Sökning: WFRF:(Ranefall Petter 1968 ) > Learning Cell Nucle...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 02976naa a2200385 4500 | |
001 | oai:DiVA.org:uu-453417 | |
003 | SwePub | |
008 | 210916s2021 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-4534172 URI |
024 | 7 | a https://doi.org/10.24132/CSRN.2021.3002.372 DOI |
040 | a (SwePub)uu | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a kon2 swepub-publicationtype |
100 | 1 | a Matuszewski, Damian J.u Uppsala universitet,Avdelningen för visuell information och interaktion4 aut0 (Swepub:uu)damma800 |
245 | 1 0 | a Learning Cell Nuclei Segmentation Using Labels Generated with Classical Image Analysis Methods |
264 | 1 | b University of West Bohemia,c 2021 |
338 | a print2 rdacarrier | |
520 | a Creating manual annotations in a large number of images is a tedious bottleneck that limits deep learning use inmany applications. Here, we present a study in which we used the output of a classical image analysis pipeline aslabels when training a convolutional neural network (CNN). This may not only reduce the time experts spendannotating images but it may also lead to an improvement of results when compared to the output from the classicalpipeline used in training. In our application, i.e., cell nuclei segmentation, we generated the annotations usingCellProfiler (a tool for developing classical image analysis pipelines for biomedical applications) and trained onthem a U-Net-based CNN model. The best model achieved a 0.96 dice-coefficient of the segmented Nuclei and a0.84 object-wise Jaccard index which was better than the classical method used for generating the annotations by0.02 and 0.34, respectively. Our experimental results show that in this application, not only such training is feasiblebut also that the deep learning segmentations are a clear improvement compared to the output from the classicalpipeline used for generating the annotations. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Annan data- och informationsvetenskap0 (SwePub)102992 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Other Computer and Information Science0 (SwePub)102992 hsv//eng |
653 | a Deep learning | |
653 | a U-Net | |
653 | a CellProfiler | |
653 | a Data annotation | |
653 | a Microscopy | |
653 | a Computerized Image Processing | |
653 | a Datoriserad bildbehandling | |
700 | 1 | a Ranefall, Petter,d 1968-u Uppsala universitet,Avdelningen för visuell information och interaktion4 aut0 (Swepub:uu)peran517 |
710 | 2 | a Uppsala universitetb Avdelningen för visuell information och interaktion4 org |
773 | 0 | t Proceedings of the WSCG 2021d : University of West Bohemiag , s. 335-338q <335-338 |
856 | 4 | u https://doi.org/10.24132/CSRN.2021.3002.37y Fulltext |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-453417 |
856 | 4 8 | u https://doi.org/10.24132/CSRN.2021.3002.37 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
Kopiera och spara länken för att återkomma till aktuell vy