LEVERAGING SUPERVISED MACHINE LEARNING FOR ALZHEIMER'S ILLNESS PREDICTION USING ROBOFLOW-ENHANCED IMAGING
This project explores the application of supervised machine learning techniques to predict Alzheimer's disease using Pathological images, through data preprocessing with Roboflow. Alzheimer's disease, a progressive neurodegenerative disorder, presents significant challenges in diagnosis, crucial for effective intervention and management, this study uses the Roboflow 3.0 Object Detection model, with the MS COCO (Microsoft Common Objects in Context) checkpoint, a powerful deep learning Model, to develop a predictive model capable of identifying Alzheimer's from pathological scans with high accuracy. The methodology involved collecting a comprehensive dataset of pathological images, which were meticulously preprocessed to ensure quality and consistency. Roboflow was utilised for preprocessing tasks, including annotation, normalisation, and data augmentation. The Roboflow 3.0 Object Detection model, with the MS COCO (Microsoft Common Objects in Context) checkpoint was then trained and validated using this refined dataset, with hyperparameters optimised to enhance performance. Evaluation metrics such as accuracy, precision, recall, and F1 score were employed to assess the model's efficacy. Results provide a robust tool for early diagnosis. The model's integration into a user-friendly web interface allows for seamless interaction by clinicians and researchers, facilitating practical application in clinical settings. Despite the promising outcomes, the project encountered limitations such as the dependency on the quality and size of the dataset, computational demands of the model, and challenges in model interpretability. Future work will focus on expanding the dataset, optimizing the model for computational efficiency, enhancing interpretability, and incorporating multimodal data for comprehensive diagnostic support. In conclusion, this project underscores the potential of supervised machine learning in revolutionising Alzheimer's disease diagnostics, offering a scalable and efficient solution that can significantly impact clinical practices and patient outcomes.