1
|
DeepFLAIR: A neural network approach to mitigate signal and contrast loss in temporal lobes at 7 Tesla FLAIR images. Magn Reson Imaging 2024; 110:57-68. [PMID: 38621552 DOI: 10.1016/j.mri.2024.04.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2024] [Revised: 04/04/2024] [Accepted: 04/10/2024] [Indexed: 04/17/2024]
Abstract
BACKGROUND AND PURPOSE Higher magnetic field strength introduces stronger magnetic field inhomogeneities in the brain, especially within temporal lobes, leading to image artifacts. Particularly, T2-weighted fluid-attenuated inversion recovery (FLAIR) images can be affected by these artifacts. Here, we aimed to improve the FLAIR image quality in temporal lobe regions through image processing of multiple contrast images via machine learning using a neural network. METHODS Thirteen drug-resistant MR-negative epilepsy patients (age 29.2 ± 9.4y, 5 females) were scanned on a 7 T MRI scanner. Magnetization-prepared (MP2RAGE) and saturation-prepared with 2 rapid gradient echoes, multi-echo gradient echo with four echo times, and the FLAIR sequence were acquired. A voxel-wise neural network was trained on extratemporal-lobe voxels from the acquired structural scans to generate a new FLAIR-like image (i.e., deepFLAIR) with reduced temporal lobe inhomogeneities. The deepFLAIR was evaluated in temporal lobes through signal-to-noise (SNR), contrast-to-noise (CNR) ratio, the sharpness of the gray-white matter boundary and joint-histogram analysis. Saliency mapping demonstrated the importance of each input image per voxel. RESULTS SNR and CNR in both gray and white matter were significantly increased (p < 0.05) in the deepFLAIR's temporal ROIs, compared to the FLAIR. The gray-white matter boundary sharpness was either preserved or improved in 10/13 right-sided temporal regions and was found significantly increased in the ROIs. Multiple image contrasts were influential for the deepFLAIR reconstruction with the MP2RAGE second inversion image being the most important. CONCLUSIONS The deepFLAIR network showed promise to restore the FLAIR signal and reduce contrast attenuation in temporal lobe areas. This may yield a valuable tool, especially when artifact-free FLAIR images are not available.
Collapse
|
2
|
One model to unite them all: Personalized federated learning of multi-contrast MRI synthesis. Med Image Anal 2024; 94:103121. [PMID: 38402791 DOI: 10.1016/j.media.2024.103121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Revised: 02/20/2024] [Accepted: 02/21/2024] [Indexed: 02/27/2024]
Abstract
Curation of large, diverse MRI datasets via multi-institutional collaborations can help improve learning of generalizable synthesis models that reliably translate source- onto target-contrast images. To facilitate collaborations, federated learning (FL) adopts decentralized model training while mitigating privacy concerns by avoiding sharing of imaging data. However, conventional FL methods can be impaired by the inherent heterogeneity in the data distribution, with domain shifts evident within and across imaging sites. Here we introduce the first personalized FL method for MRI Synthesis (pFLSynth) that improves reliability against data heterogeneity via model specialization to individual sites and synthesis tasks (i.e., source-target contrasts). To do this, pFLSynth leverages an adversarial model equipped with novel personalization blocks that control the statistics of generated feature maps across the spatial/channel dimensions, given latent variables specific to sites and tasks. To further promote communication efficiency and site specialization, partial network aggregation is employed over later generator stages while earlier generator stages and the discriminator are trained locally. As such, pFLSynth enables multi-task training of multi-site synthesis models with high generalization performance across sites and tasks. Comprehensive experiments demonstrate the superior performance and reliability of pFLSynth in MRI synthesis against prior federated methods.
