000286588 001__ 286588
000286588 005__ 20240701124349.0
000286588 0247_ $$2doi$$a10.1007/s00330-023-10540-3
000286588 0247_ $$2pmid$$apmid:38150075
000286588 0247_ $$2ISSN$$a0938-7994
000286588 0247_ $$2ISSN$$a1432-1084
000286588 0247_ $$2ISSN$$a1613-3749
000286588 0247_ $$2ISSN$$a1613-3757
000286588 0247_ $$2ISSN$$a(ISSN
000286588 0247_ $$2ISSN$$aDES
000286588 0247_ $$2ISSN$$aSUPPLEMENTS)
000286588 0247_ $$2altmetric$$aaltmetric:159881985
000286588 037__ $$aDKFZ-2023-02805
000286588 041__ $$aEnglish
000286588 082__ $$a610
000286588 1001_ $$00000-0002-4133-1194$$aAlmeida, Silvia D$$b0$$eFirst author
000286588 245__ $$aPrediction of disease severity in COPD: a deep learning approach for anomaly-based quantitative assessment of chest CT.
000286588 260__ $$aHeidelberg$$bSpringer$$c2024
000286588 3367_ $$2DRIVER$$aarticle
000286588 3367_ $$2DataCite$$aOutput Types/Journal article
000286588 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1719830586_5813
000286588 3367_ $$2BibTeX$$aARTICLE
000286588 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000286588 3367_ $$00$$2EndNote$$aJournal Article
000286588 500__ $$a#EA:E230#LA:E230# / 2024 Jul;34(7):4379-4392
000286588 520__ $$aTo quantify regional manifestations related to COPD as anomalies from a modeled distribution of normal-appearing lung on chest CT using a deep learning (DL) approach, and to assess its potential to predict disease severity.Paired inspiratory/expiratory CT and clinical data from COPDGene and COSYCONET cohort studies were included. COPDGene data served as training/validation/test data sets (N = 3144/786/1310) and COSYCONET as external test set (N = 446). To differentiate low-risk (healthy/minimal disease, [GOLD 0]) from COPD patients (GOLD 1-4), the self-supervised DL model learned semantic information from 50 × 50 × 50 voxel samples from segmented intact lungs. An anomaly detection approach was trained to quantify lung abnormalities related to COPD, as regional deviations. Four supervised DL models were run for comparison. The clinical and radiological predictive power of the proposed anomaly score was assessed using linear mixed effects models (LMM).The proposed approach achieved an area under the curve of 84.3 ± 0.3 (p < 0.001) for COPDGene and 76.3 ± 0.6 (p < 0.001) for COSYCONET, outperforming supervised models even when including only inspiratory CT. Anomaly scores significantly improved fitting of LMM for predicting lung function, health status, and quantitative CT features (emphysema/air trapping; p < 0.001). Higher anomaly scores were significantly associated with exacerbations for both cohorts (p < 0.001) and greater dyspnea scores for COPDGene (p < 0.001).Quantifying heterogeneous COPD manifestations as anomaly offers advantages over supervised methods and was found to be predictive for lung function impairment and morphology deterioration.Using deep learning, lung manifestations of COPD can be identified as deviations from normal-appearing chest CT and attributed an anomaly score which is consistent with decreased pulmonary function, emphysema, and air trapping.• A self-supervised DL anomaly detection method discriminated low-risk individuals and COPD subjects, outperforming classic DL methods on two datasets (COPDGene AUC = 84.3%, COSYCONET AUC = 76.3%). • Our contrastive task exhibits robust performance even without the inclusion of expiratory images, while voxel-based methods demonstrate significant performance enhancement when incorporating expiratory images, in the COPDGene dataset. • Anomaly scores improved the fitting of linear mixed effects models in predicting clinical parameters and imaging alterations (p < 0.001) and were directly associated with clinical outcomes (p < 0.001).
