{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T09:37:32Z","timestamp":1785317852896,"version":"3.55.0"},"reference-count":25,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: in magnetic resonance imaging (MRI), automated detection of brain metastases with convolutional neural networks (CNN) represents an extraordinary challenge due to small lesions sometimes posing as brain vessels as well as other confounders. Literature reporting high false positive rates when using conventional contrast enhanced (CE) T1 sequences questions their usefulness in clinical routine. CE black blood (BB) sequences may overcome these limitations by suppressing contrast-enhanced structures, thus facilitating lesion detection. This study compared CNN performance in conventional CE T1 and BB sequences and tested for objective improvement of brain lesion detection. Methods: we included a subgroup of 127 consecutive patients, receiving both CE T1 and BB sequences, referred for MRI concerning metastatic spread to the brain. A pretrained CNN was retrained with a customized monolayer classifier using either T1 or BB scans of brain lesions. Results: CE T1 imaging-based training resulted in an internal validation accuracy of 85.5% vs. 92.3% in BB imaging (p &lt; 0.01). In holdout validation analysis, T1 image-based prediction presented poor specificity and sensitivity with an AUC of 0.53 compared to 0.87 in BB-imaging-based prediction. Conclusions: detection of brain lesions with CNN, BB-MRI imaging represents a highly effective input type when compared to conventional CE T1-MRI imaging. Use of BB-MRI can overcome the current limitations for automated brain lesion detection and the objectively excellent performance of our CNN suggests routine usage of BB sequences for radiological analysis.<\/jats:p>","DOI":"10.3390\/diagnostics11061016","type":"journal-article","created":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T15:58:44Z","timestamp":1622563124000},"page":"1016","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Contrast-Enhanced Black Blood MRI Sequence Is Superior to Conventional T1 Sequence in Automated Detection of Brain Metastases by Convolutional Neural Networks"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5021-6895","authenticated-orcid":false,"given":"Jonathan","family":"Kottlors","sequence":"first","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Geissen","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Pneumology, Angiology and Intensive Care, University of Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah","family":"Jendreizik","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7928-0487","authenticated-orcid":false,"given":"Nils","family":"Gro\u00dfe Hokamp","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Fervers","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lenhard","family":"Pennig","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Laukamp","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Kabbasch","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Maintz","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Schlamann","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Strasse 62, 50935 Cologne, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2908-7560","authenticated-orcid":false,"given":"Jan","family":"Borggrefe","sequence":"additional","affiliation":[{"name":"Institut f\u00fcr Radiologie Neuroradiologie und Nuklearmedizin, Ruhr-Universit\u00e4t Bochum, Minden University Hospital, Hans-Nolte-Strasse 1, 32429 Minden, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1093\/neuonc\/now241","article-title":"Diagnosis and treatment of brain metastases from solid tumors: Guidelines from the European Association of Neuro-Oncology (EANO)","volume":"19","author":"Soffietti","year":"2017","journal-title":"Neuro-Oncol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1093\/neuonc\/nos087","article-title":"A nomogram for individualized estimation of survival among patients with brain metastasis","volume":"14","author":"Yu","year":"2012","journal-title":"Neuro-Oncol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1781","DOI":"10.1002\/(SICI)1097-0142(19961015)78:8<1781::AID-CNCR19>3.0.CO;2-U","article-title":"Brain metastases. Histology, multiplicity, surgery, and survival","volume":"78","author":"Nussbaum","year":"1996","journal-title":"Cancer"},{"key":"ref_4","first-page":"415","article-title":"The Interdisciplinary Management of Brain Metastases","volume":"113","author":"Schmieder","year":"2016","journal-title":"Dtsch. Aerzteblatt Online"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1007\/s00330-014-3496-z","article-title":"3D MR Sequence Capable of Simultaneous Image Acquisitions with and without Blood Vessel Suppression: Utility in Diagnosing Brain Metastases","volume":"25","author":"Kikuchi","year":"2014","journal-title":"Eur. Radiol."},{"key":"ref_6","unstructured":"D\u00f6ssel, O., and Schlegel, W.C. (2009). Computerized Detection of Metastatic Brain Tumors on Contrast-Enhanced 3D MR Images by Using a Selective Enhancement Filter. World Congress on Medical Physics and Biomedical Engineering, Springer."