000147218 001__ 147218
000147218 005__ 20240229112643.0
000147218 0247_ $$2doi$$a10.1148/radiol.2019190938
000147218 0247_ $$2pmid$$apmid:31592731
000147218 0247_ $$2ISSN$$a0033-8419
000147218 0247_ $$2ISSN$$a1527-1315
000147218 0247_ $$2altmetric$$aaltmetric:68045045
000147218 037__ $$aDKFZ-2019-02344
000147218 041__ $$aeng
000147218 082__ $$a610
000147218 1001_ $$0P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aSchelb, Patrick$$b0$$eFirst author$$udkfz
000147218 245__ $$aClassification of Cancer at Prostate MRI: Deep Learning versus Clinical PI-RADS Assessment.
000147218 260__ $$aOak Brook, Ill.$$bSoc.$$c2019
000147218 3367_ $$2DRIVER$$aarticle
000147218 3367_ $$2DataCite$$aOutput Types/Journal article
000147218 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1626959192_3042
000147218 3367_ $$2BibTeX$$aARTICLE
000147218 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000147218 3367_ $$00$$2EndNote$$aJournal Article
000147218 500__ $$a2019 Dec;293(3):607-617
000147218 520__ $$aBackground Men suspected of having clinically significant prostate cancer (sPC) increasingly undergo prostate MRI. The potential of deep learning to provide diagnostic support for human interpretation requires further evaluation. Purpose To compare the performance of clinical assessment to a deep learning system optimized for segmentation trained with T2-weighted and diffusion MRI in the task of detection and segmentation of lesions suspicious for sPC. Materials and Methods In this retrospective study, T2-weighted and diffusion prostate MRI sequences from consecutive men examined with a single 3.0-T MRI system between 2015 and 2016 were manually segmented. Ground truth was provided by combined targeted and extended systematic MRI-transrectal US fusion biopsy, with sPC defined as International Society of Urological Pathology Gleason grade group greater than or equal to 2. By using split-sample validation, U-Net was internally validated on the training set (80% of the data) through cross validation and subsequently externally validated on the test set (20% of the data). U-Net-derived sPC probability maps were calibrated by matching sextant-based cross-validation performance to clinical performance of Prostate Imaging Reporting and Data System (PI-RADS). Performance of PI-RADS and U-Net were compared by using sensitivities, specificities, predictive values, and Dice coefficient. Results A total of 312 men (median age, 64 years; interquartile range [IQR], 58-71 years) were evaluated. The training set consisted of 250 men (median age, 64 years; IQR, 58-71 years) and the test set of 62 men (median age, 64 years; IQR, 60-69 years). In the test set, PI-RADS cutoffs greater than or equal to 3 versus cutoffs greater than or equal to 4 on a per-patient basis had sensitivity of 96% (25 of 26) versus 88% (23 of 26) at specificity of 22% (eight of 36) versus 50% (18 of 36). U-Net at probability thresholds of greater than or equal to 0.22 versus greater than or equal to 0.33 had sensitivity of 96% (25 of 26) versus 92% (24 of 26) (both P > .99) with specificity of 31% (11 of 36) versus 47% (17 of 36) (both P > .99), not statistically different from PI-RADS. Dice coefficients were 0.89 for prostate and 0.35 for MRI lesion segmentation. In the test set, coincidence of PI-RADS greater than or equal to 4 with U-Net lesions improved the positive predictive value from 48% (28 of 58) to 67% (24 of 36) for U-Net probability thresholds greater than or equal to 0.33 (P = .01), while the negative predictive value remained unchanged (83% [25 of 30] vs 83% [43 of 52]; P > .99). Conclusion U-Net trained with T2-weighted and diffusion MRI achieves similar performance to clinical Prostate Imaging Reporting and Data System assessment. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Padhani and Turkbey in this issue.
