000169017 001__ 169017
000169017 005__ 20240229133635.0
000169017 0247_ $$2doi$$a10.1097/RLI.0000000000000791
000169017 0247_ $$2pmid$$apmid:34049336
000169017 0247_ $$2ISSN$$a0020-9996
000169017 0247_ $$2ISSN$$a1536-0210
000169017 0247_ $$2altmetric$$aaltmetric:106681702
000169017 037__ $$aDKFZ-2021-01185
000169017 041__ $$aEnglish
000169017 082__ $$a610
000169017 1001_ $$0P:(DE-He78)32c69a3bed6c75b378ef19ad39a74572$$aNetzer, Nils$$b0$$eFirst author
000169017 245__ $$aFully Automatic Deep Learning in Bi-institutional Prostate Magnetic Resonance Imaging: Effects of Cohort Size and Heterogeneity.
000169017 260__ $$a[s.l.]$$bOvid$$c2021
000169017 3367_ $$2DRIVER$$aarticle
000169017 3367_ $$2DataCite$$aOutput Types/Journal article
000169017 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1642584214_1940
000169017 3367_ $$2BibTeX$$aARTICLE
000169017 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000169017 3367_ $$00$$2EndNote$$aJournal Article
000169017 500__ $$a#EA:E010#LA:E010#  /December 2021 - Volume 56 - Issue 12 - p 799-808
000169017 520__ $$aThe potential of deep learning to support radiologist prostate magnetic resonance imaging (MRI) interpretation has been demonstrated.The aim of this study was to evaluate the effects of increased and diversified training data (TD) on deep learning performance for detection and segmentation of clinically significant prostate cancer-suspicious lesions.In this retrospective study, biparametric (T2-weighted and diffusion-weighted) prostate MRI acquired with multiple 1.5-T and 3.0-T MRI scanners in consecutive men was used for training and testing of prostate segmentation and lesion detection networks. Ground truth was the combination of targeted and extended systematic MRI-transrectal ultrasound fusion biopsies, with significant prostate cancer defined as International Society of Urological Pathology grade group greater than or equal to 2. U-Nets were internally validated on full, reduced, and PROSTATEx-enhanced training sets and subsequently externally validated on the institutional test set and the PROSTATEx test set. U-Net segmentation was calibrated to clinically desired levels in cross-validation, and test performance was subsequently compared using sensitivities, specificities, predictive values, and Dice coefficient.One thousand four hundred eighty-eight institutional examinations (median age, 64 years; interquartile range, 58-70 years) were temporally split into training (2014-2017, 806 examinations, supplemented by 204 PROSTATEx examinations) and test (2018-2020, 682 examinations) sets. In the test set, Prostate Imaging-Reporting and Data System (PI-RADS) cutoffs greater than or equal to 3 and greater than or equal to 4 on a per-patient basis had sensitivity of 97% (241/249) and 90% (223/249) at specificity of 19% (82/433) and 56% (242/433), respectively. The full U-Net had corresponding sensitivity of 97% (241/249) and 88% (219/249) with specificity of 20% (86/433) and 59% (254/433), not statistically different from PI-RADS (P > 0.3 for all comparisons). U-Net trained using a reduced set of 171 consecutive examinations achieved inferior performance (P < 0.001). PROSTATEx training enhancement did not improve performance. Dice coefficients were 0.90 for prostate and 0.42/0.53 for MRI lesion segmentation at PI-RADS category 3/4 equivalents.In a large institutional test set, U-Net confirms similar performance to clinical PI-RADS assessment and benefits from more TD, with neither institutional nor PROSTATEx performance improved by adding multiscanner or bi-institutional TD.
