Classifying rice leaf diseases in agricultural technology helps to maintain crop health and to ensure a good yield. In this work, deep learning algorithms were, therefore, employed for the identification and classification of rice leaf diseases from images of crops in the field. The initial algorithmic phase involved image pre-processing of the crop images, using a bilateral filter to improve image quality. The effectiveness of this step was measured by using metrics like the Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). Following this, this work employed advanced neural network architectures for classification, including Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), MobileNetV2, and Convolutional Neural Network (CNN). The proposed CNN model stood out, since it demonstrated exceptional performance in identifying rice leaf diseases, with test Accuracy of 98% and high Precision, Recall, and F1 scores. This result highlights that the proposed model is particularly well suited for rice leaf disease classification. The robustness of the proposed model was validated through k-fold cross-validation, confirming its generalizability and minimizing the risk of overfitting. This study not only focused on classifying rice leaf diseases but also has the potential to benefit farmers and the agricultural community greatly. This work highlights the advantages of custom CNN models for efficient and accurate rice leaf disease classification, paving the way for technology-driven advancements in farming practices.

Globally, breast cancer is among the most prevalent and deadly tumors that affect women. Early and accurate identification of breast cancer is essential for effective treatment planning and improving patient outcomes. This research focuses on improving breast cancer classification accuracy through machine learning (ML) methodologies, emphasizing interpretability. The study utilized the chi-square method to enhance model testing performance by pinpointing the most significant features for further analysis. The study also improved data quality by identifying and removing outliers, thus minimizing the influence of data irregularities on the performance of the models. For classification, the study evaluated six different ML algorithms—namely extreme gradient boosting (XGBoost), decision tree (DT), AdaBoost (AB), support vector machine (SVM), gradient boosting (GB), and K-nearest neighbors (KNN)—each applied to distinguish between the two variants of breast cancer. Among these, the XGBoost classifier emerged as the most accurate, achieving an impressive 99.30% accuracy rate. Moreover, the research incorporated shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) methods to boost the interpretability of the proposed model, offering crucial insights into the model’s decision-making process. Applying these interpretability techniques provided significant insights into the predictive factors influencing healthcare outcomes, ensuring the classification approach’s transparency and reliability.

Acute Lymphoblastic Leukemia (ALL), a cancer affecting the blood and bone marrow, requires precise classification for accurate diagnosis, personalized treatment plans, and improved predictive assessments to enhance patient survival and quality of life. This study presents LEU3, a novel classification model designed to improve the accuracy of leukemia detection from peripheral blood smear (PBS) images. LEU3 leverages an attention-based convolutional neural network (CNN) architecture, incorporating pooling layers, a global average pooling layer, and dense layers with dropout for regularization. The model is trained with an Adam optimizer comprising with four classes: Benign, early malignant pre-B, malignant pre-B, and malignant pro-B. Data augmentation techniques were employed to increase training set diversity. Additionally, Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) are used to enhance interpretability and transparency in the model’s decision-making process. LEU3 achieved a test accuracy of 99% and a validation accuracy of 99% on 484 PBS images, demonstrating a 3% improvement over the baseline model. These results underline the potential of LEU3 in supporting medical professionals by reducing diagnostic workload and improving the accuracy of leukemia classification.

Millions of cases of tuberculosis (TB) are recorded each year, making it a significant worldwide health concern. Early and accurate TB detection is essential for the disease to be effectively treated and controlled. Deep learning methods have recently become effective tools for analyzing medical images, and they have a lot of potential for use in the field of TB detection. This study describes a revolutionary deep-learning method for detecting TB illness. We used a dataset of 3500 chest X-ray images from individuals with tuberculosis. There are two classes in the dataset: Tuberculosis and Normal. We used the highly regarded deep learning models VGG16, VGG19, MobileNetV2, and InceptionV3 to categorize such elements. Out of all of them, MobileNetV2 has obtained the highest accuracy, which is accurate in training of 99.99% and a test's reliability of 98.93%. Furthermore, in VGG16, VGG19, and Inception-V3, we achieved test accuracy of 98.90%, 99.14%, and 97.87%, respectively.