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.compbiomed.2018.02.004","article-title":"Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network","volume":"95","author":"Charron","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1007\/s00330-018-5595-8","article-title":"Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI","volume":"29","author":"Laukamp","year":"2019","journal-title":"Eur. Radiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1002\/jmri.26766","article-title":"Deep learning enables automatic detection and segmentation of brain metastases on multisequence MRI","volume":"51","author":"Yi","year":"2020","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1634\/theoncologist.2018-0908","article-title":"Toward an Expert Level of Lung Cancer Detection and Classification Using a Deep Convolutional Neural Network","volume":"24","author":"Zhang","year":"2019","journal-title":"Oncologist"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nasrullah, N., Sang, J., Alam, M.S., Mateen, M., Cai, B., and Hu, H. (2019). Automated Lung Nodule Detection and Classification Using Deep Learning Combined with Multiple Strategies. Sensors, 19.","DOI":"10.3390\/s19173722"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1016\/j.mri.2012.02.024","article-title":"An approach for computer-aided detection of brain metastases in post-Gd T1-W MRI","volume":"30","author":"Farjam","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/S1474-4422(05)70072-7","article-title":"Therapeutic management of brain metastasis","volume":"4","author":"Kaal","year":"2005","journal-title":"Lancet Neurol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1016\/j.nurt.2009.04.012","article-title":"Current management of metastatic brain disease","volume":"6","author":"Ranjan","year":"2009","journal-title":"Neurotherapeutics"},{"key":"ref_15","first-page":"37","article-title":"Comparison of lesion enhancement on spin-echo and gradient-echo images","volume":"15","author":"Chappell","year":"1994","journal-title":"Am. J. Neuroradiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1818","DOI":"10.1007\/s00330-015-3975-x","article-title":"Comparison of contrast-enhanced modified T1-weighted 3D TSE black-blood and 3D MP-RAGE sequences for the detection of cerebral metastases and brain tumours","volume":"26","author":"Kammer","year":"2016","journal-title":"Eur. Radiol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1002\/jmri.22009","article-title":"Computer-aided detection of metastatic brain tumors using automated three-dimensional template matching","volume":"31","author":"Ambrosini","year":"2010","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Sunwoo, L., Kim, Y.J., Choi, S.H., Kim, K.-G., Kang, J.H., Kang, Y., Bae, Y.J., Yoo, R.-E., Kim, J., and Lee, K.J. (2017). Computer-aided detection of brain metastasis on 3D MR imaging: Observer performance study. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0178265"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1002\/jmri.25207","article-title":"Brain metastases detection on MR by means of three-dimensional tumor-appearance template matching","volume":"44","author":"Arana","year":"2016","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e366","DOI":"10.1016\/j.wneu.2019.08.148","article-title":"Accuracy of Radiomics-Based Feature Analysis on Multiparametric Magnetic Resonance Images for Noninvasive Meningioma Grading","volume":"132","author":"Laukamp","year":"2019","journal-title":"World Neurosurg."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Laukamp, K.R., Pennig, L., Thiele, F., Reimer, R., G\u00f6rtz, L., Shakirin, G., Zopfs, D., Timmer, M., Perkuhn, M., and Borggrefe, J. (2020). Automated Meningioma Segmentation in Multiparametric MRI. Clin. Neuroradiol., 1\u201310.","DOI":"10.1007\/s00062-020-00884-4"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1097\/RLI.0000000000000484","article-title":"Clinical Evaluation of a Multiparametric Deep Learning Model for Glioblastoma Segmentation Using Heterogeneous Magnetic Resonance Imaging Data From Clinical Routine","volume":"53","author":"Perkuhn","year":"2018","journal-title":"Investig. Radiol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1007\/s10278-017-9983-4","article-title":"Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions","volume":"30","author":"Akkus","year":"2017","journal-title":"J. Digit. Imaging"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1097\/RLI.0b013e318277f078","article-title":"Computer-Aided Detection of Metastatic Brain Tumors Using Magnetic Resonance Black-Blood Imaging","volume":"48","author":"Yang","year":"2013","journal-title":"Investig. Radiol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"9450","DOI":"10.1038\/s41598-018-27742-1","article-title":"Deep-learned 3D black-blood imaging using automatic labelling technique and 3D convolutional neural networks for detecting metastatic brain tumors","volume":"8","author":"Jun","year":"2018","journal-title":"Sci. Rep."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/6\/1016\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:09:58Z","timestamp":1760162998000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/6\/1016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,1]]},"references-count":25,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["diagnostics11061016"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics11061016","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,1]]}}}