Image quality versus outcomes

Assessing the utility of low resolution brain imaging: treatment of infant hydrocephalus

As low-field MRI technology is being disseminated into clinical settings around the world, it is important to assess the image quality required to properly diagnose and treat a given disease and evaluate the role of machine learning algorithms, such as deep learning, in the enhancement of lower quality images. In this post hoc analysis of an ongoing randomized clinical trial, we assessed the diagnostic utility of reduced-quality and deep learning enhanced images for hydrocephalus treatment planning. CT images of post-infectious infant hydrocephalus were degraded in terms of spatial resolution, noise, and contrast between brain and CSF and enhanced using deep learning algorithms. Both degraded and enhanced images were presented to three experienced pediatric neurosurgeons accustomed to working in low- to middle-income countries (LMIC) for assessment of clinical utility in treatment planning for hydrocephalus. In addition, enhanced images were presented alongside their ground-truth CT counterparts in order to assess whether reconstruction errors caused by the deep learning enhancement routine were acceptable to the evaluators. Results indicate that image resolution and contrast-to-noise ratio between brain and CSF predict the likelihood of an image being characterized as useful for hydrocephalus treatment planning. Deep learning enhancement substantially increases contrast-to-noise ratio improving the apparent likelihood of the image being useful; however, deep learning enhancement introduces structural errors which create a substantial risk of misleading clinical interpretation. We find that images with lower quality than is customarily acceptable can be useful for hydrocephalus treatment planning. Moreover, low quality images may be preferable to images enhanced with deep learning, since they do not introduce the risk of misleading information which could misguide treatment decisions. These findings advocate for new standards in assessing acceptable image quality for clinical use.

Minimum Field Strength Simulator for Proton Density Weighted MRI

OBJECTIVE

To develop and evaluate a framework for simulating low-field proton-density weighted MRI acquisitions based on high-field acquisitions, which could be used to predict the minimum B0 field strength requirements for MRI techniques. This framework would be particularly useful in the evaluation of de-noising and constrained reconstruction techniques.

MATERIALS AND METHODS

Given MRI raw data, lower field MRI acquisitions can be simulated based on the signal and noise scaling with field strength. Certain assumptions are imposed for the simulation and their validity is discussed. A validation experiment was performed using a standard resolution phantom imaged at 0.35 T, 1.5 T, 3 T, and 7 T. This framework was then applied to two sample proton-density weighted MRI applications that demonstrated estimation of minimum field strength requirements: real-time upper airway imaging and liver proton-density fat fraction measurement.

RESULTS

The phantom experiment showed good agreement between simulated and measured images. The SNR difference between simulated and measured was ≤ 8% for the 1.5T, 3T, and 7T cases which utilized scanners with the same geometry and from the same vendor. The measured SNR at 0.35T was 1.8- to 2.5-fold less than predicted likely due to unaccounted differences in the RF receive chain. The predicted minimum field strength requirements for the two sample applications were 0.2 T and 0.3 T, respectively.

CONCLUSIONS

Under certain assumptions, low-field MRI acquisitions can be simulated from high-field MRI data. This enables prediction of the minimum field strength requirements for a broad range of MRI techniques.

Signal-to-noise ratio-enhancing joint reconstruction for improved diffusion imaging of mouse spinal cord white matter injury

PURPOSE

To assess the capability of signal-to-noise ratio enhancing reconstruction (SER) to reduce the acquisition time for quantitative white matter injury assessment.

METHODS

Four single-average diffusion tensor imaging (DTI) datasets were acquired for each animal from four mouse cohorts: two models of spinal cord injury and two control groups. Quantitative parameters (apparent diffusion coefficient, relative anisotropy, axial and radial diffusivities) were computed from (I) single-average data with traditional reconstruction; (II) single-average data with SER; (III) four-average data with traditional reconstruction; and (IV) single-average data with optimized multicomponent nonlocal means (OMNLM) denoising. These approaches were compared based on coefficients of variation (COVs) and whether estimated diffusion parameters were sensitive to injury.

RESULTS

SER yielded better COVs for diffusivity and anisotropy than traditional reconstruction of single-average data, and yielded comparable COVs to that achieved with four-average data. In addition, diffusion parameters obtained using SER with single-average data had comparable injury sensitivity to those obtained from four-average data, while diffusion parameters obtained from OMNLM and traditional reconstruction of single-average data had limited sensitivity.

CONCLUSION

A four-fold reduction in the number of averages for quantitative diffusion imaging of small animal white matter injury is feasible using SER. Our results also underscore the need to validate nonlinear methods using task-based measures on an application-by-application basis.