Developing and deploying deep learning models in brain magnetic resonance imaging: A review

Aggarwal, Kunal; Jimeno, Marina Manso; Ravi, Keerthi Sravan; González, Gilberto; Geethanath, Sairam

doi:10.1002/nbm.5014

Cited by 6 publications

(5 citation statements)

References 152 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluations with five patients showed the ability of the BNN to estimate physiological parameters better than the NLLS. Nevertheless, larger studies are required to carry out a full assessment of the benefits and limitations of the proposed approach in clinical practice (Aggarwal et al 2023). One limitation of the BNN is the use of a fixed temporal resolution of 6 seconds for simulating the training C p (t) and C(t).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Unified Bayesian network for uncertainty quantification of physiological parameters in dynamic contrast enhanced (DCE) MRI of the liver

Dejene,

Brenner,

Makowski

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Physiological parameter estimation is affected by intrinsic ambiguity in the data such as noise and model inaccuracies. The aim of this work is to provide a deep learning framework for accurate parameter and uncertainty estimates for DCE-MRI in the liver. Approach. Concentration time curves are simulated to train a Bayesian neural network (BNN). Training of the BNN involves minimization of a loss function that jointly minimizes the aleatoric and epistemic uncertainties. Uncertainty estimation is evaluated for different noise levels and for different out of distribution (OD) cases, i.e., where the data during inference differs strongly to the data during training. The accuracy of parameter estimates are compared to a non-linear least squares (NLLS) fitting in numerical simulations and in-vivo data of a patient suffering from hepatic tumor lesions. Main results. BNN achieved lower root-mean-squared errors (RMSE) than the NLLS for the simulated data. RMSE of BNN was on overage of all noise levels lower by 33% ± 1.9% for ktrans, 22% ± 6% for ve and 89% ± 5% for vp than the NLLS. The aleatoric uncertainties of the parameters increased with increasing noise level, whereas the epistemic uncertainty increased when a BNN was evaluated with OD data. For the in-vivo data, more robust parameter estimates were obtained by the BNN than the NLLS fit. In addition, the differences between estimated parameters for healthy and tumor regions-of-interest were significant (p< 0.0001). Significance. The proposed framework allowed for accurate parameter estimates for quantitative DCE-MRI. In addition, the BNN provided uncertainty estimates which highlighted cases of high noise and in which the training data did not match the data during inference. This is important for clinical application because it would indicate cases in which the trained model is inadequate and additional training with an adapted training data set is required.

show abstract

Section: Discussionmentioning

confidence: 99%

“…A BNN was trained with CTCs generated without the testing data AIF. The patient data with this OD-AIF for validating the BNN was a unique scan with the same acquisition parameters as the training data as recommended in good machine learning practices (Aggarwal et al 2023).…”

Section: Uncertainty Evaluation Of Od Datamentioning

confidence: 99%

Unified Bayesian network for uncertainty quantification of physiological parameters in dynamic contrast enhanced (DCE) MRI of the liver

Dejene,

Brenner,

Makowski

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…There are no formal definitions for interpretability and explainability in the field of Artificial Intelligence and in the sub-field of DL (Doshi-Velez and Kim, 2017 ; Lipton, 2018 ; Miller, 2019 ; Aggarwal et al, 2023 ). However, current explainable AI practices can be cast as a type of model interpretability (Rahman, 2022 ).…”

Section: Methodsmentioning

confidence: 99%

Accelerated MRI using intelligent protocolling and subject-specific denoising applied to Alzheimer's disease imaging

