Deep learning 3D V-Net network for auditory ossicle segmentation

Published on August 31, 2022

Imagine you have a fancy 3D scanner that can capture detailed images of the tiny bones in your ear. Now, what if you could use a powerful deep learning method called a 3D V-Net convolutional neural network to automatically identify and separate these delicate little bones? Well, that’s exactly what this study set out to do! The researchers collected high-resolution computed tomography (HRCT) images of patients’ temporal bones and manually segmented the malleus, incus, and stapes. Then, they compared the results of the manual segmentation with those produced by their nifty 3D V-Net network. Guess what? The network did a fantastic job! It achieved impressive similarity coefficients and surface distances when capturing the shape and structure of these miniscule bones. In fact, the network’s accuracy was just as good as the manual segmentation! If you’re curious to dig deeper into this research, follow the link below and check out the full article.

ObjectiveTo explore the feasibility of a deep learning three-dimensional (3D) V-Net convolutional neural network to construct high-resolution computed tomography (HRCT)-based auditory ossicle structure recognition and segmentation models.MethodsThe temporal bone HRCT images of 158 patients were collected retrospectively, and the malleus, incus, and stapes were manually segmented. The 3D V-Net and U-Net convolutional neural networks were selected as the deep learning methods for segmenting the auditory ossicles. The temporal bone images were randomized into a training set (126 cases), a test set (16 cases), and a validation set (16 cases). Taking the results of manual segmentation as a control, the segmentation results of each model were compared.ResultsThe Dice similarity coefficients (DSCs) of the malleus, incus, and stapes, which were automatically segmented with a 3D V-Net convolutional neural network and manually segmented from the HRCT images, were 0.920 ± 0.014, 0.925 ± 0.014, and 0.835 ± 0.035, respectively. The average surface distance (ASD) was 0.257 ± 0.054, 0.236 ± 0.047, and 0.258 ± 0.077, respectively. The Hausdorff distance (HD) 95 was 1.016 ± 0.080, 1.000 ± 0.000, and 1.027 ± 0.102, respectively. The DSCs of the malleus, incus, and stapes, which were automatically segmented using the 3D U-Net convolutional neural network and manually segmented from the HRCT images, were 0.876 ± 0.025, 0.889 ± 0.023, and 0.758 ± 0.044, respectively. The ASD was 0.439 ± 0.208, 0.361 ± 0.077, and 0.433 ± 0.108, respectively. The HD 95 was 1.361 ± 0.872, 1.174 ± 0.350, and 1.455 ± 0.618, respectively. As these results demonstrated, there was a statistically significant difference between the two groups (P < 0.001).ConclusionThe 3D V-Net convolutional neural network yielded automatic recognition and segmentation of the auditory ossicles and produced similar accuracy to manual segmentation results.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>