Answers are grounded in this paper and cite their sources.
Bone cancer classification from computed tomography (CT) images is challenging because abnormal changes in bone structure and texture can be subtle. This study proposes a Gabor-Enhanced EfficientNet model for automated classification of pelvic CT images into Normal and Cancerous categories. The proposed framework first preprocesses the CT images and applies Gabor filtering to enhance directional texture and structural patterns. The Gabor representation is then fused with the original CT image to preserve both anatomical and texture information. The fused images are classified using EfficientNet, which learns discriminative features for binary classification. The effectiveness of the proposed model is evaluated using a comprehensive set of performance indicators, namely accuracy, precision, sensitivity, specificity, F1-score, and Matthews correlation coefficient. The proposed method combines Gabor-based texture features with deep learning for bone cancer classification from CT images.
No takes yet. Share an insight, caveat, or question.
Kour et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: