Reproducibility and across-site transferability of an improved deep learning approach for aneurysm detection and segmentation in time-of-flight MR-angiograms.
Convolutional neural network
Deep learning
Intracranial aneurysm
Magnetic resonance angiography
Reproducibility
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
13 08 2024
13 08 2024
Historique:
received:
04
03
2024
accepted:
29
07
2024
medline:
14
8
2024
pubmed:
14
8
2024
entrez:
13
8
2024
Statut:
epublish
Résumé
This study aimed to (1) replicate a deep-learning-based model for cerebral aneurysm segmentation in TOF-MRAs, (2) improve the approach by testing various fully automatic pre-processing pipelines, and (3) rigorously validate the model's transferability on independent, external test-datasets. A convolutional neural network was trained on 235 TOF-MRAs acquired on local scanners from a single vendor to segment intracranial aneurysms. Different pre-processing pipelines including bias field correction, resampling, cropping and intensity-normalization were compared regarding their effect on model performance. The models were tested on independent, external same-vendor and other-vendor test-datasets, each comprised of 70 TOF-MRAs, including patients with and without aneurysms. The best-performing model achieved excellent results on the external same-vendor test-dataset, surpassing the results of the previous publication with an improved sensitivity (0.97 vs. ~ 0.86), a higher Dice score coefficient (DSC, 0.60 ± 0.25 vs. 0.53 ± 0.31), and an improved false-positive rate (0.87 ± 1.35 vs. ~ 2.7 FPs/case). The model further showed excellent performance in the external other-vendor test-datasets (DSC 0.65 ± 0.26; sensitivity 0.92, 0.96 ± 2.38 FPs/case). Specificity was 0.38 and 0.53, respectively. Raising the voxel-size from 0.5 × 0.5×0.5 mm to 1 × 1×1 mm reduced the false-positive rate seven-fold. This study successfully replicated core principles of a previous approach for detecting and segmenting cerebral aneurysms in TOF-MRAs with a robust, fully automatable pre-processing pipeline. The model demonstrated robust transferability on two independent external datasets using TOF-MRAs from the same scanner vendor as the training dataset and from other vendors. These findings are very encouraging regarding the clinical application of such an approach.
Identifiants
pubmed: 39138338
doi: 10.1038/s41598-024-68805-w
pii: 10.1038/s41598-024-68805-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
18749Informations de copyright
© 2024. The Author(s).
Références
Brown, R. D. & Broderick, J. P. Unruptured intracranial aneurysms: Epidemiology, natural history, management options, and familial screening. Lancet Neurol. 13, 393–404. https://doi.org/10.1016/S1474-4422(14)70015-8 (2014).
doi: 10.1016/S1474-4422(14)70015-8
pubmed: 24646873
Brisman, J. L., Song, J. K. & Newell, D. W. Cerebral aneurysms. N. Engl. J. Med. 355, 928–939. https://doi.org/10.1056/NEJMra052760 (2006).
doi: 10.1056/NEJMra052760
pubmed: 16943405
Kapsalaki, E. Z., Rountas, C. D. & Fountas, K. N. The role of 3 tesla MRA in the detection of intracranial aneurysms. Int. J. Vasc. Med. 2012, 1–9. https://doi.org/10.1155/2012/792834 (2012).
doi: 10.1155/2012/792834
Okahara, M. et al. Diagnostic accuracy of magnetic resonance angiography for cerebral aneurysms in correlation with 3D-digital subtraction angiographic images: A study of 133 aneurysms. Stroke 33, 1803–1808. https://doi.org/10.1161/01.str.0000019510.32145.a9 (2002).
doi: 10.1161/01.str.0000019510.32145.a9
pubmed: 12105357
Kakeda, S. et al. Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system. AJR Am. J. Roentgenol. 190, 459–465. https://doi.org/10.2214/AJR.07.2642 (2008).
doi: 10.2214/AJR.07.2642
pubmed: 18212233
Štep̌ánBuksakowska, I. L. et al. Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting. AJNR Am. J. Neuroradiol. 35, 1897–1902. https://doi.org/10.3174/ajnr.A3996 (2014).
doi: 10.3174/ajnr.A3996
pubmed: 24924543
Sohn, B. et al. Deep learning-based software improves clinicians’ detection sensitivity of aneurysms on brain TOF-MRA. AJNR Am. J. Neuroradiol. https://doi.org/10.3174/ajnr.A7242 (2021).