Collapse
|
3
|
Unsupervised Medical Image Translation With Adversarial Diffusion Models. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:3524-3539. [PMID: 37379177 DOI: 10.1109/tmi.2023.3290149] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/30/2023]
Abstract
Imputation of missing images via source-to-target modality translation can improve diversity in medical imaging protocols. A pervasive approach for synthesizing target images involves one-shot mapping through generative adversarial networks (GAN). Yet, GAN models that implicitly characterize the image distribution can suffer from limited sample fidelity. Here, we propose a novel method based on adversarial diffusion modeling, SynDiff, for improved performance in medical image translation. To capture a direct correlate of the image distribution, SynDiff leverages a conditional diffusion process that progressively maps noise and source images onto the target image. For fast and accurate image sampling during inference, large diffusion steps are taken with adversarial projections in the reverse diffusion direction. To enable training on unpaired datasets, a cycle-consistent architecture is devised with coupled diffusive and non-diffusive modules that bilaterally translate between two modalities. Extensive assessments are reported on the utility of SynDiff against competing GAN and diffusion models in multi-contrast MRI and MRI-CT translation. Our demonstrations indicate that SynDiff offers quantitatively and qualitatively superior performance against competing baselines.
Collapse
|
4
|
DeepSWI: Using Deep Learning to Enhance Susceptibility Contrast on T2*-Weighted MRI. J Magn Reson Imaging 2023; 58:1200-1210. [PMID: 36733222 PMCID: PMC10443940 DOI: 10.1002/jmri.28622] [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: 10/14/2022] [Revised: 01/19/2023] [Accepted: 01/20/2023] [Indexed: 02/04/2023] Open
Abstract
BACKGROUND Although susceptibility-weighted imaging (SWI) is the gold standard for visualizing cerebral microbleeds (CMBs) in the brain, the required phase data are not always available clinically. Having a postprocessing tool for generating SWI contrast from T2*-weighted magnitude images is therefore advantageous. PURPOSE To create synthetic SWI images from clinical T2*-weighted magnitude images using deep learning and evaluate the resulting images in terms of similarity to conventional SWI images and ability to detect radiation-associated CMBs. STUDY TYPE Retrospective. POPULATION A total of 145 adults (87 males/58 females; 43.9 years old) with radiation-associated CMBs were used to train (16,093 patches/121 patients), validate (484 patches/4 patients), and test (2420 patches/20 patients) our networks. FIELD STRENGTH/SEQUENCE 3D T2*-weighted, gradient-echo acquired at 3 T. ASSESSMENT Structural similarity index (SSIM), peak signal-to-noise-ratio (PSNR), normalized mean-squared-error (nMSE), CMB counts, and line profiles were compared among magnitude, original SWI, and synthetic SWI images. Three blinded raters (J.E.V.M., M.A.M., B.B. with 8-, 6-, and 4-years of experience, respectively) independently rated and classified test-set images. STATISTICAL TESTS Kruskall-Wallis and Wilcoxon signed-rank tests were used to compare SSIM, PSNR, nMSE, and CMB counts among magnitude, original SWI, and predicted synthetic SWI images. Intraclass correlation assessed interrater variability. P values <0.005 were considered statistically significant. RESULTS SSIM values of the predicted vs. original SWI (0.972, 0.995, 0.9864) were statistically significantly higher than that of the magnitude vs. original SWI (0.970, 0.994, 0.9861) for whole brain, vascular structures, and brain tissue regions, respectively; 67% (19/28) CMBs detected on original SWI images were also detected on the predicted SWI, whereas only 10 (36%) were detected on magnitude images. Overall image quality was similar between the synthetic and original SWI images, with less artifacts on the former. CONCLUSIONS This study demonstrated that deep learning can increase the susceptibility contrast present in neurovasculature and CMBs on T2*-weighted magnitude images, without residual susceptibility-induced artifacts. This may be useful for more accurately estimating CMB burden from magnitude images alone. EVIDENCE LEVEL 3. TECHNICAL EFFICACY Stage 2.
