1
|
Zhao Y, Raghuram A, Wang F, Kim SH, Hielscher A, Robinson JT, Veeraraghavan A. Unrolled-DOT: an interpretable deep network for diffuse optical tomography. JOURNAL OF BIOMEDICAL OPTICS 2023; 28:036002. [PMID: 36908760 PMCID: PMC9995139 DOI: 10.1117/1.jbo.28.3.036002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/19/2022] [Accepted: 02/09/2023] [Indexed: 06/18/2023]
Abstract
SIGNIFICANCE Imaging through scattering media is critical in many biomedical imaging applications, such as breast tumor detection and functional neuroimaging. Time-of-flight diffuse optical tomography (ToF-DOT) is one of the most promising methods for high-resolution imaging through scattering media. ToF-DOT and many traditional DOT methods require an image reconstruction algorithm. Unfortunately, this algorithm often requires long computational runtimes and may produce lower quality reconstructions in the presence of model mismatch or improper hyperparameter tuning. AIM We used a data-driven unrolled network as our ToF-DOT inverse solver. The unrolled network is faster than traditional inverse solvers and achieves higher reconstruction quality by accounting for model mismatch. APPROACH Our model "Unrolled-DOT" uses the learned iterative shrinkage thresholding algorithm. In addition, we incorporate a refinement U-Net and Visual Geometry Group (VGG) perceptual loss to further increase the reconstruction quality. We trained and tested our model on simulated and real-world data and benchmarked against physics-based and learning-based inverse solvers. RESULTS In experiments on real-world data, Unrolled-DOT outperformed learning-based algorithms and achieved over 10× reduction in runtime and mean-squared error, compared to traditional physics-based solvers. CONCLUSION We demonstrated a learning-based ToF-DOT inverse solver that achieves state-of-the-art performance in speed and reconstruction quality, which can aid in future applications for noninvasive biomedical imaging.
Collapse
Affiliation(s)
- Yongyi Zhao
- Rice University, Department of Electrical and Computer Engineering, Houston, Texas, United States
| | - Ankit Raghuram
- Rice University, Department of Electrical and Computer Engineering, Houston, Texas, United States
| | - Fay Wang
- Columbia University, Department of Biomedical Engineering, New York, New York, United States
| | - Stephen Hyunkeol Kim
- Columbia University Irvine Medical Center, Department of Radiology, New York, New York, United States
- New York University - Tandon School of Engineering, Department of Biomedical Engineering, New York, New York, United States
| | - Andreas Hielscher
- New York University - Tandon School of Engineering, Department of Biomedical Engineering, New York, New York, United States
| | - Jacob T. Robinson
- Rice University, Department of Electrical and Computer Engineering, Houston, Texas, United States
| | - Ashok Veeraraghavan
- Rice University, Department of Electrical and Computer Engineering, Houston, Texas, United States
| |
Collapse
|
2
|
Feng J, Zhang W, Li Z, Jia K, Jiang S, Dehghani H, Pogue BW, Paulsen KD. Deep-learning based image reconstruction for MRI-guided near-infrared spectral tomography. OPTICA 2022; 9:264-267. [PMID: 35340570 PMCID: PMC8952193 DOI: 10.1364/optica.446576] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Accepted: 01/12/2022] [Indexed: 05/02/2023]
Abstract
Non-invasive near-infrared spectral tomography (NIRST) can incorporate the structural information provided by simultaneous magnetic resonance imaging (MRI), and this has significantly improved the images obtained of tissue function. However, the process of MRI guidance in NIRST has been time consuming because of the needs for tissue-type segmentation and forward diffuse modeling of light propagation. To overcome these problems, a reconstruction algorithm for MRI-guided NIRST based on deep learning is proposed and validated by simulation and real patient imaging data for breast cancer characterization. In this approach, diffused optical signals and MRI images were both used as the input to the neural network, and simultaneously recovered the concentrations of oxy-hemoglobin, deoxy-hemoglobin, and water via end-to-end training by using 20,000 sets of computer-generated simulation phantoms. The simulation phantom studies showed that the quality of the reconstructed images was improved, compared to that obtained by other existing reconstruction methods. Reconstructed patient images show that the well-trained neural network with only simulation data sets can be directly used for differentiating malignant from benign breast tumors.
