Ex vivo detection of mandibular incisors' root canal morphology using cone-beam computed tomography with 4 different voxel sizes and micro-computed tomography

Background In recent years, cone-beam computed tomography (CBCT) has been widely used to evaluate patients' root canal anatomy due to its high resolution and noninvasive nature. As voxel size is one of the most important parameters affecting CBCT image quality, the current study evaluated the diagnostic potential of CBCT with 4 different voxel sizes in the detection of double root canal systems and accessory canals (ACs) in permanent mandibular incisors. Methods A total of 106 extracted mandibular permanent incisors were collected from the dental clinics, and then were scanned by using micro-CT with a voxel size of 9 mu m. The teeth were then fixed in the tooth sockets of human dry mandibles and scanned by using a CBCT device with 4 different voxel sizes (300, 200, 250, and 125 mu m). Four observers detected in blind the root canal morphology of the teeth according to the CBCT images, and the presence or absence of a double root canal system, and the presence or absence of ACs, were scored according to a 5-point scale, respectively. Receiver operating characteristic (ROC) analysis was performed, and DeLong test was used to compare the area under the curve (AUC) values and the micro-CT data was taken as a gold standard. Results Among 106 sample teeth, 25 specimens with a double root canal system were identified by the micro-CT. ROC curve analysis of the data obtained by the four observers showed that in the detection of double root canal systems, the AUC values ranged from 0.765 to 0.889 for 300 mu m voxel size, from 0.877 to 0.926 for 250 mu m voxel size, from 0.893 to 0.967 for 200 mu m voxel size, and from 0.914 to 0.967 for 125 mu m voxel size (all p < 0.01). In general, we observed a trend that the AUC values, sensitivity, and specialty increased with the decrease in the voxel size, and significantly higher AUC values were detected in 125 mu m voxel size images. In the detection of ACs, ROC curve analysis showed that among the four observers, the AUC values ranged from 0.554 to 0.639 for 300 mu m voxel size, from 0.532 to 0.654 for 250 mu m voxel size, from 0.567 to 0.626 for 200 mu m voxel size, and from 0.638 to 0.678 for 125 mu m voxel size. CBCT images at a voxel size of 125 mu m had a weak diagnostic potential (AUC: 0.5-0.7, all p < 0.05) in the detection of AC, with a lower sensitivity ranging from 36.8 to 57.9% and a higher specialty ranging from 73.6 to 98.8%. Conclusions CBCT with 300 mu m voxel size could only provide moderate diagnostic accuracy in the detection of a double canal system in mandibular incisors. CBCT with a voxel size of 125 mu m exhibited high diagnostic value in the detection of double canal systems, while showing low but statistically significant value in the detection of ACs.