Collapse
|
5
|
One Model to Synthesize Them All: Multi-Contrast Multi-Scale Transformer for Missing Data Imputation. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:2577-2591. [PMID: 37030684 PMCID: PMC10543020 DOI: 10.1109/tmi.2023.3261707] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Multi-contrast magnetic resonance imaging (MRI) is widely used in clinical practice as each contrast provides complementary information. However, the availability of each imaging contrast may vary amongst patients, which poses challenges to radiologists and automated image analysis algorithms. A general approach for tackling this problem is missing data imputation, which aims to synthesize the missing contrasts from existing ones. While several convolutional neural networks (CNN) based algorithms have been proposed, they suffer from the fundamental limitations of CNN models, such as the requirement for fixed numbers of input and output channels, the inability to capture long-range dependencies, and the lack of interpretability. In this work, we formulate missing data imputation as a sequence-to-sequence learning problem and propose a multi-contrast multi-scale Transformer (MMT), which can take any subset of input contrasts and synthesize those that are missing. MMT consists of a multi-scale Transformer encoder that builds hierarchical representations of inputs combined with a multi-scale Transformer decoder that generates the outputs in a coarse-to-fine fashion. The proposed multi-contrast Swin Transformer blocks can efficiently capture intra- and inter-contrast dependencies for accurate image synthesis. Moreover, MMT is inherently interpretable as it allows us to understand the importance of each input contrast in different regions by analyzing the in-built attention maps of Transformer blocks in the decoder. Extensive experiments on two large-scale multi-contrast MRI datasets demonstrate that MMT outperforms the state-of-the-art methods quantitatively and qualitatively.
Collapse
|
6
|
Semi-Supervised Learning of MRI Synthesis Without Fully-Sampled Ground Truths. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:3895-3906. [PMID: 35969576 DOI: 10.1109/tmi.2022.3199155] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Learning-based translation between MRI contrasts involves supervised deep models trained using high-quality source- and target-contrast images derived from fully-sampled acquisitions, which might be difficult to collect under limitations on scan costs or time. To facilitate curation of training sets, here we introduce the first semi-supervised model for MRI contrast translation (ssGAN) that can be trained directly using undersampled k-space data. To enable semi-supervised learning on undersampled data, ssGAN introduces novel multi-coil losses in image, k-space, and adversarial domains. The multi-coil losses are selectively enforced on acquired k-space samples unlike traditional losses in single-coil synthesis models. Comprehensive experiments on retrospectively undersampled multi-contrast brain MRI datasets are provided. Our results demonstrate that ssGAN yields on par performance to a supervised model, while outperforming single-coil models trained on coil-combined magnitude images. It also outperforms cascaded reconstruction-synthesis models where a supervised synthesis model is trained following self-supervised reconstruction of undersampled data. Thus, ssGAN holds great promise to improve the feasibility of learning-based multi-contrast MRI synthesis.
Collapse
|
7
|
ResViT: Residual Vision Transformers for Multimodal Medical Image Synthesis. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:2598-2614. [PMID: 35436184 DOI: 10.1109/tmi.2022.3167808] [Citation(s) in RCA: 51] [Impact Index Per Article: 25.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Generative adversarial models with convolutional neural network (CNN) backbones have recently been established as state-of-the-art in numerous medical image synthesis tasks. However, CNNs are designed to perform local processing with compact filters, and this inductive bias compromises learning of contextual features. Here, we propose a novel generative adversarial approach for medical image synthesis, ResViT, that leverages the contextual sensitivity of vision transformers along with the precision of convolution operators and realism of adversarial learning. ResViT's generator employs a central bottleneck comprising novel aggregated residual transformer (ART) blocks that synergistically combine residual convolutional and transformer modules. Residual connections in ART blocks promote diversity in captured representations, while a channel compression module distills task-relevant information. A weight sharing strategy is introduced among ART blocks to mitigate computational burden. A unified implementation is introduced to avoid the need to rebuild separate synthesis models for varying source-target modality configurations. Comprehensive demonstrations are performed for synthesizing missing sequences in multi-contrast MRI, and CT images from MRI. Our results indicate superiority of ResViT against competing CNN- and transformer-based methods in terms of qualitative observations and quantitative metrics.
