Deep-Learning Generated Synthetic Double Inversion Recovery Images Improve Multiple Sclerosis Lesion Detection

Generating synthetic high-resolution spinal STIR and T1w images from T2w FSE and low-resolution axial Dixon

OBJECTIVES

To generate sagittal T1-weighted fast spin echo (T1w FSE) and short tau inversion recovery (STIR) images from sagittal T2-weighted (T2w) FSE and axial T1w gradient echo Dixon technique (T1w-Dixon) sequences.

MATERIALS AND METHODS

This retrospective study used three existing datasets: "Study of Health in Pomerania" (SHIP, 3142 subjects, 1.5 Tesla), "German National Cohort" (NAKO, 2000 subjects, 3 Tesla), and an internal dataset (157 patients 1.5/3 Tesla). We generated synthetic sagittal T1w FSE and STIR images from sagittal T2w FSE and low-resolution axial T1w-Dixon sequences based on two successively applied 3D Pix2Pix deep learning models. "Peak signal-to-noise ratio" (PSNR) and "structural similarity index metric" (SSIM) were used to evaluate the generated image quality on an ablations test. A Turing test, where seven radiologists rated 240 images as either natively acquired or generated, was evaluated using misclassification rate and Fleiss kappa interrater agreement.

RESULTS

Including axial T1w-Dixon or T1w FSE images resulted in higher image quality in generated T1w FSE (PSNR = 26.942, SSIM = 0.965) and STIR (PSNR = 28.86, SSIM = 0.948) images compared to using only single T2w images as input (PSNR = 23.076/24.677 SSIM = 0.952/0.928). Radiologists had difficulty identifying generated images (misclassification rate: 0.39 ± 0.09 for T1w FSE, 0.42 ± 0.18 for STIR) and showed low interrater agreement on suspicious images (Fleiss kappa: 0.09 for T1w/STIR).

CONCLUSIONS

Axial T1w-Dixon and sagittal T2w FSE images contain sufficient information to generate sagittal T1w FSE and STIR images.

CLINICAL RELEVANCE STATEMENT

T1w fast spin echo and short tau inversion recovery can be retroactively added to existing datasets, saving MRI time and enabling retrospective analysis, such as evaluating bone marrow pathologies.

KEY POINTS

Sagittal T2-weighted images alone were insufficient for differentiating fat and water and to generate T1-weighted images. Axial T1w Dixon technique, together with a T2-weighted sequence, produced realistic sagittal T1-weighted images. Our approach can be used to retrospectively generate STIR and T1-weighted fast spin echo sequences.

Clinical applications of deep learning in neuroinflammatory diseases: A scoping review

BACKGROUND

Deep learning (DL) is an artificial intelligence technology that has aroused much excitement for predictive medicine due to its ability to process raw data modalities such as images, text, and time series of signals.

OBJECTIVES

Here, we intend to give the clinical reader elements to understand this technology, taking neuroinflammatory diseases as an illustrative use case of clinical translation efforts. We reviewed the scope of this rapidly evolving field to get quantitative insights about which clinical applications concentrate the efforts and which data modalities are most commonly used.

METHODS

We queried the PubMed database for articles reporting DL algorithms for clinical applications in neuroinflammatory diseases and the radiology.healthairegister.com website for commercial algorithms.

RESULTS

The review included 148 articles published between 2018 and 2024 and five commercial algorithms. The clinical applications could be grouped as computer-aided diagnosis, individual prognosis, functional assessment, the segmentation of radiological structures, and the optimization of data acquisition. Our review highlighted important discrepancies in efforts. The segmentation of radiological structures and computer-aided diagnosis currently concentrate most efforts with an overrepresentation of imaging. Various model architectures have addressed different applications, relatively low volume of data, and diverse data modalities. We report the high-level technical characteristics of the algorithms and synthesize narratively the clinical applications. Predictive performances and some common a priori on this topic are finally discussed.

CONCLUSION

The currently reported efforts position DL as an information processing technology, enhancing existing modalities of paraclinical investigations and bringing perspectives to make innovative ones actionable for healthcare.

Deep Learning-Based Synthetic TOF-MRA Generation Using Time-Resolved MRA in Fast Stroke Imaging

BACKGROUND AND PURPOSE

Time-resolved MRA enables collateral evaluation in acute ischemic stroke with large-vessel occlusion; however, a low SNR and spatial resolution impede the diagnosis of vascular occlusion. We developed a CycleGAN-based deep learning model to generate high-resolution synthetic TOF-MRA images using time-resolved MRA and evaluated its image quality and clinical efficacy.

MATERIALS AND METHODS

This retrospective, single-center study included 397 patients who underwent both TOF- and time-resolved MRA between April 2021 and January 2022. Patients were divided into 2 groups for model development and image-quality validation. Image quality was evaluated qualitatively and quantitatively with 3 sequences. A multireader diagnostic optimality evaluation was performed by 16 radiologists. For clinical validation, we evaluated 123 patients who underwent fast stroke MR imaging to assess acute ischemic stroke. The diagnostic confidence level and decision time for large-vessel occlusion were also evaluated.

RESULTS

Median values of overall image quality, noise, sharpness, venous contamination, and SNR for M1, M2, the basilar artery, and posterior cerebral artery are better with synthetic TOF than with time-resolved MRA. However, with respect to real TOF, synthetic TOF presents worse median values of overall image quality, sharpness, vascular conspicuity, and SNR for M3, the basilar artery, and the posterior cerebral artery. During the multireader evaluation, radiologists could not discriminate synthetic TOF images from TOF images. During clinical validation, both readers demonstrated increases in diagnostic confidence levels and decreases in decision time.

CONCLUSIONS

A CycleGAN-based deep learning model was developed to generate synthetic TOF from time-resolved MRA. Synthetic TOF can potentially assist in the detection of large-vessel occlusion in stroke centers using time-resolved MRA.

Synthetic T2-weighted fat sat based on a generative adversarial network shows potential for scan time reduction in spine imaging in a multicenter test dataset

OBJECTIVES

T2-weighted (w) fat sat (fs) sequences, which are important in spine MRI, require a significant amount of scan time. Generative adversarial networks (GANs) can generate synthetic T2-w fs images. We evaluated the potential of synthetic T2-w fs images by comparing them to their true counterpart regarding image and fat saturation quality, and diagnostic agreement in a heterogenous, multicenter dataset.

