scholarly journals Transfer Learning for Task Adaptation of Brain Lesion Assessment and Prediction of Brain Abnormalities Progression/Regression Using Irregularity Age Map in Brain MRI

2018 ◽  
pp. 85-93 ◽  
Author(s):  
Muhammad Febrian Rachmadi ◽  
Maria del C. Valdés-Hernández ◽  
Taku Komura
Keyword(s):  
Transfer Learning ◽  
Brain Mri ◽  
Brain Lesion ◽  
Brain Abnormalities ◽  
Task Adaptation

scholarly journals Transfer Learning for Task Adaptation of Brain Lesion Assessment and Prediction of Brain Abnormalities Progression/Regression using Irregularity Age Map in Brain MRI

2018 ◽  
Author(s):  
Muhammad Febrian Rachmadi ◽  
Maria del C. Valdés-Hernández ◽  
Taku Komura
Keyword(s):  
Machine Learning ◽  
White Matter ◽  
Transfer Learning ◽  
White Matter Hyperintensities ◽  
Brain Mri ◽  
Brain Lesion ◽  
Transfer Task ◽  
Mri Brain ◽  
Brain White Matter ◽  
Task Adaptation

AbstractThe Irregularity Age Map (IAM) for the unsupervised assessment of brain white matter hyperintensities (WMH) opens several opportunities in machine learning-based brain MRI analysis, including transfer task adaptation learning in the MRI brain lesion’s segmentation and prediction of lesion progression and regression. The lack of need for manual labels is useful for transfer learning. Whereas, the nature of IAM itself can be exploited for predicting lesion progression/regression. In this study, we propose the use of task adaptation transfer learning for WMH segmentation using CNN through weakly-training UNet and UResNet using the output from IAM and the use of IAM for predicting patterns of WMH progression and regression.

scholarly journals Risk factors for hip dislocation in dyskinetic cerebral palsy

2021 ◽  
Vol 29 (1) ◽  
pp. 230949902110011
Author(s):  
Kyoko Okuno ◽  
Yukihiro Kitai ◽  
Toru Shibata ◽  
Hiroshi Arai
Keyword(s):  
Risk Factors ◽  
Cerebral Palsy ◽  
Birth Weight ◽  
Gestational Age ◽  
Brain Mri ◽  
Brain Lesion ◽  
Brain Lesions ◽  
Lesion Location ◽  
Hip Displacement ◽  
Gmfcs Level

Purpose: To investigate the risk factors for hip displacement in patients with dyskinetic cerebral palsy (DCP). Methods: We evaluated 81 patients with DCP, 45 males and 36 females, aged 10–22 years, risk factors for hip displacement were evaluated using multivariate logistic regression analysis with primary brain lesions, Gross Motor Function Classification System (GMFCS) level, gestational age, birth weight, Cobb’s angle, and complication of epilepsy as independent factors. Hip displacement was defined as migration percentage >30%. Primary brain lesions were classified into globus pallidus (GP), thalamus and putamen (TP), and others using brain magnetic resonance imaging (MRI). Perinatal and clinical features were compared between patients with GP lesions and those with TP lesions. Results: Hip displacement was observed in 53 patients (67%). Higher GMFCS levels (p = 0.013, odds ratio [OR] 2.6) and the presence of GP lesions (p = 0.04, OR 16.5) were independent risk factors for hip displacement. Patients with GP lesions showed significantly higher GMFCS levels, more frequent hip displacement, and lower gestational age and birth weight than those with TP lesions. Conclusion: Primary brain lesion location may be an important factor in predicting hip displacement among patients with DCP. Appropriate risk assessment using brain MRI may contribute to the early detection and intervention of hip displacement because brain lesion location can be assessed during infancy before GMFCS level is decided.