000147218 536__ $$0G:(DE-HGF)POF3-315$$a315 - Imaging and radiooncology (POF3-315)$$cPOF3-315$$fPOF III$$x0
000147218 588__ $$aDataset connected to CrossRef, PubMed,
000147218 7001_ $$0P:(DE-He78)a35f3fa04c359e037b2377f96920f93f$$aKohl, Simon$$b1
000147218 7001_ $$0P:(DE-He78)79897f8897ff77676549d9895258a0f2$$aRadtke, Jan Philipp$$b2
000147218 7001_ $$0P:(DE-He78)1042737c83ba70ec508bdd99f0096864$$aWiesenfarth, Manuel$$b3
000147218 7001_ $$0P:(DE-He78)3da06896bf2a50a84d40c33c3b7a9b3e$$aKickingereder, Philipp$$b4
000147218 7001_ $$0P:(DE-He78)d2d971750bce6217eb90fff9b01e61f9$$aBickelhaupt, Sebastian$$b5
000147218 7001_ $$0P:(DE-He78)59dfdd0ee0a7f0db81535f0781a3a6d6$$aKuder, Tristan Anselm$$b6
000147218 7001_ $$00000-0003-1001-103X$$aStenzinger, Albrecht$$b7
000147218 7001_ $$aHohenfellner, Markus$$b8
000147218 7001_ $$0P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aSchlemmer, Heinz-Peter$$b9
000147218 7001_ $$0P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aMaier-Hein, Klaus$$b10
000147218 7001_ $$0P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aBonekamp, David$$b11$$eLast author
000147218 773__ $$0PERI:(DE-600)2010588-5$$a10.1148/radiol.2019190938$$gp. 190938 -$$n3$$p607-617$$tRadiology$$v293$$x1527-1315$$y2019
000147218 909CO $$ooai:inrepo02.dkfz.de:147218$$pVDB
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a35f3fa04c359e037b2377f96920f93f$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)79897f8897ff77676549d9895258a0f2$$aDeutsches Krebsforschungszentrum$$b2$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)1042737c83ba70ec508bdd99f0096864$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)3da06896bf2a50a84d40c33c3b7a9b3e$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)d2d971750bce6217eb90fff9b01e61f9$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)59dfdd0ee0a7f0db81535f0781a3a6d6$$aDeutsches Krebsforschungszentrum$$b6$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aDeutsches Krebsforschungszentrum$$b9$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aDeutsches Krebsforschungszentrum$$b10$$kDKFZ
000147218 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aDeutsches Krebsforschungszentrum$$b11$$kDKFZ
000147218 9131_ $$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$$x0
000147218 9132_ $$0G:(DE-HGF)POF4-315$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vBildgebung und Radioonkologie$$x0
000147218 9141_ $$y2019
000147218 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000147218 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline
000147218 915__ $$0StatID:(DE-HGF)0310$$2StatID$$aDBCoverage$$bNCBI Molecular Biology Database
000147218 915__ $$0StatID:(DE-HGF)0320$$2StatID$$aDBCoverage$$bPubMed Central
000147218 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bRADIOLOGY : 2017
000147218 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List
000147218 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index
000147218 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000147218 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded
000147218 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine
000147218 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences
000147218 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews
000147218 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bRADIOLOGY : 2017
000147218 9201_ $$0I:(DE-He78)E010-20160331$$kE010$$lE010 Radiologie$$x0
000147218 9201_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x1
000147218 9201_ $$0I:(DE-He78)C060-20160331$$kC060$$lC060 Biostatistik$$x2
000147218 9201_ $$0I:(DE-He78)E250-20160331$$kE250$$lMuliparametrische Methoden zur Früherkennung des Prostatakarzinoms$$x3
000147218 9201_ $$0I:(DE-He78)E020-20160331$$kE020$$lE020 Med. Physik in der Radiologie$$x4
000147218 9201_ $$0I:(DE-He78)L101-20160331$$kL101$$lDKTK Heidelberg$$x5
000147218 980__ $$ajournal
000147218 980__ $$aVDB
000147218 980__ $$aI:(DE-He78)E010-20160331
000147218 980__ $$aI:(DE-He78)E230-20160331
000147218 980__ $$aI:(DE-He78)C060-20160331
000147218 980__ $$aI:(DE-He78)E250-20160331
000147218 980__ $$aI:(DE-He78)E020-20160331
000147218 980__ $$aI:(DE-He78)L101-20160331
000147218 980__ $$aUNRESTRICTED