AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis.

BACKGROUND: Contrast-enhancing (CE) lesions are an important finding on brain magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) but can be missed easily. Automated solutions for reliable CE lesion detection are emerging; however, independent validation of artificial intelligence (AI) tools in the clinical routine is still rare. METHODS: A three-dimensional convolutional neural network for CE lesion segmentation was trained externally on 1488 datasets of 934 MS patients from 81 scanners using concatenated information from FLAIR and T1-weighted post-contrast imaging. This externally trained model was tested on an independent dataset comprising 504 T1-weighted post-contrast and FLAIR image datasets of MS patients from clinical routine. Two neuroradiologists (R1, R2) labeled CE lesions for gold standard definition in the clinical test dataset. The algorithmic output was evaluated on both patient- and lesion-level. RESULTS: On a patient-level, recall, specificity, precision, and accuracy of the AI tool to predict patients with CE lesions were 0.75, 0.99, 0.91, and 0.96. The agreement between the AI tool and both readers was within the range of inter-rater agreement (Cohen's kappa; AI vs. R1: 0.69; AI vs. R2: 0.76; R1 vs. R2: 0.76). On a lesion-level, false negative lesions were predominately found in infratentorial location, significantly smaller, and at lower contrast than true positive lesions (p < 0.05). CONCLUSIONS: AI-based identification of CE lesions on brain MRI is feasible, approaching human reader performance in independent clinical data and might be of help as a second reader in the neuroradiological assessment of active inflammation in MS patients. CRITICAL RELEVANCE STATEMENT: Al-based detection of contrast-enhancing multiple sclerosis lesions approaches human reader performance, but careful visual inspection is still needed, especially for infratentorial, small and low-contrast lesions.

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.

AI in Radiology: Where are we today in Multiple Sclerosis Imaging? / KI in der Radiologie: Wo stehen wir in der MS-Bildgebung?

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: · Computer algorithms have a growing impact on analyzing MR imaging in MS.. · Artificial intelligence is more and more commonly employed in such computer tools.. · Applications include lesion segmentation, prediction of clinical parameters and image synthesizing.. CITATION FORMAT: · Eichinger P, Zimmer C, Wiestler B. AI in Radiology: Where are we today in Multiple Sclerosis Imaging?. Fortschr Röntgenstr 2020; 192: 847 - 853.

Predicting Glioblastoma Recurrence from Preoperative MR Scans Using Fractional-Anisotropy Maps with Free-Water Suppression.

Diffusion tensor imaging (DTI), and fractional-anisotropy (FA) maps in particular, have shown promise in predicting areas of tumor recurrence in glioblastoma. However, analysis of peritumoral edema, where most recurrences occur, is impeded by free-water contamination. In this study, we evaluated the benefits of a novel, deep-learning-based approach for the free-water correction (FWC) of DTI data for prediction of later recurrence. We investigated 35 glioblastoma cases from our prospective glioma cohort. A preoperative MR image and the first MR scan showing tumor recurrence were semiautomatically segmented into areas of contrast-enhancing tumor, edema, or recurrence of the tumor. The 10th, 50th and 90th percentiles and mean of FA and mean-diffusivity (MD) values (both for the original and FWC-DTI data) were collected for areas with and without recurrence in the peritumoral edema. We found significant differences in the FWC-FA maps between areas of recurrence-free edema and areas with later tumor recurrence, where differences in noncorrected FA maps were less pronounced. Consequently, a generalized mixed-effect model had a significantly higher area under the curve when using FWC-FA maps (AUC = 0.9) compared to noncorrected maps (AUC = 0.77, p < 0.001). This may reflect tumor infiltration that is not visible in conventional imaging, and may therefore reveal important information for personalized treatment decisions.

Automatic detection of lesion load change in Multiple Sclerosis using convolutional neural networks with segmentation confidence.

