An end-to-end deep learning framework for the automated diagnosis of OPLL in CT images

Abstract

Accurate assessment of K-line status is vital for surgical planning and prognosis in patients with cervical Ossification of the Posterior Longitudinal Ligament (OPLL). However, variations in tissue appearance and morphological similarities between adjacent vertebrae in lateral cervical CT images complicate reliable edge identification for algorithms, posing challenges in recognizing easily confused vertebral landmarks. To address this issue, we propose an innovative approach that integrates K-line theory with deep learning techniques to evaluate K-line status efficiently and accurately in lateral cervical CT images of OPLL patients. Our method, the Dilated TransUNet, employs dilated convolution and Transformer modules to enhance the identification of easily confused vertebral landmarks, thereby improving detection accuracy. Additionally, we developed a discriminative algorithm utilizing dynamic thresholds for detailed pixel analysis around suspected ossification areas, effectively differentiating ossification from surrounding tissues. Experimental results demonstrate that our method achieves an average landmark detection accuracy of 98.49% and an image classification accuracy of 97.8%, both of which surpass existing methodologies. This framework reliably determines the position of ossification relative to the K-line, providing essential support for clinical surgical decision-making.