Yield of Brain Magnetic Resonance Imaging in Epilepsy Diagnosis from 1998 to 2020: A Large Retrospective Cohort Study

2021 ◽  
Author(s):  
Tomer Stern ◽  
Liora Kornreich ◽  
Hadassa Goldberg
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Focal Epilepsy ◽  
Brain Mri ◽  
Brain Magnetic Resonance Imaging ◽  
Infantile Spasms ◽  
Mesial Temporal Sclerosis ◽  
Resonance Imaging ◽  
Brain Abnormalities ◽  
Epilepsy Diagnosis

Abstract Background We aimed to find the clinical significance of brain abnormalities on magnetic resonance imaging (MRI) in epilepsy and the lateralization of these findings with electroencephalogram (EEG). Methods We retrospectively analyzed the results of all EEGs and brain MRIs of 600 consecutive epilepsy patients from 1998 to 2020. Results Data were available for 563 cases (267 females). Ninety percent of the patients were 18 years old or younger. A total of 345 patients (61.3%) had focal epilepsy, 180 (32%), generalized, and 38 (6.7%), inconclusive. In 187 (33.2%), the first MRI was abnormal and in 81 (out of 108 repeated MRI), the second was pathological. The most frequent brain abnormalities were cortical dysplasia in 41 (18.1%), other structural abnormalities in 25 (11%), various phacomatoses in 23 (10.1%), and mesial temporal sclerosis in 17 (7.5%). Among 226 patients with abnormal MRI, 171 (75.6%) had focal epilepsy when compared with 36 (15.9%) with generalized epilepsy (p <0.001). In 121 patients (53.5%), the result of the abnormal MRI contributed significantly to the understanding of the epilepsy etiology. The side of abnormality was lateralized to the EEG focus in 120 cases (53%); in 10/15 cases with infantile spasms (66%), MRI was significantly abnormal. In 33, in whom the first MRI was normal, a second MRI revealed a significant abnormality. Conclusion Brain MRI is an important tool in epilepsy diagnosis, mainly in focal seizures and infantile spasms. A repeat MRI is mandatory in intractable focal cases to improve the yield of this test.

scholarly journals MRI phenotypes of the brain are related to future stroke and mortality in patients with manifest arterial disease: The SMART-MR study

2018 ◽  
Vol 40 (2) ◽  
pp. 354-364 ◽  
Author(s):  
Myriam G Jaarsma-Coes ◽  
Rashid Ghaznawi ◽  
Jeroen Hendrikse ◽  
Cornelis Slump ◽  
Theo D Witkamp ◽  
...  
Keyword(s):  
Clustering Analysis ◽  
Cox Regression ◽  
Reference Group ◽  
Brain Mri ◽  
Arterial Disease ◽  
Brain Abnormalities ◽  
Accurate Representation ◽  
Increased Risk ◽  
The Brain ◽  
Mr Study

Neurodegenerative and neurovascular diseases lead to heterogeneous brain abnormalities. A combined analysis of these abnormalities by phenotypes of the brain might give a more accurate representation of the underlying aetiology. We aimed to identify different MRI phenotypes of the brain and assessed the risk of future stroke and mortality within these subgroups. In 1003 patients (59 ± 10 years) from the Second Manifestations of ARTerial disease-Magnetic Resonance (SMART-MR) study, different quantitative 1.5T brain MRI markers were used in a hierarchical clustering analysis to identify 11 distinct subgroups with a different distribution in brain MRI markers and cardiovascular risk factors, and a different risk of stroke (Cox regression: from no increased risk compared to the reference group with relatively few brain abnormalities to HR = 10.34; 95% CI 3.80↔28.12 for the multi-burden subgroup) and mortality (from no increased risk compared to the reference group to HR = 4.00; 95% CI 2.50↔6.40 for the multi-burden subgroup). In conclusion, within a group of patients with manifest arterial disease, we showed that different MRI phenotypes of the brain can be identified and that these were associated with different risks of future stroke and mortality. These MRI phenotypes can possibly classify individual patients and assess their risk of future stroke and mortality.