doi: 10.3174/ajnr.A7242
pubmed: 34385143
pmcid: 8562741
Sichtermann, T. et al. Deep learning-based detection of intracranial aneurysms in 3D TOF-MRA. AJNR Am. J. Neuroradiol. 40, 25–32. https://doi.org/10.3174/ajnr.A5911 (2019).
doi: 10.3174/ajnr.A5911
pubmed: 30573461
pmcid: 7048599
Claux, F., Baudouin, M., Bogey, C. & Rouchaud, A. Dense, deep learning-based intracranial aneurysm detection on TOF MRI using two-stage regularized U-Net. J. Neuroradiol. https://doi.org/10.1016/j.neurad.2022.03.005 (2022).
doi: 10.1016/j.neurad.2022.03.005
pubmed: 35307554
Ueda, D. et al. Deep learning for MR angiography: Automated detection of cerebral aneurysms. Radiology 290, 187–194. https://doi.org/10.1148/radiol.2018180901 (2019).
doi: 10.1148/radiol.2018180901
pubmed: 30351253
Um, H. et al. Impact of image preprocessing on the scanner dependence of multi-parametric MRI radiomic features and covariate shift in multi-institutional glioblastoma datasets. Phys. Med. Biol. 64, 165011. https://doi.org/10.1088/1361-6560/ab2f44 (2019).
doi: 10.1088/1361-6560/ab2f44
pubmed: 31272093
Yushkevich, P. A. et al. User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. NeuroImage 31, 1116–1128. https://doi.org/10.1016/j.neuroimage.2006.01.015 (2006).
doi: 10.1016/j.neuroimage.2006.01.015
pubmed: 16545965
Tustison, N. J. et al. N4ITK: Improved N3 bias correction. IEEE Trans. Med. Imaging 29, 1310–1320. https://doi.org/10.1109/TMI.2010.2046908 (2010).
doi: 10.1109/TMI.2010.2046908
pubmed: 20378467
pmcid: 3071855
Jenkinson, M. et al. FSL. Neuroimage 62, 782–790. https://doi.org/10.1016/j.neuroimage.2011.09.015 (2012).
doi: 10.1016/j.neuroimage.2011.09.015
pubmed: 21979382
Kamnitsas, K. et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78. https://doi.org/10.1016/j.media.2016.10.004 (2017).
doi: 10.1016/j.media.2016.10.004
pubmed: 27865153
Jenkinson, M., Pechaud, M. & Smith, S. BET2 - MR-based estimation of brain, skull and scalp surfaces. Eleventh Annual Meeting of the Organization for Human Brain Mapping 2005, 167 (2005).
Virtanen, P. et al. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nat. Methods 17, 261–272. https://doi.org/10.1038/s41592-019-0686-2 (2020).
doi: 10.1038/s41592-019-0686-2
pubmed: 32015543
pmcid: 7056644
Fiehler, J. Nicht rupturierte intrakranielle Aneurysmen: Wann suchen, wann behandeln?. Fortschr. Röntgenstr. 184, 97–104. https://doi.org/10.1055/s-0031-1281984 (2012).
doi: 10.1055/s-0031-1281984
Chen, G. et al. Automated computer-assisted detection system for cerebral aneurysms in time-of-flight magnetic resonance angiography using fully convolutional network. Biomed. Eng. Online 19, 38. https://doi.org/10.1186/s12938-020-00770-7 (2020).
doi: 10.1186/s12938-020-00770-7
pubmed: 32471439
pmcid: 7257213
Joo, B. et al. A deep learning model with high standalone performance for diagnosis of unruptured intracranial aneurysm. Yonsei Med. J. 62, 1052–1061. https://doi.org/10.3349/ymj.2021.62.11.1052 (2021).
doi: 10.3349/ymj.2021.62.11.1052
pubmed: 34672139
pmcid: 8542476
Wichtmann, B. D. et al. Influence of image processing on radiomic features from magnetic resonance imaging. Investig. Radiol. https://doi.org/10.1097/RLI.0000000000000921 (2023).
doi: 10.1097/RLI.0000000000000921
Gresser, E. et al. Performance variability of radiomics machine learning models for the detection of clinically significant prostate cancer in heterogeneous MRI datasets. Quant. Imaging Med. Surg. 12, 4990–5003. https://doi.org/10.21037/qims-22-265 (2022).
doi: 10.21037/qims-22-265
pubmed: 36330197
pmcid: 9622454
Huber, F. A. et al. Whole-body composition profiling using a deep learning algorithm: Influence of different acquisition parameters on algorithm performance and robustness. Investig. Radiol. 57, 33. https://doi.org/10.1097/RLI.0000000000000799 (2022).
doi: 10.1097/RLI.0000000000000799