Advancing microbiome research with machine learning: key findings from the ML4Microbiome COST action.

The rapid development of machine learning (ML) techniques has opened up the data-dense field of microbiome research for novel therapeutic, diagnostic, and prognostic applications targeting a wide range of disorders, which could substantially improve healthcare practices in the era of precision medicine. However, several challenges must be addressed to exploit the benefits of ML in this field fully. In particular, there is a need to establish "gold standard" protocols for conducting ML analysis experiments and improve interactions between microbiome researchers and ML experts. The Machine Learning Techniques in Human Microbiome Studies (ML4Microbiome) COST Action CA18131 is a European network established in 2019 to promote collaboration between discovery-oriented microbiome researchers and data-driven ML experts to optimize and standardize ML approaches for microbiome analysis. This perspective paper presents the key achievements of ML4Microbiome, which include identifying predictive and discriminatory 'omics' features, improving repeatability and comparability, developing automation procedures, and defining priority areas for the novel development of ML methods targeting the microbiome. The insights gained from ML4Microbiome will help to maximize the potential of ML in microbiome research and pave the way for new and improved healthcare practices.

Assessment of liver cirrhosis severity with extracellular volume fraction MRI.

We aimed to investigate the diagnostic utility of MRI extracellular volume fraction (ECV) for the assessment of liver cirrhosis severity as defined by Child-Pugh class. In this retrospective study, 90 patients (68 cirrhotic patients and 22 controls), who underwent multiparametric liver MRI, were identified. Hepatic T1 relaxation times and ECV were assessed. Clinical scores of liver disease severity were calculated. One-way analysis of variance (ANOVA) followed by Tukey's multiple comparison test, Spearman's correlation coefficient, and receiver operating characteristic (ROC) analysis were used for statistical analysis. In cirrhotic patients, hepatic native T1 increased depending on Child-Pugh class (620.5 ± 78.9 ms (Child A) vs. 666.6 ± 73.4 ms (Child B) vs. 828.4 ± 91.2 ms (Child C), P < 0.001). ECV was higher in cirrhotic patients compared to the controls (40.1 ± 11.9% vs. 25.9 ± 4.5%, P < 0.001) and increased depending of Child-Pugh class (33.3 ± 6.0% (Child A) vs. 39.6 ± 4.9% (Child B) vs. 52.8 ± 1.2% (Child C), P < 0.001). ECV correlated with Child-Pugh score (r = 0.64, P < 0.001). ECV allowed differentiating between Child-Pugh classes A and B, and B and C with an AUC of 0.785 and 0.944 (P < 0.001, respectively). The diagnostic performance of ECV for differentiating between Child-Pugh classes A and B, and B and C was higher compared to hepatic native T1 (AUC: 0.651 and 0.910) and MELD score (AUC: 0.740 and 0.795) (P < 0.05, respectively). MRI-derived ECV correlated with Child-Pugh score and had a high diagnostic performance for the discrimination of different Child-Pugh classes. ECV might become a valuable non-invasive biomarker for the assessment of liver cirrhosis severity.

Magnetic resonance parametric mapping of the spleen for non-invasive assessment of portal hypertension.

OBJECTIVES: In patients with advanced liver disease, portal hypertension is an important risk factor, leading to complications such as esophageal variceal bleeding, ascites, and hepatic encephalopathy. This study aimed to determine the diagnostic value of T1 and T2 mapping and extracellular volume fraction (ECV) for the non-invasive assessment of portal hypertension. METHODS: In this prospective study, 50 participants (33 patients with indication for trans-jugular intrahepatic portosystemic shunt (TIPS) and 17 healthy volunteers) underwent MRI. The derivation and validation cohorts included 40 and 10 participants, respectively. T1 and T2 relaxation times and ECV of the liver and the spleen were assessed using quantitative mapping techniques. Direct hepatic venous pressure gradient (HVPG) and portal pressure measurements were performed during TIPS procedure. ROC analysis was performed to compare diagnostic performance. RESULTS: Splenic ECV correlated with portal pressure (r = 0.72; p < 0.001) and direct HVPG (r = 0.50; p = 0.003). No significant correlations were found between native splenic T1 and T2 relaxation times with portal pressure measurements (p > 0.05, respectively). In the derivation cohort, splenic ECV revealed a perfect diagnostic performance with an AUC of 1.000 for the identification of clinically significant portal hypertension (direct HVPG ≥ 10 mmHg) and outperformed other parameters: hepatic T2 (AUC, 0.731), splenic T2 (AUC, 0.736), and splenic native T1 (AUC, 0.806) (p < 0.05, respectively). The diagnostic performance of mapping parameters was comparable in the validation cohort. CONCLUSION: Splenic ECV was associated with portal pressure measurements in patients with advanced liver disease. Future studies should explore the diagnostic value of parametric mapping accross a broader range of pressure values. KEY POINTS: • Non-invasive assessment and monitoring of portal hypertension is an area of unmet interest. • Splenic extracellular volume fraction is strongly associated with portal pressure in patients with end-stage liver disease. • Quantitative splenic and hepatic MRI-derived parameters have a potential to become a new non-invasive diagnostic parameter to assess and monitor portal pressure.

