Retrospective in silico evaluation of optimized preoperative planning for temporal bone surgery

Application of Artificial Intelligence in Otology: Past, Present, and Future

Artificial Intelligence (AI) is a concept whose goal is to imitate human intellectual activity in computers. It emerged in the 1950s and has gone through three booms. We are in the third boom, and it will continue. Medical applications of AI include diagnosing otitis media from images of the eardrum, often outperforming human doctors. Temporal bone CT and MRI analyses also benefit from AI, with segmentation accuracy improved in anatomically significant structures or diagnostic accuracy improved in conditions such as otosclerosis and vestibular schwannoma. In treatment, AI predicts hearing outcomes for sudden sensorineural hearing loss and post-operative hearing outcomes for patients who have undergone tympanoplasty. AI helps patients with hearing aids hear in challenging situations, such as in noisy environments or when multiple people are speaking. It also provides fitting information to help improve hearing with hearing aids. AI also improves cochlear implant mapping and outcome prediction, even in cases of cochlear malformation. Future trends include generative AI, such as ChatGPT, which can provide medical advice and information, although its reliability and application in clinical settings requires further investigation.

Towards fully automated inner ear analysis with deep-learning-based joint segmentation and landmark detection framework

Automated analysis of the inner ear anatomy in radiological data instead of time-consuming manual assessment is a worthwhile goal that could facilitate preoperative planning and clinical research. We propose a framework encompassing joint semantic segmentation of the inner ear and anatomical landmark detection of helicotrema, oval and round window. A fully automated pipeline with a single, dual-headed volumetric 3D U-Net was implemented, trained and evaluated using manually labeled in-house datasets from cadaveric specimen ([Formula: see text]) and clinical practice ([Formula: see text]). The model robustness was further evaluated on three independent open-source datasets ([Formula: see text] scans) consisting of cadaveric specimen scans. For the in-house datasets, Dice scores of [Formula: see text], intersection-over-union scores of [Formula: see text] and average Hausdorff distances of [Formula: see text] and [Formula: see text] voxel units were achieved. The landmark localization task was performed automatically with an average localization error of [Formula: see text] voxel units. A robust, albeit reduced performance could be attained for the catalogue of three open-source datasets. Results of the ablation studies with 43 mono-parametric variations of the basal architecture and training protocol provided task-optimal parameters for both categories. Ablation studies against single-task variants of the basal architecture showed a clear performance benefit of coupling landmark localization with segmentation and a dataset-dependent performance impact on segmentation ability.

A Self-Configuring Deep Learning Network for Segmentation of Temporal Bone Anatomy in Cone-Beam CT Imaging

OBJECTIVE

Preoperative planning for otologic or neurotologic procedures often requires manual segmentation of relevant structures, which can be tedious and time-consuming. Automated methods for segmenting multiple geometrically complex structures can not only streamline preoperative planning but also augment minimally invasive and/or robot-assisted procedures in this space. This study evaluates a state-of-the-art deep learning pipeline for semantic segmentation of temporal bone anatomy.

STUDY DESIGN

A descriptive study of a segmentation network.

SETTING

Academic institution.

METHODS

A total of 15 high-resolution cone-beam temporal bone computed tomography (CT) data sets were included in this study. All images were co-registered, with relevant anatomical structures (eg, ossicles, inner ear, facial nerve, chorda tympani, bony labyrinth) manually segmented. Predicted segmentations from no new U-Net (nnU-Net), an open-source 3-dimensional semantic segmentation neural network, were compared against ground-truth segmentations using modified Hausdorff distances (mHD) and Dice scores.

RESULTS

Fivefold cross-validation with nnU-Net between predicted and ground-truth labels were as follows: malleus (mHD: 0.044 ± 0.024 mm, dice: 0.914 ± 0.035), incus (mHD: 0.051 ± 0.027 mm, dice: 0.916 ± 0.034), stapes (mHD: 0.147 ± 0.113 mm, dice: 0.560 ± 0.106), bony labyrinth (mHD: 0.038 ± 0.031 mm, dice: 0.952 ± 0.017), and facial nerve (mHD: 0.139 ± 0.072 mm, dice: 0.862 ± 0.039). Comparison against atlas-based segmentation propagation showed significantly higher Dice scores for all structures (p < .05).

CONCLUSION

Using an open-source deep learning pipeline, we demonstrate consistently submillimeter accuracy for semantic CT segmentation of temporal bone anatomy compared to hand-segmented labels. This pipeline has the potential to greatly improve preoperative planning workflows for a variety of otologic and neurotologic procedures and augment existing image guidance and robot-assisted systems for the temporal bone.

Application of UNETR for automatic cochlear segmentation in temporal bone CTs

OBJECTIVE

To investigate the feasibility of a deep learning method based on a UNETR model for fully automatic segmentation of the cochlea in temporal bone CT images.

METHODS

The normal temporal bone CTs of 77 patients were used in 3D U-Net and UNETR model automatic cochlear segmentation. Tests were performed on two types of CT datasets and cochlear deformity datasets.

RESULTS

Through training the UNETR model, when batch_size=1, the Dice coefficient of the normal cochlear test set was 0.92, which was higher than that of the 3D U-Net model; on the GE 256 CT, SE-DS CT and Cochlear Deformity CT dataset tests, the Dice coefficients were 0.91, 0.93, 0 93, respectively.

CONCLUSION

According to the anatomical characteristics of the temporal bone, the use of the UNETR model can achieve fully automatic segmentation of the cochlea and obtain an accuracy close to manual segmentation. This method is feasible and has high accuracy.