Objectives: Colorectal cancer (CRC) is the second-deadliest cancer globally, with an estimated 52,900 additional deaths expected in the United States by 2025. Early detection through colonoscopy significantly reduces CRC mortality by enabling the removal of pre-cancerous polyps. However, manual visual inspection of colonoscopy images is time-consuming, tedious, and prone to human error. This study aims to develop an automated and reliable polyp segmentation and classification method to improve CRC screening. Methods: We propose a novel deep learning architecture called µ-Net for accurate polyp segmentation in colonoscopy images. The model was trained and evaluated using the Kvasir-SEG dataset. To ensure transparency and reliability, we incorporated Explainable AI (XAI) techniques, including saliency maps and Grad-CAM, to highlight regions of interest and interpret the model’s decision-making process. Results: The µ-Net model achieved a Dice coefficient of 94.02%, outperforming other available segmentation models in accuracy, indicating its strong potential for clinical deployment. Integrating XAI provided meaningful visual explanations, enhancing trust in model predictions. Conclusions: The proposed µ-Net framework significantly improves the Precision and efficiency of automated polyp screening. Its ability to segment, classify, and interpret colonoscopy images enables early detection and supports clinical decision-making. This comprehensive approach offers a valuable tool for CRC prevention, ultimately contributing to better patient outcomes.

Objective: Segmentation of liver and liver tumors from 3D medical images is a challenging and computationally expensive task. Organs that are in close proximity may have similar shape, texture, and intensity, which makes it difficult for accurate segmentation. Accurate segmentation of liver tumors is important for diagnosis and treatment planning of liver cancer. Methods: A hybrid model with a U-Net based structure and the Whale Optimization Algorithm (WOA) was proposed. WOA was used to optimize the hyperparameters of the conventional LiTS-Res-UNet to obtain the best segmentation performance of the deep learning model. Results: The LiTS-Res-Unet + WOA hybrid model achieved a performance of 99.54% for accuracy, with a Dice coefficient of 92.38% and a Jaccard index of 86.73% on the benchmark dataset, outperforming state-of-the-art methods. Conclusions: The WOA-based adaptive search space was able to obtain an optimal set of hyperparameters for deep learning model convergence while increasing the accuracy of the model in the proposed hybrid model. The robust performance and clinical applicability of the model in liver tumor segmentation were demonstrated.

Breast cancer is a serious public health problem and is one of the leading causes of cancer-related deaths in women worldwide. Early detection of the disease can significantly increase the chances of survival. However, manual analysis of mammogram mastery images is complex and time-consuming, which can lead to disagreements among experts. For this reason, automated diagnostic systems can play a significant role in increasing the accuracy and efficiency of diagnosis. In this study, we present an effective deep learning (DL) method, which classifies mammogram mastery images into cancer and noncancer categories using a collected dataset. Our model is pretrained based on the Inception V3 architecture. First, we run 5-fold cross-validation tests on the fully trained and fine-tuned Inception V3 model. Next, we apply a combined method based on likelihood and mean, where the fine-tuned Inception V3 model demonstrated superior performance in classification. Our DL model achieved 99% accuracy and 99% F1 score. In addition, interpretable AI techniques were used to enhance the transparency of the classification process. The finely tuned Inception V3 model demonstrated the highest performance in classification, confirming its effectiveness in automatic breast cancer detection. The experimental results clearly indicate that our proposed DL-based method for breast cancer image classification is highly effective, especially its application in image-based diagnostic methods. This study brings to the fore the huge potential of AI-based solutions, which can play a significant role in increasing the accuracy and reliability of breast cancer diagnosis.

Background: Malaria continues to be a significant global health concern, particularly in tropical and subtropical areas. Timely and accurate diagnosis is crucial in minimizing the disease’s mortality. The standard method, microscopic diagnosis, which represents the gold standard, is heavily reliant on skilled interpretation, labor-intensive, and prone to human error. Methods: To address these challenges, we propose the NOVA (Novel Multi-Scale Adaptive Vision Architecture) for the diagnosis of malaria. NOVA is based on an innovative dynamic channel attention and Learnable Temperature Spatial Pyramid Attention to achieve more powerful feature representation and better classification performance. In addition, adaptive feature refinement and enhanced transformer blocks are used to obtain multi-scale feature extraction and contextual reasoning. Furthermore, a multi-strategy pooling mechanism that fuses average, max, and attention-based aggregation is developed to enhance the model’s discriminative capability. Results: We conduct experiments on a publicly accessible dataset of 15,031 microscopic thin blood smear images to validate the effectiveness of the proposed approach. The model is assessed and compared on a benchmark malaria microscopy dataset, achieving an accuracy of 97.00%, a precision of 96.00%, and an F1-score of 97.00%, outperforming other existing models. Conclusions: The experimental results demonstrate the feasibility of the proposed approach as a potential research prototype for the automated diagnosis of malaria. Before clinical deployment, further multi-site clinical evaluation on a large patient cohort is required for validation.

Accurate detection and severity estimation of corrosion on metallic surfaces is essential for maintaining material integrity and ensuring operational safety in industrial systems. To address limitations in manual inspection methods, this study presents a two-stage deep learning pipeline tailored for high-resolution scanning electron microscopy images. The framework combines instance-level corrosion segmentation using the YOLOv8-seg architecture with subsequent severity classification performed by EfficientNet-B0 and ResNet18. In the segmentation stage, models are trained using both manually annotated and automatically generated binary masks, enabling robust instance mask prediction through prototype-based mask decoding. The classification stage assesses the severity of corrosion by analyzing localized regions based on morphological features, leveraging convolutional neural networks optimized for binary output. Experimental results demonstrate strong performance: the segmentation model trained on manual annotations achieves a mean Intersection-over-Union (mIoU) of 89.91, a mask mAP@50 of 98.6, and an ROC-AUC of 94.69. For severity classification, EfficientNet-B0 achieves an accuracy of 93.75% and an F1-score of 93.29, outperforming ResNet18. These findings underscore the potential of combining lightweight segmentation and classification models to enable precise and automated corrosion analysis, supporting integration into real-time inspection workflows and intelligent material diagnostics in industrial settings.

Parkinson disease (PD) is a degenerative disorder of the brain and afflicts approximately 6 in 10 people aged 50 years or older. PD patients have motor and speech problems, so regular visits to and monitoring of the patients are hard. It is necessary to detect the presence of PD promptly and accurately, since early treatment will contribute greatly to enhancing patients’ lives. As the number of aging people increases, there is a great demand for noninvasive, reliable, and remote diagnosis. In the current work, we studied 31 patients with PD and healthy subjects, their voice recordings, to create an automatic classification system. A Light Gradient Boosting Machine (LightGBM) classifier was adapted and boosted using metaheuristic-based feature selection (FS), namely the Pelican Optimization Algorithm (PAO). Hyperparameter optimization was made to optimize predictive performance. The models have been assessed on typical classification measures, i.e., accuracy, sensitivity, specificity, precision, and AUC. We classified using the baseline LightGBM classifier, with an accuracy of 95%. The resulting model had a better prediction accuracy of 97% after using PAO-based FS and hyperparameter optimization. More than that, the model was also sensitive, specific, precise, and had a high area under the curve, which validates its effectiveness at classifying PD. The paper shows that FS and hyperparameter tuning are effective approaches when applied to voice data and combined with LightGBM to detect PD as early as possible. The results point to the promise of noninvasive diagnostic systems based on the use of telemedicine to allow early intervention and enhance the lives of people with PD.