A novel radiological software prototype for automatically detecting the inner ear and classifying normal from malformed anatomy.

BACKGROUND: To develop an effective radiological software prototype that could read Digital Imaging and Communications in Medicine (DICOM) files, crop the inner ear automatically based on head computed tomography (CT), and classify normal and inner ear malformation (IEM). METHODS: A retrospective analysis was conducted on 2053 patients from 3 hospitals. We extracted 1200 inner ear CTs for importing, cropping, and training, testing, and validating an artificial intelligence (AI) model. Automated cropping algorithms based on CTs were developed to precisely isolate the inner ear volume. Additionally, a simple graphical user interface (GUI) was implemented for user interaction. Using cropped CTs as input, a deep learning convolutional neural network (DL CNN) with 5-fold cross-validation was used to classify inner ear anatomy as normal or abnormal. Five specific IEM types (cochlear hypoplasia, ossification, incomplete partition types I and III, and common cavity) were included, with data equally distributed between classes. Both the cropping tool and the AI model were extensively validated. RESULTS: The newly developed DICOM viewer/software successfully achieved its objectives: reading CT files, automatically cropping inner ear volumes, and classifying them as normal or malformed. The cropping tool demonstrated an average accuracy of 92.25%. The DL CNN model achieved an area under the curve (AUC) of 0.86 (95% confidence interval: 0.81-0.91). Performance metrics for the AI model were: accuracy (0.812), precision (0.791), recall (0.8), and F1-score (0.766). CONCLUSION: This study successfully developed and validated a fully automated workflow for classifying normal versus abnormal inner ear anatomy using a combination of advanced image processing and deep learning techniques. The tool exhibited good diagnostic accuracy, suggesting its potential application in risk stratification. However, it is crucial to emphasize the need for supervision by qualified medical professionals when utilizing this tool for clinical decision-making.

Applications of visualizing cochlear basal turn in cochlear implantation.

Objective: To report a reliable method in obtaining optimal cochlear basal turn and cross-section (c/s) of internal auditory canal (IAC) supporting Cochlear implantation (CI) procedure. Materials and Methods: Computer tomography (CT) and magnetic resonance image (MRI) scans of potential CI candidates from 2018 to 2022 from the tertiary center were considered for analysis. Slicer software was used in three-dimensional (3D) segmentation of inner ear and for capturing the cochlear basal turn. Results: A total of 1932 head scans were made available for the analysis and out of which 1866 scans had normal anatomy (NA) inner ear. Incomplete partition (IP) type-I was identified in 19 ears, IP type-II in 27 ears, IP type-III in 6 ears, cochlear hypoplasia (CH) type-I in 6 ears, CH type-II in 1 ear, CH type-III in 3 ears, and CH type-IV is 3 ears, and enlarged vestibular aqueduct syndrome in 1 ear. 3D segmented inner ear helped in successfully obtaining the cochlear basal turn and the c/s of IAC in all anatomical types. Time taken to capture the cochlear basal turn with the help of 3D segmented inner ear was <1 min. Within the NA category, five cases showed scalar ossification, and its extent was identified in the cochlear basal turn. Conclusion: The identification and the extent of ossification in the scala tympani, shape of the basal turn, and the cochlear size measurement in cochlear basal turn has high clinical relevance as this helps in surgical planning and in choosing appropriate electrode length. Level of evidence: Level 2 to the best of our understanding.