Early detection of acute mandibular osteomyelitis using computed tomography texture analysis

Objectives

Early detection of acute suppurative osteomyelitis is difficult in clinical practice. The aim of this study was to evaluate the usefulness of computed tomography (CT) texture analysis in diagnosing acute mandibular osteomyelitis.

Materials and Methods

Seventeen patients who complained of severe mandibular pain and underwent CT examinations between July 2018 and September 2023 were included in the study. MaZda ver.3.3 software was used to extract 279 texture features from region of interests (ROIs) on CT images of patients with osteomyelitis (n = 17) and controls (contralateral sides) (n = 17). The acute osteomyelitis sites and controls were compared for each feature, and the 6 features that differed most significantly between groups were selected using Fisher's coefficient. The groups were compared using the Wilcoxon signed-rank test or paired t-test. Significance was set at P < 0.05. Receiver operating characteristic curves were used to evaluate the ability of the CT texture features to detect acute osteomyelitis.

Results

Significant differences in all 6 features were observed between the acute osteomyelitis and controls (P < 0.001). The sensitivity, specificity, accuracy, and area under the curve for detecting acute osteomyelitis were 0.94–1.0, 0.94–1.0, 0.97–1.0, and 0.96–1.0, respectively.

Conclusions

CT texture analysis may be useful in the early detection of acute mandibular osteomyelitis.