000176902 001__ 176902
000176902 005__ 20240229133723.0
000176902 0247_ $$2doi$$a10.1002/path.5800
000176902 0247_ $$2pmid$$apmid:34561876
000176902 0247_ $$2ISSN$$a0022-3417
000176902 0247_ $$2ISSN$$a0368-3494
000176902 0247_ $$2ISSN$$a1096-9896
000176902 0247_ $$2ISSN$$a1555-2039
000176902 0247_ $$2altmetric$$aaltmetric:114030343
000176902 037__ $$aDKFZ-2021-02144
000176902 041__ $$aEnglish
000176902 082__ $$a610
000176902 1001_ $$aSchrammen, Peter Leonard$$b0
000176902 245__ $$aWeakly supervised annotation-free cancer detection and prediction of genotype in routine histopathology.
000176902 260__ $$aBognor Regis [u.a.]$$bWiley$$c2022
000176902 3367_ $$2DRIVER$$aarticle
000176902 3367_ $$2DataCite$$aOutput Types/Journal article
000176902 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1642427568_11679
000176902 3367_ $$2BibTeX$$aARTICLE
000176902 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000176902 3367_ $$00$$2EndNote$$aJournal Article
000176902 500__ $$a2022 Jan;256(1):50-60
000176902 520__ $$aDeep Learning is a powerful tool in computational pathology: it can be used for tumor detection and for predicting genetic alterations based on histopathology images alone. Conventionally, tumor detection and prediction of genetic alterations are two separate workflows. Newer methods have combined them, but require complex, manually engineered computational pipelines, restricting reproducibility and robustness. To address these issues, we present a new method for simultaneous tumor detection and prediction of genetic alterations: The 'Slide-Level Assessment Model' (SLAM) uses a single off-the-shelf neural network to predict molecular alterations directly from routine pathology slides without any manual annotations, improving upon previous methods by automatically excluding normal and non-informative tissue regions. SLAM requires only standard programming libraries and is conceptually simpler than previous approaches. We have extensively validated SLAM for clinically relevant tasks using two large multicentric cohorts of colorectal cancer patients, DACHS from Germany and YCR-BCIP from the United Kingdom. We show that SLAM yields reliable slide-level classification of tumor presence with an area under the receiver operating curve (AUROC) of 0.980 (confidence interval 0.975, 0.984; N = 2297 tumor and N = 1281 normal slides). In addition, SLAM can detect microsatellite instability (MSI) / mismatch repair deficiency (dMMR) or microsatellite stability (MSS) /mismatch repair proficiency (pMMR) with an AUROC of 0.909 (0.888, 0.929; N = 2039 patients) and BRAF mutational status with an AUROC of 0.821 (0.786, 0.852; N = 2075 patients). The improvement with respect to previous methods was validated in a large external testing cohort in which MSI/dMMR status was detected with an AUROC of 0.900 (0.864, 0.931; N = 805 patients). In addition, SLAM provides human-interpretable visualization maps, enabling the analysis of multiplexed network predictions by human experts. In summary, SLAM is a new simple and powerful method for computational pathology which could be applied to multiple disease contexts. This article is protected by copyright. All rights reserved.
