Multi-atlas segmentation of the facial nerve from clinical CT for virtual reality simulators

Gare, Bradley; Hudson, Thomas J.; Rohani, Seyed Alireza; Allen, Daniel; Agrawal, Sumit; Ladak, Hanif M.

doi:10.1007/s11548-019-02091-0

Cited by 11 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our findings in the objective analysis are superior to those of other recently published automated segmentation methods for the inner ear, ossicles 28 and facial nerve 5,15 . Despite these encouraging metrics, there is still variability between the structures.…”

Section: Discussionmentioning

confidence: 52%

Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Neves

Tran

Kessler

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Middle- and inner-ear surgery is a vital treatment option in hearing loss, infections, and tumors of the lateral skull base. Segmentation of otologic structures from computed tomography (CT) has many potential applications for improving surgical planning but can be an arduous and time-consuming task. We propose an end-to-end solution for the automated segmentation of temporal bone CT using convolutional neural networks (CNN). Using 150 manually segmented CT scans, a comparison of 3 CNN models (AH-Net, U-Net, ResNet) was conducted to compare Dice coefficient, Hausdorff distance, and speed of segmentation of the inner ear, ossicles, facial nerve and sigmoid sinus. Using AH-Net, the Dice coefficient was 0.91 for the inner ear; 0.85 for the ossicles; 0.75 for the facial nerve; and 0.86 for the sigmoid sinus. The average Hausdorff distance was 0.25, 0.21, 0.24 and 0.45 mm, respectively. Blinded experts assessed the accuracy of both techniques, and there was no statistical difference between the ratings for the two methods (p = 0.93). Objective and subjective assessment confirm good correlation between automated segmentation of otologic structures and manual segmentation performed by a specialist. This end-to-end automated segmentation pipeline can help to advance the systematic application of augmented reality, simulation, and automation in otologic procedures.

show abstract

Section: Discussionmentioning

confidence: 52%

Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Neves

Tran

Kessler

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

“…However, the generalisation and fidelity of active shape models are limited by the training dataset and the predefined deformation model. Gare et al 22 . present a semiautomatic multiatlas segmentation method of the facial nerve from clinical CT for virtual reality simulators.…”

Section: Related Workmentioning

confidence: 99%

“…Existing automatic segmentation methods in the literature for temporal bone anatomy from temporal bone CT images can be divided into the following two categories: active shape model (ASM)based 19,20 and atlas-based approaches. [21][22][23] Actually, the former is often performed accompanying with the latter. Atlas-based methods cast the segmentation problem into a spatial registration problem between the subject of interest and a fine pre-segmented model (such as from high-resolution micro-CT images).…”

Section: Related Workmentioning

confidence: 99%

“…However, the generalisation and fidelity of active shape models are limited by the training dataset and the predefined deformation model. Gare et al 22 introduce U-Net to pancreas segmentation. Couteaux et al 5 propose to use U-Net for renal cortex segmentation.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic segmentation of temporal bone structures from clinical conventional CT using a CNN approach

et al. 2021

Robotics Computer Surgery

View full text Add to dashboard Cite

Background Automatic segmentation of temporal bone structures from patients' conventional computed tomography (CT) data plays an important role in the image‐guided cochlear implant surgery. Existing convolutional neural network approaches have difficulties in segmenting such small tubular structures. Methods We propose a light‐weight three‐dimensional convolutional neural network referred to as W‐Net to achieve multiobjective segmentation of temporal bone structures including the cochlear labyrinth, ossicular chain and facial nerve from conventional temporal bone CT images. Data augmentation with morphological enhancement is proposed to increase the segmentation accuracy of small tubular structures. Evaluation against the state‐of‐the‐art methods is performed. Results Our method achieved mean Dice similarity coefficients (DSCs) of 0.90, 0.85 and 0.77 for the cochlear labyrinth, ossicular chain and facial nerve, respectively. These results were also close to the DSCs between human expert annotators (0.91, 0.91 and 0.72). Conclusions Our method achieves human‐level accuracy in the segmentation of the cochlear labyrinth, ossicular chain and facial nerve.

show abstract

Facial and Cochlear Nerves Characterization Using Deep Reinforcement Learning for Landmark Detection

Diez

Sundgaard

Patou

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Multi-atlas segmentation of the facial nerve from clinical CT for virtual reality simulators

Cited by 11 publications

References 28 publications

Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Fully automated preoperative segmentation of temporal bone structures from clinical CT scans

Automatic segmentation of temporal bone structures from clinical conventional CT using a CNN approach

Facial and Cochlear Nerves Characterization Using Deep Reinforcement Learning for Landmark Detection

Contact Info

Product

Resources

About