Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310584315> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4310584315 abstract "Low-complexity convolutional neural networks have been shown to be sufficient for segmentation of cardiac US images in A2C and A4C views. The performance of 24 varying-complexity implementations of U-Net and DeepLabV3+ (popular segmentation architectures) has been tested on cardiac US data (CAMUS data set) and street view data (Cityscapes data set). The inference speed of the models has also been measured before and after post-training optimization. The models systematically differed in their structural components: the number of layers and convolutional filters as well as the receptive field size. All models trained to maximize the Dice Coefficient. The Dice Coefficient was consistently high (0.86-0.90) on CA-MUS data and low (0.48-0.67) on Cityscapes data for all models. Each ten-fold reduction in the number of model parameters tended to reduce the score by ≈0.01 on CAMUS and by 0.03-0.05 on Cityscapes. Likewise, low-parameter models, especially the ones based on U-Net, had yielded predictions with higher (worse) Hausdorff Distance values. Increasing the receptive field size of the models partially mitigated this effect. Without post-training optimization, the inference speed mostly varied with the number of layers in the networks. The least complex U-Net model was 83% faster than the most complex one; for the DeepLab models the difference was 53%. With post-training optimization, any reduction in the number of parameters led to increased speed: up to more than 700% for both architecture types." @default.
- W4310584315 created "2022-12-12" @default.
- W4310584315 creator A5034424258 @default.
- W4310584315 creator A5044809861 @default.
- W4310584315 creator A5048844030 @default.
- W4310584315 creator A5063361706 @default.
- W4310584315 date "2022-10-10" @default.
- W4310584315 modified "2023-09-27" @default.
- W4310584315 title "Segmentation of 2D cardiac ultrasound with deep learning: simpler models for a simple task" @default.
- W4310584315 cites W2340897893 @default.
- W4310584315 cites W3103215654 @default.
- W4310584315 doi "https://doi.org/10.1109/ius54386.2022.9957618" @default.
- W4310584315 hasPublicationYear "2022" @default.
- W4310584315 type Work @default.
- W4310584315 citedByCount "0" @default.
- W4310584315 crossrefType "proceedings-article" @default.
- W4310584315 hasAuthorship W4310584315A5034424258 @default.
- W4310584315 hasAuthorship W4310584315A5044809861 @default.
- W4310584315 hasAuthorship W4310584315A5048844030 @default.
- W4310584315 hasAuthorship W4310584315A5063361706 @default.
- W4310584315 hasConcept C105795698 @default.
- W4310584315 hasConcept C108583219 @default.
- W4310584315 hasConcept C111335779 @default.
- W4310584315 hasConcept C11413529 @default.
- W4310584315 hasConcept C124504099 @default.
- W4310584315 hasConcept C141898687 @default.
- W4310584315 hasConcept C153180895 @default.
- W4310584315 hasConcept C154945302 @default.
- W4310584315 hasConcept C163892561 @default.
- W4310584315 hasConcept C22029948 @default.
- W4310584315 hasConcept C2524010 @default.
- W4310584315 hasConcept C2776214188 @default.
- W4310584315 hasConcept C33923547 @default.
- W4310584315 hasConcept C41008148 @default.
- W4310584315 hasConcept C58489278 @default.
- W4310584315 hasConcept C81363708 @default.
- W4310584315 hasConcept C89600930 @default.
- W4310584315 hasConceptScore W4310584315C105795698 @default.
- W4310584315 hasConceptScore W4310584315C108583219 @default.
- W4310584315 hasConceptScore W4310584315C111335779 @default.
- W4310584315 hasConceptScore W4310584315C11413529 @default.
- W4310584315 hasConceptScore W4310584315C124504099 @default.
- W4310584315 hasConceptScore W4310584315C141898687 @default.
- W4310584315 hasConceptScore W4310584315C153180895 @default.
- W4310584315 hasConceptScore W4310584315C154945302 @default.
- W4310584315 hasConceptScore W4310584315C163892561 @default.
- W4310584315 hasConceptScore W4310584315C22029948 @default.
- W4310584315 hasConceptScore W4310584315C2524010 @default.
- W4310584315 hasConceptScore W4310584315C2776214188 @default.
- W4310584315 hasConceptScore W4310584315C33923547 @default.
- W4310584315 hasConceptScore W4310584315C41008148 @default.
- W4310584315 hasConceptScore W4310584315C58489278 @default.
- W4310584315 hasConceptScore W4310584315C81363708 @default.
- W4310584315 hasConceptScore W4310584315C89600930 @default.
- W4310584315 hasLocation W43105843151 @default.
- W4310584315 hasOpenAccess W4310584315 @default.
- W4310584315 hasPrimaryLocation W43105843151 @default.
- W4310584315 hasRelatedWork W2630229246 @default.
- W4310584315 hasRelatedWork W2769435486 @default.
- W4310584315 hasRelatedWork W2920218276 @default.
- W4310584315 hasRelatedWork W2954747211 @default.
- W4310584315 hasRelatedWork W2979303128 @default.
- W4310584315 hasRelatedWork W3135174555 @default.
- W4310584315 hasRelatedWork W3144574764 @default.
- W4310584315 hasRelatedWork W3152950745 @default.
- W4310584315 hasRelatedWork W3198334642 @default.
- W4310584315 hasRelatedWork W4297786172 @default.
- W4310584315 isParatext "false" @default.
- W4310584315 isRetracted "false" @default.
- W4310584315 workType "article" @default.