000157380 001__ 157380
000157380 005__ 20240229133507.0
000157380 0247_ $$2doi$$a10.1007/s00330-020-07086-z
000157380 0247_ $$2pmid$$apmid:32767102
000157380 0247_ $$2ISSN$$a0938-7994
000157380 0247_ $$2ISSN$$a1432-1084
000157380 0247_ $$2ISSN$$a1613-3749
000157380 0247_ $$2ISSN$$a1613-3757
000157380 0247_ $$2altmetric$$aaltmetric:87898522
000157380 037__ $$aDKFZ-2020-01603
000157380 041__ $$aeng
000157380 082__ $$a610
000157380 1001_ $$0P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aSchelb, Patrick$$b0$$eFirst author
000157380 245__ $$aSimulated clinical deployment of fully automatic deep learning for clinical prostate MRI assessment.
000157380 260__ $$aHeidelberg$$bSpringer$$c2021
000157380 3367_ $$2DRIVER$$aarticle
000157380 3367_ $$2DataCite$$aOutput Types/Journal article
000157380 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1609765244_8234
000157380 3367_ $$2BibTeX$$aARTICLE
000157380 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000157380 3367_ $$00$$2EndNote$$aJournal Article
000157380 500__ $$a2021 Jan;31(1):302-313#EA:E010#LA:E010#
000157380 520__ $$aTo simulate clinical deployment, evaluate performance, and establish quality assurance of a deep learning algorithm (U-Net) for detection, localization, and segmentation of clinically significant prostate cancer (sPC), ISUP grade group ≥ 2, using bi-parametric MRI.In 2017, 284 consecutive men in active surveillance, biopsy-naïve or pre-biopsied, received targeted and extended systematic MRI/transrectal US-fusion biopsy, after examination on a single MRI scanner (3 T). A prospective adjustment scheme was evaluated comparing the performance of the Prostate Imaging Reporting and Data System (PI-RADS) and U-Net using sensitivity, specificity, predictive values, and the Dice coefficient.In the 259 eligible men (median 64 [IQR 61-72] years), PI-RADS had a sensitivity of 98% [106/108]/84% [91/108] with a specificity of 17% [25/151]/58% [88/151], for thresholds at ≥ 3/≥ 4 respectively. U-Net using dynamic threshold adjustment had a sensitivity of 99% [107/108]/83% [90/108] (p > 0.99/> 0.99) with a specificity of 24% [36/151]/55% [83/151] (p > 0.99/> 0.99) for probability thresholds d3 and d4 emulating PI-RADS ≥ 3 and ≥ 4 decisions respectively, not statistically different from PI-RADS. Co-occurrence of a radiological PI-RADS ≥ 4 examination and U-Net ≥ d3 assessment significantly improved the positive predictive value from 59 to 63% (p = 0.03), on a per-patient basis.U-Net has similar performance to PI-RADS in simulated continued clinical use. Regular quality assurance should be implemented to ensure desired performance.• U-Net maintained similar diagnostic performance compared to radiological assessment of PI-RADS ≥ 4 when applied in a simulated clinical deployment. • Application of our proposed prospective dynamic calibration method successfully adjusted U-Net performance within acceptable limits of the PI-RADS reference over time, while not being limited to PI-RADS as a reference. • Simultaneous detection by U-Net and radiological assessment significantly improved the positive predictive value on a per-patient and per-lesion basis, while the negative predictive value remained unchanged.
000157380 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000157380 588__ $$aDataset connected to CrossRef, PubMed,
000157380 7001_ $$0P:(DE-He78)aec14a1077ed145f9ebe9de1d50905b0$$aWang, Xianfeng$$b1
000157380 7001_ $$0P:(DE-He78)79897f8897ff77676549d9895258a0f2$$aRadtke, Jan Philipp$$b2$$udkfz
000157380 7001_ $$0P:(DE-He78)1042737c83ba70ec508bdd99f0096864$$aWiesenfarth, Manuel$$b3
000157380 7001_ $$aKickingereder, Philipp$$b4
000157380 7001_ $$0P:(DE-HGF)0$$aStenzinger, Albrecht$$b5
000157380 7001_ $$aHohenfellner, Markus$$b6
000157380 7001_ $$0P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aSchlemmer, Heinz-Peter$$b7
000157380 7001_ $$0P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aMaier-Hein, Klaus H$$b8
000157380 7001_ $$0P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aBonekamp, David$$b9$$eLast author$$udkfz
000157380 773__ $$0PERI:(DE-600)1472718-3$$a10.1007/s00330-020-07086-z$$n1$$p302-313$$tEuropean radiology$$v31$$x1432-1084$$y2021
000157380 8564_ $$uhttps://pubmed.ncbi.nlm.nih.gov/32767102/
000157380 909CO $$ooai:inrepo02.dkfz.de:157380$$pVDB
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)aec14a1077ed145f9ebe9de1d50905b0$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)79897f8897ff77676549d9895258a0f2$$aDeutsches Krebsforschungszentrum$$b2$$kDKFZ
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)1042737c83ba70ec508bdd99f0096864$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aDeutsches Krebsforschungszentrum$$b7$$kDKFZ
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aDeutsches Krebsforschungszentrum$$b8$$kDKFZ
000157380 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aDeutsches Krebsforschungszentrum$$b9$$kDKFZ
000157380 9130_ $$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$$x0
000157380 9131_ $$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$$x0
000157380 9141_ $$y2021
000157380 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2020-01-14$$wger
000157380 915__ $$0StatID:(DE-HGF)3002$$2StatID$$aDEAL Springer$$d2020-01-14$$wger
000157380 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bEUR RADIOL : 2018$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-01-14
000157380 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2020-01-14
000157380 9202_ $$0I:(DE-He78)E010-20160331$$kE010$$lE010 Radiologie$$x0
000157380 9200_ $$0I:(DE-He78)E010-20160331$$kE010$$lE010 Radiologie$$x0
000157380 9201_ $$0I:(DE-He78)E010-20160331$$kE010$$lE010 Radiologie$$x0
000157380 9201_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x1
000157380 9201_ $$0I:(DE-He78)C060-20160331$$kC060$$lC060 Biostatistik$$x2
000157380 9201_ $$0I:(DE-He78)HD01-20160331$$kHD01$$lDKTK HD zentral$$x3
000157380 980__ $$ajournal
000157380 980__ $$aVDB
000157380 980__ $$aI:(DE-He78)E010-20160331
000157380 980__ $$aI:(DE-He78)E230-20160331
000157380 980__ $$aI:(DE-He78)C060-20160331
000157380 980__ $$aI:(DE-He78)HD01-20160331
000157380 980__ $$aUNRESTRICTED