Alam, AshrafulRahman, MD FahmidurRidoy, MD AshaduzamanMahajabin, SK FahemaTasawar, Sadman Rahman2025-09-182025-09-1820252025-06ID 24241275ID 20301021ID 20341013ID 21201680http://hdl.handle.net/10361/26773Cataloged from PDF version of thesis.Includes bibliographical references (pages 50-52).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2025.We recommend an effective,reliable and efficient deep-learning approach to classify bone fractures using X-ray images. The proposed system comprises several steps as dataset collection, preprocessing, and categorization of fractures. The dataset contains different types of X-ray images for various fractures and annotated as fractured and non-fractured cases. Dataset was collected from Kaggle. The images were processed through resizing,augmentation to be standardized for deep learning models. The classification of fractures utilizes neural network paged deep learning models as the last process. The research uses Inception,VGG-19 and a custom CNN model for fracture detection while using Grad-CAM to demonstrate how each model makes its decisions. These models utilize CNN architectures to overcome current models accuracy limitations when detecting fractures. The study also shows how CNN-based approaches elevate the precision of bone fracture detection which creates potential benefits for medical use and improved patient healthcare.52 pagesenBRAC University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Bone fracturesX-ray imagesMedical diagnosticsRadiologistsDeep learningConvolutional neural networksFractures, Bone.X-ray microscopy.Radiology.Neural networks (Computer science).Datra mining.Thesis