METHODS

A GAN was used to synthesize T2-w fs from T1- and non-fs T2-w. The training dataset comprised scans of 73 patients from two scanners, and the test dataset, scans of 101 patients from 38 multicenter scanners. Apparent signal- and contrast-to-noise ratios (aSNR/aCNR) were measured in true and synthetic T2-w fs. Two neuroradiologists graded image (5-point scale) and fat saturation quality (3-point scale). To evaluate whether the T2-w fs images are indistinguishable, a Turing test was performed by eleven neuroradiologists. Six pathologies were graded on the synthetic protocol (with synthetic T2-w fs) and the original protocol (with true T2-w fs) by the two neuroradiologists.

RESULTS

aSNR and aCNR were not significantly different between the synthetic and true T2-w fs images. Subjective image quality was graded higher for synthetic T2-w fs (p = 0.023). In the Turing test, synthetic and true T2-w fs could not be distinguished from each other. The intermethod agreement between synthetic and original protocol ranged from substantial to almost perfect agreement for the evaluated pathologies.

DISCUSSION

The synthetic T2-w fs might replace a physical T2-w fs. Our approach validated on a challenging, multicenter dataset is highly generalizable and allows for shorter scan protocols.

KEY POINTS

• Generative adversarial networks can be used to generate synthetic T2-weighted fat sat images from T1- and non-fat sat T2-weighted images of the spine. • The synthetic T2-weighted fat sat images might replace a physically acquired T2-weighted fat sat showing a better image quality and excellent diagnostic agreement with the true T2-weighted fat images. • The present approach validated on a challenging, multicenter dataset is highly generalizable and allows for significantly shorter scan protocols.

Longitudinal Assessment of Multiple Sclerosis Lesion Load With Synthetic Magnetic Resonance Imaging-A Multicenter Validation Study

INTRODUCTION

Double inversion recovery (DIR) has been validated as a sensitive magnetic resonance imaging (MRI) contrast in multiple sclerosis (MS). Deep learning techniques can use basic input data to generate synthetic DIR (synthDIR) images that are on par with their acquired counterparts. As assessment of longitudinal MRI data is paramount in MS diagnostics, our study's purpose is to evaluate the utility of synthDIR longitudinal subtraction imaging for detection of disease progression in a multicenter data set of MS patients.

METHODS

We implemented a previously established generative adversarial network to synthesize DIR from input T1-weighted and fluid-attenuated inversion recovery (FLAIR) sequences for 214 MRI data sets from 74 patients and 5 different centers. One hundred and forty longitudinal subtraction maps of consecutive scans (follow-up scan-preceding scan) were generated for both acquired FLAIR and synthDIR. Two readers, blinded to the image origin, independently quantified newly formed lesions on the FLAIR and synthDIR subtraction maps, grouped into specific locations as outlined in the McDonald criteria.

RESULTS

Both readers detected significantly more newly formed MS-specific lesions in the longitudinal subtractions of synthDIR compared with acquired FLAIR (R1: 3.27 ± 0.60 vs 2.50 ± 0.69 [ P = 0.0016]; R2: 3.31 ± 0.81 vs 2.53 ± 0.72 [ P < 0.0001]). Relative gains in detectability were most pronounced in juxtacortical lesions (36% relative gain in lesion counts-pooled for both readers). In 5% of the scans, synthDIR subtraction maps helped to identify a disease progression missed on FLAIR subtraction maps.

CONCLUSIONS

Generative adversarial networks can generate high-contrast DIR images that may improve the longitudinal follow-up assessment in MS patients compared with standard sequences. By detecting more newly formed MS lesions and increasing the rates of detected disease activity, our methodology promises to improve clinical decision-making.

Multicenter Evaluation of AI-generated DIR and PSIR for Cortical and Juxtacortical Multiple Sclerosis Lesion Detection

Background Cortical multiple sclerosis lesions are clinically relevant but inconspicuous at conventional clinical MRI. Double inversion recovery (DIR) and phase-sensitive inversion recovery (PSIR) are more sensitive but often unavailable. In the past 2 years, artificial intelligence (AI) was used to generate DIR and PSIR from standard clinical sequences (eg, T1-weighted, T2-weighted, and fluid-attenuated inversion-recovery sequences), but multicenter validation is crucial for further implementation. Purpose To evaluate cortical and juxtacortical multiple sclerosis lesion detection for diagnostic and disease monitoring purposes on AI-generated DIR and PSIR images compared with MRI-acquired DIR and PSIR images in a multicenter setting. Materials and Methods Generative adversarial networks were used to generate AI-based DIR (n = 50) and PSIR (n = 43) images. The number of detected lesions between AI-generated images and MRI-acquired (reference) images was compared by randomized blinded scoring by seven readers (all with >10 years of experience in lesion assessment). Reliability was expressed as the intraclass correlation coefficient (ICC). Differences in lesion subtype were determined using Wilcoxon signed-rank tests. Results MRI scans of 202 patients with multiple sclerosis (mean age, 46 years ± 11 [SD]; 127 women) were retrospectively collected from seven centers (February 2020 to January 2021). In total, 1154 lesions were detected on AI-generated DIR images versus 855 on MRI-acquired DIR images (mean difference per reader, 35.0% ± 22.8; P < .001). On AI-generated PSIR images, 803 lesions were detected versus 814 on MRI-acquired PSIR images (98.9% ± 19.4; P = .87). Reliability was good for both DIR (ICC, 0.81) and PSIR (ICC, 0.75) across centers. Regionally, more juxtacortical lesions were detected on AI-generated DIR images than on MRI-acquired DIR images (495 [42.9%] vs 338 [39.5%]; P < .001). On AI-generated PSIR images, fewer juxtacortical lesions were detected than on MRI-acquired PSIR images (232 [28.9%] vs 282 [34.6%]; P = .02). Conclusion Artificial intelligence-generated double inversion-recovery and phase-sensitive inversion-recovery images performed well compared with their MRI-acquired counterparts and can be considered reliable in a multicenter setting, with good between-reader and between-center interpretative agreement. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Zivadinov and Dwyer in this issue.

