Objectives
To investigate the clinical meaning of brain parenchymal computed-tomography hyperdensities (CTHD) in patients treated of anterior circulation acute stroke with reperfusion therapy.
...Methods
Patients were retrospectively enrolled from three different hospitals. Brain CT scans were assessed at four time points: We recorded ASPECT scores of pre-treatment CTs, assessed ASPECT scores and the presence of CTHD on post-treatment CTs acquired within 24–30 h and 24–72 h, and examined a one-month CTs follow-up to determine the ischemic evolution of CTHD. We correlated the presence of CTHD with clinical and radiological data to define its predictive and prognostic factors.
Results
In total, 165 patients were evaluated. At post-treatment CTs acquired within 24–30 h, 68 (41%) patients showed the presence of CTHD. On post-treatment CTs acquired within 24–72 h, 43 (63%) of the CTHD showed hemorrhagic transformation. Sixty-five (95%) out of the 68 CTHD evolved in a final ischemic brain area. Multivariate statistical analysis identified puncture to recanalization time to be the only independent factors predicting the presence of CTHD (
p
= 0.045). The presence of CTHD at the first post-treatment CTs was an independent factor for clinical outcome determined with mRS scores at 3-month follow-up (
p
= 0.05). Outcomes were worse for hemorrhagic transformation at follow-up CTs compared to the ischemic evolution of the CTHD (
p
= 0.01).
Conclusions
The presence of CTHD at CTs imaging acquired within 24–30 h after reperfusion therapy is an independent prognostic factor of a worse clinical outcome, regardless of its ASPECT score at baseline CTs and of its hemorrhagic evolution.
Background
Tumor heterogeneity poses major clinical challenges in high-grade gliomas (HGGs). Quantitative radiomic analysis with spatial tumor habitat clustering represents an innovative, ...non-invasive approach to represent and quantify tumor microenvironment heterogeneity. To date, habitat imaging has been applied mainly on conventional magnetic resonance imaging (MRI), although virtually extendible to any imaging modality, including advanced MRI techniques such as perfusion and diffusion MRI as well as positron emission tomography (PET) imaging.
Objectives
This study aims to evaluate an innovative PET and MRI approach for assessing hypoxia, perfusion, and tissue diffusion in HGGs and derive a combined map for clustering of intra-tumor heterogeneity.
Materials and Methods
Seventeen patients harboring HGGs underwent a pre-operative acquisition of MR perfusion (PWI), Diffusion (dMRI) and
18
F-labeled fluoroazomycinarabinoside (
18
F-FAZA) PET imaging to evaluate tumor vascularization, cellularity, and hypoxia, respectively. Tumor volumes were segmented on fluid-attenuated inversion recovery (FLAIR) and T1 post-contrast images, and voxel-wise clustering of each quantitative imaging map identified eight combined PET and physiologic MRI habitats. Habitats’ spatial distribution, quantitative features and histopathological characteristics were analyzed.
Results
A highly reproducible distribution pattern of the clusters was observed among different cases, particularly with respect to morphological landmarks as the necrotic core, contrast-enhancing vital tumor, and peritumoral infiltration and edema, providing valuable supplementary information to conventional imaging. A preliminary analysis, performed on stereotactic bioptic samples where exact intracranial coordinates were available, identified a reliable correlation between the expected microenvironment of the different spatial habitats and the actual histopathological features. A trend toward a higher representation of the most aggressive clusters in WHO (World Health Organization) grade IV compared to WHO III was observed.
Conclusion
Preliminary findings demonstrated high reproducibility of the PET and MRI hypoxia, perfusion, and tissue diffusion spatial habitat maps and correlation with disease-specific histopathological features.
Combining MRI techniques with machine learning methodology is rapidly gaining attention as a promising method for staging of brain gliomas. This study assesses the diagnostic value of such a ...framework applied to dynamic susceptibility contrast (DSC)-MRI in classifying treatment-naïve gliomas from a multi-center patients into WHO grades II-IV and across their isocitrate dehydrogenase (IDH) mutation status.