000169017 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000169017 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo01.inet.dkfz-heidelberg.de
000169017 7001_ $$0P:(DE-He78)119873a14bddcea13d0c7c2d27bc3f4b$$aWeißer, Cedric$$b1
000169017 7001_ $$0P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aSchelb, Patrick$$b2
000169017 7001_ $$0P:(DE-He78)aec14a1077ed145f9ebe9de1d50905b0$$aWang, Xianfeng$$b3
000169017 7001_ $$0P:(DE-He78)a5f2932521a52b287143c4177c8e3d1f$$aQin, Xiaoyan$$b4
000169017 7001_ $$aGörtz, Magdalena$$b5
000169017 7001_ $$aSchütz, Viktoria$$b6
000169017 7001_ $$0P:(DE-He78)79897f8897ff77676549d9895258a0f2$$aRadtke, Jan Philipp$$b7
000169017 7001_ $$0P:(DE-He78)743a4a82daab55306a2c88b9f6bf8c2f$$aHielscher, Thomas$$b8
000169017 7001_ $$aSchwab, Constantin$$b9
000169017 7001_ $$aStenzinger, Albrecht$$b10
000169017 7001_ $$0P:(DE-He78)59dfdd0ee0a7f0db81535f0781a3a6d6$$aKuder, Tristan Anselm$$b11$$udkfz
000169017 7001_ $$0P:(DE-He78)77bc493068847c689d894d2eda891c0c$$aGnirs, Regula$$b12
000169017 7001_ $$aHohenfellner, Markus$$b13
000169017 7001_ $$0P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aSchlemmer, Heinz-Peter$$b14
000169017 7001_ $$0P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aMaier-Hein, Klaus H$$b15
000169017 7001_ $$0P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aBonekamp, David$$b16$$eLast author
000169017 773__ $$0PERI:(DE-600)2041543-6$$a10.1097/RLI.0000000000000791$$gVol. Publish Ahead of Print$$n12$$p799-808$$tInvestigative radiology$$v56$$x0020-9996$$y2021
000169017 909CO $$ooai:inrepo02.dkfz.de:169017$$pVDB
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)32c69a3bed6c75b378ef19ad39a74572$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)119873a14bddcea13d0c7c2d27bc3f4b$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aDeutsches Krebsforschungszentrum$$b2$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)aec14a1077ed145f9ebe9de1d50905b0$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a5f2932521a52b287143c4177c8e3d1f$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)79897f8897ff77676549d9895258a0f2$$aDeutsches Krebsforschungszentrum$$b7$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)743a4a82daab55306a2c88b9f6bf8c2f$$aDeutsches Krebsforschungszentrum$$b8$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)59dfdd0ee0a7f0db81535f0781a3a6d6$$aDeutsches Krebsforschungszentrum$$b11$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)77bc493068847c689d894d2eda891c0c$$aDeutsches Krebsforschungszentrum$$b12$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aDeutsches Krebsforschungszentrum$$b14$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aDeutsches Krebsforschungszentrum$$b15$$kDKFZ
000169017 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aDeutsches Krebsforschungszentrum$$b16$$kDKFZ
000169017 9131_ $$0G:(DE-HGF)POF4-315$$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
000169017 9130_ $$0G:(DE-HGF)POF3-315$$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
000169017 9141_ $$y2021
000169017 915__ $$0StatID:(DE-HGF)0410$$2StatID$$aAllianz-Lizenz$$d2021-01-27$$wger
000169017 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2021-01-27$$wger
000169017 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bINVEST RADIOL : 2019$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2021-01-27
000169017 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bINVEST RADIOL : 2019$$d2021-01-27
000169017 9201_ $$0I:(DE-He78)E010-20160331$$kE010$$lE010 Radiologie$$x0
000169017 9201_ $$0I:(DE-He78)C060-20160331$$kC060$$lC060 Biostatistik$$x1
000169017 9201_ $$0I:(DE-He78)E020-20160331$$kE020$$lE020 Med. Physik in der Radiologie$$x2
000169017 9201_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x3
000169017 9201_ $$0I:(DE-He78)HD01-20160331$$kHD01$$lDKTK HD zentral$$x4
000169017 980__ $$ajournal
000169017 980__ $$aVDB
000169017 980__ $$aI:(DE-He78)E010-20160331
000169017 980__ $$aI:(DE-He78)C060-20160331
000169017 980__ $$aI:(DE-He78)E020-20160331
000169017 980__ $$aI:(DE-He78)E230-20160331
000169017 980__ $$aI:(DE-He78)HD01-20160331
000169017 980__ $$aUNRESTRICTED