The detection of new or enlarged white-matter lesions is a vital task in the monitoring of patients undergoing disease-modifying treatment for multiple sclerosis. However, the definition of 'new or enlarged' is not fixed, and it is known that lesion-counting is highly subjective, with high degree of inter- and intra-rater variability. Automated methods for lesion quantification, if accurate enough, hold the potential to make the detection of new and enlarged lesions consistent and repeatable. However, the majority of lesion segmentation algorithms are not evaluated for their ability to separate radiologically progressive from radiologically stable patients, despite this being a pressing clinical use-case. In this paper, we explore the ability of a deep learning segmentation classifier to separate stable from progressive patients by lesion volume and lesion count, and find that neither measure provides a good separation. Instead, we propose a method for identifying lesion changes of high certainty, and establish on an internal dataset of longitudinal multiple sclerosis cases that this method is able to separate progressive from stable time-points with a very high level of discrimination (AUC = 0.999), while changes in lesion volume are much less able to perform this separation (AUC = 0.71). Validation of the method on two external datasets confirms that the method is able to generalize beyond the setting in which it was trained, achieving an accuracies of 75 % and 85 % in separating stable and progressive time-points.

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

OBJECTIVES: The aim of the study was to implement a deep-learning tool to produce synthetic double inversion recovery (synthDIR) images and compare their diagnostic performance to conventional sequences in patients with multiple sclerosis (MS). MATERIALS AND METHODS: For this retrospective analysis, 100 MS patients (65 female, 37 [22-68] years) were randomly selected from a prospective observational cohort between 2014 and 2016. In a subset of 50 patients, an artificial neural network (DiamondGAN) was trained to generate a synthetic DIR (synthDIR) from standard acquisitions (T1, T2, and fluid-attenuated inversion recovery [FLAIR]). With the resulting network, synthDIR was generated for the remaining 50 subjects. These images as well as conventionally acquired DIR (trueDIR) and FLAIR images were assessed for MS lesions by 2 independent readers, blinded to the source of the DIR image. Lesion counts in the different modalities were compared using a Wilcoxon signed-rank test, and interrater analysis was performed. Contrast-to-noise ratios were compared for objective image quality. RESULTS: Utilization of synthDIR allowed to detect significantly more lesions compared with the use of FLAIR images (31.4 ± 20.7 vs 22.8 ± 12.7, P < 0.001). This improvement was mainly attributable to an improved depiction of juxtacortical lesions (12.3 ± 10.8 vs 7.2 ± 5.6, P < 0.001). Interrater reliability was excellent in FLAIR 0.92 (95% confidence interval [CI], 0.85-0.95), synthDIR 0.93 (95% CI, 0.87-0.96), and trueDIR 0.95 (95% CI, 0.85-0.98).Contrast-to-noise ratio in synthDIR exceeded that of FLAIR (22.0 ± 6.4 vs 16.7 ± 3.6, P = 0.009); no significant difference was seen in comparison to trueDIR (22.0 ± 6.4 vs 22.4 ± 7.9, P = 0.87). CONCLUSIONS: Computationally generated DIR images improve lesion depiction compared with the use of standard modalities. This method demonstrates how artificial intelligence can help improving imaging in specific pathologies.

Accuracy of Unenhanced MRI in the Detection of New Brain Lesions in Multiple Sclerosis.

Background Administration of a gadolinium-based contrast material is widely considered obligatory for follow-up imaging of patients with multiple sclerosis (MS). However, advances in MRI have substantially improved the sensitivity for detecting new or enlarged lesions in MS. Purpose To investigate whether the use of contrast material has an effect on the detection of new or enlarged MS lesions and, consequently, the assessment of interval progression. Materials and Methods In this retrospective study based on a local prospective observational cohort, 507 follow-up MR images obtained in 359 patients with MS (mean age, 38.2 years ± 10.3; 246 women, 113 men) were evaluated. With use of subtraction maps, nonenhanced images (double inversion recovery [DIR], fluid-attenuated inversion recovery [FLAIR]) and contrast material-enhanced (gadoterate meglumine, 0.1 mmol/kg) T1-weighted images were separately assessed for new or enlarged lesions in independent readings by two readers blinded to each other's findings and to clinical information. Primary outcome was the percentage of new or enlarged lesions detected only on contrast-enhanced T1-weighted images and the assessment of interval progression. Interval progression was defined as at least one new or unequivocally enlarged lesion on follow-up MR images. Results Of 507 follow-up images, 264 showed interval progression, with a total of 1992 new or enlarged and 207 contrast-enhancing lesions. Four of these lesions (on three MR images) were retrospectively detected on only the nonenhanced images, corresponding to 1.9% (four of 207) of the enhancing and 0.2% (four of 1992) of all new or enlarged lesions. Nine enhancing lesions were not detected on FLAIR-based subtraction maps (nine of 1442, 0.6%). In none of the 507 images did the contrast-enhanced sequences reveal interval progression that was missed in the readouts of the nonenhanced sequences, with use of either DIR- or FLAIR-based subtraction maps. Interrater agreement was high for all three measures, with intraclass correlation coefficients of 0.91 with FLAIR, 0.94 with DIR, and 0.99 with contrast-enhanced T1-weighted imaging. Conclusion At 3.0 T, use of a gadolinium-based contrast agent at follow-up MRI did not change the diagnosis of interval disease progression in patients with multiple sclerosis. © RSNA, 2019 See also the editorial by Saindane in this issue.

