all the deployed classifiers.

Brain tumors are deadly but become deadliest because of delayed and inefficient diagnosis process. Large variations in tumor types also instigate additional complexity. Machine vision brain tumor diagnosis addresses the problem. This research’s objective was to develop a brain tumor classification model based on machine vision techniques using brain Magnetic Resonance Imaging (MRI). For this purpose, a novel hybrid-brain-tumor-classification (HBTC) framework was designed and evaluated for the classification of cystic (cyst), glioma, meningioma (menin), and metastatic (meta) brain tumors. The proposed framework lessens the inherent complexities and boosts performance of the brain tumor diagnosis process. The brain MRI dataset was input to the HBTC framework, pre-processed, segmented to localize the tumor region. From the segmented dataset Co-occurrence matrix (COM), run-length matrix (RLM), and gradient features were extracted. After the application of hybrid multi-features, the nine most optimized features were selected and input to the framework’s classifiers, namely multilayer perception (MLP), J48, meta bagging (MB), and random tree (RT) to classify cyst, glioma, menin, and meta tumors. Maximum brain tumor classification performance achieved by the HBTC framework was 98.8%. The components and performance of the proposed framework show that it is a novel and robust classification framework.

The object of this study was to demonstrate the ability of machine learning (ML) methods for the segmentation and classification of diabetic retinopathy (DR). Two-dimensional (2D) retinal fundus (RF) images were used. The datasets of DR—that is, the mild, moderate, non-proliferative, proliferative, and normal human eye ones—were acquired from 500 patients at Bahawal Victoria Hospital (BVH), Bahawalpur, Pakistan. Five hundred RF datasets (sized 256 × 256) for each DR stage and a total of 2500 (500 × 5) datasets of the five DR stages were acquired. This research introduces the novel clustering-based automated region growing framework. For texture analysis, four types of features—histogram (H), wavelet (W), co-occurrence matrix (COM) and run-length matrix (RLM)—were extracted, and various ML classifiers were employed, achieving 77.67%, 80%, 89.87%, and 96.33% classification accuracies, respectively. To improve classification accuracy, a fused hybrid-feature dataset was generated by applying the data fusion approach. From each image, 245 pieces of hybrid feature data (H, W, COM, and RLM) were observed, while 13 optimized features were selected after applying four different feature selection techniques, namely Fisher, correlation-based feature selection, mutual information, and probability of error plus average correlation. Five ML classifiers named sequential minimal optimization (SMO), logistic (Lg), multi-layer perceptron (MLP), logistic model tree (LMT), and simple logistic (SLg) were deployed on selected optimized features (using 10-fold cross-validation), and they showed considerably high classification accuracies of 98.53%, 99%, 99.66%, 99.73%, and 99.73%, respectively.

Smart grid plays an important role in managing demand response management in modern smart city using Information and Communication Technologies (ICTs). In smart grid environment, sensors are widely used for surveillance. These are deployed on the high tension power supply lines which help to share the information to control center about line breakage or any other flaw. Besides the cyber-attacks, sensors may also experience physical attacks as they are deployed on high-tension power lines in an open environment. Moreover, an attacker can also impersonate the information exchanged between sensors, gateways and control centers. Therefore, the most indispensable requirement is to prevent these cyber-attacks and physical attacks so that a secure and efficient surveillance system can be maintained for smart grid environment. Motivated from these, in this article, we propose an identity based authentication protocol for power supply-line surveillance in smart grid environment using physical uncloneable function. The performance analysis shows that our proposed protocol is resilient to various cyber-attacks alongwith the physical attacks on sensors. The proposed protocol is efficient as it has less computation cost as compared to various related protocols. Although, the communication cost of devised protocol is slightly higher than some protocols but it also offers three added security features as compared to other related protocols.