1
|
Zhao X, Wen Z. Super-resolution of diffusion-weighted images using space-customized learning model. Technol Health Care 2024; 32:423-435. [PMID: 38759065 PMCID: PMC11191469 DOI: 10.3233/thc-248037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/19/2024]
Abstract
BACKGROUND Diffusion-weighted imaging (DWI) is a noninvasive method used for investigating the microstructural properties of the brain. However, a tradeoff exists between resolution and scanning time in clinical practice. Super-resolution has been employed to enhance spatial resolution in natural images, but its application on high-dimensional and non-Euclidean DWI remains challenging. OBJECTIVE This study aimed to develop an end-to-end deep learning network for enhancing the spatial resolution of DWI through post-processing. METHODS We proposed a space-customized deep learning approach that leveraged convolutional neural networks (CNNs) for the grid structural domain (x-space) and graph CNNs (GCNNs) for the diffusion gradient domain (q-space). Moreover, we represented the output of CNN as a graph using correlations defined by a Gaussian kernel in q-space to bridge the gap between CNN and GCNN feature formats. RESULTS Our model was evaluated on the Human Connectome Project, demonstrating the effective improvement of DWI quality using our proposed method. Extended experiments also highlighted its advantages in downstream tasks. CONCLUSION The hybrid convolutional neural network exhibited distinct advantages in enhancing the spatial resolution of DWI scans for the feature learning of heterogeneous spatial data.
Collapse
Affiliation(s)
- Xitong Zhao
- Department of Mathematics, College of Sciences, Shanghai University, Shanghai, China
| | - Zhijie Wen
- Department of Mathematics, College of Sciences, Shanghai University, Shanghai, China
| |
Collapse
|
2
|
Aja-Fernández S, Martín-Martín C, Planchuelo-Gómez Á, Faiyaz A, Uddin MN, Schifitto G, Tiwari A, Shigwan SJ, Kumar Singh R, Zheng T, Cao Z, Wu D, Blumberg SB, Sen S, Goodwin-Allcock T, Slator PJ, Yigit Avci M, Li Z, Bilgic B, Tian Q, Wang X, Tang Z, Cabezas M, Rauland A, Merhof D, Manzano Maria R, Campos VP, Santini T, da Costa Vieira MA, HashemizadehKolowri S, DiBella E, Peng C, Shen Z, Chen Z, Ullah I, Mani M, Abdolmotalleby H, Eckstrom S, Baete SH, Filipiak P, Dong T, Fan Q, de Luis-García R, Tristán-Vega A, Pieciak T. Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies. Neuroimage Clin 2023; 39:103483. [PMID: 37572514 PMCID: PMC10440596 DOI: 10.1016/j.nicl.2023.103483] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2023] [Revised: 07/24/2023] [Accepted: 07/25/2023] [Indexed: 08/14/2023]
Abstract
The objective of this study is to evaluate the efficacy of deep learning (DL) techniques in improving the quality of diffusion MRI (dMRI) data in clinical applications. The study aims to determine whether the use of artificial intelligence (AI) methods in medical images may result in the loss of critical clinical information and/or the appearance of false information. To assess this, the focus was on the angular resolution of dMRI and a clinical trial was conducted on migraine, specifically between episodic and chronic migraine patients. The number of gradient directions had an impact on white matter analysis results, with statistically significant differences between groups being drastically reduced when using 21 gradient directions instead of the original 61. Fourteen teams from different institutions were tasked to use DL to enhance three diffusion metrics (FA, AD and MD) calculated from data acquired with 21 gradient directions and a b-value of 1000 s/mm2. The goal was to produce results that were comparable to those calculated from 61 gradient directions. The results were evaluated using both standard image quality metrics and Tract-Based Spatial Statistics (TBSS) to compare episodic and chronic migraine patients. The study results suggest that while most DL techniques improved the ability to detect statistical differences between groups, they also led to an increase in false positive. The results showed that there was a constant growth rate of false positives linearly proportional to the new true positives, which highlights the risk of generalization of AI-based tasks when assessing diverse clinical cohorts and training using data from a single group. The methods also showed divergent performance when replicating the original distribution of the data and some exhibited significant bias. In conclusion, extreme caution should be exercised when using AI methods for harmonization or synthesis in clinical studies when processing heterogeneous data in clinical studies, as important information may be altered, even when global metrics such as structural similarity or peak signal-to-noise ratio appear to suggest otherwise.