Assessment of biopsy-proven liver fibrosis by two-dimensional shear wave elastography: An individual patient data-based meta-analysis.

Two-dimensional shear wave elastography (2D-SWE) has proven to be efficient for the evaluation of liver fibrosis in small to moderate-sized clinical trials. We aimed at running a larger-scale meta-analysis of individual data. Centers which have worked with Aixplorer ultrasound equipment were contacted to share their data. Retrospective statistical analysis used direct and paired receiver operating characteristic and area under the receiver operating characteristic curve (AUROC) analyses, accounting for random effects. Data on both 2D-SWE and liver biopsy were available for 1,134 patients from 13 sites, as well as on successful transient elastography in 665 patients. Most patients had chronic hepatitis C (n = 379), hepatitis B (n = 400), or nonalcoholic fatty liver disease (n = 156). AUROCs of 2D-SWE in patients with hepatitis C, hepatitis B, and nonalcoholic fatty liver disease were 86.3%, 90.6%, and 85.5% for diagnosing significant fibrosis and 92.9%, 95.5%, and 91.7% for diagnosing cirrhosis, respectively. The AUROC of 2D-SWE was 0.022-0.084 (95% confidence interval) larger than the AUROC of transient elastography for diagnosing significant fibrosis (P = 0.001) and 0.003-0.034 for diagnosing cirrhosis (P = 0.022) in all patients. This difference was strongest in hepatitis B patients. CONCLUSION: 2D-SWE has good to excellent performance for the noninvasive staging of liver fibrosis in patients with hepatitis B; further prospective studies are needed for head-to-head comparison between 2D-SWE and other imaging modalities to establish disease-specific appropriate cutoff points for assessment of fibrosis stage. (Hepatology 2018;67:260-272).

In vivo MR-angiography for the assessment of aortic aneurysms in an experimental mouse model on a clinical MRI scanner: Comparison with high-frequency ultrasound and histology.

BACKGROUND: MR-angiography currently represents one of the clinical reference-standards for the assessment of aortic-dimensions. For experimental research in mice, dedicated preclinical high-field MRI scanners are used in most studies. This type of MRI scanner is not available in most institutions. The aim of this study was to evaluate the potential of MR-angiography performed on a clinical MR scanner for the assessment of aortic aneurysms in an experimental mouse model, compared to a preclinical high-resolution ultrasound imaging system and histopathology. METHODS: All in vivo MR imaging was performed with a clinical 3T MRI system (Philips Achieva) equipped with a clinical gradient system in combination with a single-loop surface-coil (47 mm). All MR sequences were based on clinically used sequences. For ultrasound, a dedicated preclinical high-resolution system (30 MHz linear transducer, Vevo770, VisualSonics) was used. All imaging was performed with an ApoE knockout mouse-model for aortic aneurysms. Histopathology was performed as reference-standard at all stages of aneurysm development. RESULTS: MR-angiography on a clinical 3T system enabled the clear visualization of the aortic lumen and aneurysmal dilation at different stages of aneurysm development. A close correlation (R2 = 0.98; p < 0.001) with histological area measurements was found. Additionally, a good agreement between MR and ultrasound area measurements in systole (R2 = 0.91; p < 0.001) and diastole (R2 = 0.94; p < 0.001) were measured. Regarding interobserver reproducibility, MRI measurements yielded a smaller 95% confidence interval and a closer interreader correlation compared to ultrasound measurements (-0.37-0.46; R2 = 0.97 vs. -0.78-0.88; R2 = 0.87). CONCLUSION: This study demonstrates that MR-angiography, performed on a clinical 3T MR scanner, enables the reliable detection and quantification of the aortic dilatation at different stages of aneurysm development in an experimental mouse model.

In vivo assessment of aortic aneurysm wall integrity using elastin-specific molecular magnetic resonance imaging.