Implementation of GAN-Based, Synthetic T2-Weighted Fat Saturated Images in the Routine Radiological Workflow Improves Spinal Pathology Detection

(1) Background and Purpose: In magnetic resonance imaging (MRI) of the spine, T2-weighted (T2-w) fat-saturated (fs) images improve the diagnostic assessment of pathologies. However, in the daily clinical setting, additional T2-w fs images are frequently missing due to time constraints or motion artifacts. Generative adversarial networks (GANs) can generate synthetic T2-w fs images in a clinically feasible time. Therefore, by simulating the radiological workflow with a heterogenous dataset, this study's purpose was to evaluate the diagnostic value of additional synthetic, GAN-based T2-w fs images in the clinical routine. (2) Methods: 174 patients with MRI of the spine were retrospectively identified. A GAN was trained to synthesize T2-w fs images from T1-w, and non-fs T2-w images of 73 patients scanned in our institution. Subsequently, the GAN was used to create synthetic T2-w fs images for the previously unseen 101 patients from multiple institutions. In this test dataset, the additional diagnostic value of synthetic T2-w fs images was assessed in six pathologies by two neuroradiologists. Pathologies were first graded on T1-w and non-fs T2-w images only, then synthetic T2-w fs images were added, and pathologies were graded again. Evaluation of the additional diagnostic value of the synthetic protocol was performed by calculation of Cohen's ĸ and accuracy in comparison to a ground truth (GT) grading based on real T2-w fs images, pre- or follow-up scans, other imaging modalities, and clinical information. (3) Results: The addition of the synthetic T2-w fs to the imaging protocol led to a more precise grading of abnormalities than when grading was based on T1-w and non-fs T2-w images only (mean ĸ GT versus synthetic protocol = 0.65; mean ĸ GT versus T1/T2 = 0.56; p = 0.043). (4) Conclusions: The implementation of synthetic T2-w fs images in the radiological workflow significantly improves the overall assessment of spine pathologies. Thereby, high-quality, synthetic T2-w fs images can be virtually generated by a GAN from heterogeneous, multicenter T1-w and non-fs T2-w contrasts in a clinically feasible time, which underlines the reproducibility and generalizability of our approach.

Radiomics and Deep Learning for Disease Detection in Musculoskeletal Radiology: An Overview of Novel MRI- and CT-Based Approaches

ABSTRACT

Radiomics and machine learning-based methods offer exciting opportunities for improving diagnostic performance and efficiency in musculoskeletal radiology for various tasks, including acute injuries, chronic conditions, spinal abnormalities, and neoplasms. While early radiomics-based methods were often limited to a smaller number of higher-order image feature extractions, applying machine learning-based analytic models, multifactorial correlations, and classifiers now permits big data processing and testing thousands of features to identify relevant markers. A growing number of novel deep learning-based methods describe magnetic resonance imaging- and computed tomography-based algorithms for diagnosing anterior cruciate ligament tears, meniscus tears, articular cartilage defects, rotator cuff tears, fractures, metastatic skeletal disease, and soft tissue tumors. Initial radiomics and deep learning techniques have focused on binary detection tasks, such as determining the presence or absence of a single abnormality and differentiation of benign versus malignant. Newer-generation algorithms aim to include practically relevant multiclass characterization of detected abnormalities, such as typing and malignancy grading of neoplasms. So-called delta-radiomics assess tumor features before and after treatment, with temporal changes of radiomics features serving as surrogate markers for tumor responses to treatment. New approaches also predict treatment success rates, surgical resection completeness, and recurrence risk. Practice-relevant goals for the next generation of algorithms include diagnostic whole-organ and advanced classification capabilities. Important research objectives to fill current knowledge gaps include well-designed research studies to understand how diagnostic performances and suggested efficiency gains of isolated research settings translate into routine daily clinical practice. This article summarizes current radiomics- and machine learning-based magnetic resonance imaging and computed tomography approaches for musculoskeletal disease detection and offers a perspective on future goals and objectives.

Diagnostic utility of 3D DIR MRI in the estimation of MS lesions overall load with special emphasis on cortical subtypes

Background

A number of magnetic resonance imaging studies have shown that a significant proportion of multiple sclerosis (MS) lesions are located in the cerebral cortex and correlate with the patient's disability level. Double inversion recovery (DIR) has a higher sensitivity to detect cortical lesions and their different types. The aim of our study was to assess the superiority of 3D DIR as compared to FLAIR in detecting the different cortical subtypes and to enhance its role as a test for the clinical disability of the patient.

Results

The current study included 82 MS patients (60 female and 22 male with mean age of 34.5 ± 8.2 years); 59 cases having relapsing–remitting MS, 5 having secondary progressive MS, and 4 having primary progressive MS, as well as eight clinically isolated syndrome cases, and six radiologically isolated syndrome cases. DIR was superior to FLAIR in MS plaque number detection of cortical plaque-types 1, 2, 3 and 4 with a p value < 0.001. DIR was superior to FLAIR for detection of overall cortical types, juxtacortical and juxtacortical extended MS plaques with p =  < 0.001, 0.010 and < 0.001, respectively. DIR was significantly better than FLAIR for MS plaque number detection in the periventricular white matter, subcortical white matter, infratentorial region and the overall MS plaques burden with a p < 0.001, 0.038, < 0.001, < 0.001, respectively. No significant difference was noted between both sequences for plaques number detection in deep white matter and deep gray matter. A significant correlation between MS disease duration, number of attacks and EDSS and the overall cortical MS plaques types and the overall MS plaque burden.

Conclusion

3D DIR is a reliable tool and provides superior delineation in detecting cortical subtypes. In addition, DIR is of value in assessing the degree of clinical and cognitive impairment of MS affected patients.

A Systematic Literature Review on Applications of GAN-Synthesized Images for Brain MRI

With the advances in brain imaging, magnetic resonance imaging (MRI) is evolving as a popular radiological tool in clinical diagnosis. Deep learning (DL) methods can detect abnormalities in brain images without an extensive manual feature extraction process. Generative adversarial network (GAN)-synthesized images have many applications in this field besides augmentation, such as image translation, registration, super-resolution, denoising, motion correction, segmentation, reconstruction, and contrast enhancement. The existing literature was reviewed systematically to understand the role of GAN-synthesized dummy images in brain disease diagnosis. Web of Science and Scopus databases were extensively searched to find relevant studies from the last 6 years to write this systematic literature review (SLR). Predefined inclusion and exclusion criteria helped in filtering the search results. Data extraction is based on related research questions (RQ). This SLR identifies various loss functions used in the above applications and software to process brain MRIs. A comparative study of existing evaluation metrics for GAN-synthesized images helps choose the proper metric for an application. GAN-synthesized images will have a crucial role in the clinical sector in the coming years, and this paper gives a baseline for other researchers in the field.

