Intersegmenter Variability in High‐Speed Laryngoscopy‐Based Glottal Area Waveform Measures

Maryn, Youri; Verguts, Monique; Demarsin, Hannelore; Dinther, Joost van; Gómez, Pablo; Schlegel, Patrick; Döllinger, Michael

doi:10.1002/lary.28475

Cited by 23 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…segmenter variability common to glottis segmentation [57], and thus, are performing as good as experts in the field. Our method is also superior to other (fully automatic) glottis segmentation algorithms available [8], [9], [12], as it is validated on a diverse dataset, computationally highly efficient and also highly portable.…”

Section: Discussionmentioning

confidence: 99%

Efficient Biomedical Image Segmentation on EdgeTPUs at Point of Care

Kist

Döllinger

2020

IEEE Access

View full text Add to dashboard Cite

The U-Net architecture is a state-of-the-art neural network for semantic image segmentation that is widely used in biomedical research. It is based on an encoder-decoder framework and its vanilla version shows already high performance in terms of segmentation quality. Due to its large parameter space, however, it has high computational costs on both, CPUs and GPUs. In a research setting, inference time is relevant, but not crucial for the results. However, especially in mobile, clinical applications a light and fast variant would allow deep-learning assisted, objective diagnosis at the point of care. In this work, we suggest an optimized, tiny-weight U-Net for an inexpensive hardware accelerator. We first mined the U-Net architecture to reduce computational complexity to increase runtime performance by simultaneously keeping the accuracy on a high level. Using an open, biomedical dataset for high-speed videoendoscopy (BAGLS), we show that we can dramatically reduce the parameter space and computations by over 99.8% while keeping the segmentation performance at 95% of our baseline. Using a custom upscaling routine, we further successfully deployed our optimized U-Net to an EdgeTPU hardware accelerator to gain costeffective speed improvements on conventional computers and to showcase the applicability of EdgeTPUs for biomedical imaging processing of large images on portable devices. Combining the optimized architecture and the EdgeTPU, we gain a speedup of >79-times compared to our initial baseline while keeping high accuracy. This combination allows to provide immediate results to the clinician, especially in constrained computational environments, and an objective diagnosis at the point of care.

show abstract

Section: Discussionmentioning

confidence: 99%

Efficient Biomedical Image Segmentation on EdgeTPUs at Point of Care

Kist

Döllinger

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This resulted in an average IoU score of 0.772 indicating a high overlap across experts. As recently shown, glottis segmentation is inherently subjective 58 , although we believe that the three experts providing the ground-truth ensured being as objective as possible.…”

Section: Technical Validationmentioning

confidence: 96%

“…Previous studies have shown that inter-and intra-rater variability in voice research can be a concern [55][56][57][58] . The BAGLS dataset aims to compensate for this by using segmentations that were crosschecked by multiple experts.…”

Section: Videoendoscopy and Glottis Segmentation Several Imaging Tecmentioning

confidence: 99%

“…the segmentation masks for the data, is the GAT software developed in-house by the Erlangen group. The software is well known in the field and utilized by several renowned research groups to analyze HSV data 13,[58][59][60] . The software provides a semi-automatic method to create segmentation masks using a seed-based region growing algorithm that relies on grayscale thresholds.…”

Section: Videoendoscopy and Glottis Segmentation Several Imaging Tecmentioning

confidence: 99%

See 1 more Smart Citation

BAGLS, a multihospital Benchmark for Automatic Glottis Segmentation

et al. 2020

Self Cite

View full text Add to dashboard Cite

Laryngeal videoendoscopy is one of the main tools in clinical examinations for voice disorders and voice research. Using high-speed videoendoscopy, it is possible to fully capture the vocal fold oscillations, however, processing the recordings typically involves a time-consuming segmentation of the glottal area by trained experts. Even though automatic methods have been proposed and the task is particularly suited for deep learning methods, there are no public datasets and benchmarks available to compare methods and to allow training of generalizing deep learning models. In an international collaboration of researchers from seven institutions from the EU and USa, we have created BaGLS, a large, multihospital dataset of 59,250 high-speed videoendoscopy frames with individually annotated segmentation masks. The frames are based on 640 recordings of healthy and disordered subjects that were recorded with varying technical equipment by numerous clinicians. the BaGLS dataset will allow an objective comparison of glottis segmentation methods and will enable interested researchers to train their own models and compare their methods.

show abstract

“…the glottal midline, is of great importance for an accurate diagnosis. An anatomical derivation is the most appropriate, yet hard to unequivocally define 13,14 and maybe a source for inter-annotator variability 40 . Defining the glottal midline from a simpler representation, i.e.…”

Section: Definition Of Glottal Midlinementioning

confidence: 99%

Rethinking glottal midline detection

Kist

Zilker

Gómez

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

A healthy voice is crucial for verbal communication and hence in daily as well as professional life. The basis for a healthy voice are the sound producing vocal folds in the larynx. A hallmark of healthy vocal fold oscillation is the symmetric motion of the left and right vocal fold. Clinically, videoendoscopy is applied to assess the symmetry of the oscillation and evaluated subjectively. High-speed videoendoscopy, an emerging method that allows quantification of the vocal fold oscillation, is more commonly employed in research due to the amount of data and the complex, semi-automatic analysis. In this study, we provide a comprehensive evaluation of methods that detect fully automatically the glottal midline. We used a biophysical model to simulate different vocal fold oscillations, extended the openly available BAGLS dataset using manual annotations, utilized both, simulations and annotated endoscopic images, to train deep neural networks at different stages of the analysis workflow, and compared these to established computer vision algorithms. We found that classical computer vision perform well on detecting the glottal midline in glottis segmentation data, but are outperformed by deep neural networks on this task. We further suggest GlottisNet, a multi-task neural architecture featuring the simultaneous prediction of both, the opening between the vocal folds and the symmetry axis, leading to a huge step forward towards clinical applicability of quantitative, deep learning-assisted laryngeal endoscopy, by fully automating segmentation and midline detection.

show abstract

Intersegmenter Variability in High‐Speed Laryngoscopy‐Based Glottal Area Waveform Measures

Cited by 23 publications

References 30 publications

Efficient Biomedical Image Segmentation on EdgeTPUs at Point of Care

Efficient Biomedical Image Segmentation on EdgeTPUs at Point of Care

BAGLS, a multihospital Benchmark for Automatic Glottis Segmentation

Rethinking glottal midline detection

Contact Info

Product

Resources

About