ABSTRACT Approximately fifty percent of the world's population depend on rice as a primary food source. This situation illustrates the importance of consistent and sustainable rice cultivation for food security. A significant issue in rice cultivation is the prevalence of leaf diseases, which can substantially impact plant growth and yield. Rapid and precise identification of these diseases is crucial to mitigate crop losses and reduce excessive pesticide application. Historically, disease identification through manual inspection was based on expert visual evaluation, which is challenging, subjective, and difficult to implement on a broad scale in agricultural environments. This work proposes an advanced deep learning model named ResNet‐50+SaE‐PE, a modified edition of the ResNet‐50 architecture, to address this issue. This model uses positional encoding (PE) to improve its ability to give more attention to spatial information and adds squeeze‐aggregatio‐excitation (SaE) modules to better focus on important features. These enhancements facilitate the identification and classification of disease‐affected regions in rice leaves. The proposed model has been tested on a publicly available standard Rice Leaf Disease dataset consisting of 4624 images. We partitioned the dataset into 80:20 ratios for training and testing, respectively. The performance of the model has been evaluated using accuracy, recall, specificity, precision, and F1‐score. The modified version of ResNet‐50+SaE‐PE shows that it is better at being accurate, precise, and reliable compared to older models. After experimenting with several optimizers, Stochastic Gradient Descent (SGD) with a learning rate of 0.001 emerged as the most reliable option. The average accuracy of 99.89% indicates that the model is effective for use in intelligent and scalable systems to monitor agricultural diseases.

Abstract Rice is one of the significant crops, and the early identification and prevention of its diseases are essential to ensure adequate and healthy availability to the world's growing population. The use of image processing is an encouraging method for automatic rice leaf disease identification and detection. In particular, the recent advancements indicate the effectiveness of convolutional neural network (CNN) based deep learning approaches. In this direction, the present work proposes a novel stacked parallel convolution layers‐based network (SPnet) with the squeeze‐and‐excitation (SE) architecture, named (SE_SPnet), for classifying diseased rice leaf images. The stacked parallel network block comprises four parallel convolution layers with different kernel sizes for abstractions of the global and local features. The SE block extracts feature information automatically while removing invalid ones. We compare the SE_SPnet model with state‐of‐the‐art CNN models such as VGG16, DenseNet121, and InceptionV3 based on computational effort, accuracy, sensitivity, specificity, precision, recall, and F1‐score. The experimental results show that the SE_SPnet outperforms standard CNN models for the considered rice leaf disease image datasets. In particular, the SE_SPnet achieves the highest accuracy (99.2%), sensitivity (98.2%), specificity (98.5%), precision (98.4%), recall (98.2%), and F1‐score (98.5%) while using stochastic gradient descent (with momentum) optimizer with a 0.01 learning rate. Furthermore, the SE_SPnet also exhibits to outperform when compared with some of the most recent and relevant existing works.

Summary Among all diabetic‐related complications, the diabetic foot ulcer (DFU) is severe, demanding serious attention, and timely treatment. The purpose of the present study was to conduct features fusion of machine learning (ML) based handcrafted low‐level and convolutional neural networks (CNNs) based high‐level features for improving automatic diagnosis of DFU. A standard image dataset containing 1038 abnormal (DFU) and 641 normal color skin patches has been used for experimental evaluation. Handcrafted features are extracted to uncover the edge, color, shape, and texture information from the images. Also, a new CNN architecture has been proposed based on deeper residual blocks for extracting high‐level features. Features fusion with several ML classifiers like logistic regression classifier, support vector machine, gradient boosting, and artificial neural network have shown improved DFU identification results compared to the individual feature categories. Thereby, LRC outperformed the state‐of‐the‐art results for all evaluation metrics by achieving 95.23% sensitivity, 95.37% F1‐score, and 96.50% area under the curve (AUC) value. Such impressive experimental observations suggest that the proposed approach is expected to provide efficient decision support to medical practitioners, thereby improving patient care.