Collapse
Affiliation(s)
- Santiago Aja-Fernández
- Laboratorio de Procesado de Imagen (LPI), ETSI Telecomunicación, Universidad de Valladolid, Spain.
| | - Carmen Martín-Martín
- Laboratorio de Procesado de Imagen (LPI), ETSI Telecomunicación, Universidad de Valladolid, Spain
| | - Álvaro Planchuelo-Gómez
- Laboratorio de Procesado de Imagen (LPI), ETSI Telecomunicación, Universidad de Valladolid, Spain; Cardiff University Brain Research Imaging Centre (CUBRIC), School of Psychology, Cardiff University, Cardiff, UK
| | | | | | | | | | | | | | | | | | - Dan Wu
- Zhejiang University, China
| | | | | | | | | | | | - Zihan Li
- Athinoula A. Martinos Center for Biomedical Imaging, USA
| | - Berkin Bilgic
- Athinoula A. Martinos Center for Biomedical Imaging, USA
| | - Qiyuan Tian
- Athinoula A. Martinos Center for Biomedical Imaging, USA
| | | | | | | | | | | | | | | | | | | | | | | | | | | | - Zan Chen
- Zhejiang University of Technology, China
| | | | | | | | | | | | | | | | | | - Rodrigo de Luis-García
- Laboratorio de Procesado de Imagen (LPI), ETSI Telecomunicación, Universidad de Valladolid, Spain
| | - Antonio Tristán-Vega
- Laboratorio de Procesado de Imagen (LPI), ETSI Telecomunicación, Universidad de Valladolid, Spain
| | - Tomasz Pieciak
- Laboratorio de Procesado de Imagen (LPI), ETSI Telecomunicación, Universidad de Valladolid, Spain
| |
Collapse
|
3
|
Chen G, Hong Y, Huynh KM, Yap PT. Deep learning prediction of diffusion MRI data with microstructure-sensitive loss functions. Med Image Anal 2023; 85:102742. [PMID: 36682154 PMCID: PMC9974781 DOI: 10.1016/j.media.2023.102742] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2022] [Revised: 12/05/2022] [Accepted: 01/05/2023] [Indexed: 01/15/2023]
Abstract
Deep learning prediction of diffusion MRI (DMRI) data relies on the utilization of effective loss functions. Existing losses typically measure the signal-wise differences between the predicted and target DMRI data without considering the quality of derived diffusion scalars that are eventually utilized for quantification of tissue microstructure. Here, we propose two novel loss functions, called microstructural loss and spherical variance loss, to explicitly consider the quality of both the predicted DMRI data and derived diffusion scalars. We apply these loss functions to the prediction of multi-shell data and enhancement of angular resolution. Evaluation based on infant and adult DMRI data indicates that both microstructural loss and spherical variance loss improve the quality of derived diffusion scalars.
Collapse
Affiliation(s)
- Geng Chen
- Department of Radiology, University of North Carolina, Chapel Hill, NC, USA; Biomedical Research Imaging Center (BRIC), University of North Carolina, Chapel Hill, NC, USA
| | - Yoonmi Hong
- Department of Radiology, University of North Carolina, Chapel Hill, NC, USA; Biomedical Research Imaging Center (BRIC), University of North Carolina, Chapel Hill, NC, USA
| | - Khoi Minh Huynh
- Department of Radiology, University of North Carolina, Chapel Hill, NC, USA; Biomedical Research Imaging Center (BRIC), University of North Carolina, Chapel Hill, NC, USA
| | - Pew-Thian Yap
- Department of Radiology, University of North Carolina, Chapel Hill, NC, USA; Biomedical Research Imaging Center (BRIC), University of North Carolina, Chapel Hill, NC, USA.
| |
Collapse
|
4
|
Chen G, Jiang H, Liu J, Ma J, Cui H, Xia Y, Yap PT. Hybrid Graph Transformer for Tissue Microstructure Estimation with Undersampled Diffusion MRI Data. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2022; 13431:113-122. [PMID: 37126477 PMCID: PMC10141974 DOI: 10.1007/978-3-031-16431-6_11] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/02/2023]
Abstract
Advanced contemporary diffusion models for tissue microstructure often require diffusion MRI (DMRI) data with sufficiently dense sampling in the diffusion wavevector space for reliable model fitting, which might not always be feasible in practice. A potential remedy to this problem is by using deep learning techniques to predict high-quality diffusion microstructural indices from sparsely sampled data. However, existing methods are either agnostic to the data geometry in the diffusion wavevector space ( q -space) or limited to leveraging information from only local neighborhoods in the physical coordinate space ( x -space). Here, we propose a hybrid graph transformer (HGT) to explicitly consider the q -space geometric structure with a graph neural network (GNN) and make full use of spatial information with a novel residual dense transformer (RDT). The RDT consists of multiple densely connected transformer layers and a residual connection to facilitate model training. Extensive experiments on the data from the Human Connectome Project (HCP) demonstrate that our method significantly improves the quality of microstructural estimations over existing state-of-the-art methods.