Synthetic Time of Flight Magnetic Resonance Angiography Generation Model Based on Cycle-Consistent Generative Adversarial Network Using PETRA-MRA in the Patients With Treated Intracranial Aneurysm

BACKGROUND

Pointwise encoding time reduction with radial acquisition (PETRA) magnetic resonance angiography (MRA) is useful for evaluating intracranial aneurysm recurrence, but the problem of severe background noise and low peripheral signal-to-noise ratio (SNR) remain. Deep learning could reduce noise using high- and low-quality images.

PURPOSE

To develop a cycle-consistent generative adversarial network (cycleGAN)-based deep learning model to generate synthetic TOF (synTOF) using PETRA.

STUDY TYPE

Retrospective.

POPULATION

A total of 377 patients (mean age: 60 ± 11; 293 females) with treated intracranial aneurysms who underwent both PETRA and TOF from October 2017 to January 2021. Data were randomly divided into training (49.9%, 188/377) and validation (50.1%, 189/377) groups.

FIELD STRENGTH/SEQUENCE

Ultra-short echo time and TOF-MRA on a 3-T MR system.

ASSESSMENT

For the cycleGAN model, the peak SNR (PSNR) and structural similarity (SSIM) were evaluated. Image quality was compared qualitatively (5-point Likert scale) and quantitatively (SNR). A multireader diagnostic optimality evaluation was performed with 17 radiologists (experience of 1-18 years).

STATISTICAL TESTS

Generalized estimating equation analysis, Friedman's test, McNemar test, and Spearman's rank correlation. P < 0.05 indicated statistical significance.

RESULTS

The PSNR and SSIM between synTOF and TOF were 17.51 [16.76; 18.31] dB and 0.71 ± 0.02. The median values of overall image quality, noise, sharpness, and vascular conspicuity were significantly higher for synTOF than for PETRA (4.00 [4.00; 5.00] vs. 4.00 [3.00; 4.00]; 5.00 [4.00; 5.00] vs. 3.00 [2.00; 4.00]; 4.00 [4.00; 4.00] vs. 4.00 [3.00; 4.00]; 3.00 [3.00; 4.00] vs. 3.00 [2.00; 3.00]). The SNRs of the middle cerebral arteries were the highest for synTOF (synTOF vs. TOF vs. PETRA; 63.67 [43.25; 105.00] vs. 52.42 [32.88; 74.67] vs. 21.05 [12.34; 37.88]). In the multireader evaluation, there was no significant difference in diagnostic optimality or preference between synTOF and TOF (19.00 [18.00; 19.00] vs. 20.00 [18.00; 20.00], P = 0.510; 8.00 [6.00; 11.00] vs. 11.00 [9.00, 14.00], P = 1.000).

DATA CONCLUSION

The cycleGAN-based deep learning model provided synTOF free from background artifact. The synTOF could be a versatile alternative to TOF in patients who have undergone PETRA for evaluating treated aneurysms.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 1.

Convolutional Neural Network Based Frameworks for Fast Automatic Segmentation of Thalamic Nuclei from Native and Synthesized Contrast Structural MRI

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.

The role of generative adversarial networks in brain MRI: a scoping review

The performance of artificial intelligence (AI) for brain MRI can improve if enough data are made available. Generative adversarial networks (GANs) showed a lot of potential to generate synthetic MRI data that can capture the distribution of real MRI. Besides, GANs are also popular for segmentation, noise removal, and super-resolution of brain MRI images. This scoping review aims to explore how GANs methods are being used on brain MRI data, as reported in the literature. The review describes the different applications of GANs for brain MRI, presents the most commonly used GANs architectures, and summarizes the publicly available brain MRI datasets for advancing the research and development of GANs-based approaches. This review followed the guidelines of PRISMA-ScR to perform the study search and selection. The search was conducted on five popular scientific databases. The screening and selection of studies were performed by two independent reviewers, followed by validation by a third reviewer. Finally, the data were synthesized using a narrative approach. This review included 139 studies out of 789 search results. The most common use case of GANs was the synthesis of brain MRI images for data augmentation. GANs were also used to segment brain tumors and translate healthy images to diseased images or CT to MRI and vice versa. The included studies showed that GANs could enhance the performance of AI methods used on brain MRI imaging data. However, more efforts are needed to transform the GANs-based methods in clinical applications.

Role of artificial intelligence in MS clinical practice

•

For medical applications, machine learning (including deep learning) are the most commonly used artificial intelligence (AI) approaches.

•

It can improve multiple sclerosis (MS) diagnosis, prognostication and treatment monitoring.

•

Thanks to AI, MRI and cognitive phenotypes of MS patients were identified.

•

AI can shorten MRI protocols for MS, allowing the application of advanced techniques.

•

It can reduce the human effort for MRI analysis, especially for lesion segmentation.

Machine learning (ML) and its subset, deep learning (DL), are branches of artificial intelligence (AI) showing promising findings in the medical field, especially when applied to imaging data. Given the substantial role of MRI in the diagnosis and management of patients with multiple sclerosis (MS), this disease is an ideal candidate for the application of AI techniques. In this narrative review, we are going to discuss the potential applications of AI for MS clinical practice, together with their limitations. Among their several advantages, ML algorithms are able to automate repetitive tasks, to analyze more data in less time and to achieve higher accuracy and reproducibility than the human counterpart. To date, these algorithms have been applied to MS diagnosis, prognosis, disease and treatment monitoring. Other fields of application have been improvement of MRI protocols as well as automated lesion and tissue segmentation. However, several challenges remain, including a better understanding of the information selected by AI algorithms, appropriate multicenter and longitudinal validations of results and practical aspects regarding hardware and software integration. Finally, one cannot overemphasize the paramount importance of human supervision, in order to optimize the use and take full advantage of the potential of AI approaches.

