Automated algorithm for counting microbleeds in patients with familial cerebral cavernous malformations

Zou, Xiaowei; Hart, Blaine L.; Mabray, Marc C.; Bartlett, Mary R.; Bian, Wei; Nelson, Jeffrey; Morrison, Leslie; McCulloch, Charles E.; Hess, Christopher P.; Lupo, Janine M.; Kim, Helen

doi:10.1007/s00234-017-1845-8

Cited by 8 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5 shows the comparison of false positives per individual as well as a comparison as per microbleeds. [28] 86.5 44.9 1.5 Dou et al [29] 89.4 7.7 0.9 Chen et al [21] 89.1 6.4 -Douh et al [23] 93.16 2.74 -Heuvel et al [30] 89 25.9 0.29 Proposed Method 99.9 1.5 -…”

Section: Resultsmentioning

confidence: 99%

An Efficient False-Positive Reduction System for Cerebral Microbleeds Detection

Afzal¹,

Maqsood²,

Mehmood³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Cerebral Microbleeds (CMBs) are microhemorrhages caused by certain abnormalities of brain vessels. CMBs can be found in people with Traumatic Brain Injury (TBI), Alzheimer's disease, and in old individuals having a brain injury. Current research reveals that CMBs can be highly dangerous for individuals having dementia and stroke. The CMBs seriously impact individuals' life which makes it crucial to recognize the CMBs in its initial phase to stop deterioration and to assist individuals to have a normal life. The existing work report good results but often ignores false-positive's perspective for this research area. In this paper, an efficient approach is presented to detect CMBs from the Susceptibility Weighted Images (SWI). The proposed framework consists of four main phases (i) making clusters of brain Magnetic Resonance Imaging (MRI) using k-mean classifier (ii) reduce false positives for better classification results (iii) discriminative feature extraction specific to CMBs (iv) classification using a five layers convolutional neural network (CNN). The proposed method is evaluated on a public dataset available for 20 subjects. The proposed system shows an accuracy of 98.9% and a 1.1% false-positive rate value. The results show the superiority of the proposed work as compared to existing states of the art methods.

show abstract

Section: Resultsmentioning

confidence: 99%

An Efficient False-Positive Reduction System for Cerebral Microbleeds Detection

Afzal¹,

Maqsood²,

Mehmood³

et al. 2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…As previously reported, there was high interobserver agreement in lesion counts (pairwise correlation >0.95) between the 2 neuroradiologists. 16 However, there are several limitations including (1) the majority of patients have the CCM1 genetic mutation, thus we are unable to assess and compare the ICH rate in those who harbor CCM2 or CCM3 genetic risk factors; (2) the small number of ICH events prohibited us from assessing additional ICH risk factors such as imaging characteristics; (3) MRI technical heterogeneity across recruitment sites may limit the assessment of accurate lesion burden particularly with respect to smaller lesions; and (4) our results may be subject to selection bias, which may affect ICH rates.…”

Section: Discussionmentioning

confidence: 99%

“…CCM lesions were manually counted to obtain counts of total and large lesions (≥5 mm at maximal diameter, defined as the greatest trans axial dimension measured on the T2‐weighted images, including the hypointense rim) as previously described. 15 , 16 Prior history of ICH and subsequent symptomatic ICH during follow‐up were reported by patients and/or documented in medical records using standard definition of symptomatic hemorrhage. 17 Not all cases were able to be verified by MRI; for example, MRIs performed at outside hospitals may have not been available for review.…”

Section: Methodsmentioning

confidence: 99%

Intracranial Hemorrhage Rate and Lesion Burden in Patients With Familial Cerebral Cavernous Malformation