Collapse
Affiliation(s)
- Geng Chen
- National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China
- Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Haotian Jiang
- Department of Software Engineering, Heilongjiang University, Harbin, China
| | - Jiannan Liu
- Department of Computer Science and Technology, Heilongjiang University, Harbin, China
| | - Jiquan Ma
- Department of Computer Science and Technology, Heilongjiang University, Harbin, China
| | - Hui Cui
- Department of Computer Science and Information Technology, La Trobe University, Melbourne, Australia
| | - Yong Xia
- National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an, China
| | - Pew-Thian Yap
- Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| |
Collapse
|
5
|
Luo S, Zhou J, Yang Z, Wei H, Fu Y. Diffusion MRI super-resolution reconstruction via sub-pixel convolution generative adversarial network. Magn Reson Imaging 2022; 88:101-107. [DOI: 10.1016/j.mri.2022.02.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2021] [Revised: 02/08/2022] [Accepted: 02/08/2022] [Indexed: 11/26/2022]
|
6
|
Ren M, Kim H, Dey N, Gerig G. Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2021; 12907:530-540. [PMID: 36383495 PMCID: PMC9662206 DOI: 10.1007/978-3-030-87234-2_50] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
Current deep learning approaches for diffusion MRI modeling circumvent the need for densely-sampled diffusion-weighted images (DWIs) by directly predicting microstructural indices from sparsely-sampled DWIs. However, they implicitly make unrealistic assumptions of static q-space sampling during training and reconstruction. Further, such approaches can restrict downstream usage of variably sampled DWIs for usages including the estimation of microstructural indices or tractography. We propose a generative adversarial translation framework for high-quality DWI synthesis with arbitrary q-space sampling given commonly acquired structural images (e.g., B0, T1, T2). Our translation network linearly modulates its internal representations conditioned on continuous q-space information, thus removing the need for fixed sampling schemes. Moreover, this approach enables downstream estimation of high-quality microstructural maps from arbitrarily subsampled DWIs, which may be particularly important in cases with sparsely sampled DWIs. Across several recent methodologies, the proposed approach yields improved DWI synthesis accuracy and fidelity with enhanced downstream utility as quantified by the accuracy of scalar microstructure indices estimated from the synthesized images. Code is available at https://github.com/mengweiren/q-space-conditioned-dwi-synthesis.
Collapse
Affiliation(s)
- Mengwei Ren
- Department of Computer Science and Engineering, New York University, New York, NY, USA
| | - Heejong Kim
- Department of Computer Science and Engineering, New York University, New York, NY, USA
| | - Neel Dey
- Department of Computer Science and Engineering, New York University, New York, NY, USA
| | - Guido Gerig
- Department of Computer Science and Engineering, New York University, New York, NY, USA
| |
Collapse
|
7
|
Chen G, Hong Y, Zhang Y, Kim J, Huynh KM, Ma J, Lin W, Shen D, Yap PT. Estimating Tissue Microstructure with Undersampled Diffusion Data via Graph Convolutional Neural Networks. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2020; 12267:280-290. [PMID: 34308440 PMCID: PMC8294782 DOI: 10.1007/978-3-030-59728-3_28] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/03/2022]
Abstract
Advanced diffusion models for tissue microstructure are widely employed to study brain disorders. However, these models usually require diffusion MRI (DMRI) data with densely sampled q-space, which is prohibitive in clinical settings. This problem can be resolved by using deep learning techniques, which learn the mapping between sparsely sampled q-space data and the high-quality diffusion microstructural indices estimated from densely sampled data. However, most existing methods simply view the input DMRI data as a vector without considering data structure in the q-space. In this paper, we propose to overcome this limitation by representing DMRI data using graphs and utilizing graph convolutional neural networks to estimate tissue microstructure. Our method makes full use of the q-space angular neighboring information to improve estimation accuracy. Experimental results based on data from the Baby Connectome Project demonstrate that our method outperforms state-of-the-art methods both qualitatively and quantitatively.
Collapse
Affiliation(s)
- Geng Chen
- Department of Radiology and BRIC, University of North Carolina, Chapel Hill, USA
| | - Yoonmi Hong
- Department of Radiology and BRIC, University of North Carolina, Chapel Hill, USA
| | - Yongqin Zhang
- School of Information Science and Technology, Northwest University, Xi'an, China
| | - Jaeil Kim
- School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea
| | - Khoi Minh Huynh
- Department of Radiology and BRIC, University of North Carolina, Chapel Hill, USA
| | - Jiquan Ma
- Department of Computer Science and Technology, Heilongjiang University, Harbin, China
| | - Weili Lin
- Department of Radiology and BRIC, University of North Carolina, Chapel Hill, USA
| | - Dinggang Shen
- Department of Radiology and BRIC, University of North Carolina, Chapel Hill, USA
| | - Pew-Thian Yap
- Department of Radiology and BRIC, University of North Carolina, Chapel Hill, USA
| |
Collapse
|