File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1002/mp.13756
- Scopus: eid_2-s2.0-85071607400
- PMID: 31396973
- WOS: WOS:000491038000033
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Technical Note: Simultaneous Segmentation and Relaxometry for MRI through Multitask Learning
Title | Technical Note: Simultaneous Segmentation and Relaxometry for MRI through Multitask Learning |
---|---|
Authors | |
Keywords | Brain segmentation Deep neural network Gray matter Machine learning MR fingerprinting Relaxometry White matter |
Issue Date | 2019 |
Publisher | Wiley-Blackwell Publishing, Inc. The Journal's web site is located at http://aapm.onlinelibrary.wiley.com/hub/journal/10.1002/(ISSN)2473-4209/ |
Citation | Medical Physics, 2019, v. 46 n. 10, p. 4610-4621 How to Cite? |
Abstract | Purpose:
This study demonstrated a magnetic resonance (MR) signal multitask learning method for three‐dimensional (3D) simultaneous segmentation and relaxometry of human brain tissues.
Materials and Methods:
A 3D inversion‐prepared balanced steady‐state free precession sequence was used for acquiring in vivo multicontrast brain images. The deep neural network contained three residual blocks, and each block had 8 fully connected layers with sigmoid activation, layer norm, and 256 neurons in each layer. Online‐synthesized MR signal evolutions and labels were used to train the neural network batch‐by‐batch. Empirically defined ranges of T1 and T2 values for the normal gray matter, white matter, and cerebrospinal fluid (CSF) were used as the prior knowledge. MRI brain experiments were performed on three healthy volunteers. The mean and standard deviation for the T1 and T2 values in vivo were reported and compared to literature values. Additional animal (N = 6) and prostate patient (N = 1) experiments were performed to compare the estimated T1 and T2 values with those from gold standard methods and to demonstrate clinical applications of the proposed method.
Results:
In animal validation experiment, the differences/errors (mean difference ± standard deviation of difference) between the T1 and T2 values estimated from the proposed method and the ground truth were 113 ± 486 and 154 ± 512 ms for T1, and 5 ± 33 and 7 ± 41 ms for T2, respectively. In healthy volunteer experiments (N = 3), whole brain segmentation and relaxometry were finished within ~ 5 s. The estimated apparent T1 and T2 maps were in accordance with known brain anatomy, and not affected by coil sensitivity variation. Gray matter, white matter, and CSF were successfully segmented. The deep neural network can also generate synthetic T1‐ and T2‐weighted images.
Conclusion:
The proposed multitask learning method can directly generate brain apparent T1 and T2 maps, as well as synthetic T1‐ and T2‐weighted images, in conjunction with segmentation of gray matter, white matter, and CSF. |
Persistent Identifier | http://hdl.handle.net/10722/274940 |
ISSN | 2023 Impact Factor: 3.2 2023 SCImago Journal Rankings: 1.052 |
PubMed Central ID | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cao, P | - |
dc.contributor.author | Liu, J | - |
dc.contributor.author | Tang, S | - |
dc.contributor.author | Leynes, AP | - |
dc.contributor.author | Lupo, JM | - |
dc.contributor.author | Xu, D | - |
dc.contributor.author | Larson, PEZ | - |
dc.date.accessioned | 2019-09-10T02:32:02Z | - |
dc.date.available | 2019-09-10T02:32:02Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Medical Physics, 2019, v. 46 n. 10, p. 4610-4621 | - |
dc.identifier.issn | 0094-2405 | - |
dc.identifier.uri | http://hdl.handle.net/10722/274940 | - |
dc.description.abstract | Purpose: This study demonstrated a magnetic resonance (MR) signal multitask learning method for three‐dimensional (3D) simultaneous segmentation and relaxometry of human brain tissues. Materials and Methods: A 3D inversion‐prepared balanced steady‐state free precession sequence was used for acquiring in vivo multicontrast brain images. The deep neural network contained three residual blocks, and each block had 8 fully connected layers with sigmoid activation, layer norm, and 256 neurons in each layer. Online‐synthesized MR signal evolutions and labels were used to train the neural network batch‐by‐batch. Empirically defined ranges of T1 and T2 values for the normal gray matter, white matter, and cerebrospinal fluid (CSF) were used as the prior knowledge. MRI brain experiments were performed on three healthy volunteers. The mean and standard deviation for the T1 and T2 values in vivo were reported and compared to literature values. Additional animal (N = 6) and prostate patient (N = 1) experiments were performed to compare the estimated T1 and T2 values with those from gold standard methods and to demonstrate clinical applications of the proposed method. Results: In animal validation experiment, the differences/errors (mean difference ± standard deviation of difference) between the T1 and T2 values estimated from the proposed method and the ground truth were 113 ± 486 and 154 ± 512 ms for T1, and 5 ± 33 and 7 ± 41 ms for T2, respectively. In healthy volunteer experiments (N = 3), whole brain segmentation and relaxometry were finished within ~ 5 s. The estimated apparent T1 and T2 maps were in accordance with known brain anatomy, and not affected by coil sensitivity variation. Gray matter, white matter, and CSF were successfully segmented. The deep neural network can also generate synthetic T1‐ and T2‐weighted images. Conclusion: The proposed multitask learning method can directly generate brain apparent T1 and T2 maps, as well as synthetic T1‐ and T2‐weighted images, in conjunction with segmentation of gray matter, white matter, and CSF. | - |
dc.language | eng | - |
dc.publisher | Wiley-Blackwell Publishing, Inc. The Journal's web site is located at http://aapm.onlinelibrary.wiley.com/hub/journal/10.1002/(ISSN)2473-4209/ | - |
dc.relation.ispartof | Medical Physics | - |
dc.subject | Brain segmentation | - |
dc.subject | Deep neural network | - |
dc.subject | Gray matter | - |
dc.subject | Machine learning | - |
dc.subject | MR fingerprinting | - |
dc.subject | Relaxometry | - |
dc.subject | White matter | - |
dc.title | Technical Note: Simultaneous Segmentation and Relaxometry for MRI through Multitask Learning | - |
dc.type | Article | - |
dc.identifier.email | Cao, P: caopeng1@hku.hk | - |
dc.identifier.authority | Cao, P=rp02474 | - |
dc.description.nature | link_to_OA_fulltext | - |
dc.identifier.doi | 10.1002/mp.13756 | - |
dc.identifier.pmid | 31396973 | - |
dc.identifier.pmcid | PMC6800607 | - |
dc.identifier.scopus | eid_2-s2.0-85071607400 | - |
dc.identifier.hkuros | 304755 | - |
dc.identifier.volume | 46 | - |
dc.identifier.issue | 10 | - |
dc.identifier.spage | 4610 | - |
dc.identifier.epage | 4621 | - |
dc.identifier.isi | WOS:000491038000033 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 0094-2405 | - |