Combining multimodal magnetic resonance brain imaging and machine learning to unravel neurocognitive function in non-neuropsychiatric systemic lupus erythematosus.

OBJECTIVE: To study whether multimodal brain MRI comprising permeability and perfusion measures coupled with machine learning can predict neurocognitive function in young patients with SLE without neuropsychiatric manifestations. METHODS: SLE patients and healthy controls (HCs) (≤40 years of age) underwent multimodal structural brain MRI that comprised voxel-based morphometry (VBM), magnetization transfer ratio (MTR) and dynamic contrast-enhanced (DCE) MRI in this cross-sectional study. Neurocognitive function assessed by Automated Neuropsychological Assessment Metrics was reported as the total throughput score (TTS). Olfactory function was assessed. A machine learning-based model (i.e. glmnet) was constructed to predict TTS. RESULTS: Thirty SLE patients and 10 HCs were studied. Both groups had comparable VBM, MTR, olfactory bulb volume (OBV), olfactory function and TTS. While after correction for multiple comparisons the uncorrected increase in the blood-brain barrier (BBB) permeability parameters compared with HCs did not remain evident in SLE patients, DCE-MRI perfusion parameters, notably an increase in right amygdala perfusion, was positively correlated with TTS in SLE patients (r = 0.636, false discovery rate P < 0.05). A machine learning-trained multimodal MRI model comprising alterations of VBM, MTR, OBV and DCE-MRI parameters mainly in the limbic system regions predicted TTS in SLE patients (r = 0.644, P < 0.0005). CONCLUSION: Multimodal brain MRI demonstrated increased right amygdala perfusion that was associated with better neurocognitive performance in young SLE patients without statistically significant BBB leakage and microstructural abnormalities. A machine learning-constructed multimodal model comprising microstructural, perfusion and permeability parameters accurately predicted neurocognitive performance in SLE patients.

Comparison of quantitative parameters and radiomic features as inputs into machine learning models to predict the Gleason score of prostate cancer lesions.

INTRODUCTION: The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification. METHODS: 20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (KTRANS), efflux rate constant (Kep), and extracellular volume ratio (Ve) from mpMR images, and SUVmean and SUVmax from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM). RESULTS: SUVmax yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input. CONCLUSIONS: ML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy.

Diffusion tensor tractography: corticospinal tract fiber reduction is associated with temporary hemiparesis in benign extracerebral lesions.

OBJECTIVE: Benign extracerebral lesions such as meningiomas may cause hemiparesis by compression and deviation without infiltrating the white matter. We used magnetic resonance diffusion tensor imaging and diffusion tensor tractography to investigate the effects of benign extracerebral lesions on the corticospinal tract (CST). METHODS: Thirteen patients with extracerebral lesions (11 benign meningiomas and 2 benign cysts) underwent magnetic resonance diffusion tensor imaging and diffusion tensor tractography of the CST using fiber assignment by continuous tractography. The CST was reconstructed and assessed by comparing the ipsilateral and unaffected contralateral fibers. The tumor volume, relative fractional anisotropy, fiber deviation, relative fiber number, and relative fiber per voxel were compared between patients without and with temporary presurgical hemiparesis. RESULTS: Seven patients without hemiparesis and five patients with temporary hemiparesis were analyzed; one patient had permanent weakness and was excluded from analysis. There was no significant difference in the tumor volume, relative fractional anisotropy, presence of cerebral edema, or CST deviation between groups. In patients with temporary hemiparesis, the median relative fiber number (mean, 0.35 +/- 0.32) and relative fiber per voxel (mean, 0.49 +/- 0.14) were significantly reduced compared with patients without hemiparesis (0.92 +/- 0.55, P = 0.04; and 0.96 +/- 0.28, P < 0.01, respectively). CONCLUSION: In patients with benign extracerebral lesions, reduction in fiber number and fiber per voxel, but not fiber deviation, correlated with temporary hemiparesis. Clinical recovery was possible even if the CST fibers detected by diffusion tensor tractography were reduced by benign extracerebral lesions.