Browsing by Author "Ismail Idowu Akuji"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    An Explainable ResNet-101 Framework for Hand Fracture Classification in X-ray
    (Co hosted by Baze University Big Data Analytics and Innovation Research Group, American University Yola, and Sule Lamido University, 2026-04-23) Ayodeji Jubril Alabi; Shakirat Ronke Yusuff; Sulaiman Olaniyi Abdulsalam; Ismail Idowu Akuji; Oyindamola Eniola Ajiboye
    : Fracture detection in radiographic images continues to be a difficult task due to subtle bone disruptions and variations in anatomical structures, especially within the hand region. This study proposes an explainable deep learning framework for automated hand fracture detection using a ResNet-101 architecture. The model was trained and evaluated on the hand subset of the publicly available MURA dataset, with preprocessing methods and data balancing strategies applied to mitigate class imbalance and enhance model generalization. Bayesian hyperparameter optimization was utilized to determine the most suitable training parameters, including learning rate, dropout rate, and network capacity, thereby improving model stability and overall performance. The optimized model achieved an accuracy of 79.7% with an area under the curve (AUC) of 0.75, indicating dependable classification performance. To enhance interpretability, Grad-CAM++ was incorporated to visualize the regions of interest that influence the model’s predictions, allowing verification of clinically meaningful focus areas. The results demonstrate that the model effectively detects fracture regions while maintaining stable performance across diverse radiographic samples. In addition, the system produces automated PDF-based clinical reports that combine predictions with corresponding heatmaps, thereby improving its practical relevance in clinical environments. Overall, the proposed approach offers a robust, interpretable, and clinically valuable solution for hand fracture detection, with strong potential for integration into computer-aided diagnosis systems. Future work will focus on extending the model to multi-centre datasets and incorporating additional clinical features to further enhance generalization and diagnostic reliability
  • No Thumbnail Available
    Item
    Enhanced Interpretable Deep Learning Framework for Dengue Fever Prediction: A Rule Extraction Approach
    (co-hosted by Baze University Big Data Analytics and Innovation Research Group, American University Yola, and Sule Lamido University, 2026-04-23) Kolawole Muhammed Abdulsalam; Hamidat Ayodeji Arikewuyo; Ismail Idowu Akuji; Abdulmumeen Sekinat Shaban; Islamiyat Oluwakemi Giwa; Muhammad Sharafadeen Jimoh; Taofik Abiodun Ahmed; Shakirat Ronke Yusuff; Ronke Seyi Babatunde
    Dengue fever poses a critical public health challenge worldwide, particularly in developing countries with laboratory-constrained healthcare systems. Existing methods show promise but are prone to overfitting, which can be mitigated by LSTM-based deep learning models. However, LSTM inherently lack interpretability, a major barrier to clinical adoption in disease prediction. This study bridges robustness and clinical interpretability by integrating rule extraction with LSTM for dengue fever prediction, using a Mendeley dengue fever dataset comprising 1,003 instances and 9 features, preprocessed with label encoding, simple imputation, and synthetic minority oversampling (SMOTE).The LSTM algorithm is optimized using GridSearchCV and RandomizedSearchCV and combined with G-REX for transparent generation, evaluated using accuracy, precision, recall, F1 score, and ROC AUC. All three LSTM variants, including Baseline, GridSearchCV, and RSCV (20 iterations), achieve 100% across Accuracy, Precision, Recall, F1-Score, and ROC-AUC. However, G-REX rules deliver exceptional practical performance: 98.99% Accuracy, 98.53% Precision, 100% Recall, 99.26% F1-Score, and 99.09% ROC-AUC, while maintaining 93.3% fidelity to LSTM predictions, affirming medical validity. These findings position LSTM models as a strong reference standard for dengue classification, enabling resource-limited clinics to achieve high-quality diagnostics through transparent, rulebased support systems. This study can be strengthened in future by exploring other rule-extraction techniques and incorporating diverse, time-series datasets to enhance reliability, interpretability, and generalizability across varied clinical settings.