Acceleration of Double Inversion Recovery Sequences in Multiple Sclerosis With Compressed Sensing.

OBJECTIVE: The aim of this study was to assess the performance of double inversion recovery (DIR) sequences accelerated by compressed sensing (CS) in a clinical setting. MATERIALS AND METHODS: We included 106 patients with MS (62 female [58%]; mean age, 44.9 ± 11.0 years) in this prospective study. In addition to a full magnetic resonance imaging protocol including a conventional SENSE accelerated DIR, we acquired a CS DIR (time reduction, 51%). We generated subtraction maps between the two DIR sequences to visualize focal intensity differences. Two neuroradiologists independently assessed these maps for intensity differences, which were categorized into definite MS lesions, possible lesions, or definite artifacts. Counts of focal intensity differences were compared using a Wilcoxon rank sum test. Moreover, conventional lesion counts were acquired for both sequences in independent readouts, and agreement between the DIR variants was assessed with intraclass correlation coefficients. RESULTS: No hyperintensity that was rated as definite lesion was missed in the CS DIR. Two possible lesions were only detected in the conventional DIR, one only in the CS DIR (no significant difference, P = 0.57). The conventional DIR showed significantly more definite artifacts within the white matter (P = 0.024) and highly significantly more at the cortical-sulcal interface (P < 0.001). For both readers, intraclass correlation coefficient between the lesion counts in the two DIR variants was near perfect (0.985 for reader 1 and 0.981 for reader 2). CONCLUSIONS: Compressed sensing can be used to substantially reduce scan time of DIR sequences without compromising diagnostic quality. Moreover, the CS accelerated DIR proved to be significantly less prone to imaging artifacts.

Predicting conversion from clinically isolated syndrome to multiple sclerosis-An imaging-based machine learning approach.

Magnetic resonance imaging (MRI) scans play a pivotal role in the evaluation of patients presenting with a clinically isolated syndrome (CIS), as these may depict brain lesions suggestive of an inflammatory cause. We hypothesized that it is possible to predict the conversion from CIS to multiple sclerosis (MS) based on the baseline MRI scan by studying image features of these lesions. We analyzed 84 patients diagnosed with CIS from a prospective observational single center cohort. The patients were followed up for at least three years. Conversion to MS was defined according to the 2010 McDonald criteria. Brain lesions were segmented based on 3D FLAIR and 3D T1 images. We generated brain lesion masks by a computer assisted manual segmentation. We also generated a set of automated segmentations using the Lesion Segmentation Toolbox for SPM to assess the influence of different segmentation methods. Shape and brightness features were automatically calculated from the segmented masks and used as input data to train an oblique random forest classifier. Prediction accuracies of the resulting model were validated through a three-fold cross-validation. Conversion from CIS to MS occurred in 66 of 84 patients (79%). The conversion or non-conversion was predicted correctly in 71 patients based on shape features derived from the computer assisted manual segmentation masks (84.5% accuracy). This predictor was more accurate than predicting conversion using dissemination in space at baseline according to the 2010 McDonald criteria (75% accuracy). While shape features strongly contributed to the accuracy of the predictor, including intensity features did not further improve performance. As patients who convert to definite MS benefit from early treatment, an early classification model is highly desirable. Our study shows that shape parameters of lesions can contribute to predicting the future course of CIS patients more accurately.

Human T cells in silico: Modelling dynamic intracellular calcium and its influence on cellular electrophysiology.

