Akademik Veri Yönetim Sistemi
JOURNAL OF IMAGING INFORMATICS IN MEDICINE, 2026 (SCI-Expanded, Scopus)
Botox is one of the most frequently performed procedures in cosmetic dermatology, aimed at reducing wrinkles and enhancing facial aesthetics. However, the procedure is technically demanding, time-consuming, and physically fatiguing, and it is prone to both intra- and inter-expert variability. Consequently, automated systems play a crucial role in ensuring accurate and consistent identification of injection points. In this study, we propose an enhanced YOLOv8-based object detection framework by integrating two architectural modules: the Convolutional Block Attention Module (CBAM) and the Bidirectional Feature Pyramid Network (BiFPN), to enable precise detection of Botox injection points on facial images. The proposed approach is evaluated on four clinically relevant subsets of a novel high-resolution dataset, demonstrating consistent improvements over the baseline YOLOv8n architecture. The integration of CBAM and BiFPN results in relative mAP@0.5 gains ranging from 1.3 to 4.2% on the validation sets, with the most significant improvements observed in small wrinkle localization tasks. Overall, the proposed system presents a promising step toward AI-assisted clinical decision support in cosmetic dermatology.