.png){kind=icon}
返回
New ultra-fast algorithm for cochlear implant misalignment detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ejrad.2022.110283.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Purpose: Postoperative imaging following cochlear implant (CI) placement is currently the only means of diagnosing proper electrode position. Manual multiplanar reconstruction (MPR) analysis of CT and CBCT is time-consuming and requires extensive training. This study aims to evaluate the rate of CI misalignment and to determine the amount of time necessary to reach a diagnosis of correct versus incorrect CI placement for readers of different experience levels, using a novel algorithm for image analysis (ACIR) compared to MPR analysis. Method: The retrospective single centre study included 333 patients with cochlear implant surgery between May 2002 and May 2021. Postoperative CT and CBCT images were evaluated in three subgroups and the time to diagnosis was documented. Group 1: image evaluation using conventional MPR analysis; group 2: image evaluation by an experienced neuroradiologist via a novel ultra-fast algorithm; group 3: image evaluation by a young specialist via novel ultra-fast algorithm. T-test and Pearson's chi-squared test were used for inter-group comparisons. Results: 333 patients (63.3 +/- 15.9 years; 188 men) with 335 CIs were evaluated. The rate of CI misalignment diagnosed from 3D imaging was 14.3% (n = 48). MPR analysis required 255.7 +/- 70.4 s per temporal bone, whereas Slicer plugin reduced analysis time to 83.3 +/- 7.7 s (p < 0.001) for the experienced reader and 89.6 +/- 8.7 s for the young specialist (p < 0.001). Conclusion: 3D postoperative imaging reveals high incidences of CI misalignment. Application of a novel ultra-fast algorithm significantly reduces the time for diagnosis compared to MPR analysis for readers of varying experience levels.
Keyword:
Cochlea
Cochlea implant
Artificial intelligence
Automatic cochlear image registration
Electrode misalignment
期刊
IF:
3.3
论文数:
1.1W
被引数:
1.8W
机构
引用论文
Deep learning for the fully automated segmentation of the inner ear on MRI.png)
SCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏
查看更多内容