Automated analysis of low-field brain MRI in cerebral malaria

UNITY: A low-field magnetic resonance neuroimaging initiative to characterize neurodevelopment in low and middle-income settings

Measures of physical growth, such as weight and height have long been the predominant outcomes for monitoring child health and evaluating interventional outcomes in public health studies, including those that may impact neurodevelopment. While physical growth generally reflects overall health and nutritional status, it lacks sensitivity and specificity to brain growth and developing cognitive skills and abilities. Psychometric tools, e.g., the Bayley Scales of Infant and Toddler Development, may afford more direct assessment of cognitive development but they require language translation, cultural adaptation, and population norming. Further, they are not always reliable predictors of future outcomes when assessed within the first 12-18 months of a child's life. Neuroimaging may provide more objective, sensitive, and predictive measures of neurodevelopment but tools such as magnetic resonance (MR) imaging are not readily available in many low and middle-income countries (LMICs). MRI systems that operate at lower magnetic fields (< 100mT) may offer increased accessibility, but their use for global health studies remains nascent. The UNITY project is envisaged as a global partnership to advance neuroimaging in global health studies. Here we describe the UNITY project, its goals, methods, operating procedures, and expected outcomes in characterizing neurodevelopment in sub-Saharan Africa and South Asia.

Bridging the gap: improving correspondence between low-field and high-field magnetic resonance images in young people

Background

Portable low-field-strength magnetic resonance imaging (MRI) systems represent a promising alternative to traditional high-field-strength systems with the potential to make MR technology available at scale in low-resource settings. However, lower image quality and resolution may limit the research and clinical potential of these devices. We tested two super-resolution methods to enhance image quality in a low-field MR system and compared their correspondence with images acquired from a high-field system in a sample of young people.

Methods

T1- and T2-weighted structural MR images were obtained from a low-field (64mT) Hyperfine and high-field (3T) Siemens system in N = 70 individuals (mean age = 20.39 years, range 9-26 years). We tested two super-resolution approaches to improve image correspondence between images acquired at high- and low-field: (1) processing via a convolutional neural network ('SynthSR'), and (2) multi-orientation image averaging. We extracted brain region volumes, cortical thickness, and cortical surface area estimates. We used Pearson correlations to test the correspondence between these measures, and Steiger Z tests to compare the difference in correspondence between standard imaging and super-resolution approaches.

Results

Single pairs of T1- and T2-weighted images acquired at low field showed high correspondence to high-field-strength images for estimates of total intracranial volume, surface area cortical volume, subcortical volume, and total brain volume (r range = 0.60-0.88). Correspondence was lower for cerebral white matter volume (r = 0.32, p = 0.007, q = 0.009) and non-significant for mean cortical thickness (r = -0.05, p = 0.664, q = 0.664). Processing images with SynthSR yielded significant improvements in correspondence for total brain volume, white matter volume, total surface area, subcortical volume, cortical volume, and total intracranial volume (r range = 0.85-0.97), with the exception of global mean cortical thickness (r = 0.14). An alternative multi-orientation image averaging approach improved correspondence for cerebral white matter and total brain volume. Processing with SynthSR also significantly improved correspondence across widespread regions for estimates of cortical volume, surface area and subcortical volume, as well as within isolated prefrontal and temporal regions for estimates of cortical thickness.

Conclusion

Applying super-resolution approaches to low-field imaging improves regional brain volume and surface area accuracy in young people. Finer-scale brain measurements, such as cortical thickness, remain challenging with the limited resolution of low-field systems.

MRI-Based Brain Volume Scoring in Cerebral Malaria Is Externally Valid and Applicable to Lower-Resolution Images

BACKGROUND AND PURPOSE

Children with cerebral malaria have an elevated risk of mortality and neurologic morbidity. Both mortality and morbidity are associated with initially increased brain volume on MR imaging, as graded by the Brain Volume Score, a subjective ordinal rating scale created specifically for brain MRIs in children with cerebral malaria. For the Brain Volume Score to be more widely clinically useful, we aimed to determine its independent reproducibility and whether it can be applicable to lower-resolution MRIs.

MATERIALS AND METHODS

To assess the independent reproducibility of the Brain Volume Score, radiologists not associated with the initial study were trained to score MRIs from a new cohort of patients with cerebral malaria. These scores were then compared with survival and neurologic outcomes. To assess the applicability to lower-resolution MRI, we assigned Brain Volume Scores to brain MRIs degraded to simulate a very-low-field (64 mT) portable scanner and compared these with the original scores assigned to the original nondegraded MRIs.

RESULTS

Brain Volume Scores on the new cohort of patients with cerebral malaria were highly associated with outcomes (OR for mortality = 16, P < .001). Scoring of the simulated degraded images remained consistent with the Brain Volume Scores assigned to the original higher-quality (0.35 T) images (intraclass coefficients > 0.86).

CONCLUSIONS

Our findings demonstrate that the Brain Volume Score is externally valid in reproducibly predicting outcomes and can be reliably assigned to lower-resolution images.

Prediction of malaria positivity using patients' demographic and environmental features and clinical symptoms to complement parasitological confirmation before treatment

BACKGROUND

Current malaria diagnosis methods that rely on microscopy and Histidine Rich Protein-2 (HRP2)-based rapid diagnostic tests (RDT) have drawbacks that necessitate the development of improved and complementary malaria diagnostic methods to overcome some or all these limitations. Consequently, the addition of automated detection and classification of malaria using laboratory methods can provide patients with more accurate and faster diagnosis. Therefore, this study used a machine-learning model to predict Plasmodium falciparum (Pf) antigen positivity (presence of malaria) based on sociodemographic behaviour, environment, and clinical features.

METHOD

Data from 200 Nigerian patients were used to develop predictive models using nested cross-validation and sequential backward feature selection (SBFS), with 80% of the dataset randomly selected for training and optimisation and the remaining 20% for testing the models. Outcomes were classified as Pf-positive or Pf-negative, corresponding to the presence or absence of malaria, respectively.

RESULTS

Among the three machine learning models examined, the penalised logistic regression model had the best area under the receiver operating characteristic curve for the training set (AUC = 84%; 95% confidence interval [CI]: 75-93%) and test set (AUC = 83%; 95% CI: 63-100%). Increased odds of malaria were associated with higher body weight (adjusted odds ratio (AOR) = 4.50, 95% CI: 2.27 to 8.01, p < 0.0001). Even though the association between the odds of having malaria and body temperature was not significant, patients with high body temperature had higher odds of testing positive for the Pf antigen than those who did not have high body temperature (AOR = 1.40, 95% CI: 0.99 to 1.91, p = 0.068). In addition, patients who had bushes in their surroundings (AOR = 2.60, 95% CI: 1.30 to 4.66, p = 0.006) or experienced fever (AOR = 2.10, 95% CI: 0.88 to 4.24, p = 0.099), headache (AOR = 2.07; 95% CI: 0.95 to 3.95, p = 0.068), muscle pain (AOR = 1.49; 95% CI: 0.66 to 3.39, p = 0.333), and vomiting (AOR = 2.32; 95% CI: 0.85 to 6.82, p = 0.097) were more likely to experience malaria. In contrast, decreased odds of malaria were associated with age (AOR = 0.62, 95% CI: 0.41 to 0.90, p = 0.012) and BMI (AOR = 0.47, 95% CI: 0.26 to 0.80, p = 0.006).

CONCLUSION

Newly developed routinely collected baseline sociodemographic, environmental, and clinical features to predict Pf antigen positivity may be a valuable tool for clinical decision-making.