Summary Diabetes is one of the most common chronic disease causes severe life threatening complications. Therefore, it is important to diagnose diabetes at early stage to avoid health and financial burdens. In this work, a machine learning (ML) pipeline based systematic data‐driven architecture is proposed to identify diabetes. The proposed ML pipeline consisted of support vector machine‐synthetic minority oversampling technique (SVM‐SMOTE), followed by multiple tree based feature selection (FS) approaches, and ensemble learners. Further, Bayesian optimization (BO) has been used to tune the hyperparameters in classifiers. The use of SVM‐SMOTE, FS, and BO methods together improved classifiers' performance impressively in a highly imbalanced Virginia dataset. Also, the proposed model is proved to be a useful approach in comparatively less imbalanced Pima Indian Diabetes (PID) dataset. Among all classifiers used, random forest (RFC) has achieved the highest sensitivity of 91.44% in PID dataset and in Virginia AdaBoost (ABC) has achieved the highest of 88.53% sensitivity. Subsequently, XGBoost (XGB) and AdaBoost (ABC) classifiers have achieved the highest 92.08% and 88.27% AUC in PID and Virginia dataset, respectively. Such kind of impressive results suggest that the proposed approach can have a very high practical utility, in real medical diagnostic settings.

Abstract Automatic segmentation and classification of breast tumours in ultrasound images using deep learning approaches can help early detect breast cancer. Such predictive modelling can potentially significantly improve the survival chances of the involved patients. Most of the typical deep convolutional neural network (CNN) based approaches consider segmentation and classification tasks separately. But this loses important supervisory information to help achieve better model training. This work proposes the integrated learning of both of these tasks in an end‐to‐end manner, using a multi‐task learning based approach. More specifically, a convolutional encoder‐decoder based architecture is coupled with a residual CNN for performing segmentation and classification together. The level‐wise feature maps from both the encoder and decoder parts of the segmentation network are utilized for classification in the proposed approach. From experimental analysis on a publicly available breast ultrasound image (BUSI) dataset, it has been observed that the proposed approach can achieve impressive performances, both with respect to tumour segmentation and classification. A mean test set AUC of 0.97 and a mean dice score of 0.74 is achieved, establishing a new state‐of‐the‐art performance on the BUSI dataset. From the impressive experimental observations, it can be concluded that learning to perform both segmentation and classification simultaneously can have a very high positive impact on the overall quality of the predictive model. Such observations suggest that the proposed approach can be beneficial in providing real‐time decision support to the involved diagnostic radiologists, which can help improve the survival chances of the corresponding patients.

Abstract Prediction of breast tumour malignancy using ultrasound imaging, is an important step for early detection of breast cancer. An efficient prediction system can be a great help to improve the survival chances of the involved patients. In this work, a machine learning (ML)—radiomics based classification pipeline is proposed, to perform this predictive modelling task, in a much more efficient manner. Multiple different types of image features of the region of interests are considered in this work, followed by a recursive feature elimination based feature selection step. Furthermore, a synthetic minority oversampling technique based step is also included in the pipeline, to deal with the class imbalance problem, that is often present in medical imaging datasets. Various ML models are considered in the subsequent model training phase, on a publicly available breast ultrasound image dataset (BUSI). From experimental analysis it has been observed that, shape, texture and histogram oriented gradients related features are the most informative, with respect to the predictive modelling task. Furthermore, it was observed that ensemble learners such as random forest, gradient boosting and AdaBoost classifiers are able to achieve significant results with respect to multiple evaluation metrics. The proposed approach achieved the state‐of‐the‐art accuracy, area under the curve, F1‐score and Mathews correlation coefficient values of 0.974, 0.97, 0.94 and 0.959, respectively, on the BUSI dataset. Such kind of impressive results suggest that the proposed approach can have a very high practical utility, in real medical diagnostic settings.