SinusNet: Label-Free Segmentation of Maxillary Sinus Lesion in CBCT Images
DaEl Kim, Su Yang, Seryong Kang, Jin Kim, Soyoung Chun, MinHyuk Choi, Won-Jin Yi
To alleviate the workload of data annotation, we propose a label-free approach (SinusNet) for the segmentation of maxillary sinus lesions in CBCT images via learning the anomaly features from diverse synthetic lesions within the normal maxillary sinus. Our SinusNet achieved average F1 of 80.9 ± 11.6%, precision of 82.7 ± 9.1%, and recall of 80.1 ± 15.0%, respectively, and comparable performance with those of previous supervised approaches.
Wednesday 6th July
Poster Session 1.1 - onsite 15:20 - 16:20, virtual 11:00 - 12:00 (UTC+2)