Collapse
Affiliation(s)
- Jinchao Feng
- Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
- Beijing Laboratory of Advanced Information Networks, Beijing 100124, China
- Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire 03755, USA
| | - Wanlong Zhang
- Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
- Beijing Laboratory of Advanced Information Networks, Beijing 100124, China
| | - Zhe Li
- Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
- Beijing Laboratory of Advanced Information Networks, Beijing 100124, China
| | - Kebin Jia
- Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
- Beijing Laboratory of Advanced Information Networks, Beijing 100124, China
| | - Shudong Jiang
- Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire 03755, USA
| | - Hamid Dehghani
- School of Computer Science, University of Birmingham, Birmingham, B15 2TT, UK
| | - Brian W. Pogue
- Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire 03755, USA
| | - Keith D. Paulsen
- Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire 03755, USA
| |
Collapse
|
3
|
Krej M, Osuch T, Anuszkiewicz A, Stopinski S, Anders K, Matuk K, Weigl A, Tarasow E, Piramidowicz R, Dziuda L. Deep learning-based method for the continuous detection of heart rate in signals from a multi-fiber Bragg grating sensor compatible with magnetic resonance imaging. BIOMEDICAL OPTICS EXPRESS 2021; 12:7790-7806. [PMID: 35003867 PMCID: PMC8713690 DOI: 10.1364/boe.441932] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/20/2021] [Revised: 10/21/2021] [Accepted: 10/22/2021] [Indexed: 05/10/2023]
Abstract
A method for the continuous detection of heart rate (HR) in signals acquired from patients using a sensor mat comprising a nine-element array of fiber Bragg gratings during routine magnetic resonance imaging (MRI) procedures is proposed. The method is based on a deep learning neural network model, which learned from signals acquired from 153 MRI patients. In addition, signals from 343 MRI patients were used for result verification. The proposed method provides automatic continuous extraction of HR with the root mean square error of 2.67 bpm, and the limits of agreement were -4.98-5.45 bpm relative to the reference HR.
Collapse
Affiliation(s)
- Mariusz Krej
- Military Institute of Aviation Medicine, Department of Psychophysiological Measurements and Human Factor Research, Krasinskiego 54/56, 01-755 Warsaw, Poland
| | - Tomasz Osuch
- Warsaw University of Technology, Faculty of Electronics and Information Technology, Institute of Electronic Systems, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland
- National Institute of Telecommunications, Szachowa 1, 04-894 Warsaw, Poland
| | - Alicja Anuszkiewicz
- Warsaw University of Technology, Faculty of Electronics and Information Technology, Institute of Electronic Systems, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland
- Lukasiewicz Research Network - Institute of Microelectronics and Photonics, Photonic Materials Group, al. Lotnikow 32/46, 02-668 Warsaw, Poland
| | - Stanisław Stopinski
- Warsaw University of Technology, Faculty of Electronics and Information Technology, Institute of Microelectronics and Optoelectronics, Koszykowa 75, 00-662 Warsaw, Poland
| | - Krzysztof Anders
- Warsaw University of Technology, Faculty of Electronics and Information Technology, Institute of Microelectronics and Optoelectronics, Koszykowa 75, 00-662 Warsaw, Poland
| | - Krzysztof Matuk
- TMS Diagnostyka Sp. z o.o., Wiertnicza 84, 02-952 Warsaw, Poland
| | - Andrzej Weigl
- TMS Diagnostyka Sp. z o.o., Wiertnicza 84, 02-952 Warsaw, Poland
| | - Eugeniusz Tarasow
- TMS Diagnostyka Sp. z o.o., Wiertnicza 84, 02-952 Warsaw, Poland
- Medical University of Bialystok, Faculty of Medicine, Department of Radiology, Kilinskiego 1, 15-089 Bialystok, Poland
| | - Ryszard Piramidowicz
- Warsaw University of Technology, Faculty of Electronics and Information Technology, Institute of Microelectronics and Optoelectronics, Koszykowa 75, 00-662 Warsaw, Poland
| | - Lukasz Dziuda
- Military Institute of Aviation Medicine, Department of Psychophysiological Measurements and Human Factor Research, Krasinskiego 54/56, 01-755 Warsaw, Poland
| |
Collapse
|