Nuclear Magnetic Resonance Microimaging for the Qualitative Assessment of Root Canal Treatment: An Ex Vivo Preliminary Study

Artificial Intelligence in Orthopedic Radiography Analysis: A Narrative Review

Artificial intelligence (AI) in medicine is a rapidly growing field. In orthopedics, the clinical implementations of AI have not yet reached their full potential. Deep learning algorithms have shown promising results in computed radiographs for fracture detection, classification of OA, bone age, as well as automated measurements of the lower extremities. Studies investigating the performance of AI compared to trained human readers often show equal or better results, although human validation is indispensable at the current standards. The objective of this narrative review is to give an overview of AI in medicine and summarize the current applications of AI in orthopedic radiography imaging. Due to the different AI software and study design, it is difficult to find a clear structure in this field. To produce more homogeneous studies, open-source access to AI software codes and a consensus on study design should be aimed for.

Reliability and accuracy of dental MRI for measuring root canal length of incisors and canines: a clinical pilot study

To evaluate whether high-resolution, non-contrast-enhanced dental MRI (dMRI) can reliably and accurately measure the canal length of incisors and canines compared with cone-beam computed tomography (CBCT). Three-Tesla dMRI was performed in 31 participants (mean age: 50.1 ± 14.2 years) with CBCT data. In total, 67 teeth were included (28 from the upper jaw and 39 from the lower jaw; 25 central incisors, 22 lateral incisors, and 20 canines). CBCT and dMRI datasets were reconstructed to visualize the root canal pathway in a single slice in the vestibulo-oral (V-O) and mesio-distal (M-D) direction. Root canal length was measured twice by two radiologists using dMRI and CBCT. Data were statistically analyzed by calculating intraclass correlation coefficients (ICCs) and performing Bland–Altman analysis. The reliability of dMRI measurements was excellent and comparable to that of CBCT measurements (intra-rater I/intra-rater II/inter-rater was 0.990/0.965/0.951 for dMRI vs. 0.990/0.994/0.992 for CBCT in the M-D direction and 0.991/0.956/0.967 for dMRI vs. 0.998/0.994/0.996 for CBCT in the V-O direction). According to Bland–Altman analysis, the mean (95% confidence interval) underestimation of root canal lengths was 0.67 mm (− 1.22 to 2.57) for dMRI and 0.87 mm (− 0.29 to 2.04) for CBCT in the M-D direction/V-O direction. In 92.5% of cases, dMRI measurements of canal length had an accuracy within 0–2 mm. Visualization and measurement of canal length in vivo using dMRI is feasible. The reliability of dMRI measurements was high and comparable to that of CBCT measurements. However, the spatial and temporal resolution of dMRI is lower than that of CBCT, which means dMRI measurements are less accurate than CBCT measurements. This means dMRI is currently unsuitable for measuring canal length in clinical practice.