Advanced Analysis of Diffusion Tensor Imaging Along With Machine Learning Provides New Sensitive Measures of Tissue Pathology and Intra-Lesion Activity in Multiple Sclerosis

Can machine learning models improve early detection of brain metastases using diffusion weighted imaging-based radiomics?

Background

Metastatic complications are a major cause of cancer-related morbidity, with up to 40% of cancer patients experiencing at least one brain metastasis. Earlier detection may significantly improve patient outcomes and overall survival. We investigated machine learning (ML) models for early detection of brain metastases based on diffusion weighted imaging (DWI) radiomics.

Methods

Longitudinal diffusion imaging from 116 patients previously treated with stereotactic radiosurgery (SRS) for brain metastases were retrospectively analyzed. Clinical contours from 600 metastases were extracted from radiosurgery planning computed tomography, and rigidly registered to corresponding contrast enhanced-T1 and apparent diffusion coefficient (ADC) maps. Contralateral contours located in healthy brain tissue were used as control. The dataset consisted of (I) radiomic features using ADC maps, (II) radiomic feature change calculated using timepoints before the metastasis manifested on contrast enhanced-T1, (III) primary cancer, and (IV) anatomical location. The dataset was divided into training and internal validation sets using an 80/20 split with stratification. Four classification algorithms [Linear Support Vector Machine (SVM), Random Forest (RF), AdaBoost, and XGBoost] underwent supervised classification training, with contours labeled either 'control' or 'metastasis'. Hyperparameters were optimized towards balanced accuracy. Various model metrics (receiver operating characteristic curve area scores, accuracy, recall, and precision) were calculated to gauge performance.

Results

The radiomic and clinical data set, feature engineering, and ML models developed were able to identify metastases with an accuracy of up to 87.7% on the training set, and 85.8% on an unseen test set. XGBoost and RF showed superior accuracy (XGBoost: 0.877±0.021 and 0.833±0.47, RF: 0.823±0.024 and 0.858±0.045) for training and validation sets, respectively. XGBoost and RF also showed strong area under the receiver operating characteristic curve (AUC) performance on the validation set (0.910±0.037 and 0.922±0.034, respectively). AdaBoost performed slightly lower in all metrics. SVM model generalized poorly with the internal validation set. Important features involved changes in radiomics months before manifesting on contrast enhanced-T1.

Conclusions

The proposed models using diffusion-based radiomics showed encouraging results in differentiating healthy brain tissue from metastases using clinical imaging data. These findings suggest that longitudinal diffusion imaging and ML may help improve patient care through earlier diagnosis and increased patient monitoring/follow-up. Future work aims to improve model classification metrics, robustness, user-interface, and clinical applicability.

Distinct characteristics and severity of brain magnetic resonance imaging lesions in women and men with multiple sclerosis assessed using verified texture analysis measures

Background and goal

In vivo characterization of brain lesion types in multiple sclerosis (MS) has been an ongoing challenge. Based on verified texture analysis measures from clinical magnetic resonance imaging (MRI), this study aimed to develop a method to identify two extremes of brain MS lesions that were approximately severely demyelinated (sDEM) and highly remyelinated (hREM), and compare them in terms of common clinical variables.

Method

Texture analysis used an optimized gray-level co-occurrence matrix (GLCM) method based on FLAIR MRI from 200 relapsing-remitting MS participants. Two top-performing metrics were calculated: texture contrast and dissimilarity. Lesion identification applied a percentile approach according to texture values calculated: ≤ 25 percentile for hREM and ≥75 percentile for sDEM.

Results

The sDEM had a greater total normalized volume yet smaller average size, and worse MRI texture than hREM. In lesion distribution mapping, the two lesion types appeared to overlap largely in location and were present the most in the corpus callosum and periventricular regions. Further, in sDEM, the normalized volume was greater and in hREM, the average size was smaller in men than women. There were no other significant results in clinical variable-associated analyses.

Conclusion

Percentile statistics of competitive MRI texture measures may be a promising method for probing select types of brain MS lesion pathology. Associated findings can provide another useful dimension for improved measurement and monitoring of disease activity in MS. The different characteristics of sDEM and hREM between men and women likely adds new information to the literature, deserving further confirmation.

Cortical lesions, central vein sign, and paramagnetic rim lesions in multiple sclerosis: Emerging machine learning techniques and future avenues

The current diagnostic criteria for multiple sclerosis (MS) lack specificity, and this may lead to misdiagnosis, which remains an issue in present-day clinical practice. In addition, conventional biomarkers only moderately correlate with MS disease progression. Recently, some MS lesional imaging biomarkers such as cortical lesions (CL), the central vein sign (CVS), and paramagnetic rim lesions (PRL), visible in specialized magnetic resonance imaging (MRI) sequences, have shown higher specificity in differential diagnosis. Moreover, studies have shown that CL and PRL are potential prognostic biomarkers, the former correlating with cognitive impairments and the latter with early disability progression. As machine learning-based methods have achieved extraordinary performance in the assessment of conventional imaging biomarkers, such as white matter lesion segmentation, several automated or semi-automated methods have been proposed as well for CL, PRL, and CVS. In the present review, we first introduce these MS biomarkers and their imaging methods. Subsequently, we describe the corresponding machine learning-based methods that were proposed to tackle these clinical questions, putting them into context with respect to the challenges they are facing, including non-standardized MRI protocols, limited datasets, and moderate inter-rater variability. We conclude by presenting the current limitations that prevent their broader deployment and suggesting future research directions.

