Cited 0 times in
Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 박예원 | - |
dc.contributor.author | 안성수 | - |
dc.contributor.author | 이승구 | - |
dc.date.accessioned | 2021-11-19T01:38:09Z | - |
dc.date.available | 2021-11-19T01:38:09Z | - |
dc.date.issued | 2021-09 | - |
dc.identifier.issn | 0938-7994 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/185956 | - |
dc.description.abstract | Objectives: To evaluate whether a deep learning (DL) model using both three-dimensional (3D) black-blood (BB) imaging and 3D gradient echo (GRE) imaging may improve the detection and segmentation performance of brain metastases compared to that using only 3D GRE imaging. Methods: A total of 188 patients with brain metastases (917 lesions) who underwent a brain metastasis MRI protocol including contrast-enhanced 3D BB and 3D GRE were included in the training set. DL models based on 3D U-net were constructed. The models were validated in the test set consisting of 45 patients with brain metastases (203 lesions) and 49 patients without brain metastases. Results: The combined 3D BB and 3D GRE model yielded better performance than the 3D GRE model (sensitivities of 93.1% vs 76.8%, p < 0.001), and this effect was significantly stronger in subgroups with small metastases (p interaction < 0.001). For metastases < 3 mm, ≥ 3 mm and < 10 mm, and ≥ 10 mm, the sensitivities were 82.4%, 93.2%, and 100%, respectively. The combined 3D BB and 3D GRE model showed a false-positive per case of 0.59 in the test set. The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while 3D GRE model showed a lower Dice coefficient of 0.756. Conclusions: The combined 3D BB and 3D GRE DL model may improve the detection and segmentation performance of brain metastases, especially in detecting small metastases. Key points: • The combined 3D BB and 3D GRE model yielded better performance for the detection of brain metastases than the 3D GRE model (p < 0.001), with sensitivities of 93.1% and 76.8%, respectively. • The combined 3D BB and 3D GRE model showed a false-positive rate per case of 0.59 in the test set. • The combined 3D BB and 3D GRE model showed a Dice coefficient of 0.822, while the 3D GRE model showed a lower Dice coefficient of 0.756. | - |
dc.description.statementOfResponsibility | restriction | - |
dc.language | English | - |
dc.publisher | Springer International | - |
dc.relation.isPartOf | EUROPEAN RADIOLOGY | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.subject.MESH | African Americans | - |
dc.subject.MESH | Brain Neoplasms* / diagnostic imaging | - |
dc.subject.MESH | Contrast Media | - |
dc.subject.MESH | Deep Learning* | - |
dc.subject.MESH | Humans | - |
dc.subject.MESH | Imaging, Three-Dimensional | - |
dc.subject.MESH | Magnetic Resonance Imaging | - |
dc.title | Robust performance of deep learning for automatic detection and segmentation of brain metastases using three-dimensional black-blood and three-dimensional gradient echo imaging | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine (의과대학) | - |
dc.contributor.department | Dept. of Radiology (영상의학교실) | - |
dc.contributor.googleauthor | Yae Won Park | - |
dc.contributor.googleauthor | Yohan Jun | - |
dc.contributor.googleauthor | Yangho Lee | - |
dc.contributor.googleauthor | Kyunghwa Han | - |
dc.contributor.googleauthor | Chansik An | - |
dc.contributor.googleauthor | Sung Soo Ahn | - |
dc.contributor.googleauthor | Dosik Hwang | - |
dc.contributor.googleauthor | Seung-Koo Lee | - |
dc.identifier.doi | 10.1007/s00330-021-07783-3 | - |
dc.contributor.localId | A05330 | - |
dc.contributor.localId | A02234 | - |
dc.contributor.localId | A02912 | - |
dc.relation.journalcode | J00851 | - |
dc.identifier.eissn | 1432-1084 | - |
dc.identifier.pmid | 33738598 | - |
dc.identifier.url | https://link.springer.com/article/10.1007%2Fs00330-021-07783-3 | - |
dc.subject.keyword | Artificial intelligence | - |
dc.subject.keyword | Deep learning | - |
dc.subject.keyword | Magnetic resonance imaging | - |
dc.subject.keyword | Neoplasm metastasis | - |
dc.contributor.alternativeName | Park, Yae-Won | - |
dc.contributor.affiliatedAuthor | 박예원 | - |
dc.contributor.affiliatedAuthor | 안성수 | - |
dc.contributor.affiliatedAuthor | 이승구 | - |
dc.citation.volume | 31 | - |
dc.citation.number | 9 | - |
dc.citation.startPage | 6686 | - |
dc.citation.endPage | 6695 | - |
dc.identifier.bibliographicCitation | EUROPEAN RADIOLOGY, Vol.31(9) : 6686-6695, 2021-09 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.