BACKGROUND: The incidence of abdominal aortic aneurysms (AAAs) has increased during the last decades. However, there is still controversy about the management of medium-sized AAAs. Therefore, novel biomarkers, besides aneurysmal diameter, are needed to assess aortic wall integrity and risk of rupture. Elastin is the key protein for maintaining aortic wall tensile strength and stability. The progressive breakdown of structural proteins, in particular, medial elastin, is responsible for the inability of the aortic wall to withstand intraluminal hemodynamic forces. Here, we evaluate the usefulness of elastin-specific molecular MRI for the in vivo characterization of AAAs. METHODS AND RESULTS: To induce AAAs, ApoE(-/-) mice were infused with angiotensin-II. An elastin-specific magnetic resonance molecular imaging agent (ESMA) was administered after 1, 2, 3, and 4 weeks of angiotensin-II infusion to assess elastin composition of the aorta (n=8 per group). The high signal provided by ESMA allowed for imaging with high spatial resolution, resulting in an accurate assessment of ruptured elastic laminae and the compensatory expression of elastic fibers. In vivo contrast-to-noise ratios and R1-relaxation rates after ESMA administration were in good agreement with ex vivo histomorphometry (Elastica van Gieson stain) and gadolinium concentrations determined by inductively coupled plasma mass spectroscopy. Electron microscopy confirmed colocalization of ESMA with elastic fibers. CONCLUSIONS: Changes in elastin content could be readily delineated and quantified at different stages of AAAs by elastin-specific molecular magnetic resonance imaging. ESMA-MRI offers potential for the noninvasive detection of the aortic rupture site prior to dilation of the aorta and the subsequent in vivo monitoring of compensatory repair processes during the progression of AAAs.

Single breath-hold assessment of cardiac function using an accelerated 3D single breath-hold acquisition technique--comparison of an intravascular and extravascular contrast agent.

BACKGROUND: Cardiovascular magnetic resonance (CMR) is the current gold standard for the assessment of left ventricular (LV) function. Repeated breath-holds are needed for standard multi-slice 2D cine steady-state free precession sequences (M2D-SSFP). Accelerated single breath-hold techniques suffer from low contrast between blood pool and myocardium. In this study an intravascular contrast agent was prospectively compared to an extravascular contrast agent for the assessment of LV function using a single-breath-hold 3D-whole-heart cine SSFP sequence (3D-SSFP). METHODS: LV function was assessed in fourteen patients on a 1.5 T MR-scanner (Philips Healthcare) using 32-channel coil technology. Patients were investigated twice using a 3D-SSFP sequence (acquisition time 18-25 s) after Gadopentetate dimeglumine (GdD, day 1) and Gadofosveset trisodium (GdT, day 2) administration. Image acquisition was accelerated using sensitivity encoding in both phase encoding directions (4xSENSE). CNR and BMC were both measured between blood and myocardium. The CNR incorporated noise measurements, while the BMC represented the coeffiancy between the signal from blood and myocardium [1]. Contrast to noise ratio (CNR), blood to myocardium contrast (BMC), image quality, LV functional parameters and intra-/interobserver variability were compared. A M2D-SSFP sequence was used as a reference standard on both days. RESULTS: All 3D-SSFP sequences were successfully acquired within one breath-hold after GdD and GdT administration. CNR and BMC were significantly (p < 0.05) higher using GdT compared to GdD, resulting in an improved endocardial definition. Using 3D-SSFP with GdT, Bland-Altman plots showed a smaller bias (95% confidence interval LVEF: 9.0 vs. 23.7) and regression analysis showed a stronger correlation to the reference standard (R2 = 0.92 vs. R2 = 0.71), compared to 3D-SSFP with GdD. CONCLUSIONS: A single-breath-hold 3D-whole-heart cine SSFP sequence in combination with 32-channel technology and an intravascular contrast agent allows for the accurate and fast assessment of LV function.

In vivo assessment of intraplaque and endothelial fibrin in ApoE(-/-) mice by molecular MRI.

OBJECTIVE: Molecular magnetic resonance imaging (MRI) has emerged as a promising non-invasive modality to characterize atherosclerotic vessel wall changes on a morphological and molecular level. Intraplaque and endothelial fibrin has recently been recognized to play an important role in the progression of atherosclerosis. This study aimed to investigate the feasibility of intraplaque and endothelial fibrin detection using a fibrin-targeted contrast-agent, FTCA (EPIX Pharmaceuticals, Lexington, MA), in a mouse model of atherosclerosis. METHODS: Male apolipoproteinE-knockout mice (ApoE(-/-)) were fed a high fat diet (HFD) for one to three months. MRI of the brachiocephalic artery was performed prior to and 90 min after the administration of FTCA (n=8 per group). Contrast to noise ratios (CNR) and longitudinal relaxation rates (R1) of plaques were determined and compared to ex vivo fibrin density measurements on immunohistological sections stained with a fibrin-specific antibody and gadolinium concentrations measured by inductively coupled mass spectroscopy (ICP-MS). RESULTS: Molecular MRI after FTCA administration demonstrated a significant increase (p<0.05) in contrast agent uptake in brachiocephalic artery plaques. In vivo CNR measurements were in good agreement with ex vivo fibrin density measurements on immunohistochemistry (y=2.4x+11.3, R(2)=0.82) and ICP-MS (y=0.95x+7.1, R(2)=0.70). Late stage atherosclerotic plaques displayed the strongest increase in CNR, R1, ex vivo fibrin staining and gadolinium concentration (p<0.05). CONCLUSION: This study demonstrated the feasibility of intraplaque and endothelial fibrin imaging using FTCA. Direct in vivo fibrin detection and quantification could be useful for characterization and staging of coronary and carotid atherosclerotic lesions, which may aid diagnosis and intervention.