Collapse
|
8
|
Evaluating the use of synthetic T1-w images in new T2 lesion detection in multiple sclerosis. Front Neurosci 2022; 16:954662. [PMID: 36248650 PMCID: PMC9558286 DOI: 10.3389/fnins.2022.954662] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Accepted: 08/30/2022] [Indexed: 11/23/2022] Open
Abstract
The assessment of disease activity using serial brain MRI scans is one of the most valuable strategies for monitoring treatment response in patients with multiple sclerosis (MS) receiving disease-modifying treatments. Recently, several deep learning approaches have been proposed to improve this analysis, obtaining a good trade-off between sensitivity and specificity, especially when using T1-w and T2-FLAIR images as inputs. However, the need to acquire two different types of images is time-consuming, costly and not always available in clinical practice. In this paper, we investigate an approach to generate synthetic T1-w images from T2-FLAIR images and subsequently analyse the impact of using original and synthetic T1-w images on the performance of a state-of-the-art approach for longitudinal MS lesion detection. We evaluate our approach on a dataset containing 136 images from MS patients, and 73 images with lesion activity (the appearance of new T2 lesions in follow-up scans). To evaluate the synthesis of the images, we analyse the structural similarity index metric and the median absolute error and obtain consistent results. To study the impact of synthetic T1-w images, we evaluate the performance of the new lesion detection approach when using (1) both T2-FLAIR and T1-w original images, (2) only T2-FLAIR images, and (3) both T2-FLAIR and synthetic T1-w images. Sensitivities of 0.75, 0.63, and 0.81, respectively, were obtained at the same false-positive rate (0.14) for all experiments. In addition, we also present the results obtained when using the data from the international MSSEG-2 challenge, showing also an improvement when including synthetic T1-w images. In conclusion, we show that the use of synthetic images can support the lack of data or even be used instead of the original image to homogenize the contrast of the different acquisitions in new T2 lesions detection algorithms.
Collapse
|
9
|
Convolutional Neural Network Based Frameworks for Fast Automatic Segmentation of Thalamic Nuclei from Native and Synthesized Contrast Structural MRI. Neuroinformatics 2022; 20:651-664. [PMID: 34626333 PMCID: PMC8993941 DOI: 10.1007/s12021-021-09544-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/19/2021] [Indexed: 12/31/2022]
Abstract
Thalamic nuclei have been implicated in several neurological diseases. Thalamic nuclei parcellation from structural MRI is challenging due to poor intra-thalamic nuclear contrast while methods based on diffusion and functional MRI are affected by limited spatial resolution and image distortion. Existing multi-atlas based techniques are often computationally intensive and time-consuming. In this work, we propose a 3D convolutional neural network (CNN) based framework for thalamic nuclei parcellation using T1-weighted Magnetization Prepared Rapid Gradient Echo (MPRAGE) images. Transformation of images to an efficient representation has been proposed to improve the performance of subsequent classification tasks especially when working with limited labeled data. We investigate this by transforming the MPRAGE images to White-Matter-nulled MPRAGE (WMn-MPRAGE) contrast, previously shown to exhibit good intra-thalamic nuclear contrast, prior to the segmentation step. We trained two 3D segmentation frameworks using MPRAGE images (n = 35 subjects): (a) a native contrast segmentation (NCS) on MPRAGE images and (b) a synthesized contrast segmentation (SCS) where synthesized WMn-MPRAGE representation generated by a contrast synthesis CNN were used. Thalamic nuclei labels were generated using THOMAS, a multi-atlas segmentation technique proposed for WMn-MPRAGE images. The segmentation accuracy and clinical utility were evaluated on a healthy cohort (n = 12) and a cohort (n = 45) comprising of healthy subjects and patients with alcohol use disorder (AUD), respectively. Both the segmentation CNNs yielded comparable performances on most thalamic nuclei with Dice scores greater than 0.84 for larger nuclei and at least 0.7 for smaller nuclei. However, for some nuclei, the SCS CNN yielded significant improvements in Dice scores (medial geniculate nucleus, P = 0.003, centromedian nucleus, P = 0.01) and percent volume difference (ventral anterior, P = 0.001, ventral posterior lateral, P = 0.01) over NCS. In the AUD cohort, the SCS CNN demonstrated a significant atrophy in ventral lateral posterior nucleus in AUD patients compared to healthy age-matched controls (P = 0.01), agreeing with previous studies on thalamic atrophy in alcoholism, whereas the NCS CNN showed spurious atrophy of the ventral posterior lateral nucleus. CNN-based segmentation of thalamic nuclei provides a fast and automated technique for thalamic nuclei prediction in MPRAGE images. The transformation of images to an efficient representation, such as WMn-MPRAGE, can provide further improvements in segmentation performance.
