Automatic segmentation of inner ear on CT-scan using auto-context convolutional neural network

Abstract

Temporal bone CT-scan is a prerequisite in most surgical procedures concerning the ear such as cochlear implants. The 3D vision of inner ear structures is crucial for diagnostic and surgical preplanning purposes. Since clinical CT-scans are acquired at relatively low resolutions, improved performance can be achieved by registering patient-specific CT images to a high-resolution inner ear model built from accurate 3D segmentations based on micro-CT of human temporal bone specimens. This paper presents a framework based on convolutional neural network for human inner ear segmentation from micro-CT images which can be used to build such a model from an extensive database. The proposed approach employs an auto-context based cascaded 2D U-net architecture with 3D connected component refinement to segment the cochlear scalae, semicircular canals, and the vestibule. The system was formulated on a data set composed of 17 micro-CT from public Hear-EU dataset. A Dice coefficient of 0.90 and Hausdorff distance of 0.74 mm were obtained. The system yielded precise and fast automatic inner-ear segmentations.

Bayesian logistic shape model inference: Application to cochlear image segmentation

“…Quantitative comparison of performances is not straightforward due to differences in image modality (CT, µCT or ultra high resolution CT), in metrics (Dice, precision, mean surface error), in subject population (cadaveric vs patient) but also in the target anatomical structures (cochlea vs cochlea labyrinth). In most cases, cochlea segmentation from µCT images are used as ground truth information and a direct comparison between our work with (Raabid et al, 2021) is possible since they used a subset of dataset #3 which is a public database (Wimmer et al, 2019). We see that our unsupervised approach performs as well as the supervised methods with Dice scores in the range [0.85, 0.91] and outperforms previous unsupervised methods.…”

“…The former approaches are mostly based on cochlear shape fitting based on template image registration (Baker and Barnes, 2005), parametric shape model (Baker, 2008). The supervised methods are based on statistical deformation models (Ruiz Pujadas et al, 2018) and deep learning (Lv et al, 2021;Raabid et al, 2021;Heutink et al, 2020).…”

“…Deep Learning) is an effective way to perform image segmentation or processing in many cases. Specifically, in inner ear CT imaging analysis, many works achieved impressive results (Lv et al, 2021;Raabid et al, 2021;Heutink et al, 2020;Wang et al, 2019;Li et al, 2021;Alshazly et al, 2019;Zhang et al, 2019;Wang et al, 2020b). However, supervised learning methods have also many limitations.…”

Ear Biometrics Using Deep Learning: A Survey

“…is architecture is formed from two significant parts: convolutional and deconvolutional networks [24]. Deconvolutional networks are CNNs that operate during a reversed process, and networks extract discriminated features.…”

Development of Mastoid Air Cell System Extraction Method on Temporal CT-scan Image

“…Furthermore, the automatic extraction process on the micro part of the Temporal bone structure from the CT-scan image with the Morphological Enhancement and Convolutional Neural Network (CNN) methods produces an accurate detection of the Temporal bone structure [18]. In another study, it was explained that the segmentation and extraction process using the Convolutional Neural Network (CNN) method combined with the Region Extraction method gave limited results in the middle ear and did not focus on the MACS [19].…”