000286588 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000286588 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000286588 650_7 $$2Other$$aArtificial intelligence
000286588 650_7 $$2Other$$aChronic obstructive pulmonary disease
000286588 650_7 $$2Other$$aComputed tomography
000286588 650_7 $$2Other$$aDeep learning
000286588 7001_ $$0P:(DE-He78)a70f21a2bf78bbc1306c3d432ae08dc7$$aNorajitra, Tobias$$b1$$udkfz
000286588 7001_ $$0P:(DE-He78)6a78e3a44a8038881d941fb467eb4e19$$aLüth, Carsten$$b2$$udkfz
000286588 7001_ $$0P:(DE-He78)4412d586f86ca57943732a2b9318c44f$$aWald, Tassilo$$b3$$udkfz
000286588 7001_ $$0P:(DE-He78)7dc85735e114a4ace658ba1450a2cca6$$aWeru, Vivienn$$b4$$udkfz
000286588 7001_ $$0P:(DE-He78)a657bf15b4cbdf70baed30e14c19d9d3$$aNolden, Marco$$b5$$udkfz
000286588 7001_ $$0P:(DE-He78)04a0b5a49db132d8f00cee326cb743ca$$aJäger, Paul$$b6$$udkfz
000286588 7001_ $$avon Stackelberg, Oyunbileg$$b7
000286588 7001_ $$aHeußel, Claus Peter$$b8
000286588 7001_ $$aWeinheimer, Oliver$$b9
000286588 7001_ $$aBiederer, Jürgen$$b10
000286588 7001_ $$aKauczor, Hans-Ulrich$$b11
000286588 7001_ $$0P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aMaier-Hein, Klaus$$b12$$eLast author$$udkfz
000286588 773__ $$0PERI:(DE-600)1472718-3$$a10.1007/s00330-023-10540-3$$n7$$p4379-4392$$tEuropean radiology$$v34$$x0938-7994$$y2024
000286588 909CO $$ooai:inrepo02.dkfz.de:286588$$pVDB
000286588 9101_ $$0I:(DE-588b)2036810-0$$60000-0002-4133-1194$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000286588 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a70f21a2bf78bbc1306c3d432ae08dc7$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000286588 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)6a78e3a44a8038881d941fb467eb4e19$$aDeutsches Krebsforschungszentrum$$b2$$kDKFZ
000286588 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)4412d586f86ca57943732a2b9318c44f$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000286588 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)7dc85735e114a4ace658ba1450a2cca6$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000286588 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)a657bf15b4cbdf70baed30e14c19d9d3$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ
000286588 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)04a0b5a49db132d8f00cee326cb743ca$$aDeutsches Krebsforschungszentrum$$b6$$kDKFZ
000286588 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aDeutsches Krebsforschungszentrum$$b12$$kDKFZ
000286588 9131_ $$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$$x0
000286588 9141_ $$y2023
000286588 915__ $$0StatID:(DE-HGF)3002$$2StatID$$aDEAL Springer$$d2023-08-19$$wger
000286588 915__ $$0StatID:(DE-HGF)3002$$2StatID$$aDEAL Springer$$d2023-08-19$$wger
000286588 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bEUR RADIOL : 2022$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2023-08-19
000286588 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bEUR RADIOL : 2022$$d2023-08-19
000286588 9202_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x0
000286588 9201_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x0
000286588 9201_ $$0I:(DE-He78)E290-20160331$$kE290$$lNWG Interaktives maschinelles Lernen$$x1
000286588 9201_ $$0I:(DE-He78)C060-20160331$$kC060$$lC060 Biostatistik$$x2
000286588 9200_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x0
000286588 980__ $$ajournal
000286588 980__ $$aVDB
000286588 980__ $$aI:(DE-He78)E230-20160331
000286588 980__ $$aI:(DE-He78)E290-20160331
000286588 980__ $$aI:(DE-He78)C060-20160331
000286588 980__ $$aUNRESTRICTED