scholarly journals Early postmortem brain MRI findings in COVID-19 non-survivors

Neurology ◽  
2020 ◽  
Vol 95 (14) ◽  
pp. e2016-e2027 ◽  
Author(s):  
Tim Coolen ◽  
Valentina Lolli ◽  
Niloufar Sadeghi ◽  
Antonin Rovai ◽  
Nicola Trotta ◽  
...  
Keyword(s):  
Respiratory Distress ◽  
Brain Mri ◽  
Postmortem Brain ◽  
Inclusion Criteria ◽  
Brain Abnormalities ◽  
Mri Findings ◽  
Olfactory Bulbs ◽  
Case Series Study ◽  
Structural Brain ◽  
Early Postmortem

ObjectivesThe severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is considered to have potential neuroinvasiveness that might lead to acute brain disorders or contribute to respiratory distress in patients with coronavirus disease 2019 (COVID-19). This study investigates the occurrence of structural brain abnormalities in non-survivors of COVID-19 in a virtopsy framework.MethodsIn this prospective, monocentric, case series study, consecutive patients who fulfilled the following inclusion criteria benefited from an early postmortem structural brain MRI: death <24 hours, SARS-CoV-2 detection on nasopharyngeal swab specimen, chest CT scan suggestive of COVID-19, absence of known focal brain lesion, and MRI compatibility.ResultsAmong the 62 patients who died of COVID-19 from March 31, 2020, to April 24, 2020, at our institution, 19 decedents fulfilled the inclusion criteria. Parenchymal brain abnormalities were observed in 4 decedents: subcortical microbleeds and macrobleeds (2 decedents), cortico-subcortical edematous changes evocative of posterior reversible encephalopathy syndrome (PRES; 1 decedent), and nonspecific deep white matter changes (1 decedent). Asymmetric olfactory bulbs were found in 4 other decedents without downstream olfactory tract abnormalities. No brainstem MRI signal abnormality was observed.ConclusionsPostmortem brain MRI demonstrates hemorrhagic and PRES-related brain lesions in non-survivors of COVID-19. SARS-CoV-2–related olfactory impairment seems to be limited to olfactory bulbs. Brainstem MRI findings do not support a brain-related contribution to respiratory distress in COVID-19.

Relevance of hypointense brain MRI lesions for long-term worsening of clinical disability in relapsing multiple sclerosis

2013 ◽  
Vol 20 (2) ◽  
pp. 214-219 ◽  
Author(s):  
Antonio Giorgio ◽  
Maria Laura Stromillo ◽  
Maria Letizia Bartolozzi ◽  
Francesca Rossi ◽  
Marco Battaglini ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Brain Mri ◽  
Univariate Analysis ◽  
Brain Lesion ◽  
Brain Magnetic Resonance Imaging ◽  
Stepwise Multiple Regression ◽  
Lesion Volume ◽  
Magnetic Resonance Imaging Mri ◽  
Relapsing Remitting Multiple Sclerosis

Background: The accrual of brain focal pathology is considered a good substrate of disability in relapsing–remitting multiple sclerosis (RRMS). However, knowledge on long-term lesion evolution and its relationship with disability progression is poor. Objective: The objective of this paper is to evaluate in RRMS the long-term clinical relevance of brain lesion evolution. Methods: In 58 RRMS patients we acquired, using the same scanner and protocol, brain magnetic resonance imaging (MRI) at baseline and 10±0.5 years later. MRI data were correlated with disability changes as measured by the Expanded Disability Status Scale (EDSS). Results: The annualized 10-year lesion volume (LV) growth was +0.25±0.5 cm3 (+6.7±8.7%) for T2-weighted (T2-W) lesions and +0.20±0.31 cm3 (+11.5±12.3%) for T1-weighted (T1-W) lesions. The univariate analysis showed moderate correlations between baseline MRI measures and EDSS at 10 years ( p < 0.001). Also, 10-year EDSS worsening correlated with LV growth and the number of new/enlarging lesions measured over the same period ( p < 0.005). In the stepwise multiple regression analysis, EDSS worsening over 10 years was best correlated with the combination of baseline T1-W lesion count and increasing T1-W LV ( R = 0.61, p < 0.001). Conclusion: In RRMS patients, long-term brain lesion accrual is associated with worsening in clinical disability. This is particularly true for hypointense, destructive lesions.

