Whole body MR imaging in diabetes

Deep learning for the prediction of type 2 diabetes mellitus from neck-to-knee Dixon MRI in the UK biobank

Rationale and objectives

We evaluate the automatic identification of type 2 diabetes from neck-to-knee, two-point Dixon MRI scans with 3D convolutional neural networks on a large, population-based dataset. To this end, we assess the best combination of MRI contrasts and stations for diabetes prediction, and the benefit of integrating risk factors.

Materials and methods

Subjects with type 2 diabetes mellitus have been identified in the prospective UK Biobank Imaging study, and a matched control sample has been created to avoid confounding bias. Five-fold cross-validation is used for the evaluation. All scans from the two-point Dixon neck-to-knee sequence have been standardized. A neural network that considers multi-channel MRI input was developed and integrates clinical information in tabular format. An ensemble strategy is used to combine multi-station MRI predictions. A subset with quantitative fat measurements is identified for comparison to prior approaches.

Results

MRI scans from 3406 subjects (mean age, 66.2 years ± 7.1 [standard deviation]; 1128 women) were analyzed with 1703 diabetics. A balanced accuracy of 78.7 %, AUC ROC of 0.872, and an average precision of 0.878 was obtained for the classification of diabetes. The ensemble over multiple Dixon MRI stations yields better performance than selecting the individually best station. Moreover, combining fat and water scans as multi-channel inputs to the networks improves upon just using single contrasts as input. Integrating clinical information about known risk factors of diabetes in the network boosts the performance across all stations and the ensemble. The neural network achieved superior results compared to the prediction based on quantitative MRI measurements.

Conclusions

The developed deep learning model accurately predicted type 2 diabetes from neck-to-knee two-point Dixon MRI scans.

Findings in whole body MRI and conventional imaging in patients with fever of unknown origin-a retrospective study

Background

To analyse the influence of whole body (wb)-MRI on patient management compared to routine diagnostic tests in patients with fever of unknown origin (FUO).

Methods

Twenty-four patients with FUO, defined as illness of more than three weeks with fever greater than 38.3 °C, underwent wb-MRI at a 1.5 T MR-system. The MR-protocol consisted of the following sequences: axial T1 VIBE, coronal T2-TIRM and a coronal echoplanar diffusion weighted sequence (overall acquisition time 29:39 min:s). Furthermore, laboratory findings, chest-x-ray, abdominal ultrasound, CT-scans and/or PET-CT scans were evaluated and compared to the wb-MRI findings in regard to treatment changes.

Results

Wb-MRI yielded a correct diagnosis in 70% of the patients. In 46% the inflammatory focus was exclusively detected by wb-MRI. Focus detection by wb-MRI led to a subsequent change of the clinical management in 92% of the patients. In 6 patients both a wb-MRI and a PET-CT were performed yielding the correct diagnosis in the same 4 of 6 patients for both imaging modalities.

Conclusions

Wb-MRI appears to be of value in the evaluation of FUO patients, allowing for optimized treatment by increasing diagnostic certainty. Due to its lack of nephrotoxicity and ionizing radiation it may be preferred over standard imaging techniques and PET-CT in the future. However, given the low number of patients in our trial, further prospective studies have to be performed to confirm our results.

How to report incidental findings from population whole-body MRI: view of participants of the German National Cohort

OBJECTIVES

In the German National Cohort (GNC), 30,000 individuals are examined with whole-body MRI (wbMRI), of which about 3000 participants are expected to receive an incidental finding (IF) disclosure. In order to get feedback from participants and to evaluate the IF-management procedure of the wbMRI substudy, a follow-up questionnaire was developed. This single-center pilot trial was aimed to get a first impression on feasibility reproducibility and validity of such a survey in order to take necessary adjustments before initiating the survey among several thousand participants.

METHODS

The questionnaires were sent out in test-retest manner to 86 participants who received a wbMRI examination in January-February 2016 at the imaging center in Neubrandenburg. The ratio of participants with and without IF notification was 1:1. Descriptive statistics was performed.

RESULTS

A first response of 94% and completion proportion of 99% were achieved. Participants were satisfied with the examination procedure. Ninety-five percent of participants considered it very important to receive notification of IFs. Participants reported minimal stress levels while waiting for a possible IF notification letter, but high stress levels when an IF letter was received. Phrasing of the IF reports was rated in 97% as well understandable and in 55% as beneficial to health status.

CONCLUSIONS

This questionnaire will serve researchers within the GNC as a fundamental instrument not only for quality management analyses but also for the investigation of still unacknowledged scientific and ethical questions contributing to evidence-based guidelines concerning the complex approach to IFs in future population-based imaging.

KEY POINTS

• Evidence-based guidelines for reporting incidental findings in population whole-body MRI are lacking. • Pilot-testing of a questionnaire for the evaluation of practical and ethical aspects of the procedure to report incidental findings in the German National Cohort shows a high level of acceptance and high return rate by participants. • Participants reported minimal stress levels while waiting for a possible incidental finding notification letter, which increased significantly, when such a letter was received.