Advanced diffusion MRI and image texture analysis detect widespread brain structural differences between relapsing-remitting and secondary progressive multiple sclerosis

Introduction

Disease development in multiple sclerosis (MS) causes dramatic structural changes, but the exact changing patterns are unclear. Our objective is to investigate the differences in brain structure locally and spatially between relapsing-remitting MS (RRMS) and its advanced form, secondary progressive MS (SPMS), through advanced analysis of diffusion magnetic resonance imaging (MRI) and image texture.

Methods

A total of 20 patients with RRMS and nine patients with SPMS from two datasets underwent 3T anatomical and diffusion tensor imaging (DTI). The DTI was harmonized, augmented, and then modeled, which generated six voxel- and sub-voxel-scale measures. Texture analysis focused on T2 and FLAIR MRI, which produced two phase-based measures, namely, phase congruency and weighted mean phase. Data analysis was 3-fold, i.e., histogram analysis of whole-brain normal appearing white matter (NAWM); region of interest (ROI) analysis of NAWM and lesions within three critical white matter tracts, namely, corpus callosum, corticospinal tract, and optic radiation; and along-tract statistics. Furthermore, by calculating the z-score of core-rim pathology within lesions based on diffusion measures, we developed a novel method to define chronic active lesions and compared them between cohorts.

Results

Histogram features from diffusion and all but one texture measure differentiated between RRMS and SPMS. Within-tract ROI analysis detected cohort differences in both NAWM and lesions of the corpus callosum body in three measures of neurite orientation and anisotropy. Along-tract statistics detected cohort differences from multiple measures, particularly lesion extent, which increased significantly in SPMS in posterior corpus callosum and optic radiations. The number of chronic active lesions were also significantly higher (by 5-20% over z-scores 0.5 and 1.0) in SPMS than RRMS based on diffusion anisotropy, neurite content, and diameter.

Conclusion

Advanced diffusion MRI and texture analysis may be promising approaches for thorough understanding of brain structural changes from RRMS to SPMS, thereby providing new insight into disease development mechanisms in MS.

MAGNIMS recommendations for harmonization of MRI data in MS multicenter studies

•

Sharing data from cooperative studies is essential to develop new biomarkers in MS.

•

Differences in MRI acquisition, analysis, storage represent a substantial constraint.

•

We review the state of the art and developments in the harmonization of MRI.

•

We provide recommendations to harmonize large MRI datasets in the MS field.

There is an increasing need of sharing harmonized data from large, cooperative studies as this is essential to develop new diagnostic and prognostic biomarkers. In the field of multiple sclerosis (MS), the issue has become of paramount importance due to the need to translate into the clinical setting some of the most recent MRI achievements. However, differences in MRI acquisition parameters, image analysis and data storage across sites, with their potential bias, represent a substantial constraint. This review focuses on the state of the art, recent technical advances, and desirable future developments of the harmonization of acquisition, analysis and storage of large-scale multicentre MRI data of MS cohorts. Huge efforts are currently being made to achieve all the requirements needed to provide harmonized MRI datasets in the MS field, as proper management of large imaging datasets is one of our greatest opportunities and challenges in the coming years. Recommendations based on these achievements will be provided here. Despite the advances that have been made, the complexity of these tasks requires further research by specialized academical centres, with dedicated technical and human resources. Such collective efforts involving different professional figures are of crucial importance to offer to MS patients a personalised management while minimizing consumption of resources.

Altered regional brain white matter in dry eye patients: a brain imaging study

This study aimed to investigate the regional changes of brain white matter (WM) in DE patients using diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI). A total of 25 dry eye patients (PAT) and 25 healthy controls (HC) were recruited. All subjects underwent DTI and NODDI, fractional anisotropy (FA), mean diffusivity (MD), radial diffusivity (RD), isotropic volume fraction (FISO), intra-cellular volume fraction (FICVF), and orientation dispersion index (ODI) were obtained respectively. Then complete Hospital Anxiety and Depression Scale (HADS), anxiety score (AS) or depression scores (DS) were obtained. Receiver operating characteristic (ROC) curve analysis was used to evaluate the reliability of DTI and NODDI in distinguishing the two groups. DTI revealed that PAT had lower FA in both the left superior longitudinal fasciculus (LSLF) and the corpus callosum (CC), and higher MD in the LSLF, the right posterior limb of the internal capsule and the right posterior thalamic radiation. PAT had significant AD changes in regions including the genu of the CC, the right posterior limb of internal capsule, and the right splenium of the CC. From NODDI, PAT showed increased ODI in the LSLF and increased FISO in the right splenium of the CC. FICVF showed a significant decrease in the LSLF while increased in the left anterior corona radiata and the CC. Furthermore, the average values of MD and FICVF were significantly correlated with DS and AS. Hence the results of this study suggest that there are regional changes in WM in DE patients which may contribute to further understanding of the pathological mechanism of DE.

Advanced Diffusion MR Imaging for Multiple Sclerosis in the Brain and Spinal Cord

Diffusion tensor imaging (DTI) has been established its usefulness in evaluating normal-appearing white matter (NAWM) and other lesions that are difficult to evaluate with routine clinical MRI in the evaluation of the brain and spinal cord lesions in multiple sclerosis (MS), a demyelinating disease. With the recent advances in the software and hardware of MRI systems, increasingly complex and sophisticated MRI and analysis methods, such as q-space imaging, diffusional kurtosis imaging, neurite orientation dispersion and density imaging, white matter tract integrity, and multiple diffusion encoding, referred to as advanced diffusion MRI, have been proposed. These are capable of capturing in vivo microstructural changes in the brain and spinal cord in normal and pathological states in greater detail than DTI.

This paper reviews the current status of recent advanced diffusion MRI for assessing MS in vivo as part of an issue celebrating two decades of magnetic resonance in medical sciences (MRMS), an official journal of the Japanese Society of Magnetic Resonance in Medicine.