Brain metastases in patients with urothelial carcinoma.

2013 ◽  
Vol 31 (6_suppl) ◽  
pp. 282-282
Author(s):  
Helen Jane Boyle ◽  
Emilie Lavergne ◽  
Jean Pierre Droz ◽  
Nathalie Bonnin ◽  
Aude Flechon
Keyword(s):  
Brain Metastases ◽  
Urothelial Carcinoma ◽  
Metastatic Disease ◽  
Cox Model ◽  
Brain Mri ◽  
Brain Lesion ◽  
Local Treatment ◽  
Local Therapy ◽  
Initial Diagnosis ◽  
Initial Presentation

282 Background: Muscle invasive urothelial cancers are infrequent. Patients (pts) with metastatic disease have poor prognosis. Brain metastases (BM) are rare. The aim of this retrospective study is to analyse the characteristics, the treatment and the evolution of patients with BM treated in a single centre. Methods: Thirty pts with BM were identified among the 1591 pts with urothelial carcinoma seen at the Centre Léon Bérard, between 1994 and 2011. The study population was described, overall survival (OS) from diagnosis of BM was estimated by Kaplan-Meier method and prognostic factors were explored using a Cox model. Results: Twenty seven pts in our series were male. Median age at initial diagnosis was 60 years (range: 33.9-78.9 years). Twenty two pts had primary bladder tumours and 8 upper urinary tract tumours. Twenty four pts underwent surgery for their primary lesion, 2 received chemoradiotherapy and 4 did not receive any radical local treatment. Six pts had metastatic disease at initial presentation: 3 were operated on. Median delay between initial diagnosis and BM was 16.6 months (range: 0-56.4 months), 3 patients had BM at initial presentation. Median time between first metastases and BM was 10 months (range=0-52 months). Eleven patients developed BM as one of the first sites of metastases. BM were symptomatic in 28 pts: specific neurological symptoms (n=25), headaches (n=6), epilepsy (n=2). For the 2 other pts, they were discovered on a systematic brain MRI. Eighteen pts had cerebral metastases only, 5 pts had cerebellar metastases only, 6 had both; the last patient had cerebral, cerebellar and meningeal involvement. Half of the pts had only 1 brain lesion. Five pts were operated on: 4 received postoperative radiotherapy; 19 patients were given radiotherapy alone and 6 did not get any local therapy. In this series, median OS from diagnosis of BM was 3.4 months (IC95% [2.2-10.3]). Only the administration of chemotherapy after the diagnosis of BM was significantly associated with OS; probably because only fit enough patients were offered treatment. Conclusions: Prognosis of patients with urothelial carcinoma and BM is poor; however some patients have long survivals. Treatment is not codified as there is little data in the literature.

Intracerebral immunotherapy for brain tumors.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e13522-e13522
Author(s):  
Guido Carillio ◽  
Luigi Santaguida ◽  
Eugenio Donato Di Paola ◽  
Anna Maria Lavecchia ◽  
Virginia Vescio ◽  
...  
Keyword(s):  
Brain Tumors ◽  
Checkpoint Inhibitors ◽  
Brain Mri ◽  
Brain Lesion ◽  
Real Life ◽  
Convection Enhanced Delivery ◽  
Heavily Pretreated ◽  
Solitary Metastases ◽  
Frameless Biopsy

