Diagnostic performance of synthetic relaxometry for predicting neurodevelopmental outcomes in premature infants: a feasibility study

OBJECTIVES

To investigate the predictability of synthetic relaxometry for neurodevelopmental outcomes in premature infants and to evaluate whether a combination of relaxation times with clinical variables or qualitative MRI abnormalities improves the predictive performance.

METHODS

This retrospective study included 33 premature infants scanned with synthetic MRI near or at term equivalent age. Based on neurodevelopmental assessments at 18-24 months of corrected age, infants were classified into two groups (no/mild disability [n = 23] vs. moderate/severe disability [n = 10]). Clinical and MRI characteristics associated with moderate/severe disability were explored, and combined models incorporating independent predictors were established. Ultimately, the predictability of relaxation times, clinical variables, MRI findings, and a combination of the two were evaluated and compared. The models were internally validated using bootstrap resampling.

RESULTS

Prolonged T1-frontal/parietal and T2-parietal periventricular white matter (PVWM), moderate-to-severe white matter abnormality, and bronchopulmonary dysplasia were significantly associated with moderate/severe disability. The overall predictive performance of each T1-frontal/-parietal PVWM model was comparable to that of individual MRI finding and clinical models (AUC = 0.71 and 0.76 vs. 0.73 vs. 0.83, respectively; p > 0.27). The combination of clinical variables and T1-parietal PVWM achieved an AUC of 0.94, sensitivity of 90%, and specificity of 91.3%, outperforming the clinical model alone (p = 0.049). The combination of MRI finding and T1-frontal PVWM yielded AUC of 0.86, marginally outperforming the MRI finding model (p = 0.09). Bootstrap resampling showed that the models were valid.

CONCLUSIONS

It is feasible to predict adverse outcomes in premature infants by using early synthetic relaxometry. Combining relaxation time with clinical variables or MRI finding improved prediction.

CLINICAL RELEVANCE STATEMENT

Synthetic relaxometry performed during the neonatal period may serve as a biomarker for predicting adverse neurodevelopmental outcomes in premature infants.

KEY POINTS

• Synthetic relaxometry based on T1 relaxation time of parietal periventricular white matter showed acceptable performance in predicting adverse outcome with an AUC of 0.76 and an accuracy of 78.8%. • The combination of relaxation time with clinical variables and/or structural MRI abnormalities improved predictive performance of adverse outcomes. • Synthetic relaxometry performed during the neonatal period helps predict adverse neurodevelopmental outcome in premature infants.

Clinical adaptation of synthetic MRI-based whole brain volume segmentation in children at 3 T: comparison with modified SPM segmentation methods

PURPOSE

To validate the use of synthetic magnetic resonance imaging (SyMRI) volumetry by comparing with child-optimized SPM 12 volumetry in 3 T pediatric neuroimaging.

METHODS

In total, 106 children aged 4.7-18.7 years who underwent both synthetic and 3D T1-weighted imaging and had no abnormal imaging/neurologic findings were included for the SyMRI vs. SPM T1-only segmentation (SPM T1). Forty of the 106 children who underwent an additional 3D T2-weighted imaging were included for the SyMRI vs. SPM multispectral segmentation (SPM multi). SPM segmentation using an age-appropriate atlas and inverse-transforming template-space intracranial mask was compared with SyMRI segmentation. Volume differences between SyMRI and SPM T1 were plotted against age to evaluate the influence of age on volume difference.

RESULTS

Measurements derived from SyMRI and two SPM methods showed excellent agreements and strong correlations except for the CSF volume (CSFV) (intraclass correlation coefficients = 0.87-0.98; r = 0.78-0.96; relative volume difference other than CSFV = 6.8-18.5% [SyMRI vs. SPM T1] and 11.3-22.7% [SyMRI vs. SPM multi]). Dice coefficients of all brain tissues (except CSF) were in the range 0.78-0.91. The Bland-Altman plot and age-related volume difference change suggested that the volume differences between the two methods were influenced by the volume of each brain tissue and subject's age (p < 0.05).

CONCLUSION

SyMRI and SPM segmentation results were consistent except for CSFV, which supports routine clinical use of SyMRI-based volumetry in pediatric neuroimaging. However, caution should be taken in the interpretation of the CSF segmentation results.

Improved white matter integrity after contralateral seventh cervical nerve transfer measured by tractographic representation

Contralateral C7 (CC7) nerve transfer surgery was shown to significantly improve the spasticity condition and the motor function of paralyzed arms. However, the involvement of the white matter tract in the recovery process is not well established. We here investigated the possible biologic explanation for this phenomenon. A 62-year-old female patient, who suffered from spastic hemiparesis due to intracranial hemorrhage, underwent CC7 transfer surgery 13 years after the initial stroke event. Six months after the surgery, the patient's Modified Ashworth Scale and Fugl-Myere score improved, even though no specific rehabilitation programs were applied. Diffusion tensor imaging (DTI) was performed before and 6 months after the surgery. The pre-surgery DTI showed both ipsilesional and contralesional CST from the cerebral peduncles to the cortices. After surgery, however, only the contralesional CST was observed. In conclusion, functional alterations of the brain white matter tract after CC7 nerve transfer surgery possibly provided a neurophysiological substrate for ameliorating the spasticity and improving the motor function in a spastic hemiplegia patient.

CT window trainable neural network for improving intracranial hemorrhage detection by combining multiple settings

Window settings to rescale and contrast stretch raw data from radiographic images such as Computed Tomography (CT), X-ray and Magnetic Resonance images is a crucial step as data pre-processing to examine abnormalities and diagnose diseases. We propose a distant-supervised method for determining automatically the best window settings by attaching a window estimator module (WEM) to a deep convolutional neural network (DCNN)-based lesion classifier and training them in conjunction. Aside from predicting a flexible window setting for each raw image, we statistically identify the top four window settings by calculating the mean and standard deviations for the entire dataset. Images are scaled on each of the top settings estimated by WEM and following lesion classifiers are subsequently trained. We study the effects of only using the flexible window, the single fixed window as either a known default window used by radiologists or an estimated mean value, and two different approaches to combine results from the top window settings to improve the detection of intracranial hemorrhage (ICH) from brain CT images. Experimental results showed that using the top four window settings identified from the window estimator module and combining the results had the best performance.