Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165197891> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3165197891 abstract "Fluorescence microscopy images contain several channels, each indicating a marker staining the sample. Since many different marker combinations are utilized in practice, it has been challenging to apply deep learning based segmentation models, which expect a predefined channel combination for all training samples as well as at inference for future application. Recent work circumvents this problem using a modality attention approach to be effective across any possible marker combination. However, for combinations that do not exist in a labeled training dataset, one cannot have any estimation of potential segmentation quality if that combination is encountered during inference. Without this, not only one lacks quality assurance but one also does not know where to put any additional imaging and labeling effort. We herein propose a method to estimate segmentation quality on unlabeled images by (i) estimating both aleatoric and epistemic uncertainties of convolutional neural networks for image segmentation, and (ii) training a Random Forest model for the interpretation of uncertainty features via regression to their corresponding segmentation metrics. Additionally, we demonstrate that including these uncertainty measures during training can provide an improvement on segmentation performance." @default.
- W3165197891 created "2021-06-07" @default.
- W3165197891 creator A5016658563 @default.
- W3165197891 creator A5022031011 @default.
- W3165197891 creator A5036633606 @default.
- W3165197891 creator A5049300439 @default.
- W3165197891 creator A5053308385 @default.
- W3165197891 date "2021-04-13" @default.
- W3165197891 modified "2023-09-23" @default.
- W3165197891 title "Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers" @default.
- W3165197891 cites W2095705004 @default.
- W3165197891 cites W2600383743 @default.
- W3165197891 cites W2808795969 @default.
- W3165197891 cites W2900936384 @default.
- W3165197891 cites W2964059111 @default.
- W3165197891 cites W2964121744 @default.
- W3165197891 cites W2964422934 @default.
- W3165197891 cites W2972629588 @default.
- W3165197891 cites W2992525328 @default.
- W3165197891 cites W3082435012 @default.
- W3165197891 cites W601603264 @default.
- W3165197891 doi "https://doi.org/10.1109/isbi48211.2021.9434158" @default.
- W3165197891 hasPublicationYear "2021" @default.
- W3165197891 type Work @default.
- W3165197891 sameAs 3165197891 @default.
- W3165197891 citedByCount "1" @default.
- W3165197891 countsByYear W31651978912022 @default.
- W3165197891 crossrefType "proceedings-article" @default.
- W3165197891 hasAuthorship W3165197891A5016658563 @default.
- W3165197891 hasAuthorship W3165197891A5022031011 @default.
- W3165197891 hasAuthorship W3165197891A5036633606 @default.
- W3165197891 hasAuthorship W3165197891A5049300439 @default.
- W3165197891 hasAuthorship W3165197891A5053308385 @default.
- W3165197891 hasBestOaLocation W31651978912 @default.
- W3165197891 hasConcept C108583219 @default.
- W3165197891 hasConcept C119857082 @default.
- W3165197891 hasConcept C124504099 @default.
- W3165197891 hasConcept C127162648 @default.
- W3165197891 hasConcept C153180895 @default.
- W3165197891 hasConcept C154945302 @default.
- W3165197891 hasConcept C169258074 @default.
- W3165197891 hasConcept C185592680 @default.
- W3165197891 hasConcept C198531522 @default.
- W3165197891 hasConcept C2776214188 @default.
- W3165197891 hasConcept C31258907 @default.
- W3165197891 hasConcept C41008148 @default.
- W3165197891 hasConcept C43617362 @default.
- W3165197891 hasConcept C81363708 @default.
- W3165197891 hasConcept C89600930 @default.
- W3165197891 hasConceptScore W3165197891C108583219 @default.
- W3165197891 hasConceptScore W3165197891C119857082 @default.
- W3165197891 hasConceptScore W3165197891C124504099 @default.
- W3165197891 hasConceptScore W3165197891C127162648 @default.
- W3165197891 hasConceptScore W3165197891C153180895 @default.
- W3165197891 hasConceptScore W3165197891C154945302 @default.
- W3165197891 hasConceptScore W3165197891C169258074 @default.
- W3165197891 hasConceptScore W3165197891C185592680 @default.
- W3165197891 hasConceptScore W3165197891C198531522 @default.
- W3165197891 hasConceptScore W3165197891C2776214188 @default.
- W3165197891 hasConceptScore W3165197891C31258907 @default.
- W3165197891 hasConceptScore W3165197891C41008148 @default.
- W3165197891 hasConceptScore W3165197891C43617362 @default.
- W3165197891 hasConceptScore W3165197891C81363708 @default.
- W3165197891 hasConceptScore W3165197891C89600930 @default.
- W3165197891 hasFunder F4320306076 @default.
- W3165197891 hasFunder F4320306900 @default.
- W3165197891 hasLocation W31651978911 @default.
- W3165197891 hasLocation W31651978912 @default.
- W3165197891 hasOpenAccess W3165197891 @default.
- W3165197891 hasPrimaryLocation W31651978911 @default.
- W3165197891 hasRelatedWork W2738221750 @default.
- W3165197891 hasRelatedWork W2790662084 @default.
- W3165197891 hasRelatedWork W2948658236 @default.
- W3165197891 hasRelatedWork W3102253946 @default.
- W3165197891 hasRelatedWork W3144574764 @default.
- W3165197891 hasRelatedWork W4226289457 @default.
- W3165197891 hasRelatedWork W4281616679 @default.
- W3165197891 hasRelatedWork W4293211451 @default.
- W3165197891 hasRelatedWork W4308191152 @default.
- W3165197891 hasRelatedWork W4322727400 @default.
- W3165197891 isParatext "false" @default.
- W3165197891 isRetracted "false" @default.
- W3165197891 magId "3165197891" @default.
- W3165197891 workType "article" @default.