Collapse
|
10
|
The stability of oncologic MRI radiomic features and the potential role of deep learning: a review. Phys Med Biol 2022; 67. [DOI: 10.1088/1361-6560/ac60b9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Accepted: 03/24/2022] [Indexed: 11/11/2022]
Abstract
Abstract
The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.
Collapse
|
11
|
Higher-resolution quantification of white matter hypointensities by large-scale transfer learning from 2D images on the JPSC-AD cohort. Hum Brain Mapp 2022; 43:3998-4012. [PMID: 35524684 PMCID: PMC9374893 DOI: 10.1002/hbm.25899] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Revised: 03/24/2022] [Accepted: 04/20/2022] [Indexed: 12/14/2022] Open
Abstract
White matter lesions (WML) commonly occur in older brains and are quantifiable on MRI, often used as a biomarker in Aging research. Although algorithms are regularly proposed that identify these lesions from T2‐fluid‐attenuated inversion recovery (FLAIR) sequences, none so far can estimate lesions directly from T1‐weighted images with acceptable accuracy. Since 3D T1 is a polyvalent and higher‐resolution sequence, it could be beneficial to obtain the distribution of WML directly from it. However a serious difficulty, both for algorithms and human, can be found in the ambiguities of brain signal intensity in T1 images. This manuscript shows that a cross‐domain ConvNet (Convolutional Neural Network) approach can help solve this problem. Still, this is non‐trivial, as it would appear to require a large and varied dataset (for robustness) labelled at the same high resolution (for spatial accuracy). Instead, our model was taught from two‐dimensional FLAIR images with a loss function designed to handle the super‐resolution need. And crucially, we leveraged a very large training set for this task, the recently assembled, multi‐sites Japan Prospective Studies Collaboration for Aging and Dementia (JPSC‐AD) cohort. We describe the two‐step procedure that we followed to handle such a large number of imperfectly labeled samples. A large‐scale accuracy evaluation conducted against FreeSurfer 7, and a further visual expert rating revealed that WML segmentation from our ConvNet was consistently better. Finally, we made a directly usable software program based on that trained ConvNet model, available at https://github.com/bthyreau/deep-T1-WMH.
Collapse
|
12
|
On the proper use of structural similarity for the robust evaluation of medical image synthesis models. Med Phys 2022; 49:2462-2474. [PMID: 35106778 DOI: 10.1002/mp.15514] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2021] [Revised: 01/18/2022] [Accepted: 01/19/2022] [Indexed: 11/07/2022] Open
Abstract
PURPOSE To propose good practices for using the structural similarity metric (SSIM) and reporting its value. SSIM is one of the most popular image quality metrics in use in the medical image synthesis community because of its alleged superiority over voxel-by-voxel measurements like the average error or the peak signal noise ratio (PSNR). It has seen massive adoption since its introduction, but its limitations are often overlooked. Notably, SSIM is designed to work on a strictly positive intensity scale, which is generally not the case in medical imaging. Common intensity scales such as the Houndsfield units (HU) contain negative numbers, and they can also be introduced by image normalization techniques such as the z-normalization. METHODS We created a series of experiments to quantify the impact of negative values in the SSIM computation. Specifically, we trained a 3D U-Net to synthesize T2 weighted MRI from T1 weighted MRI using the BRATS 2018 dataset. SSIM was computed on the synthetic images with a shifted dynamic range. Next, to evaluate the suitability of SSIM as a loss function on images with negative values, it was used as a loss function to synthesize z-normalized images. Finally, the difference between 2D SSIM and 3D SSIM was investigated using multiple 2D U-Nets trained on different planes of the images. RESULTS The impact of the misuse of the SSIM was quantified; it was established that it introduces a large downward bias in the computed SSIM. It also introduces a small random error that can change the relative ranking of models. The exact values for this bias and error depend on the quality and the intensity histogram of the synthetic images. Although small, the reported error is significant considering the small SSIM difference between state-of-the-art models. It was shown therefore that SSIM cannot be used as a loss function when images contain negative values due to major errors in the gradient calculation, resulting in under-performing models. 2D SSIM was also found to be overestimated in 2D image synthesis models when computed along the plane of synthesis, due to the discontinuities between slices that is typical of 2D synthesis methods. CONCLUSION Various types of misuse of the SSIM were identified and their impact was quantified. Based on the findings, this paper proposes good practices when using SSIM, such as reporting the average over the volume of the image containing tissue and appropriately defining the dynamic range. This article is protected by copyright. All rights reserved.
