Standard observation plane annotation for diagnosis of ossicular chain in the temporal bone CT images

Temporal bone CT is an essential technique for diagnosing ossicular chain trauma, and the location of standard observation planes (SOP) is the foundation of imaging diagnosis. The ossicular chain is small in volume, and there are about 11 standard observation planes for ossicular chain diagnosis, so it is a professional and time-consuming task to label SOPs accurately. An automatic annotation method of SOP is proposed. Firstly, an SOP-Graph model is introduced to represent the spatial relative position of different SOPs and the radiologists' SOP searching experience. Secondly, based on the precise segmentation of auditory ossicles, an SOP annotation algorithm was proposed to implement the parameter estimation of the SOP Graph. Finally, the evaluation of ossicular chain SOP localization was conducted, which converts the intensive SOP labeling task to automatic labeling and subjective verification. In the experiments, 610 CT images of temporal bone were automatically annotated, and the average success rate of annotation was 65.8% after being verified by a radiologist. By converting the manual annotation to automatic annotation and subjective verification, the annotation time of one case was reduced from 12 min to about 2 min. A data set that included 4414 SOP annotated slices was established.