Ravi

Nandakumar²,

Thomas³

et al. 2023

Front. Neuroimaging

View full text Add to dashboard Cite

Magnetic Resonance Imaging (MR Imaging) is routinely employed in diagnosing Alzheimer's Disease (AD), which accounts for up to 60–80% of dementia cases. However, it is time-consuming, and protocol optimization to accelerate MR Imaging requires local expertise since each pulse sequence involves multiple configurable parameters that need optimization for contrast, acquisition time, and signal-to-noise ratio (SNR). The lack of this expertise contributes to the highly inefficient utilization of MRI services diminishing their clinical value. In this work, we extend our previous effort and demonstrate accelerated MRI via intelligent protocolling of the modified brain screen protocol, referred to as the Gold Standard (GS) protocol. We leverage deep learning-based contrast-specific image-denoising to improve the image quality of data acquired using the accelerated protocol. Since the SNR of MR acquisitions depends on the volume of the object being imaged, we demonstrate subject-specific (SS) image-denoising. The accelerated protocol resulted in a 1.94 × gain in imaging throughput. This translated to a 72.51% increase in MR Value—defined in this work as the ratio of the sum of median object-masked local SNR values across all contrasts to the protocol's acquisition duration. We also computed PSNR, local SNR, MS-SSIM, and variance of the Laplacian values for image quality evaluation on 25 retrospective datasets. The minimum/maximum PSNR gains (measured in dB) were 1.18/11.68 and 1.04/13.15, from the baseline and SS image-denoising models, respectively. MS-SSIM gains were: 0.003/0.065 and 0.01/0.066; variance of the Laplacian (lower is better): 0.104/−0.135 and 0.13/−0.143. The GS protocol constitutes 44.44% of the comprehensive AD imaging protocol defined by the European Prevention of Alzheimer's Disease project. Therefore, we also demonstrate the potential for AD-imaging via automated volumetry of relevant brain anatomies. We performed statistical analysis on these volumetric measurements of the hippocampus and amygdala from the GS and accelerated protocols, and found that 27 locations were in excellent agreement. In conclusion, accelerated brain imaging with the potential for AD imaging was demonstrated, and image quality was recovered post-acquisition using DL-based image denoising models.

show abstract

“…Finally, the dataset was randomly divided into training (n = 37), validation (n = 5), and testing (n = 50) sets, to ensure the network was trained, validated, and tested on different participant data. Also, where applicable, the relevant checklist for good machine learning practices (GMLPs) has been considered 38 . To prepare for the SynthSR 32 method, we used the FLIRT registration method to co-register T1-w and T2-w images without resampling those to 1 mm isotropic resolution.…”

Section: Methodsmentioning

confidence: 99%

Improving portable low-field MRI image quality through image-to-image translation using paired low- and high-field images

Islam,

Zhong,

Zakavi

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Low-field portable magnetic resonance imaging (MRI) scanners are more accessible, cost-effective, sustainable with lower carbon emissions than superconducting high-field MRI scanners. However, the images produced have relatively poor image quality, lower signal-to-noise ratio, and limited spatial resolution. This study develops and investigates an image-to-image translation deep learning model, LoHiResGAN, to enhance the quality of low-field (64mT) MRI scans and generate synthetic high-field (3T) MRI scans. We employed a paired dataset comprising T1- and T2-weighted MRI sequences from the 64mT and 3T and compared the performance of the LoHiResGAN model with other state-of-the-art models, including GANs, CycleGAN, U-Net, and cGAN. Our proposed method demonstrates superior performance in terms of image quality metrics, such as normalized root-mean-squared error, structural similarity index measure, peak signal-to-noise ratio, and perception-based image quality evaluator. Additionally, we evaluated the accuracy of brain morphometry measurements for 33 brain regions across the original 3T, 64mT, and synthetic 3T images. The results indicate that the synthetic 3T images created using our proposed LoHiResGAN model significantly improve the image quality of low-field MRI data compared to other methods (GANs, CycleGAN, U-Net, cGAN) and provide more consistent brain morphometry measurements across various brain regions in reference to 3T. Synthetic images generated by our method demonstrated high quality both quantitatively and qualitatively. However, additional research, involving diverse datasets and clinical validation, is necessary to fully understand its applicability for clinical diagnostics, especially in settings where high-field MRI scanners are less accessible.

show abstract

Developing and deploying deep learning models in brain magnetic resonance imaging: A review

Cited by 6 publications

References 152 publications

Unified Bayesian network for uncertainty quantification of physiological parameters in dynamic contrast enhanced (DCE) MRI of the liver

Unified Bayesian network for uncertainty quantification of physiological parameters in dynamic contrast enhanced (DCE) MRI of the liver

Accelerated MRI using intelligent protocolling and subject-specific denoising applied to Alzheimer's disease imaging

Improving portable low-field MRI image quality through image-to-image translation using paired low- and high-field images

Contact Info

Product

Resources

About