Automatic Alignment and Performance Validation of Temporal Bone Standard Planes in U-HRCT

Objective This study aimed to validate an automatic standard-plane alignment algorithm for temporal bone ultra-high resolution CT (U-HRCT) using large-scale imaging datasets. Based on lateral semicircular canal segmentation and statistical priors of angles between reference lines and planes, the proposed algorithm solves the problem of tedious and inefficient manual post-processing during unilateral temporal bone examinations. In addition, we performed clinical efficacy evaluation and analysis of cases with alignment failure to assess the reliability of this algorithm. A total of 3094 patients (5668 ears) with U-HRCT data were enrolled retrospectively. A Inner ear substructure segmentation network model was applied to automatically segment the lateral semicircular canal (LSC). Statistical priors of the extracted reference line-plane angles (θ) were adopted to identify and align standard unilateral planes. A three-point scoring system was adopted to evaluate the automatic alignment outcomes of all 5668 ear samples. For samples with failed alignment, further three-point scoring was performed on corresponding automatic LSC segmentation results, followed by an analysis of failure causes. Finally, we compared the LSC automatic segmentation scores of randomly sampled success group and the failure group. Among the 5668 enrolled ears, scoring results demonstrated that 69.83% (3958 ears) achieved a score of 3 (excellent), 21.81% (1236 ears) scored 2 (good), and 8.36% (474 ears) scored 1 (failure), yielding a qualified rate (score≥2) of 91.64%. Within the 474 ears with alignment failure, none of the automatic LSC segmentations attained a score of 3 (intact segmentation with well-defined borders); 6.12% (29 ears) were graded 2 (essentially intact segmentation with partial marginal deviation), and the remaining 93.88% (445 ears) were graded 1 (incomplete segmentation, blurred boundaries or positional offset). There was a statistically significant difference in LSC segmentation scores between the qualified alignment group and the failed alignment group, indicating poor LSC segmentation served as the predominant direct contributor to alignment failure. Etiological analysis of failures revealed the following constituent ratios: inner ear anatomical variation or malformation sparing the lateral semicircular canal (10.34%), abnormal temporal bone mineral density or osseous defects unrelated to LSC (27.00%), postoperative changes secondary to metallic implant placement (12.66%), and intrinsic algorithmic failure of automatic segmentation (50.00%).The proposed automatic alignment method relying on LSC segmentation and statistical priors of reference line-plane angles achieves a qualified rate of 91.64% for standard slice alignment of unilateral temporal bone on U-HRCT, which markedly improves the standardisation and efficiency of radiological post-processing. Alignment failure is strongly correlated with LSC segmentation quality, providing a clear direction for the optimisation of subsequent algorithms.