Automatic segmentation and classification of frontal sinuses for sex determination from CBCT scans using a two-stage anatomy-guided attention network

• Published in: Scientific reports Vol. 14; no. 1; pp. 11750 - 14
• Main Authors: da Silva, Renan Lucio Berbel, Yang, Su, Kim, DaEl, Kim, Jun Ho, Lim, Sang-Heon, Han, Jiyong, Kim, Jun-Min, Kim, Jo-Eun, Huh, Kyung-Hoe, Lee, Sam-Sun, Heo, Min-Suk, Yi, Won-Jin
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 23.05.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/1564; 692/700/3032/3093; 692/700/3032/3124; Adult; Anatomy; Anatomy-guided attention; CBCT; Cone-Beam Computed Tomography - methods; Deep learning; Embedding; Female; Frontal sinus; Frontal Sinus - anatomy & histology; Frontal Sinus - diagnostic imaging; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Male; multidisciplinary; Neural Networks, Computer; Science; Science (multidisciplinary); Segmentation; Sex determination; Sex Determination by Skeleton - methods; Sinuses; Deep learning; Sex determination; Anatomy-guided attention; Frontal sinus; CBCT
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-62211-y

Sex determination is essential for identifying unidentified individuals, particularly in forensic contexts. Traditional methods for sex determination involve manual measurements of skeletal features on CBCT scans. However, these manual measurements are labor-intensive, time-consuming, and error-prone. The purpose of this study was to automatically and accurately determine sex on a CBCT scan using a two-stage anatomy-guided attention network (SDetNet). SDetNet consisted of a 2D frontal sinus segmentation network (FSNet) and a 3D anatomy-guided attention network (SDNet). FSNet segmented frontal sinus regions in the CBCT images and extracted regions of interest (ROIs) near them. Then, the ROIs were fed into SDNet to predict sex accurately. To improve sex determination performance, we proposed multi-channel inputs (MSIs) and an anatomy-guided attention module (AGAM), which encouraged SDetNet to learn differences in the anatomical context of the frontal sinus between males and females. SDetNet showed superior sex determination performance in the area under the receiver operating characteristic curve, accuracy, Brier score, and specificity compared with the other 3D CNNs. Moreover, the results of ablation studies showed a notable improvement in sex determination with the embedding of both MSI and AGAM. Consequently, SDetNet demonstrated automatic and accurate sex determination by learning the anatomical context information of the frontal sinus on CBCT scans.