SHREC 2021: Classification in Cryo-electron Tomograms

Simple item page
dc.contributor.authorGubins, Iljaen_US
dc.contributor.authorChaillet, Marten L.en_US
dc.contributor.authorSchot, Gijs van deren_US
dc.contributor.authorTrueba, M. Cristinaen_US
dc.contributor.authorVeltkamp, Remco C.en_US
dc.contributor.authorFörster, Friedrichen_US
dc.contributor.authorWang, Xiaoen_US
dc.contributor.authorKihara, Daisukeen_US
dc.contributor.authorMoebel, Emmanuelen_US
dc.contributor.authorNguyen, Nguyen P.en_US
dc.contributor.authorWhite, Tommien_US
dc.contributor.authorBunyak, Filizen_US
dc.contributor.authorPapoulias, Giorgosen_US
dc.contributor.authorGerolymatos, Stavrosen_US
dc.contributor.authorZacharaki, Evangelia I.en_US
dc.contributor.authorMoustakas, Konstantinosen_US
dc.contributor.authorZeng, Xiangruien_US
dc.contributor.authorLiu, Sinuoen_US
dc.contributor.authorXu, Minen_US
dc.contributor.authorWang, Yaoyuen_US
dc.contributor.authorChen, Chengen_US
dc.contributor.authorCui, Xuefengen_US
dc.contributor.authorZhang, Faen_US
dc.contributor.editorBiasotti, Silvia and Dyke, Roberto M. and Lai, Yukun and Rosin, Paul L. and Veltkamp, Remco C.en_US
dc.date.accessioned2021-09-01T08:25:35Z
dc.date.available2021-09-01T08:25:35Z
dc.date.issued2021
dc.description.abstractCryo-electron tomography (cryo-ET) is an imaging technique that allows three-dimensional visualization of macro-molecular assemblies under near-native conditions. Cryo-ET comes with a number of challenges, mainly low signal-to-noise and inability to obtain images from all angles. Computational methods are key to analyze cryo-electron tomograms. To promote innovation in computational methods, we generate a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in tomograms. Our publicly available dataset contains ten tomographic reconstructions of simulated cell-like volumes. Each volume contains twelve different types of complexes, varying in size, function and structure. In this paper, we have evaluated seven different methods of finding and classifying proteins. Seven research groups present results obtained with learning-based methods and trained on the simulated dataset, as well as a baseline template matching (TM), a traditional method widely used in cryo-ET research. We show that learning-based approaches can achieve notably better localization and classification performance than TM. We also experimentally confirm that there is a negative relationship between particle size and performance for all methods.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20211307
dc.identifier.isbn978-3-03868-137-3
dc.identifier.issn1997-0471
dc.identifier.pages5-17
dc.identifier.urihttps://doi.org/10.2312/3dor.20211307
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20211307
dc.publisherThe Eurographics Associationen_US
dc.subjectInformation systems
dc.subjectEvaluation of retrieval results
dc.subjectSpecialized information retrieval
dc.subjectMultimedia and multimodal retrieval
dc.subjectRetrieval models and ranking
dc.titleSHREC 2021: Classification in Cryo-electron Tomogramsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
005-017.pdf
Size:
3.37 MB
Format:
Adobe Portable Document Format
Download
Collections
3DOR 2021 - Short Papers