TY - JOUR
T1 - Comparison of deep learning segmentation and multigrader-annotated mandibular canals of multicenter CBCT scans
AU - Järnstedt, Jorma
AU - Sahlsten, Jaakko
AU - Jaskari, Joel
AU - Kaski, Kimmo
AU - Mehtonen, Helena
AU - Lin, Ziyuan
AU - Hietanen, Ari
AU - Sundqvist, Osku
AU - Varjonen, Vesa
AU - Mattila, Vesa
AU - Prapayasotok, Sangsom
AU - Nalampang, Sakarat
N1 - Funding Information:
The project was partly supported by Business Finland under project “Digital and Physical Immersion in Radiology and Surgery”. Mandibular canal annotations used in this study were partly provided by Antti Lehtinen, D.D.S. and Mika Mattila, D.D.S., both Specialists of Dentomaxillofacial Radiology.
PY - 2022/12
Y1 - 2022/12
N2 - Deep learning approach has been demonstrated to automatically segment the bilateral mandibular canals from CBCT scans, yet systematic studies of its clinical and technical validation are scarce. To validate the mandibular canal localization accuracy of a deep learning system (DLS) we trained it with 982 CBCT scans and evaluated using 150 scans of five scanners from clinical workflow patients of European and Southeast Asian Institutes, annotated by four radiologists. The interobserver variability was compared to the variability between the DLS and the radiologists. In addition, the generalisation of DLS to CBCT scans from scanners not used in the training data was examined to evaluate its out-of-distribution performance. The DLS had a statistically significant difference (p < 0.001) with lower variability to the radiologists with 0.74 mm than the interobserver variability of 0.77 mm and generalised to new devices with 0.63 mm, 0.67 mm and 0.87 mm (p < 0.001). For the radiologists’ consensus segmentation, used as a gold standard, the DLS showed a symmetric mean curve distance of 0.39 mm, which was statistically significantly different (p < 0.001) compared to those of the individual radiologists with values of 0.62 mm, 0.55 mm, 0.47 mm, and 0.42 mm. These results show promise towards integration of DLS into clinical workflow to reduce time-consuming and labour-intensive manual tasks in implantology.
AB - Deep learning approach has been demonstrated to automatically segment the bilateral mandibular canals from CBCT scans, yet systematic studies of its clinical and technical validation are scarce. To validate the mandibular canal localization accuracy of a deep learning system (DLS) we trained it with 982 CBCT scans and evaluated using 150 scans of five scanners from clinical workflow patients of European and Southeast Asian Institutes, annotated by four radiologists. The interobserver variability was compared to the variability between the DLS and the radiologists. In addition, the generalisation of DLS to CBCT scans from scanners not used in the training data was examined to evaluate its out-of-distribution performance. The DLS had a statistically significant difference (p < 0.001) with lower variability to the radiologists with 0.74 mm than the interobserver variability of 0.77 mm and generalised to new devices with 0.63 mm, 0.67 mm and 0.87 mm (p < 0.001). For the radiologists’ consensus segmentation, used as a gold standard, the DLS showed a symmetric mean curve distance of 0.39 mm, which was statistically significantly different (p < 0.001) compared to those of the individual radiologists with values of 0.62 mm, 0.55 mm, 0.47 mm, and 0.42 mm. These results show promise towards integration of DLS into clinical workflow to reduce time-consuming and labour-intensive manual tasks in implantology.
UR - http://www.scopus.com/inward/record.url?scp=85141147712&partnerID=8YFLogxK
U2 - 10.1038/s41598-022-20605-w
DO - 10.1038/s41598-022-20605-w
M3 - Article
C2 - 36329051
AN - SCOPUS:85141147712
SN - 2045-2322
VL - 12
SP - 1
EP - 11
JO - Scientific Reports
JF - Scientific Reports
IS - 1
M1 - 18598
ER -