Collapse
|
13
|
Deep learning-based convolutional neural network for intramodality brain MRI synthesis. J Appl Clin Med Phys 2022; 23:e13530. [PMID: 35044073 PMCID: PMC8992958 DOI: 10.1002/acm2.13530] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2021] [Revised: 12/22/2021] [Accepted: 12/25/2021] [Indexed: 12/16/2022] Open
Abstract
PURPOSE The existence of multicontrast magnetic resonance (MR) images increases the level of clinical information available for the diagnosis and treatment of brain cancer patients. However, acquiring the complete set of multicontrast MR images is not always practically feasible. In this study, we developed a state-of-the-art deep learning convolutional neural network (CNN) for image-to-image translation across three standards MRI contrasts for the brain. METHODS BRATS'2018 MRI dataset of 477 patients clinically diagnosed with glioma brain cancer was used in this study, with each patient having T1-weighted (T1), T2-weighted (T2), and FLAIR contrasts. It was randomly split into 64%, 16%, and 20% as training, validation, and test set, respectively. We developed a U-Net model to learn the nonlinear mapping of a source image contrast to a target image contrast across three MRI contrasts. The model was trained and validated with 2D paired MR images using a mean-squared error (MSE) cost function, Adam optimizer with 0.001 learning rate, and 120 epochs with a batch size of 32. The generated synthetic-MR images were evaluated against the ground-truth images by computing the MSE, mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM). RESULTS The generated synthetic-MR images with our model were nearly indistinguishable from the real images on the testing dataset for all translations, except synthetic FLAIR images had slightly lower quality and exhibited loss of details. The range of average PSNR, MSE, MAE, and SSIM values over the six translations were 29.44-33.25 dB, 0.0005-0.0012, 0.0086-0.0149, and 0.932-0.946, respectively. Our results were as good as the best-reported results by other deep learning models on BRATS datasets. CONCLUSIONS Our U-Net model exhibited that it can accurately perform image-to-image translation across brain MRI contrasts. It could hold great promise for clinical use for improved clinical decision-making and better diagnosis of brain cancer patients due to the availability of multicontrast MRIs. This approach may be clinically relevant and setting a significant step to efficiently fill a gap of absent MR sequences without additional scanning.
Collapse
|
14
|
Deep learning based MRI contrast synthesis using full volume prediction using full volume prediction. Biomed Phys Eng Express 2021; 8. [PMID: 34814130 DOI: 10.1088/2057-1976/ac3c64] [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: 09/13/2021] [Accepted: 11/23/2021] [Indexed: 11/12/2022]
Abstract
In Magnetic Resonance Imaging (MRI), depending on the image acquisition settings, a large number of image types or contrasts can be generated showing complementary information of the same imaged subject. This multi-spectral information is highly beneficial since can improve MRI analysis tasks such as segmentation and registration, thanks to pattern ambiguity reduction. However, the acquisition of several contrasts is not always possible due to time limitations and patient comfort constraints. Contrast synthesis has emerged recently as an approximate solution to generate other image types different from those acquired originally. Most of the previously proposed methods for contrast synthesis are slice-based which result in intensity inconsistencies between neighbor slices when applied in 3D. We propose the use of a 3D convolutional neural network (CNN) capable of generating T2 and FLAIR images from a single anatomical T1 source volume. The proposed network is a 3D variant of the UNet that processes the whole volume at once breaking with the inconsistency in the resulting output volumes related to 2D slice or patch-based methods. Since working with a full volume at once has a huge memory demand we have introduced a spatial-to-depth and a reconstruction layer that allows working with the full volume but maintain the required network complexity to solve the problem. Our approach enhances the coherence in the synthesized volume while improving the accuracy thanks to the integrated three-dimensional context-awareness. Finally, the proposed method has been validated with a segmentation method, thus demonstrating its usefulness in a direct and relevant application.
