Intelligent diagnosis of ossicular chain malformations on CT: development and clinical efficacy of a cascaded AI framework.
Authors
Affiliations (6)
Affiliations (6)
- Department of Diagnostic Radiology, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi, China.
- Xi'an Key Laboratory of Metabolic Disease Imaging, Xi'an No.3 Hospital, Affiliated Hospital of Northwest University, Xi'an, Shaanxi, China.
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China.
- Department of Radiology, Xi'an Central Hospital, Xi'an, Shaanxi, China.
- Shaanxi Engineering Research Center of Computational Imaging and Medical Intelligence, Xi'an, Shaanxi, China.
- Xi'an Key Laboratory of Medical Computational Imaging, Xi'an, Shaanxi, China.
Abstract
The aim of this study was to develop and validate a cascaded artificial intelligence (AI) framework using a segmentation-discrimination strategy for automated detection of ossicular chain malformations (OCM) on computed tomography scans. Patients diagnosed with OCM between January 2009 and January 2023, along with healthy controls, were retrospectively enrolled. A coarse-to-fine nnU-Net framework was applied for automated segmentation of the auditory ossicles. Separate discrimination models were developed for the malleus, incus, and stapes, and subsequently integrated to generate a patient-level model. The performance of the proposed framework was compared with deep learning networks, a volume-threshold algorithm, and by radiologists. The temporal external validation was conducted on data from multiple sites within Shaanxi Province, using the same CT vendors. The discriminatory capacity of each ossicular-level model was assessed using area under the curve (AUC), sensitivity, specificity, and accuracy. A total of 2,462 temporal bone computed tomography scans (training set, n = 1,302; test set, n = 556; validation set, n = 604) were analyzed. The cascaded network demonstrated AUC values of 0.962, 0.930, and 0.931 for the malleus, incus, and stapes, respectively. At the patient level, accuracy, sensitivity, and specificity were 0.874, 0.949, and 0.800, respectively, surpassing the performance of ResNet, DenseNet, the volume-threshold algorithm, and junior radiologists, while equaling that of senior radiologists. In temporal validation, the network maintained robust performance, with AUC values of 0.972, 0.973, and 0.963, and patient-level metrics of 0.960 (accuracy), 0.974 (sensitivity), and 0.947 (specificity). The cascaded AI framework using a segmentation-discrimination strategy demonstrated high performance in identifying patients with diverse types of OCMs on computed tomography scans. This approach has the potential to support radiologists in the diagnostic evaluation of OCMs.