|
1
|
Ren J, Wang X, Liu C, Sun H, Tong J, Lin M, Li J, Liang L, Yin F, Xie M, Liu Y. 3D Ultrasonic Brain Imaging with Deep Learning Based on Fully Convolutional Networks. SENSORS (BASEL, SWITZERLAND) 2023; 23:8341. [PMID: 37837171 PMCID: PMC10575417 DOI: 10.3390/s23198341] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/21/2023] [Revised: 09/16/2023] [Accepted: 09/25/2023] [Indexed: 10/15/2023]
Abstract
Compared to magnetic resonance imaging (MRI) and X-ray computed tomography (CT), ultrasound imaging is safer, faster, and more widely applicable. However, the use of conventional ultrasound in transcranial brain imaging for adults is predominantly hindered by the high acoustic impedance contrast between the skull and soft tissue. This study introduces a 3D AI algorithm, Brain Imaging Full Convolution Network (BIFCN), combining waveform modeling and deep learning for precise brain ultrasound reconstruction. We constructed a network comprising one input layer, four convolution layers, and one pooling layer to train our algorithm. In the simulation experiment, the Pearson correlation coefficient between the reconstructed and true images was exceptionally high. In the laboratory, the results showed a slightly lower but still impressive coincidence degree for 3D reconstruction, with pure water serving as the initial model and no prior information required. The 3D network can be trained in 8 h, and 10 samples can be reconstructed in just 12.67 s. The proposed 3D BIFCN algorithm provides a highly accurate and efficient solution for mapping wavefield frequency domain data to 3D brain models, enabling fast and precise brain tissue imaging. Moreover, the frequency shift phenomenon of blood may become a hallmark of BIFCN learning, offering valuable quantitative information for whole-brain blood imaging.
Collapse
Affiliation(s)
- Jiahao Ren
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
| | - Xiaocen Wang
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
| | - Chang Liu
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
| | - He Sun
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
| | - Junkai Tong
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
| | - Min Lin
- Department of Mechanical Engineering, University of Wyoming, Laramie, WY 82071, USA;
| | - Jian Li
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
| | - Lin Liang
- Schlumberger-Doll Research, Cambridge, MA 02139, USA;
| | - Feng Yin
- State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing 210096, China;
| | - Mengying Xie
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
| | - Yang Liu
- State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China; (J.R.); (X.W.); (C.L.); (H.S.); (J.T.); (J.L.)
- International Institute for Innovative Design and Intelligent Manufacturing of Tianjin University in Zhejiang, Shaoxing 330100, China
| |
Collapse
|
|
2
|
Raghuram H, Looi T, Pichardo S, Waspe AC, Drake JM. A robotic MR-guided high-intensity focused ultrasound platform for intraventricular hemorrhage: assessment of clot lysis efficacy in a brain phantom. J Neurosurg Pediatr 2022; 30:586-594. [PMID: 36115058 DOI: 10.3171/2022.8.peds22144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/18/2022] [Accepted: 08/05/2022] [Indexed: 11/06/2022]
Abstract
OBJECTIVE Intraventricular hemorrhage (IVH) is a neurovascular complication due to premature birth that results in blood clots forming within the ventricles. Magnetic resonance-guided high-intensity focused ultrasound (MRgHIFU) has been investigated as a noninvasive treatment to lyse clots. The authors designed and constructed a robotic MRgHIFU platform to treat the neonatal brain that facilitates ergonomic patient positioning. The clot lysis efficacy of the platform is quantified using a brain phantom and clinical MRI system. METHODS A thermosensitive brain-mimicking phantom with ventricular cavities was developed to test the clot lysis efficacy of the robotic MRgHIFU platform. Whole porcine blood was clotted within the phantom's cavities. Using the MRgHIFU platform and a boiling histotripsy treatment procedure (500 W, 10-msec pulse duration, 1.0% duty cycle, and 40-second duration), the clots were lysed inside the phantom. The contents of the cavities were vacuum filtered, and the remaining mass of the solid clot particles was used to quantify the percentage of clot lysis. The interior of the phantom's cavities was inspected for any collateral damage during treatment. RESULTS A total of 9 phantoms were sonicated, yielding an average (± SD) clot lysis of 97.0% ± 2.57%. Treatment resulted in substantial clot lysis within the brain-mimicking phantoms that were apparent on postsonication T2-weighted MR images. No apparent collateral damage was observed within the phantom after treatment. The results from the study showed the MRgHIFU platform was successful at lysing more than 90% of a blood clot at a statistically significant level. CONCLUSIONS The robotic MRgHIFU platform was shown to lyse a large percentage of a blood clot with no observable collateral damage. These results demonstrate the platform's ability to induce clot lysis when targeting through simulated brain matter and show promise toward the final application in neonatal patients.
Collapse
Affiliation(s)
- Hrishikesh Raghuram
- 1Posluns Centre for Image Guided Innovation and Therapeutic Intervention, Hospital for Sick Children, Toronto, Ontario
- 2The Institute of Biomedical Engineering, University of Toronto, Ontario
| | - Thomas Looi
- 1Posluns Centre for Image Guided Innovation and Therapeutic Intervention, Hospital for Sick Children, Toronto, Ontario
- 4Mechanical Engineering, and
| | - Samuel Pichardo
- 5Radiology and Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Alberta; and
- 6Hotchkiss Brain Institute, University of Calgary, Alberta, Canada
| | - Adam C Waspe
- 1Posluns Centre for Image Guided Innovation and Therapeutic Intervention, Hospital for Sick Children, Toronto, Ontario
- Departments of3Medical Imaging
| | - James M Drake
- 1Posluns Centre for Image Guided Innovation and Therapeutic Intervention, Hospital for Sick Children, Toronto, Ontario
- 2The Institute of Biomedical Engineering, University of Toronto, Ontario
- 4Mechanical Engineering, and
- 7Neurosurgery, University of Toronto, Ontario
| |
Collapse
|