Three hundred thirty-three patients from 6 tertiary centres, diagnosed histologically and molecularly with primary gliomas (IDH-mutant = 151 or IDH-wildtype = 182) were retrospectively identified. Raw DSC-MRI data was post-processed for normalised leakage-corrected relative cerebral blood volume (rCBV) maps. Shape, intensity distribution (histogram) and rotational invariant Haralick texture features over the tumour mask were extracted. Differences in extracted features across glioma grades and mutation status were tested using the Wilcoxon two-sample test. A random-forest algorithm was employed (2-fold cross-validation, 250 repeats) to predict grades or mutation status using the extracted features.
Shape, distribution and texture features showed significant differences across mutation status. WHO grade II-III differentiation was mostly driven by shape features while texture and intensity feature were more relevant for the III-IV separation. Increased number of features became significant when differentiating grades further apart from one another. Gliomas were correctly stratified by mutation status in 71% and by grade in 53% of the cases (87% of the gliomas grades predicted with distance less than 1).
Despite large heterogeneity in the multi-center dataset, machine learning assisted DSC-MRI radiomics hold potential to address the inherent variability and presents a promising approach for non-invasive glioma molecular subtyping and grading.
Background
Contrast-enhanced magnetic resonance angiography (CE-MRA) has become a very popular imaging technique in the evaluation of the extracranial vessels pathology, while it is not commonly used ...to rule out intracranial vascular pathology. On the contrary, 3D time of flight MRA (TOF-MRA) has a solid role in the study of intracranial arterial vessels disease.
Materials and methods
One hundred and eight patients were consecutively included in the study. All patients were submitted to a 3 Tesla 3D CE-MRA imaging to rule out extracranial vessels pathology. A comparison was made with a 3D-TOF sequence acquired at the same time in the assessment of intracranial vessels diseases such as steno-occlusion, dissection, and aneurysms.
Results
With regard to steno-occlusive disease, Spearman’s rank correlation coefficient was of 0.56 for stenosis detection and of 0.57 for occlusive disease detection. The two techniques shared similar results in the evaluation of anterior circulation, while 3D-TOF found higher grades of stenosis for posterior circulation. With regard to dissection, Spearman’s rank correlation coefficient was of 0.7. 3D-TOF depicted more intramural hematoma (Spearman’s rank = 0.46), while CE-MRA showed more pseudo-aneurysms (Spearman’s rank = 0.56). Both the technique equally evaluated the presence of intracranial aneurysms (Spearman’s rank = 1).
Conclusion
CE-MRA can be considered a reliable tool to rule out intracranial pathology associated to supraortic steno-occlusive disease, also allowing time reduction. In the suspicion of dissection a T1-weighted sequence has to be added to detect the presence of a subacute vessel wall hematoma.
Alzheimer disease (AD) and vascular dementia (VaD) together represent the majority of dementia cases. Since their neuropsychological profiles often overlap and white matter lesions are observed in ...elderly subjects including AD, differentiating between VaD and AD can be difficult. Characterization of these different forms of dementia would benefit by identification of quantitative imaging biomarkers specifically sensitive to AD or VaD. Parameters of microstructural abnormalities derived from diffusion tensor imaging (DTI) have been reported to be helpful in differentiating between dementias, but only few studies have used them to compare AD and VaD with a voxelwise approach. Therefore, in this study a whole brain statistical analysis was performed on DTI data of 93 subjects (31 AD, 27 VaD, and 35 healthy controls-HC) to identify specific white matter patterns of alteration in patients affected by VaD and AD with respect to HC. Parahippocampal tracts were found to be mainly affected in AD, while VaD showed more spread white matter damages associated with thalamic radiations involvement. The genu of the corpus callosum was predominantly affected in VaD, while the splenium was predominantly affected in AD revealing the existence of specific patterns of alteration useful in distinguishing between VaD and AD. Therefore, DTI parameters of these regions could be informative to understand the pathogenesis and support the etiological diagnosis of dementia. Further studies on larger cohorts of subjects, characterized for brain amyloidosis, will allow to confirm and to integrate the present findings and, furthermore, to elucidate the mechanisms of mixed dementia. These steps will be essential to translate these advances to clinical practice.
Purpose
Primary central nervous system lymphoma (PCNSL) is a rare, aggressive form of extranodal non-Hodgkin lymphoma. To predict the overall survival (OS) in advance is of utmost importance as it ...has the potential to aid clinical decision-making. Though radiomics-based machine learning (ML) has demonstrated the promising performance in PCNSL, it demands large amounts of manual feature extraction efforts from magnetic resonance images beforehand. deep learning (DL) overcomes this limitation.