Uncertainty-Aware and Lesion-Specific Image Synthesis in Multiple Sclerosis Magnetic Resonance Imaging: A Multicentric Validation Study

Generative adversarial networks (GANs) can synthesize high-contrast MRI from lower-contrast input. Targeted translation of parenchymal lesions in multiple sclerosis (MS), as well as visualization of model confidence further augment their utility, provided that the GAN generalizes reliably across different scanners. We here investigate the generalizability of a refined GAN for synthesizing high-contrast double inversion recovery (DIR) images and propose the use of uncertainty maps to further enhance its clinical utility and trustworthiness. A GAN was trained to synthesize DIR from input fluid-attenuated inversion recovery (FLAIR) and T1w of 50 MS patients (training data). In another 50 patients (test data), two blinded readers (R1 and R2) independently quantified lesions in synthetic DIR (synthDIR), acquired DIR (trueDIR) and FLAIR. Of the 50 test patients, 20 were acquired on the same scanner as training data (internal data), while 30 were scanned at different scanners with heterogeneous field strengths and protocols (external data). Lesion-to-Background ratios (LBR) for MS-lesions vs. normal appearing white matter, as well as image quality parameters were calculated. Uncertainty maps were generated to visualize model confidence. Significantly more MS-specific lesions were found in synthDIR compared to FLAIR (R1: 26.7 ± 2.6 vs. 22.5 ± 2.2 p < 0.0001; R2: 22.8 ± 2.2 vs. 19.9 ± 2.0, p = 0.0005). While trueDIR remained superior to synthDIR in R1 [28.6 ± 2.9 vs. 26.7 ± 2.6 (p = 0.0021)], both sequences showed comparable lesion conspicuity in R2 [23.3 ± 2.4 vs. 22.8 ± 2.2 (p = 0.98)]. Importantly, improvements in lesion counts were similar in internal and external data. Measurements of LBR confirmed that lesion-focused GAN training significantly improved lesion conspicuity. The use of uncertainty maps furthermore helped discriminate between MS lesions and artifacts. In conclusion, this multicentric study confirms the external validity of a lesion-focused Deep-Learning tool aimed at MS imaging. When implemented, uncertainty maps are promising to increase the trustworthiness of synthetic MRI.

Improving Automated Glioma Segmentation in Routine Clinical Use Through Artificial Intelligence-Based Replacement of Missing Sequences With Synthetic Magnetic Resonance Imaging Scans

OBJECTIVES

Although automated glioma segmentation holds promise for objective assessment of tumor biology and response, its routine clinical use is impaired by missing sequences, for example, due to motion artifacts. The aim of our study was to develop and validate a generative adversarial network for synthesizing missing sequences to allow for a robust automated segmentation.

MATERIALS AND METHODS

Our model was trained on data from The Cancer Imaging Archive (n = 238 WHO II-IV gliomas) to synthesize either missing FLAIR, T2-weighted, T1-weighted (T1w), or contrast-enhanced T1w images from available sequences, using a novel tumor-targeting loss to improve synthesis of tumor areas. We validated performance in a test set from both the REMBRANDT repository and our local institution (n = 68 WHO II-IV gliomas), using qualitative image appearance metrics, but also segmentation performance with state-of-the-art segmentation models. Segmentation of synthetic images was compared with 2 commonly used strategies for handling missing input data, entering a blank mask or copying an existing sequence.

RESULTS

Across tumor areas and missing sequences, synthetic images generally outperformed both conventional approaches, in particular when FLAIR was missing. Here, for edema and whole tumor segmentation, we improved the Dice score, a common metric for evaluation of segmentation performance, by 12% and 11%, respectively, over the best conventional method. No method was able to reliably replace missing contrast-enhanced T1w images.

DISCUSSION

Replacing missing nonenhanced magnetic resonance sequences via synthetic images significantly improves segmentation quality over most conventional approaches. This model is freely available and facilitates more widespread use of automated segmentation in routine clinical use, where missing sequences are common.

Artificial double inversion recovery images can substitute conventionally acquired images: an MRI-histology study

Cortical multiple sclerosis lesions are disease-specific, yet inconspicuous on magnetic resonance images (MRI). Double inversion recovery (DIR) images are sensitive, but often unavailable in clinical routine and clinical trials. Artificially generated images can mitigate this issue, but lack histopathological validation. In this work, artificial DIR images were generated from postmortem 3D-T1 and proton-density (PD)/T2 or 3D-T1 and 3D fluid-inversion recovery (FLAIR) images, using a generative adversarial network. All sequences were scored for cortical lesions, blinded to histopathology. Subsequently, tissue samples were stained for proteolipid protein (myelin) and scored for cortical lesions type I-IV (leukocortical, intracortical, subpial and cortex-spanning, respectively). Histopathological scorings were then (unblinded) compared to MRI using linear mixed models. Images from 38 patients (26 female, mean age 64.3 ± 10.7) were included. A total of 142 cortical lesions were detected, predominantly subpial. Histopathology-blinded/unblinded sensitivity was 13.4/35.2% for artificial DIR generated from T1-PD/T2, 14.1/41.5% for artificial DIR from T1-FLAIR, 17.6/49.3% for conventional DIR and 10.6/34.5% for 3D-T1. When blinded to histopathology, there were no differences; with histopathological feedback at hand, conventional DIR and artificial DIR from T1-FLAIR outperformed the other sequences. Differences between histopathology-blinded/unblinded sensitivity could be minified through adjustment of the scoring criteria. In conclusion, artificial DIR images, particularly generated from T1-FLAIR could potentially substitute conventional DIR images when these are unavailable.

Symmetry GAN Detection Network: An Automatic One-Stage High-Accuracy Detection Network for Various Types of Lesions on CT Images

Computed tomography (CT) is the first modern slice-imaging modality. Recent years have witnessed its widespread application and improvement in detecting and diagnosing related lesions. Nonetheless, there are several difficulties in detecting lesions in CT images: (1) image quality degrades as the radiation dose is reduced to decrease radiational injury to the human body; (2) image quality is frequently hampered by noise interference; (3) because of the complicated circumstances of diseased tissue, lesion pictures typically show complex shapes; (4) the difference between the orientated object and the background is not discernible. This paper proposes a symmetry GAN detection network based on a one-stage detection network to tackle the challenges mentioned above. This paper employs the DeepLesion dataset, containing 10,594 CT scans (studies) of 4427 unique patients. The symmetry GANs proposed in this research consist of two distinct GAN models that serve different functions. A generative model is introduced ahead of the backbone to increase the input CT image series to address the typical problem of small sample size in medical datasets. Afterward, GAN models are added to the attention extraction module to generate attention masks. Furthermore, experimental data indicate that this strategy has significantly improved the model’s robustness. Eventually, the proposed method reaches 0.9720, 0.9858, and 0.9833 on P, R, and mAP, on the validation set. The experimental outcome shows that the suggested model outperforms other comparison models. In addition to this innovation, we are inspired by the innovation of the ResNet model in terms of network depth. Thus, we propose parallel multi-activation functions, an optimization method in the network width. It is theoretically proven that by adding coefficients to each base activation function and performing a softmax function on all coefficients, parallel multi-activation functions can express a single activation function, which is a unique ability compared to others. Ultimately, our model outperforms all comparison models in terms of P, R, and mAP, achieving 0.9737, 0.9845, and 0.9841. In addition, we encapsulate the model and build a related iOS application to make the model more applicable. The suggested model also won the second prize in the 2021 Chinese Collegiate Computing Competition.

