Long-term performance assessment of fully automatic biomedical glottis segmentation at the point of care

Abstract

Deep Learning has a large impact on medical image analysis and lately has been adopted for clinical use at the point of care. However, there is only a small number of reports of long-term studies that show the performance of deep neural networks (DNNs) in such a clinical environment. In this study, we measured the long-term performance of a clinically optimized DNN for laryngeal glottis segmentation. We have collected the video footage for two years from an AI-powered laryngeal high-speed videoendoscopy imaging system and found that the footage image quality is stable across time. Next, we determined the DNN segmentation performance on lossy and lossless compressed data revealing that only 9% of recordings contain segmentation artefacts. We found that lossy and lossless compression are on par for glottis segmentation, however, lossless compression provides significantly superior image quality. Lastly, we employed continual learning strategies to continuously incorporate new data to the DNN to remove aforementioned segmentation artefacts. With modest manual intervention, we were able to largely alleviate these segmentation artefacts by up to 81%. We believe that our suggested deep learning-enhanced laryngeal imaging platform consistently provides clinically sound results, and  together with our proposed continual learning scheme will have a long-lasting impact in the future of laryngeal imaging.

Competing Interest Statement

The authors have declared no competing interest.

Funding Statement

This work was funded in part by the German Research Foundation (DFG, https://www.dfg.de/) under grant no. SCHU 3441/3-2 (to AS).

Author Declarations

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Not Applicable

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The ethics committee of the Friedrich-Alexander-University and the University Hospital Erlangen approved the study (approval number #290_15).

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Not Applicable

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Not Applicable

I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.

Not Applicable

Data Availability

Primary data cannot be shared publicly because of patient data protection and privacy measurements. Data are available upon reasonable request from the corresponding author in close exchange with the ethics committee of the University Hospital Erlangen for researchers who meet the criteria for access to confidential data. However, we do share the code that has been used to analyze the data and the deep neural network such that our results can be confirmed independently.

留言 (0)

沒有登入
gif