Leveraging AdamW Golden Search Optimized Multi-Level Attention Stacked Feature Generators for Cephalometric Landmark Prediction

Abstract

The identification of cephalometric landmarks is an essential and imperative process commonly employed in the planning and diagnosis of orthodontic treatments. Computer-aided completely automated methods have the potential to enhance the efficiency of orthodontists and orthognathic surgeons by accurately identifying landmarks from cephalograms. In this article, an AdamW Golden Search Optimization based multi-level attention enhanced Stacked Feature Generator architecture (AWGSO_SFGCephX) is proposed to automatically predict 19 landmarks from cephalometric radiographs. The Stacked Feature Generator (SFGCephX) model utilized multiple multi-level attention integrated feature extractors combined with a characteristic meta-learner to provide well-balanced landmark prediction results with higher Successful Detection Rates (SDRs) and minimum Mean Radial Errors (MREs) with Standard Deviations (SDs). The proposed architecture collaborated Gaussian dropout layers to acquire more resilient unique landmark features that are not excessively reliant on specific input landmarks and spatial dropout strategy for learning more robust landmark features from the skull X-rays by randomly dropping out the feature maps during the training. The SFGCephX is trained using the AWGSO technique by integrating Golden Search Optimization (GSO) algorithm with AdamW optimizer. The proposed framework achieved average SDRs of 89.17%, 79.8% for Test1 and Test2 dataset in 2mm precision using the Institute of Electrical and Electronics Engineers (IEEE) organized 2015 International Symposium on Biomedical Imaging (ISBI) grand challenge for dental X-ray analysis dataset. The proposed AWGSO_SFGCephX is evaluated using a clinical private dataset consisting of 130 skull X-rays obtained from Solanki Dental Care Clinic in Sharjah, United Arab Emirates, and obtained an average SDR of 75.71% within precision range of 2 mm.