A network of ion currents influences basic cellular T cell functions. After T cell receptor activation, changes in highly regulated calcium levels play a central role in triggering effector functions and cell differentiation. A dysregulation of these processes might be involved in the pathogenesis of several diseases. We present a mathematical model based on the NEURON simulation environment that computes dynamic calcium levels in combination with the current output of diverse ion channels (KV1.3, KCa3.1, K2P channels (TASK1-3, TRESK), VRAC, TRPM7, CRAC). In line with experimental data, the simulation shows a strong increase in intracellular calcium after T cell receptor stimulation before reaching a new, elevated calcium plateau in the T cell's activated state. Deactivation of single ion channel modules, mimicking the application of channel blockers, reveals that two types of potassium channels are the main regulators of intracellular calcium level: calcium-dependent potassium (KCa3.1) and two-pore-domain potassium (K2P) channels.

Diffusion tensor image features predict IDH genotype in newly diagnosed WHO grade II/III gliomas.

We hypothesized that machine learning analysis based on texture information from the preoperative MRI can predict IDH mutational status in newly diagnosed WHO grade II and III gliomas. This retrospective study included in total 79 consecutive patients with a newly diagnosed WHO grade II or III glioma. Local binary pattern texture features were generated from preoperative B0 and fractional anisotropy (FA) diffusion tensor imaging. Using a training set of 59 patients, a single hidden layer neural network was then trained on the texture features to predict IDH status. The model was validated based on the prediction accuracy calculated in a previously unseen set of 20 gliomas. Prediction accuracy of the generated model was 92% (54/59 cases; AUC = 0.921) in the training and 95% (19/20; AUC = 0.952) in the validation cohort. The ten most important features were comprised of tumor size and both B0 and FA texture information, underlining the joint contribution of imaging data to classification. Machine learning analysis of DTI texture information and tumor size reliably predicts IDH status in preoperative MRI of gliomas. Such information may increasingly support individualized surgical strategies, supplement pathological analysis and highlight the potential of radiogenomics.

A novel imaging technique for better detecting new lesions in multiple sclerosis.

We developed a tool that performs longitudinal subtraction of 3D double inversion recovery (DIR) images in follow-up magnetic resonance (MR) examinations of patients with multiple sclerosis. As DIR sequences show a high lesion-to-parenchyma contrast, we hypothesized that such a tool might lead to increased sensitivity for new lesions as well as to speeding up the routine clinical work-up of follow-up MR imaging in multiple sclerosis by directly visualizing new lesions. DIR subtraction images of serial MR examinations were calculated in 106 patients with multiple sclerosis. Existence of new lesions was assessed in three different ways: by standard visual comparison, by FLAIR, and by DIR subtraction maps. A reference standard, to which the single modalities were compared, was defined by combining all information from all readouts and all readers. The presence and number of new lesions were determined and the time needed for analysis measured. Accuracy of detecting overall existence of new lesions using DIR subtraction maps was significantly higher than using visual comparison (96 vs. 86%, p = 0.013) or FLAIR subtraction maps (p < 0.001), with increased sensitivity and higher negative predictive value. Significantly more new lesions were detected when using DIR subtraction maps (p < 0.001). Analyzing subtraction maps took less than a third of the time needed for the standard visual comparison (p = 0.007). Thus, DIR subtraction maps improve the detection of new lesions in a clinical setting both in terms of accuracy and in terms of speed.

Human T cells in silico: Modelling their electrophysiological behaviour in health and disease.

Although various types of ion channels are known to have an impact on human T cell effector functions, their exact mechanisms of influence are still poorly understood. The patch clamp technique is a well-established method for the investigation of ion channels in neurons and T cells. However, small cell sizes and limited selectivity of pharmacological blockers restrict the value of this experimental approach. Building a realistic T cell computer model therefore can help to overcome these kinds of limitations as well as reduce the overall experimental effort. The computer model introduced here was fed off ion channel parameters from literature and new experimental data. It is capable of simulating the electrophysiological behaviour of resting and activated human CD4(+) T cells under basal conditions and during extracellular acidification. The latter allows for the very first time to assess the electrophysiological consequences of tissue acidosis accompanying most forms of inflammation.