CT-based quantification of trachea shape to detect invasion by thyroid cancer

ObjectiveThis study aims to develop a CT-based method for quantifying tracheal shape and evaluating its ability to distinguish between cases with or without tracheal invasion in patients with thyroid carcinoma.MethodsA total of 116 quantitative shape features, including 56 geometric moments and 60 bounding shape features, were defined. The tracheal lumen was semi-automatically defined with a CT threshold of less than - 500 HU. Three contiguous slices with the 1st, 2nd, and 3rd smallest trachea lumen areas were contiguously selected, and the appropriate number of slices to be included was determined. Fifty-six patients with differentiated thyroid carcinoma (DTC) invading the trachea and 22 patients with DTC but without invasion were retrospectively included. A receiver operating characteristic (ROC) curve was applied to select the representative shape features and determine the optimal threshold.Results23.3%, 25.9%, and 24.1% of the features displayed an area under the ROC curve (AUC) >= 0.800 when derived from 1, 2, and 3 slices, respectively. Calculating feature values from two slices with the 1st and 2nd smallest tracheal lumen area were considered appropriate. Six final features, including 3 geometric moments and 3 bounding shape features, were selected to determine the tracheal invasion status of DTC and displayed AUCs of 0.875-0.918, accuracies of 0.821-0.891, sensitivities of 0.813-0.893, and specificities of 0.818-0.932, outperforming the visual evaluation results.ConclusionsGeometric moments and bounding shape features can quantify the tracheal shape and are reliable for identifying DTC tracheal invasion. The selected features quantified the extent of tracheal deformity in DTC patients with and without tracheal invasion.Clinical relevance statementSix geometric features provide a non-invasive, semi-automated evaluation of the tracheal invasion status of thyroid cancer.Key Points center dot A novel method for quantifying tracheal shape using 56 geometric moments and 60 bounding shape features was developed.center dot Six features identify tracheal invasion by thyroid carcinoma.center dot The selected features quantified the extent of tracheal deformity in differentiated thyroid carcinoma patients with and without tracheal invasion.Key Points center dot A novel method for quantifying tracheal shape using 56 geometric moments and 60 bounding shape features was developed.center dot Six features identify tracheal invasion by thyroid carcinoma.center dot The selected features quantified the extent of tracheal deformity in differentiated thyroid carcinoma patients with and without tracheal invasion.Key Points center dot A novel method for quantifying tracheal shape using 56 geometric moments and 60 bounding shape features was developed.center dot Six features identify tracheal invasion by thyroid carcinoma.center dot The selected features quantified the extent of tracheal deformity in differentiated thyroid carcinoma patients with and without tracheal invasion.

Automated summary

This study developed a CT-based method to quantify tracheal shape and evaluate its ability to distinguish between cases with or without tracheal invasion in patients with thyroid carcinoma. By selecting appropriate slices and features, this method can reliably identify tracheal invasion in DTC patients.