DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI
Abstract Lobar cerebral microbleeds (CMBs) and localized non-hemorrhage iron deposits in the basal ganglia have been associated with brain aging, vascular disease and neurodegenerative disorders. Particularly, CMBs are small lesions and require multiple neuroimaging modalities for accurate detection...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/f7b5390bd4814809ab0c8ab840d245ea |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:f7b5390bd4814809ab0c8ab840d245ea |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:f7b5390bd4814809ab0c8ab840d245ea2021-12-02T16:15:06ZDEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI10.1038/s41598-021-93427-x2045-2322https://doaj.org/article/f7b5390bd4814809ab0c8ab840d245ea2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93427-xhttps://doaj.org/toc/2045-2322Abstract Lobar cerebral microbleeds (CMBs) and localized non-hemorrhage iron deposits in the basal ganglia have been associated with brain aging, vascular disease and neurodegenerative disorders. Particularly, CMBs are small lesions and require multiple neuroimaging modalities for accurate detection. Quantitative susceptibility mapping (QSM) derived from in vivo magnetic resonance imaging (MRI) is necessary to differentiate between iron content and mineralization. We set out to develop a deep learning-based segmentation method suitable for segmenting both CMBs and iron deposits. We included a convenience sample of 24 participants from the MESA cohort and used T2-weighted images, susceptibility weighted imaging (SWI), and QSM to segment the two types of lesions. We developed a protocol for simultaneous manual annotation of CMBs and non-hemorrhage iron deposits in the basal ganglia. This manual annotation was then used to train a deep convolution neural network (CNN). Specifically, we adapted the U-Net model with a higher number of resolution layers to be able to detect small lesions such as CMBs from standard resolution MRI. We tested different combinations of the three modalities to determine the most informative data sources for the detection tasks. In the detection of CMBs using single class and multiclass models, we achieved an average sensitivity and precision of between 0.84–0.88 and 0.40–0.59, respectively. The same framework detected non-hemorrhage iron deposits with an average sensitivity and precision of about 0.75–0.81 and 0.62–0.75, respectively. Our results showed that deep learning could automate the detection of small vessel disease lesions and including multimodal MR data (particularly QSM) can improve the detection of CMB and non-hemorrhage iron deposits with sensitivity and precision that is compatible with use in large-scale research studies.Tanweer RashidAhmed AbdulkadirIlya M. NasrallahJeffrey B. WareHangfan LiuPascal SpincemailleJ. Rafael RomeroR. Nick BryanSusan R. HeckbertMohamad HabesNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Tanweer Rashid Ahmed Abdulkadir Ilya M. Nasrallah Jeffrey B. Ware Hangfan Liu Pascal Spincemaille J. Rafael Romero R. Nick Bryan Susan R. Heckbert Mohamad Habes DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI |
| description |
Abstract Lobar cerebral microbleeds (CMBs) and localized non-hemorrhage iron deposits in the basal ganglia have been associated with brain aging, vascular disease and neurodegenerative disorders. Particularly, CMBs are small lesions and require multiple neuroimaging modalities for accurate detection. Quantitative susceptibility mapping (QSM) derived from in vivo magnetic resonance imaging (MRI) is necessary to differentiate between iron content and mineralization. We set out to develop a deep learning-based segmentation method suitable for segmenting both CMBs and iron deposits. We included a convenience sample of 24 participants from the MESA cohort and used T2-weighted images, susceptibility weighted imaging (SWI), and QSM to segment the two types of lesions. We developed a protocol for simultaneous manual annotation of CMBs and non-hemorrhage iron deposits in the basal ganglia. This manual annotation was then used to train a deep convolution neural network (CNN). Specifically, we adapted the U-Net model with a higher number of resolution layers to be able to detect small lesions such as CMBs from standard resolution MRI. We tested different combinations of the three modalities to determine the most informative data sources for the detection tasks. In the detection of CMBs using single class and multiclass models, we achieved an average sensitivity and precision of between 0.84–0.88 and 0.40–0.59, respectively. The same framework detected non-hemorrhage iron deposits with an average sensitivity and precision of about 0.75–0.81 and 0.62–0.75, respectively. Our results showed that deep learning could automate the detection of small vessel disease lesions and including multimodal MR data (particularly QSM) can improve the detection of CMB and non-hemorrhage iron deposits with sensitivity and precision that is compatible with use in large-scale research studies. |
| format |
article |
| author |
Tanweer Rashid Ahmed Abdulkadir Ilya M. Nasrallah Jeffrey B. Ware Hangfan Liu Pascal Spincemaille J. Rafael Romero R. Nick Bryan Susan R. Heckbert Mohamad Habes |
| author_facet |
Tanweer Rashid Ahmed Abdulkadir Ilya M. Nasrallah Jeffrey B. Ware Hangfan Liu Pascal Spincemaille J. Rafael Romero R. Nick Bryan Susan R. Heckbert Mohamad Habes |
| author_sort |
Tanweer Rashid |
| title |
DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI |
| title_short |
DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI |
| title_full |
DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI |
| title_fullStr |
DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI |
| title_full_unstemmed |
DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI |
| title_sort |
deepmir: a deep neural network for differential detection of cerebral microbleeds and iron deposits in mri |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/f7b5390bd4814809ab0c8ab840d245ea |
| work_keys_str_mv |
AT tanweerrashid deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT ahmedabdulkadir deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT ilyamnasrallah deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT jeffreybware deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT hangfanliu deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT pascalspincemaille deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT jrafaelromero deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT rnickbryan deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT susanrheckbert deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri AT mohamadhabes deepmiradeepneuralnetworkfordifferentialdetectionofcerebralmicrobleedsandirondepositsinmri |
| _version_ |
1718384328073805824 |