Generative adversarial networks in medical image segmentation: A review

PURPOSE

Since Generative Adversarial Network (GAN) was introduced into the field of deep learning in 2014, it has received extensive attention from academia and industry, and a lot of high-quality papers have been published. GAN effectively improves the accuracy of medical image segmentation because of its good generating ability and capability to capture data distribution. This paper introduces the origin, working principle, and extended variant of GAN, and it reviews the latest development of GAN-based medical image segmentation methods.

METHOD

To find the papers, we searched on Google Scholar and PubMed with the keywords like "segmentation", "medical image", and "GAN (or generative adversarial network)". Also, additional searches were performed on Semantic Scholar, Springer, arXiv, and the top conferences in computer science with the above keywords related to GAN.

RESULTS

We reviewed more than 120 GAN-based architectures for medical image segmentation that were published before September 2021. We categorized and summarized these papers according to the segmentation regions, imaging modality, and classification methods. Besides, we discussed the advantages, challenges, and future research directions of GAN in medical image segmentation.

CONCLUSIONS

We discussed in detail the recent papers on medical image segmentation using GAN. The application of GAN and its extended variants has effectively improved the accuracy of medical image segmentation. Obtaining the recognition of clinicians and patients and overcoming the instability, low repeatability, and uninterpretability of GAN will be an important research direction in the future.

Applying Deep Learning to Accelerated Clinical Brain Magnetic Resonance Imaging for Multiple Sclerosis

Background: Magnetic resonance (MR) scans are routine clinical procedures for monitoring people with multiple sclerosis (PwMS). Patient discomfort, timely scheduling, and financial burden motivate the need to accelerate MR scan time. We examined the clinical application of a deep learning (DL) model in restoring the image quality of accelerated routine clinical brain MR scans for PwMS. Methods: We acquired fast 3D T1w BRAVO and fast 3D T2w FLAIR MRI sequences (half the phase encodes and half the number of slices) in parallel to conventional parameters. Using a subset of the scans, we trained a DL model to generate images from fast scans with quality similar to the conventional scans and then applied the model to the remaining scans. We calculated clinically relevant T1w volumetrics (normalized whole brain, thalamic, gray matter, and white matter volume) for all scans and T2 lesion volume in a sub-analysis. We performed paired t-tests comparing conventional, fast, and fast with DL for these volumetrics, and fit repeated measures mixed-effects models to test for differences in correlations between volumetrics and clinically relevant patient-reported outcomes (PRO). Results: We found statistically significant but small differences between conventional and fast scans with DL for all T1w volumetrics. There was no difference in the extent to which the key T1w volumetrics correlated with clinically relevant PROs of MS symptom burden and neurological disability. Conclusion: A deep learning model that improves the image quality of the accelerated routine clinical brain MR scans has the potential to inform clinically relevant outcomes in MS.

Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review)

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.

Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: A review

Multiple Sclerosis (MS) is a type of brain disease which causes visual, sensory, and motor problems for people with a detrimental effect on the functioning of the nervous system. In order to diagnose MS, multiple screening methods have been proposed so far; among them, magnetic resonance imaging (MRI) has received considerable attention among physicians. MRI modalities provide physicians with fundamental information about the structure and function of the brain, which is crucial for the rapid diagnosis of MS lesions. Diagnosing MS using MRI is time-consuming, tedious, and prone to manual errors. Research on the implementation of computer aided diagnosis system (CADS) based on artificial intelligence (AI) to diagnose MS involves conventional machine learning and deep learning (DL) methods. In conventional machine learning, feature extraction, feature selection, and classification steps are carried out by using trial and error; on the contrary, these steps in DL are based on deep layers whose values are automatically learn. In this paper, a complete review of automated MS diagnosis methods performed using DL techniques with MRI neuroimaging modalities is provided. Initially, the steps involved in various CADS proposed using MRI modalities and DL techniques for MS diagnosis are investigated. The important preprocessing techniques employed in various works are analyzed. Most of the published papers on MS diagnosis using MRI modalities and DL are presented. The most significant challenges facing and future direction of automated diagnosis of MS using MRI modalities and DL techniques are also provided.

Navigator-Guided Motion and B0 Correction of T2*-Weighted Magnetic Resonance Imaging Improves Multiple Sclerosis Cortical Lesion Detection

BACKGROUND

Cortical lesions are common in multiple sclerosis (MS). T2*-weighted (T2*w) imaging at 7 T is relatively sensitive for cortical lesions, but quality is often compromised by motion and main magnetic field (B0) fluctuations.

PURPOSE

The aim of this study was to determine whether motion and B0 correction with a navigator-guided gradient-recalled echo sequence can improve cortical lesion detection in T2*w magnetic resonance imaging.

MATERIALS AND METHODS

In this prospective study, a gradient-recalled echo sequence incorporating a navigator allowing for motion and B0 field correction was applied to collect T2*w images at 7 T from adults with MS between August 2019 and March 2020. T2*-weighted images were acquired in 1 to 3 partially overlapping scans per individual and were reconstructed using global average B0 correction ("uncorrected") or motion correction and spatially linear B0 correction ("corrected"). Image quality rating and manual segmentation of cortical lesions were performed on uncorrected and corrected images. Lesions seen on a single scan were retrospectively evaluated on the complementary scan. The association of cortical lesions with clinical disability was assessed. Mixed models were used to determine the effect of correction on lesion detection as well as on the relationship between disability and lesion count.