Macrophages mediated diagnosis of rheumatoid arthritis using fibrin based magnetic nanoparticles as MRI contrast agents

BACKGROUND

A variety of bioimaging tools assists in the diagnosis and evaluation of rheumatoid arthritis (RA) and other osteoarthritis. However, detection of RA in the early stages by targeting its macrophages with suitable contrast agents will help in arresting the progression of the disease.

METHODS

In the present study, we investigated the effectiveness of using magnetic fibrin nanoparticles (MFNPs) conjugated with folic acid (FA-MFNPs) as a specific contrast agent to target the activated macrophages, which overexpress the folate receptors (FR) in the knee joints of rats with antigen-induced arthritis (AIA).

RESULTS

FA-MFNPs were spherical with an average size of 18.3±1.6nm. In vitro studies have shown effective internalization of FA-MFNPs into the Raw264.7 macrophage cells. In vivo studies were carried out by injecting FA-MFNPs intravenously into the arthritic rats. The results showed enhanced MR imaging in the synovium of arthritic joints. Prussian blue histological staining confirmed uptake of FA-MFNPs by macrophages in the synovial tissue.

CONCLUSION

The animal experiment results indicate that FA-MFNPs can be used as a specific MRI contrast agent in identifying phagocytic active macrophages in the synovial joints.

GENERAL SIGNIFICANCE

Blood is the precursor source for synthesising the fibrin-based iron oxide (magnetic) nanoparticles (MFNPs) with diameters between 12 and 15nm. It has excellent superparamagnetic behaviour, biocompatibility, osteogenic potency, hemocompatibility, and biodegradable properties. MFNPs-based nanocomposites might be a promising contrast agent for bioimaging.

Whole-Body MRI Screening in Asymptomatic Subjects; Preliminary Experience and Long-Term Follow-Up Findings

BACKGROUND

The aim of this study is to describe the technique and to evaluate the results of whole-body magnetic resonance imaging in an asymptomatic population.

MATERIAL/METHODS

Between March 2009 and December 2011, 118 consecutive subjects undergoing thorough medical check-up were prospectively included in the study. MRI was performed with a 205-cm moving table, parallel imaging and automatic image composing software.

RESULTS

In 83 subjects (70%), 103 benign lesions were detected. Two malignant (adrenal and renal carcinoma) lesions and one precancerous (pancreatic mucinous carcinoma) lesion were detected. The most common lesions were renal cysts, liver hemangiomas, liver cysts, thyroid nodules, and uterine leiomyomas.

CONCLUSIONS

WB-MRI is able to cover area from head to toes in one diagnostic work-up, and besides the anatomic regions evaluated by conventional radiological modalities, i.e. brain parenchyma, bones and extremities, can be evaluated in one examination.

Non-contrast-enhanced whole-body magnetic resonance imaging in the general population: the incidence of abnormal findings in patients 50 years old and younger compared to older subjects

Purpose

To assess and compare the incidence of abnormal findings detected during non-contrast-enhanced whole-body magnetic resonance imaging (WB-MRI) in the general population in two age groups: (1) 50 years old and younger; and (2) over 50 years old.

Materials and Methods

The analysis included 666 non-contrast-enhanced WB-MRIs performed on a 1.5-T scanner between December 2009 and June 2013 in a private hospital in 451 patients 50 years old and younger and 215 patients over 50 years old. The following images were obtained: T2-STIR (whole body-coronal plane), T2-STIR (whole spine-sagittal), T2-TSE with fat-saturation (neck and trunk-axial), T2-FLAIR (head-axial), 3D T1-GRE (thorax-coronal, axial), T2-TSE (abdomen-axial), chemical shift (abdomen-axial). Detected abnormalities were classified as: insignificant (type I), potentially significant, requiring medical attention (type II), significant, requiring treatment (type III).

Results

There were 3375 incidental findings depicted in 659 (98.9%) subjects: 2997 type I lesions (88.8%), 363 type II lesions (10.8%) and 15 type III lesions (0.4%), including malignant or possibly malignant lesions in seven subjects. The most differences in the prevalence of abnormalities on WB-MRI between patients 50 years old and younger and over 50 years old concerned: brain infarction (22.2%, 45.0% respectively), thyroid cysts/nodules (8.7%, 18.8%), pulmonary nodules (5.0%, 16.2%), significant degenerative disease of the spine (23.3%, 44.5%), extra-spinal degenerative disease (22.4%, 61.1%), hepatic steatosis (15.8%, 24.9%), liver cysts/hemangiomas (24%, 34.5%), renal cysts (16.9%, 40.6%), prostate enlargement (5.1% of males, 34.2% of males), uterine fibroids (16.3% of females, 37.9% of females).

Conclusions

Incidental findings were detected in almost all of the subjects. WB-MRI demonstrated that the prevalence of the vast majority of abnormalities increases with age.

Diabetes revealed: multisystem danger

OBJECTIVE

The purpose of this article is to review the role of diagnostic imaging in the evaluation of women with diabetes.

CONCLUSION

Diabetic patients present a challenging population for the performance of various imaging studies and special considerations need to be made to obtain adequate studies. Imaging plays a significant role in assessing the multisystem morbidity of diabetes. Furthermore, diabetes in women may have some unique features and consequences and imaging studies can aid in the correct management of these patients.