Collapse
|
15
|
Opportunities for Understanding MS Mechanisms and Progression With MRI Using Large-Scale Data Sharing and Artificial Intelligence. Neurology 2021; 97:989-999. [PMID: 34607924 PMCID: PMC8610621 DOI: 10.1212/wnl.0000000000012884] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2020] [Accepted: 09/09/2021] [Indexed: 11/15/2022] Open
Abstract
Patients with multiple sclerosis (MS) have heterogeneous clinical presentations, symptoms, and progression over time, making MS difficult to assess and comprehend in vivo. The combination of large-scale data sharing and artificial intelligence creates new opportunities for monitoring and understanding MS using MRI. First, development of validated MS-specific image analysis methods can be boosted by verified reference, test, and benchmark imaging data. Using detailed expert annotations, artificial intelligence algorithms can be trained on such MS-specific data. Second, understanding disease processes could be greatly advanced through shared data of large MS cohorts with clinical, demographic, and treatment information. Relevant patterns in such data that may be imperceptible to a human observer could be detected through artificial intelligence techniques. This applies from image analysis (lesions, atrophy, or functional network changes) to large multidomain datasets (imaging, cognition, clinical disability, genetics). After reviewing data sharing and artificial intelligence, we highlight 3 areas that offer strong opportunities for making advances in the next few years: crowdsourcing, personal data protection, and organized analysis challenges. Difficulties as well as specific recommendations to overcome them are discussed, in order to best leverage data sharing and artificial intelligence to improve image analysis, imaging, and the understanding of MS.
Collapse
|
16
|
Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review). Exp Ther Med 2021; 22:1149. [PMID: 34504594 PMCID: PMC8393268 DOI: 10.3892/etm.2021.10583] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2021] [Accepted: 07/29/2021] [Indexed: 12/18/2022] Open
Abstract
Computer-aided diagnosis systems aim to assist clinicians in the early identification of abnormal signs in order to optimize the interpretation of medical images and increase diagnostic precision. Multiple sclerosis (MS) and clinically isolated syndrome (CIS) are chronic inflammatory, demyelinating diseases affecting the central nervous system. Recent advances in deep learning (DL) techniques have led to novel computational paradigms in MS and CIS imaging designed for automatic segmentation and detection of areas of interest and automatic classification of anatomic structures, as well as optimization of neuroimaging protocols. To this end, there are several publications presenting artificial intelligence-based predictive models aiming to increase diagnostic accuracy and to facilitate optimal clinical management in patients diagnosed with MS and/or CIS. The current study presents a thorough review covering DL techniques that have been applied in MS and CIS during recent years, shedding light on their current advances and limitations.
Collapse
|
17
|
Generating Longitudinal Atrophy Evaluation Datasets on Brain Magnetic Resonance Images Using Convolutional Neural Networks and Segmentation Priors. Neuroinformatics 2021; 19:477-492. [PMID: 33389607 DOI: 10.1007/s12021-020-09499-z] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/06/2020] [Indexed: 02/03/2023]
Abstract
Brain atrophy quantification plays a fundamental role in neuroinformatics since it permits studying brain development and neurological disorders. However, the lack of a ground truth prevents testing the accuracy of longitudinal atrophy quantification methods. We propose a deep learning framework to generate longitudinal datasets by deforming T1-w brain magnetic resonance imaging scans as requested through segmentation maps. Our proposal incorporates a cascaded multi-path U-Net optimised with a multi-objective loss which allows its paths to generate different brain regions accurately. We provided our model with baseline scans and real follow-up segmentation maps from two longitudinal datasets, ADNI and OASIS, and observed that our framework could produce synthetic follow-up scans that matched the real ones (Total scans= 584; Median absolute error: 0.03 ± 0.02; Structural similarity index: 0.98 ± 0.02; Dice similarity coefficient: 0.95 ± 0.02; Percentage of brain volume change: 0.24 ± 0.16; Jacobian integration: 1.13 ± 0.05). Compared to two relevant works generating brain lesions using U-Nets and conditional generative adversarial networks (CGAN), our proposal outperformed them significantly in most cases (p < 0.01), except in the delineation of brain edges where the CGAN took the lead (Jacobian integration: Ours - 1.13 ± 0.05 vs CGAN - 1.00 ± 0.02; p < 0.01). We examined whether changes induced with our framework were detected by FAST, SPM, SIENA, SIENAX, and the Jacobian integration method. We observed that induced and detected changes were highly correlated (Adj. R2 > 0.86). Our preliminary results on harmonised datasets showed the potential of our framework to be applied to various data collections without further adjustment.