RESULTS

A total of 22 T2*w scans were performed on 11 adults with MS (mean [SD] age, 49 [11] years; 8 women). Quality improved for 20 of 22 scans (91%) after correction. A total of 69 cortical lesions were identified on uncorrected images (median per scan, 2; range, 0-11) versus 148 on corrected images (median per scan, 4.5; range, 0-25; rate ratio [RR], 2.1; P < 0.0001). For low-quality uncorrected scans with moderate to severe motion artifact (18/22, 82%), there was an improvement in cortical lesion detection with correction (RR, 2.5; P < 0.0001), whereas there was no significant change in cortical lesion detection for high-quality scans (RR, 1.3; P = 0.43).

CONCLUSIONS

Navigator-guided motion and B0 correction substantially improves the overall image quality of T2*w magnetic resonance imaging at 7 T and increases its sensitivity for cortical lesions.

Pre-examinations Improve Automated Metastases Detection on Cranial MRI

MATERIALS AND METHODS

Our local ethics committee approved this retrospective monocenter study.First, a dual-time approach was assessed, for which the CNN was provided sequences of the MRI that initially depicted new MM (diagnosis MRI) as well as of a prediagnosis MRI: inclusion of only contrast-enhanced T1-weighted images (CNNdual_ce) was compared with inclusion of also the native T1-weighted images, T2-weighted images, and FLAIR sequences of both time points (CNNdual_all).Second, results were compared with the corresponding single time approaches, in which the CNN was provided exclusively the respective sequences of the diagnosis MRI.Casewise diagnostic performance parameters were calculated from 5-fold cross-validation.

RESULTS

In total, 94 cases with 494 MMs were included. Overall, the highest diagnostic performance was achieved by inclusion of only the contrast-enhanced T1-weighted images of the diagnosis and of a prediagnosis MRI (CNNdual_ce, sensitivity = 73%, PPV = 25%, F1-score = 36%). Using exclusively contrast-enhanced T1-weighted images as input resulted in significantly less false-positives (FPs) compared with inclusion of further sequences beyond contrast-enhanced T1-weighted images (FPs = 5/7 for CNNdual_ce/CNNdual_all, P < 1e-5). Comparison of contrast-enhanced dual and mono time approaches revealed that exclusion of prediagnosis MRI significantly increased FPs (FPs = 5/10 for CNNdual_ce/CNNce, P < 1e-9).Approaches with only native sequences were clearly inferior to CNNs that were provided contrast-enhanced sequences.

CONCLUSIONS

Automated MM detection on contrast-enhanced T1-weighted images performed with high sensitivity. Frequent FPs due to artifacts and vessels were significantly reduced by additional inclusion of prediagnosis MRI, but not by inclusion of further sequences beyond contrast-enhanced T1-weighted images. Future studies might investigate different change detection architectures for computer-aided detection.

Deep Learning on Conventional Magnetic Resonance Imaging Improves the Diagnosis of Multiple Sclerosis Mimics

OBJECTIVES

The aims of this study were to present a deep learning approach for the automated classification of multiple sclerosis and its mimics and compare model performance with that of 2 expert neuroradiologists.

MATERIALS AND METHODS

A total of 268 T2-weighted and T1-weighted brain magnetic resonance imagin scans were retrospectively collected from patients with migraine (n = 56), multiple sclerosis (n = 70), neuromyelitis optica spectrum disorders (n = 91), and central nervous system vasculitis (n = 51). The neural network architecture, trained on 178 scans, was based on a cascade of 4 three-dimensional convolutional layers, followed by a fully dense layer after feature extraction. The ability of the final algorithm to correctly classify the diseases in an independent test set of 90 scans was compared with that of the neuroradiologists.

RESULTS

The interrater agreement was 84.9% (Cohen κ = 0.78, P < 0.001). In the test set, deep learning and expert raters reached the highest diagnostic accuracy in multiple sclerosis (98.8% vs 72.8%, P < 0.001, for rater 1; and 81.8%, P < 0.001, for rater 2) and the lowest in neuromyelitis optica spectrum disorders (88.6% vs 4.4%, P < 0.001, for both raters), whereas they achieved intermediate values for migraine (92.2% vs 53%, P = 0.03, for rater 1; and 64.8%, P = 0.01, for rater 2) and vasculitis (92.1% vs 54.6%, P = 0.3, for rater 1; and 45.5%, P = 0.2, for rater 2). The overall performance of the automated method exceeded that of expert raters, with the worst misdiagnosis when discriminating between neuromyelitis optica spectrum disorders and vasculitis or migraine.

CONCLUSIONS

A neural network performed better than expert raters in terms of accuracy in classifying white matter disorders from magnetic resonance imaging and may help in their diagnostic work-up.

Cycle-Consistent Generative Adversarial Network: Effect on Radiation Dose Reduction and Image Quality Improvement in Ultralow-Dose CT for Evaluation of Pulmonary Tuberculosis

Objective

To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis.

Materials and Methods

Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively.

Results

With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT.

Conclusion

The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

MPRAGE to MP2RAGE UNI translation via generative adversarial network improves the automatic tissue and lesion segmentation in multiple sclerosis patients

BACKGROUND AND OBJECTIVE

Compared to the conventional magnetization-prepared rapid gradient-echo imaging (MPRAGE) MRI sequence, the specialized magnetization prepared 2 rapid acquisition gradient echoes (MP2RAGE) shows a higher brain tissue and lesion contrast in multiple sclerosis (MS) patients. The goal of this work is to retrospectively generate realistic-looking MP2RAGE uniform images (UNI) from already acquired MPRAGE images in order to improve the automatic lesion and tissue segmentation.

METHODS

For this task we propose a generative adversarial network (GAN). Multi-contrast MRI data of 12 healthy controls and 44 patients diagnosed with MS was retrospectively analyzed. Imaging was acquired at 3T using a SIEMENS scanner with MPRAGE, MP2RAGE, FLAIR, and DIR sequences. We train the GAN with both healthy controls and MS patients to generate synthetic MP2RAGE UNI images. These images were then compared to the real MP2RAGE UNI (considered as ground truth) analyzing the output of automatic brain tissue and lesion segmentation tools. Reference-based metrics as well as the lesion-wise true and false positives, Dice coefficient, and volume difference were considered for the evaluation. Statistical differences were assessed with the Wilcoxon signed-rank test.

