000294878 001__ 294878
000294878 005__ 20241210182915.0
000294878 0247_ $$2doi$$a10.48550/ARXIV.2403.06567
000294878 037__ $$aDKFZ-2024-02588
000294878 1001_ $$0P:(DE-He78)e35f6a9bd89b1c66d107df8a2325a758$$aDenner, Stefan$$b0$$eFirst author$$udkfz
000294878 245__ $$aLeveraging Foundation Models for Content-Based Medical Image Retrieval in Radiology
000294878 260__ $$barXiv$$c2024
000294878 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1733825110_7696
000294878 3367_ $$2ORCID$$aWORKING_PAPER
000294878 3367_ $$028$$2EndNote$$aElectronic Article
000294878 3367_ $$2DRIVER$$apreprint
000294878 3367_ $$2BibTeX$$aARTICLE
000294878 3367_ $$2DataCite$$aOutput Types/Working Paper
000294878 520__ $$aContent-based image retrieval (CBIR) has the potential to significantly improve diagnostic aid and medical research in radiology. Current CBIR systems face limitations due to their specialization to certain pathologies, limiting their utility. In response, we propose using vision foundation models as powerful and versatile off-the-shelf feature extractors for content-based medical image retrieval. By benchmarking these models on a comprehensive dataset of 1.6 million 2D radiological images spanning four modalities and 161 pathologies, we identify weakly-supervised models as superior, achieving a P@1 of up to 0.594. This performance not only competes with a specialized model but does so without the need for fine-tuning. Our analysis further explores the challenges in retrieving pathological versus anatomical structures, indicating that accurate retrieval of pathological features presents greater difficulty. Despite these challenges, our research underscores the vast potential of foundation models for CBIR in radiology, proposing a shift towards versatile, general-purpose medical image retrieval systems that do not require specific tuning.
000294878 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0
000294878 588__ $$aDataset connected to DataCite
000294878 650_7 $$2Other$$aComputer Vision and Pattern Recognition (cs.CV)
000294878 650_7 $$2Other$$aInformation Retrieval (cs.IR)
000294878 650_7 $$2Other$$aFOS: Computer and information sciences
000294878 7001_ $$0P:(DE-He78)c1fcef80eab3d1e4fc187faece1a439c$$aZimmerer, David$$b1$$udkfz
000294878 7001_ $$0P:(DE-He78)95f361c74f433d336bfd0a95bc9b0eba$$aBounias, Dimitrios$$b2$$udkfz
000294878 7001_ $$0P:(DE-He78)d52d4217d38d20b78d1bc8014e2b0c35$$aBujotzek, Markus$$b3$$udkfz
000294878 7001_ $$0P:(DE-He78)d2bf7126723ea8f6005ba141ea3c3e2c$$aXiao, Shuhan$$b4$$udkfz
000294878 7001_ $$0P:(DE-He78)4854a5d7f6e812324fd74320396f4178$$aKausch, Lisa$$b5
000294878 7001_ $$0P:(DE-He78)2529b97355581f2d933fcfd7908d9ed4$$aSchader, Philipp$$b6$$udkfz
000294878 7001_ $$aPenzkofer, Tobias$$b7
000294878 7001_ $$0P:(DE-He78)04a0b5a49db132d8f00cee326cb743ca$$aJäger, Paul F.$$b8$$udkfz
000294878 7001_ $$0P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aMaier-Hein, Klaus$$b9$$eLast author$$udkfz
000294878 773__ $$a10.48550/ARXIV.2403.06567
000294878 909CO $$ooai:inrepo02.dkfz.de:294878$$pVDB
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)e35f6a9bd89b1c66d107df8a2325a758$$aDeutsches Krebsforschungszentrum$$b0$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)c1fcef80eab3d1e4fc187faece1a439c$$aDeutsches Krebsforschungszentrum$$b1$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)95f361c74f433d336bfd0a95bc9b0eba$$aDeutsches Krebsforschungszentrum$$b2$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)d52d4217d38d20b78d1bc8014e2b0c35$$aDeutsches Krebsforschungszentrum$$b3$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)d2bf7126723ea8f6005ba141ea3c3e2c$$aDeutsches Krebsforschungszentrum$$b4$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)4854a5d7f6e812324fd74320396f4178$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)2529b97355581f2d933fcfd7908d9ed4$$aDeutsches Krebsforschungszentrum$$b6$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)04a0b5a49db132d8f00cee326cb743ca$$aDeutsches Krebsforschungszentrum$$b8$$kDKFZ
000294878 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)33c74005e1ce56f7025c4f6be15321b3$$aDeutsches Krebsforschungszentrum$$b9$$kDKFZ
000294878 9131_ $$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$$x0
000294878 9141_ $$y2024
000294878 9201_ $$0I:(DE-He78)E230-20160331$$kE230$$lE230 Medizinische Bildverarbeitung$$x0
000294878 9201_ $$0I:(DE-He78)E290-20160331$$kE290$$lNWG Interaktives maschinelles Lernen$$x1
000294878 980__ $$apreprint
000294878 980__ $$aVDB
000294878 980__ $$aI:(DE-He78)E230-20160331
000294878 980__ $$aI:(DE-He78)E290-20160331
000294878 980__ $$aUNRESTRICTED