A single latent channel is sufficient for biomedical image segmentation
Kist, A. M.; Duerr, S.; Schuetzenberger, A.; Semmler, M.
Show abstract
Glottis segmentation is a crucial step to quantify endoscopic footage in laryngeal high-speed videoendoscopy. Recent advances in using deep neural networks for glottis segmentation allow a fully automatic workflow. However, exact knowledge of integral parts of these segmentation deep neural networks remains unknown. Here, we show using systematic ablations that a single latent channel as bottleneck layer is sufficient for glottal area segmentation. We further show that the latent space is an abstraction of the glottal area segmentation relying on three spatially defined pixel subtypes. We provide evidence that the latent space is highly correlated with the glottal area waveform, can be encoded with four bits, and decoded using lean decoders while maintaining a high reconstruction accuracy. Our findings suggest that glottis segmentation is a task that can be highly optimized to gain very efficient and clinical applicable deep neural networks. In future, we believe that online deep learning-assisted monitoring is a game changer in laryngeal examinations.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Direct Speech Reconstruction from Sensorimotor Brain Activity with Optimized Deep Learning Models 93%
- Speech decoding from a small set of spatially segregated minimally invasive intracranial EEG electrodes with a compact and interpretable neural network 93%
- Learning neural decoders without labels using multiple data streams 93%
Similar papers in this journal
- Adaptive Frequency-Spatial Dual-Stream Network (AFS-DSN) for Nasal and Paranasal Sinus CT Segmentation 93%
- SN-FPN: Self-attention Nested Feature Pyramid Network for Digital Pathology Image Segmentation 92%
- The tempest in a cubic millimeter: Image-based refinements necessitate the reconstruction of 3D microvasculature from a large series of damaged alternately-stained histological sections 92%
Similar papers in this journal
- Long-term performance assessment of fully automatic biomedical glottis segmentation at the point of care 97%
- Predicting semantic segmentation quality in laryngeal endoscopy images 97%
- Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.