Noninvasive assessment of atherosclerotic plaque progression in ApoE-/- mice using susceptibility gradient mapping.

BACKGROUND: Macrophages have been identified as a major contributor to plaque development and destabilization in atherosclerosis. The aim of this study was to noninvasively assess uptake of citrate coated very small iron oxide particles at different stages of plaque development in the brachiocephalic artery of apoE(-/-) mice. Susceptibility gradient mapping (SGM) was applied to generate positive contrast images and to quantify iron oxide uptake. METHODS AND RESULTS: ApoE(-/-) mice were fed a high-fat diet for 4, 8, or 12 weeks; 300 µmol Fe/kg was injected 24 and 48 hours before final MRI. Increasing very small iron oxide particle uptake was observed over the course of atherosclerotic plaque development. Simultaneous administration of pravastatin led to a significant decrease in very small iron oxide particle uptake, assessed by mass spectroscopy and histology. SGM-MRI allowed the generation of positive contrast images, and magnitudes (mT/m) of contrast enhancement in SG parameter maps significantly correlated with the absolute iron oxide content (R(2)=0.70, P<0.05) and the macrophage density (R(2)=0.71, P<0.05). CONCLUSIONS: This study shows an increase in iron oxide uptake (measured by in vivo SGM-MRI, histology, and mass spectroscopy) with the progression of plaque development in an apoE(-/-) mouse model of accelerated atherosclerosis. Positive contrast provided by SGM-MRI allowed for a clear visualization of intraplaque iron oxide depositions, and magnitudes (mT/m) of contrast enhancement in SG parameter maps allowed for the quantification of intraplaque iron oxide particles.

Assessment of atherosclerotic plaque burden with an elastin-specific magnetic resonance contrast agent.

Atherosclerosis and its consequences remain the main cause of mortality in industrialized and developing nations. Plaque burden and progression have been shown to be independent predictors for future cardiac events by intravascular ultrasound. Routine prospective imaging is hampered by the invasive nature of intravascular ultrasound. A noninvasive technique would therefore be more suitable for screening of atherosclerosis in large populations. Here we introduce an elastin-specific magnetic resonance contrast agent (ESMA) for noninvasive quantification of plaque burden in a mouse model of atherosclerosis. The strong signal provided by ESMA allows for imaging with high spatial resolution, resulting in accurate assessment of plaque burden. Additionally, plaque characterization by quantifying intraplaque elastin content using signal intensity measurements is possible. Changes in elastin content and the high abundance of elastin during plaque development, in combination with the imaging properties of ESMA, provide potential for noninvasive assessment of plaque burden by molecular magnetic resonance imaging (MRI).

Echocardiographic quantification of atherosclerosis leads to cost-effective treatment with statins.

OBJECTIVE: Use of statins in prevention of atherosclerosis is effective but expensive. Patient selection gains wider public attention as medication costs in the US and Europe augment by 8% to 10% per year. We examined different clinical risk stratification strategies, particularly focusing on echocardiographic atherosclerosis quantification, for their impact on event reduction and cost-effectiveness in statin treatment. METHODS AND RESULTS: In a prospective, consecutive cohort of 336 patients referred to non-invasive cardiac examination, risk stratification was done by various combinations of risk factors and noninvasive atherosclerosis quantification. Atherosclerotic burden was determined through measuring "aortic elastance" by transthoracic echocardiogram, a validated non-invasive method. Cardiovascular events were recorded at a mean follow-up of one year. Echocardiographically determined atherosclerosis severity and event history, especially in combination, yielded the best selection strategies for statin treatment over a broad range of predetermined funding or required event reductions, surpassing conventional cardiovascular risk factors. From 26.8 statin-preventable events/1000 patients/year (assuming all patients treated), the best selection strategies could avoid: 24 with 66% of the cost for statin treatment (atherosclerosis and age criteria), 20.1 with <50% of the budget, 12.2 with <30% of the budget or 9.6 with <15% of the budget (using combinations of atherosclerosis and prior events), while conventional strategies without echo quantification of atherosclerosis were inferior. CONCLUSION: Non-invasive echocardiographic quantification of atherosclerosis improves efficiency and cost-effectiveness in statin treatment.