Collapse
|
18
|
A review on medical imaging synthesis using deep learning and its clinical applications. J Appl Clin Med Phys 2021; 22:11-36. [PMID: 33305538 PMCID: PMC7856512 DOI: 10.1002/acm2.13121] [Citation(s) in RCA: 94] [Impact Index Per Article: 31.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2020] [Revised: 11/12/2020] [Accepted: 11/21/2020] [Indexed: 02/06/2023] Open
Abstract
This paper reviewed the deep learning-based studies for medical imaging synthesis and its clinical application. Specifically, we summarized the recent developments of deep learning-based methods in inter- and intra-modality image synthesis by listing and highlighting the proposed methods, study designs, and reported performances with related clinical applications on representative studies. The challenges among the reviewed studies were then summarized with discussion.
Collapse
|
19
|
Deep learning for brain disorders: from data processing to disease treatment. Brief Bioinform 2020; 22:1560-1576. [PMID: 33316030 DOI: 10.1093/bib/bbaa310] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2020] [Revised: 10/09/2020] [Accepted: 10/13/2020] [Indexed: 12/19/2022] Open
Abstract
In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.
Collapse
|
20
|
Predicting PET-derived myelin content from multisequence MRI for individual longitudinal analysis in multiple sclerosis. Neuroimage 2020; 223:117308. [PMID: 32889117 DOI: 10.1016/j.neuroimage.2020.117308] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2020] [Revised: 07/20/2020] [Accepted: 08/21/2020] [Indexed: 12/31/2022] Open
Abstract
Multiple sclerosis (MS) is a demyelinating and inflammatory disease of the central nervous system (CNS). The demyelination process can be repaired by the generation of a new sheath of myelin around the axon, a process termed remyelination. In MS patients, the demyelination-remyelination cycles are highly dynamic. Over the years, magnetic resonance imaging (MRI) has been increasingly used in the diagnosis of MS and it is currently the most useful paraclinical tool to assess this diagnosis. However, conventional MRI pulse sequences are not specific for pathological mechanisms such as demyelination and remyelination. Recently, positron emission tomography (PET) with radiotracer [11C]PIB has become a promising tool to measure in-vivo myelin content changes which is essential to push forward our understanding of mechanisms involved in the pathology of MS, and to monitor individual patients in the context of clinical trials focused on repair therapies. However, PET imaging is invasive due to the injection of a radioactive tracer. Moreover, it is an expensive imaging test and not offered in the majority of medical centers in the world. In this work, by using multisequence MRI, we thus propose a method to predict the parametric map of [11C]PIB PET, from which we derived the myelin content changes in a longitudinal analysis of patients with MS. The method is based on the proposed conditional flexible self-attention GAN (CF-SAGAN) which is specifically adjusted for high-dimensional medical images and able to capture the relationships between the spatially separated lesional regions during the image synthesis process. Jointly applying the sketch-refinement process and the proposed attention regularization that focuses on the MS lesions, our approach is shown to outperform the state-of-the-art methods qualitatively and quantitatively. Specifically, our method demonstrated a superior performance for the prediction of myelin content at voxel-wise level. More important, our method for the prediction of myelin content changes in patients with MS shows similar clinical correlations to the PET-derived gold standard indicating the potential for clinical management of patients with MS.
Collapse
|