000176902 536__ $$0G:(DE-HGF)POF4-313$$a313 - Krebsrisikofaktoren und Prävention (POF4-313)$$cPOF4-313$$fPOF IV$$x0
000176902 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo01.inet.dkfz-heidelberg.de
000176902 650_7 $$2Other$$aLynch syndrome
000176902 650_7 $$2Other$$aartificial intelligence
000176902 650_7 $$2Other$$acolorectal cancer
000176902 650_7 $$2Other$$acomputational pathology
000176902 650_7 $$2Other$$adeep learning
000176902 650_7 $$2Other$$adigital pathology
000176902 650_7 $$2Other$$amicrosatellite instability
000176902 7001_ $$aGhaffari Laleh, Narmin$$b1
000176902 7001_ $$aEchle, Amelie$$b2
000176902 7001_ $$aTruhn, Daniel$$b3
000176902 7001_ $$aSchulz, Volkmar$$b4
000176902 7001_ $$0P:(DE-He78)1e33961c8780aca9b76d776d1fdc1ebb$$aBrinker, Titus J$$b5$$udkfz
000176902 7001_ $$0P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2$$aBrenner, Hermann$$b6$$udkfz
000176902 7001_ $$0P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253$$aChang-Claude, Jenny$$b7$$udkfz
000176902 7001_ $$0P:(DE-He78)9b2a61b2abe4a64ca23b6783b7c4fe63$$aAlwers, Elizabeth$$b8$$udkfz
000176902 7001_ $$aBrobeil, Alexander$$b9
000176902 7001_ $$aKloor, Matthias$$b10
000176902 7001_ $$aHeij, Lara R$$b11
000176902 7001_ $$aJäger, Dirk$$b12
000176902 7001_ $$aTrautwein, Christian$$b13
000176902 7001_ $$aGrabsch, Heike I$$b14
000176902 7001_ $$aQuirke, Philip$$b15
000176902 7001_ $$00000-0002-0346-6709$$aWest, Nicholas P$$b16
000176902 7001_ $$0P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f$$aHoffmeister, Michael$$b17$$udkfz
000176902 7001_ $$0P:(DE-He78)761f5d0f73e0d8f170394b29448a9e8d$$aKather, Jakob Nikolas$$b18$$udkfz
000176902 773__ $$0PERI:(DE-600)1475280-3$$a10.1002/path.5800$$gp. path.5800$$n1$$p50-60$$tThe journal of pathology$$v256$$x1096-9896$$y2022
000176902 909CO $$ooai:inrepo02.dkfz.de:176902$$pVDB
000176902 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)1e33961c8780aca9b76d776d1fdc1ebb$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ
000176902 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2$$aDeutsches Krebsforschungszentrum$$b6$$kDKFZ
000176902 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253$$aDeutsches Krebsforschungszentrum$$b7$$kDKFZ
000176902 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)9b2a61b2abe4a64ca23b6783b7c4fe63$$aDeutsches Krebsforschungszentrum$$b8$$kDKFZ
000176902 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f$$aDeutsches Krebsforschungszentrum$$b17$$kDKFZ
000176902 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)761f5d0f73e0d8f170394b29448a9e8d$$aDeutsches Krebsforschungszentrum$$b18$$kDKFZ
000176902 9131_ $$0G:(DE-HGF)POF4-313$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vKrebsrisikofaktoren und Prävention$$x0
000176902 9141_ $$y2021
000176902 915__ $$0StatID:(DE-HGF)3001$$2StatID$$aDEAL Wiley$$d2021-02-03$$wger
000176902 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-02-03
000176902 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2021-02-03
000176902 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-02-03
000176902 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2022-11-22$$wger
000176902 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bJ PATHOL : 2021$$d2022-11-22
000176902 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bJ PATHOL : 2021$$d2022-11-22
000176902 9201_ $$0I:(DE-He78)C140-20160331$$kC140$$lNWG Digitale Biomarker in der Onkologie$$x0
000176902 9201_ $$0I:(DE-He78)C070-20160331$$kC070$$lC070 Klinische Epidemiologie und Alternf.$$x1
000176902 9201_ $$0I:(DE-He78)C120-20160331$$kC120$$lPräventive Onkologie$$x2
000176902 9201_ $$0I:(DE-He78)HD01-20160331$$kHD01$$lDKTK HD zentral$$x3
000176902 9201_ $$0I:(DE-He78)C020-20160331$$kC020$$lC020 Epidemiologie von Krebs$$x4
000176902 980__ $$ajournal
000176902 980__ $$aVDB
000176902 980__ $$aI:(DE-He78)C140-20160331
000176902 980__ $$aI:(DE-He78)C070-20160331
000176902 980__ $$aI:(DE-He78)C120-20160331
000176902 980__ $$aI:(DE-He78)HD01-20160331
000176902 980__ $$aI:(DE-He78)C020-20160331
000176902 980__ $$aUNRESTRICTED