000143340 001__ 143340
000143340 005__ 20240229112549.0
000143340 0247_ $$2doi$$a10.1007/s11548-019-01939-9
000143340 0247_ $$2pmid$$apmid:30903566
000143340 0247_ $$2ISSN$$a1861-6410
000143340 0247_ $$2ISSN$$a1861-6429
000143340 0247_ $$2altmetric$$aaltmetric:56814481
000143340 037__ $$aDKFZ-2019-00930
000143340 041__ $$aeng
000143340 082__ $$a610
000143340 1001_ $$00000-0002-3424-6629$$aAdler, Tim J$$b0$$eFirst author
000143340 245__ $$aUncertainty-aware performance assessment of optical imaging modalities with invertible neural networks.
000143340 260__ $$aHeidelberg [u.a.]$$bSpringer$$c2019
000143340 3367_ $$2DRIVER$$aarticle
000143340 3367_ $$2DataCite$$aOutput Types/Journal article
000143340 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1567494683_4664
000143340 3367_ $$2BibTeX$$aARTICLE
000143340 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000143340 3367_ $$00$$2EndNote$$aJournal Article
000143340 520__ $$aOptical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pixel-wise multispectral reflectance measurements to underlying tissue parameters, such as oxygenation. Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be ill-posed.We present a novel approach to the assessment of optical imaging modalities, which is sensitive to the different types of uncertainties that may occur when inferring tissue parameters. Based on the concept of invertible neural networks, our framework goes beyond point estimates and maps each multispectral measurement to a full posterior probability distribution which is capable of representing ambiguity in the solution via multiple modes. Performance metrics for a hardware setup can then be computed from the characteristics of the posteriors.Application of the assessment framework to the specific use case of camera selection for physiological parameter estimation yields the following insights: (1) estimation of tissue oxygenation from multispectral images is a well-posed problem, while (2) blood volume fraction may not be recovered without ambiguity. (3) In general, ambiguity may be reduced by increasing the number of spectral bands in the camera.Our method could help to optimize optical camera design in an application-specific manner.
000143340 536__ $$0G:(DE-HGF)POF3-315$$a315 - Imaging and radiooncology (POF3-315)$$cPOF3-315$$fPOF III$$x0
000143340 588__ $$aDataset connected to CrossRef, PubMed,
000143340 7001_ $$aArdizzone, Lynton$$b1
000143340 7001_ $$0P:(DE-He78)59550e3c9ae4b46b714843863e0db8d9$$aVemuri, Anant$$b2$$udkfz
000143340 7001_ $$0P:(DE-HGF)0$$aAyala, Leonardo$$b3
000143340 7001_ $$0P:(DE-He78)fd657bfbb3c4757ac029bb6b56ab9b71$$aGröhl, Janek$$b4$$udkfz
000143340 7001_ $$0P:(DE-He78)fd68f49dada874ac262fadf9fde869df$$aKirchner, Thomas$$b5$$udkfz
000143340 7001_ $$0P:(DE-He78)f105ac59d0f6d441f098d3144e0defee$$aWirkert, Sebastian$$b6$$udkfz
000143340 7001_ $$aKruse, Jakob$$b7
000143340 7001_ $$aRother, Carsten$$b8
000143340 7001_ $$aKöthe, Ullrich$$b9
000143340 7001_ $$0P:(DE-He78)26a1176cd8450660333a012075050072$$aMaier-Hein, Lena$$b10$$eLast author$$udkfz
000143340 773__ $$0PERI:(DE-600)2235881-X$$a10.1007/s11548-019-01939-9$$n6$$p997-1007$$tInternational journal of computer assisted radiology and surgery$$v14$$x1861-6429$$y2019
000143340 909CO $$ooai:inrepo02.dkfz.de:143340$$pVDB
000143340 9101_ $$0I:(DE-588b)2036810-0$$60000-0002-3424-6629$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000143340 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)59550e3c9ae4b46b714843863e0db8d9$$aDeutsches Krebsforschungszentrum$$b2$$kDKFZ
000143340 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000143340 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)fd657bfbb3c4757ac029bb6b56ab9b71$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000143340 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)fd68f49dada874ac262fadf9fde869df$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ
000143340 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)f105ac59d0f6d441f098d3144e0defee$$aDeutsches Krebsforschungszentrum$$b6$$kDKFZ
000143340 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)26a1176cd8450660333a012075050072$$aDeutsches Krebsforschungszentrum$$b10$$kDKFZ
000143340 9131_ $$0G:(DE-HGF)POF3-315$$1G:(DE-HGF)POF3-310$$2G:(DE-HGF)POF3-300$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vImaging and radiooncology$$x0
000143340 9141_ $$y2019
000143340 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000143340 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000143340 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bINT J COMPUT ASS RAD : 2017
000143340 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List
000143340 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000143340 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000143340 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine
000143340 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5
000143340 9201_ $$0I:(DE-He78)E130-20160331$$kE130$$lComputer-assistierte medizinische Interventionen$$x0
000143340 9201_ $$0I:(DE-He78)E131-20160331$$kE131$$lComputer-assistierte Interventionen$$x1
000143340 980__ $$ajournal
000143340 980__ $$aVDB
000143340 980__ $$aI:(DE-He78)E130-20160331
000143340 980__ $$aI:(DE-He78)E131-20160331
000143340 980__ $$aUNRESTRICTED