RESULTS

The synthetic MP2RAGE UNI significantly improves the lesion and tissue segmentation masks in terms of Dice coefficient and volume difference (p-values < 0.001) compared to the MPRAGE. For the segmentation metrics analyzed no statistically significant differences are found between the synthetic and acquired MP2RAGE UNI.

CONCLUSION

Synthesized MP2RAGE UNI images are visually realistic and improve the output of automatic segmentation tools.

T1-Based Synthetic Magnetic Resonance Contrasts Improve Multiple Sclerosis and Focal Epilepsy Imaging at 7 T

OBJECTIVES

Ultra-high field magnetic resonance imaging (MRI) (≥7 T) is a unique opportunity to improve the clinical diagnosis of brain pathologies, such as multiple sclerosis or focal epilepsy. However, several shortcomings of 7 T MRI, such as radiofrequency field inhomogeneities, could degrade image quality and hinder radiological interpretation. To address these challenges, an original synthetic MRI method based on T1 mapping achieved with the magnetization-prepared 2 rapid acquisition gradient echo (MP2RAGE) sequence was developed. The radiological quality of on-demand T1-based contrasts generated by this technique was evaluated in multiple sclerosis and focal epilepsy imaging at 7 T.

MATERIALS AND METHODS

This retrospective study was carried out from October 2017 to September 2019 and included 21 patients with different phenotypes of multiple sclerosis and 35 patients with focal epilepsy who underwent MRI brain examinations using a whole-body investigative 7 T magnetic resonance system. The quality of 2 proposed synthetic contrast images were assessed and compared with conventional images acquired at 7 T using the MP2RAGE sequence by 4 radiologists, evaluating 3 qualitative criteria: signal homogeneity, contrast intensity, and lesion visualization. Statistical analyses were performed on reported quality scores using Wilcoxon rank tests and further multiple comparisons tests. Intraobserver and interobserver reliabilities were calculated as well.

RESULTS

Radiological quality scores were reported higher for synthetic images when compared with original images, regardless of contrast, pathologies, or raters considered, with significant differences found for all 3 criteria (P < 0.0001, Wilcoxon rank test). None of the 4 radiologists ever rated a synthetic image "markedly worse" than an original image. Synthetic images were rated slightly less satisfying for only 3 epileptic patients, without precluding lesion identification.

CONCLUSION

T1-based synthetic MRI with the MP2RAGE sequence provided on-demand contrasts and high-quality images to the radiologist, facilitating lesion visualization in multiple sclerosis and focal epilepsy, while reducing the magnetic resonance examination total duration by removing an additional sequence.

Deep learning for medical image analysis: a brief introduction

Advances in deep learning have led to the development of neural network algorithms which today rival human performance in vision tasks, such as image classification or segmentation. Translation of these techniques into clinical science has also significantly advanced image analysis in neuro-oncology. This has created a need in the neuro-oncology community for understanding the mechanisms behind neural networks and deep learning, as close interaction of computer scientists and neuro-oncology researchers as well as realistic expectations about the possibilities (and limitations) of the current state-of-the-art is pivotal for successful translation of deep learning techniques into practice. In this review, we will briefly introduce the building blocks of neural networks with a particular focus on convolutional neural networks. We will explain why these networks excel at identifying relevant features and how they learn to associate these imaging features with (clinical) features of interest, such as genotype, or how they automatically segment structures of interest in the image volume. We will also discuss challenges for the more widespread use of these algorithms.

3D Quantitative Synthetic MRI in the Evaluation of Multiple Sclerosis Lesions

BACKGROUND AND PURPOSE

Synthetic MR imaging creates multiple contrast-weighted images based on a single time-efficient quantitative scan, which has been mostly performed for 2D acquisition. We assessed the utility of 3D synthetic MR imaging in patients with MS by comparing its diagnostic image quality and lesion volumetry with conventional MR imaging.

MATERIALS AND METHODS

Twenty-four patients with MS prospectively underwent 3D quantitative synthetic MR imaging and conventional T1-weighted, T2-weighted, FLAIR, and double inversion recovery imaging, with acquisition times of 9 minutes 3 seconds and 18 minutes 27 seconds for the synthetic MR imaging and conventional MR imaging sequences, respectively. Synthetic phase-sensitive inversion recovery images and those corresponding to conventional MR imaging contrasts were created for synthetic MR imaging. Two neuroradiologists independently assessed the image quality on a 5-point Likert scale. The numbers of cortical lesions and lesion volumes were quantified using both synthetic and conventional image sets.

RESULTS

The overall diagnostic image quality of synthetic T1WI and double inversion recovery images was noninferior to that of conventional images (P = .23 and .20, respectively), whereas that of synthetic T2WI and FLAIR was inferior to that of conventional images (both Ps < .001). There were no significant differences in the number of cortical lesions (P = .17 and .53 for each rater) or segmented lesion volumes (P = .61) between the synthetic and conventional image sets.

CONCLUSIONS

Three-dimensional synthetic MR imaging could serve as an alternative to conventional MR imaging in evaluating MS with a reduced scan time.

AI in Radiology: Where are we today in Multiple Sclerosis Imaging?

Background MR imaging is an essential component in managing patients with Multiple sclerosis (MS). This holds true for the initial diagnosis as well as for assessing the clinical course of MS. In recent years, a growing number of computer tools were developed to analyze imaging data in MS. This review gives an overview of the most important applications with special emphasis on artificial intelligence (AI).

Methods Relevant studies were identified through a literature search in recognized databases, and through parsing the references in studies found this way. Literature published as of November 2019 was included with a special focus on recent studies from 2018 and 2019.

Results There are a number of studies which focus on optimizing lesion visualization and lesion segmentation. Some of these studies accomplished these tasks with high accuracy, enabling a reproducible quantitative analysis of lesion loads. Some studies took a radiomics approach and aimed at predicting clinical endpoints such as the conversion from a clinically isolated syndrome to definite MS. Moreover, recent studies investigated synthetic imaging, i. e. imaging data that is not measured during an MR scan but generated by a computer algorithm to optimize the contrast between MS lesions and brain parenchyma.

Conclusion Computer-based image analysis and AI are hot topics in imaging MS. Some applications are ready for use in clinical routine. A major challenge for the future is to improve prediction of expected disease courses and thereby helping to find optimal treatment decisions on an individual level. With technical improvements, more questions arise about the integration of new tools into the radiological workflow.

Key Points: 

Citation Format