Methods
In this paper, we tailored the 3D ResNet to predict the OS of patients with PCNSL. To overcome the limitation of data sparsity, we introduced data augmentation and transfer learning, and we evaluated the results using
r
stratified
k
-fold cross-validation. To explain the results of our model, gradient-weighted class activation mapping was applied.
Results
We obtained the best performance (the standard error) on post-contrast T1-weighted (T1Gd)—area under curve
=
0.81
(
0.03
)
, accuracy
=
0.87
(
0.07
)
, precision
=
0.88
(
0.07
)
, recall
=
0.88
(
0.07
)
and
F
1-score
=
0.87
(
0.07
)
, while compared with ML-based models on clinical data and radiomics data, respectively, further confirming the stability of our model. Also, we observed that PCNSL is a whole-brain disease and in the cases where the OS is less than 1 year, it is more difficult to distinguish the tumor boundary from the normal part of the brain, which is consistent with the clinical outcome.
Conclusions
All these findings indicate that T1Gd can improve prognosis predictions of patients with PCNSL. To the best of our knowledge, this is the first time to use DL to explain model patterns in OS classification of patients with PCNSL. Future work would involve collecting more data of patients with PCNSL, or additional retrospective studies on different patient populations with rare diseases, to further promote the clinical role of our model.
To describe high-resolution brain vessel wall MRI (VW-MRI) patterns and morphological brain findings in central nervous system (CNS) vasculitis patients.
Fourteen patients with confirmed CNS ...Vasculitis from two tertiary centers underwent VW-MRI using a 3T scanner. The images were reviewed by two neuroradiologists to assess vessel wall enhancement characteristics and locations.
Fourteen patients were included (six females; average age 48 ± 19 years). Diagnoses included primary CNS vasculitis (PCNSV) in six patients and secondary CNS vasculitis (SCNSV) in eight, half of which were infection-related. Thirteen patients showed vessel wall enhancement, which was intense in eleven patients (84.6%) and concentric in twelve (92.3%), affecting the anterior circulation in nine patients (69.2%), posterior in two patients (15.4%), and both circulations in two patients (15.4%). The enhancement patterns were similar across different CNS vasculitis types. DWI changes corresponded with areas of vessel wall enhancement in 77% of patients. Conclusions
CNS vasculitis is often associated with intense, concentric vessel wall enhancement in VW-MRI, especially in the anterior circulation. The consistent presence of DWI alterations in affected territories suggests a possible link to microembolization or hypoperfusion. These imaging findings complement parenchymal brain MRI and MRA/DSA data, potentially increasing the possibility of a clinical diagnosis of CNS vasculitis.
Primary Central Nervous System Lymphoma (PCNSL) is an aggressive neoplasm with a poor prognosis. Although therapeutic progresses have significantly improved Overall Survival (OS), a number of ...patients do not respond to HD-MTX-based chemotherapy (15-25%) or experience relapse (25-50%) after an initial response. The reasons underlying this poor response to therapy are unknown. Thus, there is an urgent need to develop improved predictive models for PCNSL. In this study, we investigated whether radiomics features can improve outcome prediction in patients with PCNSL. A total of 80 patients diagnosed with PCNSL were enrolled. A patient sub-group, with complete Magnetic Resonance Imaging (MRI) series, were selected for the stratification analysis. Following radiomics feature extraction and selection, different Machine Learning (ML) models were tested for OS and Progression-free Survival (PFS) prediction. To assess the stability of the selected features, images from 23 patients scanned at three different time points were used to compute the Interclass Correlation Coefficient (ICC) and to evaluate the reproducibility of each feature for both original and normalized images. Features extracted from Z-score normalized images were significantly more stable than those extracted from non-normalized images with an improvement of about 38% on average (
-value < 10-12). The area under the ROC curve (AUC) showed that radiomics-based prediction overcame prediction based on current clinical prognostic factors with an improvement of 23% for OS and 50% for PFS, respectively. These results indicate that radiomics features extracted from normalized MR images can improve prognosis stratification of PCNSL patients and pave the way for further study on its potential role to drive treatment choice.