000165963 001__ 165963
000165963 005__ 20240229133516.0
000165963 0247_ $$2doi$$a10.1055/a-1290-8070
000165963 0247_ $$2pmid$$apmid:33212541
000165963 0247_ $$2ISSN$$a0015-8151
000165963 0247_ $$2ISSN$$a0340-1618
000165963 0247_ $$2ISSN$$a0367-2239
000165963 0247_ $$2ISSN$$a0936-6652
000165963 0247_ $$2ISSN$$a1433-5972
000165963 0247_ $$2ISSN$$a1438-9010
000165963 0247_ $$2ISSN$$a1438-9029
000165963 0247_ $$2altmetric$$aaltmetric:94649617
000165963 037__ $$aDKFZ-2020-02512
000165963 041__ $$aeng
000165963 082__ $$a610
000165963 1001_ $$0P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aSchelb, Patrick$$b0$$eFirst author$$udkfz
000165963 245__ $$aComparison of Prostate MRI Lesion Segmentation Agreement Between Multiple Radiologists and a Fully Automatic Deep Learning System.[Vergleich der Kongruenz von Prostata-MRT-Läsionssegmentationen durch mehrere Radiologen und ein vollautomatisches Deep-Learning-System]. 
000165963 260__ $$aStuttgart [u.a.]$$bThieme$$c2021
000165963 3367_ $$2DRIVER$$aarticle
000165963 3367_ $$2DataCite$$aOutput Types/Journal article
000165963 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1620822120_31436
000165963 3367_ $$2BibTeX$$aARTICLE
000165963 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000165963 3367_ $$00$$2EndNote$$aJournal Article
000165963 500__ $$a#EA:E010#LA:E010#2021 May;193(5):559-573
000165963 520__ $$aA recently developed deep learning model (U-Net) approximated the clinical performance of radiologists in the prediction of clinically significant prostate cancer (sPC) from prostate MRI. Here, we compare the agreement between lesion segmentations by U-Net with manual lesion segmentations performed by different radiologists. 165 patients with suspicion for sPC underwent targeted and systematic fusion biopsy following 3 Tesla multiparametric MRI (mpMRI). Five sets of segmentations were generated retrospectively: segmentations of clinical lesions, independent segmentations by three radiologists, and fully automated bi-parametric U-Net segmentations. Per-lesion agreement was calculated for each rater by averaging Dice coefficients with all overlapping lesions from other raters. Agreement was compared using descriptive statistics and linear mixed models. The mean Dice coefficient for manual segmentations showed only moderate agreement at 0.48-0.52, reflecting the difficult visual task of determining the outline of otherwise jointly detected lesions. U-net segmentations were significantly smaller than manual segmentations (p < 0.0001) and exhibited a lower mean Dice coefficient of 0.22, which was significantly lower compared to manual segmentations (all p < 0.0001). These differences remained after correction for lesion size and were unaffected between sPC and non-sPC lesions and between peripheral and transition zone lesions. Knowledge of the order of agreement of manual segmentations of different radiologists is important to set the expectation value for artificial intelligence (AI) systems in the task of prostate MRI lesion segmentation. Perfect agreement (Dice coefficient of one) should not be expected for AI. Lower Dice coefficients of U-Net compared to manual segmentations are only partially explained by smaller segmentation sizes and may result from a focus on the lesion core and a small relative lesion center shift. Although it is primarily important that AI detects sPC correctly, the Dice coefficient for overlapping lesions from multiple raters can be used as a secondary measure for segmentation quality in future studies. · Intermediate human Dice coefficients reflect the difficulty of outlining jointly detected lesions.. · Lower Dice coefficients of deep learning motivate further research to approximate human perception.. · Comparable predictive performance of deep learning appears independent of Dice agreement.. · Dice agreement independent of significant cancer presence indicates indistinguishability of some benign imaging findings.. · Improving DWI to T2 registration may improve the observed U-Net Dice coefficients..· Schelb P, Tavakoli AA, Tubtawee T et al. Comparison of Prostate MRI Lesion Segmentation Agreement Between Multiple Radiologists and a Fully Automatic Deep Learning System. Fortschr Röntgenstr 2020; DOI: 10.1055/a-1290-8070.
000165963 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000165963 588__ $$aDataset connected to CrossRef, PubMed,
000165963 7001_ $$0P:(DE-He78)c6d2d9aa8c2d4ecd0dd6f96d2f40b7c3$$aTavakoli, Anoshirwan Andrej$$b1$$udkfz
000165963 7001_ $$0P:(DE-He78)56999133050e31cc9d173d36f4756f0b$$aTubtawee, Teeravut$$b2
000165963 7001_ $$0P:(DE-He78)743a4a82daab55306a2c88b9f6bf8c2f$$aHielscher, Thomas$$b3$$udkfz
000165963 7001_ $$aRadtke, Jan-Philipp$$b4
000165963 7001_ $$aGörtz, Magdalena$$b5
000165963 7001_ $$aSchütz, Viktoria$$b6
000165963 7001_ $$0P:(DE-He78)59dfdd0ee0a7f0db81535f0781a3a6d6$$aKuder, Tristan Anselm$$b7$$udkfz
000165963 7001_ $$00000-0001-7476-292X$$aSchimmöller, Lars$$b8
000165963 7001_ $$aStenzinger, Albrecht$$b9
000165963 7001_ $$aHohenfellner, Markus$$b10
000165963 7001_ $$0P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aSchlemmer, Heinz-Peter$$b11$$udkfz
000165963 7001_ $$0P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aBonekamp, David$$b12$$eLast author$$udkfz
000165963 773__ $$0PERI:(DE-600)2031079-1$$a10.1055/a-1290-8070$$gp. a-1290-8070$$n5$$p559-573$$tRöFo$$v193$$x1438-9010$$y2021
000165963 909CO $$ooai:inrepo02.dkfz.de:165963$$pVDB
000165963 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)4b5e5faa688c6b833c70b6777f91f662$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000165963 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)c6d2d9aa8c2d4ecd0dd6f96d2f40b7c3$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000165963 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)56999133050e31cc9d173d36f4756f0b$$aDeutsches Krebsforschungszentrum$$b2$$kDKFZ
000165963 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)743a4a82daab55306a2c88b9f6bf8c2f$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000165963 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)59dfdd0ee0a7f0db81535f0781a3a6d6$$aDeutsches Krebsforschungszentrum$$b7$$kDKFZ
000165963 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)3d04c8fee58c9ab71f62ff80d06b6fec$$aDeutsches Krebsforschungszentrum$$b11$$kDKFZ
000165963 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)ea098e4d78abeb63afaf8c25ec6d6d93$$aDeutsches Krebsforschungszentrum$$b12$$kDKFZ
000165963 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
000165963 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
000165963 9141_ $$y2021
000165963 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2020-08-28$$wger
000165963 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bROFO-FORTSCHR RONTG : 2018$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2020-08-28
000165963 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2020-08-28
000165963 9201_ $$0I:(DE-He78)E010-20160331$$kE010$$lE010 Radiologie$$x0
000165963 9201_ $$0I:(DE-He78)C060-20160331$$kC060$$lC060 Biostatistik$$x1
000165963 9201_ $$0I:(DE-He78)E020-20160331$$kE020$$lE020 Med. Physik in der Radiologie$$x2
000165963 980__ $$ajournal
000165963 980__ $$aVDB
000165963 980__ $$aI:(DE-He78)E010-20160331
000165963 980__ $$aI:(DE-He78)C060-20160331
000165963 980__ $$aI:(DE-He78)E020-20160331
000165963 980__ $$aUNRESTRICTED