e13522 Background: Immunotherapy is a promising approach for the treatment of brain tumors, but available data are still inconclusive. The main drawback is represented by transport across the blood–brain barrier of high molecular weight drugs. Convection-enhanced delivery (CED) has been designed to overcome some difficulties. We wondered whether a CED strategy based on the use of novel immune checkpoint inhibitors could be effective. Methods: Frameless biopsy by fluorescein tracer and neuronavigation-assisted system, followed by an injection of nivolumab 40mg/4mL into the brain lesion, were offered to patients with: a) high grade gliomas (HGG) inoperable or progressed during or after standard treatment (i.e. surgery and radio-chemotherapy); b) HGG at first diagnosis or after disease progression treated with radical surgery (nivolumab delivered in the surgical cavity after tumor removal); c) other brain tumors or solitary metastases judged suitable for surgical procedure. PD-L1 expression was assessed in all patients, but it was not a strict criterion for accrual. Standard therapy, usually based on chemotherapy, radiotherapy or both, was sequentially administered to patients able to tolerate such an approach. End-points were safety, response rate, disease control, predictive value of PD-L1 expression. This is a non-sponsored monocentric, real life, basket trial approved by Ethical Committee (EudraCT number: 2018-001560-33). Results: Since August 2018, 17 patients with brain tumors (16 HGG and 1 heavily pretreated medulloblastoma) and 5 patients with brain metastasis (of lung and gastrointestinal cancers) were enrolled. Median age was 63 years (range 26-83). After a median follow up of three months (range 1-6), all patients are alive and in good clinical conditions. No signs of neurologic toxicity due to intracerebral nivolumab were observed. Brain MRI performed at 4 to 12 weeks after nivolumab CED revealed findings suggesting a perivascular lymphocyte infiltration. Correlation between PD-L1 expression and treatment efficacy will be evaluated over time. Conclusions: Intracerebral nivolumab appears to be a feasible and safe option for patients with HGG and brain metastases at the dose investigated in the study. Long-term follow up could contribute to well understand the role of this strategy. Clinical trial information: 2018-001560-33.

scholarly journals Brain MRI in SARS-CoV-2 pneumonia patients with newly developed neurological manifestations suggestive of brain involvement

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Batil Alonazi ◽  
Ahmed M. Farghaly ◽  
Mohamed A. Mostafa ◽  
Jehad A. Al-Watban ◽  
Salah A. Zindani ◽  
...  
Keyword(s):  
Imaging Modality ◽  
Brain Mri ◽  
Brain Lesion ◽  
Brain Magnetic Resonance Imaging ◽  
Neurological Manifestations ◽  
Rt Pcr ◽  
Significant Difference ◽  
Brain Involvement ◽  
Magnetic Resonance Imaging Mri ◽  
The Impact

AbstractThe increased frequency of neurological manifestations, including central nervous system (CNS) manifestations, in patients with coronavirus disease 2019 (COVID-19) pandemic is consistent with the virus's neurotropic nature. In most patients, brain magnetic resonance imaging (MRI) is a sensitive imaging modality in the diagnosis of viral encephalitides in the brain. The purpose of this study was to determine the frequency of brain lesion patterns on brain MRI in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pneumonia patients who developed focal and non-focal neurological manifestations. In addition, it will compare the impact of the Glasgow Coma Scale (GCS) as an index of deteriorating cerebral function on positive brain MRIs in both neurological manifestations. This retrospective study included an examination of SARS-CoV-2 pneumonia patients with real-time reverse transcription polymerase chain reaction (RT-PCR) confirmation, admitted with clinicoradiologic evidence of COVID-19 pneumonia, and who were candidates for brain MRI due to neurological manifestations suggesting brain involvement. Brain imaging acquired on a 3.0 T MRI system (Skyra; Siemens, Erlangen, Germany) with a 20-channel receive head coil. Brain MRI revealed lesions in 38 (82.6%) of the total 46 patients for analysis and was negative in the remaining eight (17.4%) of all finally enclosed patients with RT-PCR confirmed SARS-CoV-2 pneumonia. Twenty-nine (63%) patients had focal neurological manifestations, while the remaining 17 (37%) patients had non-focal neurological manifestations. The patients had a highly significant difference (p = 0.0006) in GCS, but no significant difference (p = 0.4) in the number of comorbidities they had. Brain MRI is a feasible and important imaging modality in patients with SARS-CoV-2 pneumonia who develop neurological manifestations suggestive of brain involvement, particularly in patients with non-focal manifestations and a decline in GCS.

Sign in / Sign up

Export Citation Format

Share Document