Weinsheimer

Nelson

Abla

et al. 2023

JAHA

Self Cite

View full text Add to dashboard Cite

Background Familial cerebral cavernous alformation (CCM) is an autosomal dominant disease caused by mutations in KRIT1 , CCM2 , or PDCD10 . Cases typically present with multiple lesions, strong family history, and neurological symptoms, including seizures, headaches, or other deficits. Intracranial hemorrhage (ICH) is a severe manifestation of CCM, which can lead to death or long‐term neurological deficits. Few studies have reported ICH rates and risk factors in familial CCM. We report ICH rates and assess whether CCM lesion burden, a disease severity marker, is associated with risk of symptomatic ICH during follow‐up in a well‐characterized cohort of familial CCM cases. Methods and Results We studied 386 patients with familial CCM with follow‐up data enrolled in the Brain Vascular Malformation Consortium CCM Project. We estimated symptomatic ICH rates overall and stratified by history of ICH before enrollment. CCM lesion burden (total lesion count and large lesion size) assessed at baseline enrollment was tested for association with increased risk of subsequent ICH during follow‐up using Cox regression models adjusted for history of ICH before enrollment, age, sex, and family structure and stratified on recruitment site. The symptomatic ICH rate for familial CCM cases was 2.8 per 100 patient‐years (95% CI, 1.9–4.1). Those with ICH before enrollment had a follow‐up ICH rate of 4.5 per 100 patient‐years (95% CI, 2.6–8.1) compared with 2.0 per 100 patient‐years (95% CI, 1.3–3.5) in those without ( P =0.042). Total lesion count was associated with increased risk of ICH during follow‐up (hazard ratio [HR], 1.37 per doubling of total lesion count [95% CI, 1.10–1.71], P =0.006). The symptomatic ICH rate for familial CCM cases was 2.8 per 100 patient‐years (95% CI, 1.9–4.1). Those with ICH before enrollment had a follow‐up ICH rate of 4.5 per 100 patient‐years (95% CI, 2.6–8.1) compared with 2.0 per 100 patient‐years (95% CI, 1.3–3.5) in those without ( P =0.042). Total lesion count was associated with increased risk of ICH during follow‐up (hazard ratio [HR], 1.37 per doubling of total lesion count [95% CI, 1.10–1.71], P =0.006). Conclusions Patients with familial CCM with prior history of an ICH event are at higher risk for rehemorrhage during follow‐up. In addition, total CCM lesion burden is significantly associated with increased risk of subsequent symptomatic ICH; hence lesion burden may be an important predictor of patient outcome and aid patient risk stratification.

show abstract

“…SWI sequences provide information on venous vasculature, hemorrhage, iron deposits, and very small vascular structures within the central nervous system (including brain tumors) [4,[15][16][17]. Fractal geometry has been demonstrated to offer appropriate tools to quantify irregular-shaped biological objects, including microvascular and SWI patterns [8], that can be used in automated algorithms for counting microbleeds [18], quantitative susceptibility mapping [19], percentage-wise quantification of intratumoral-susceptibility signals [20], local image variance [21] and other quantitative methodologies [16]. The fractal dimension, the most used parameter in fractal geometry, has been shown as a reliable numerical index to objectively quantify geometrical complexity of microvascular patterns in brain tumors [22].…”

Section: Discussionmentioning

confidence: 99%

Advanced computational and statistical multiparametric analysis of Susceptibility-Weighted Imaging to characterize gliomas and brain metastases

Ieva

Russo

Reste³

et al. 2020

Preprint

View full text Add to dashboard Cite

contributed equally to this work.Abstract. Susceptibility-weighted imaging (SWI) is a technique useful for evaluation of the internal structures of brain tumors, including microvasculature and microbleeds. Intratumoral patterns of magnetic susceptibility can be quantified by means of fractal analysis. Here, we propose a radiomics methodological pipeline to merge advanced fractal-based computational modelling with statistical analysis to objectively characterize the fingerprint of gliomas and brain metastases. Forty-seven patients with glioma (grades II-IV, according to the WHO 2016 classification system) and fourteen with brain metastases underwent 3 Tesla MRI using a SWI protocol. All images underwent computational analysis aimed to quantify three Euclidean parameters (related to tumor and SWI volume) and five fractal-based parameters (related to the pixel distribution and geometrical complexity of the SWI patterns). Principal components analysis, linear and quadratic discriminant analysis, K-nearest neighbor and support vector machine methods were used to discriminate between tumor types. The combination of parameters offered an objective evaluation of the SWI pattern in gliomas and brain metastases. The model accurately predicted 88% of glioblastoma, according to the quantification of intratumoral SWI features, failing to discriminate the other types. SWI is not normally used to classify brain tumors, however fractal-based multi-parametric computational analysis can be used to characterize intratumoral SWI patterns to objectively quantify tumors-related features. Specific parameters still have to be identified to provide completely automatic computerized differential diagnosis.

show abstract

Automated algorithm for counting microbleeds in patients with familial cerebral cavernous malformations

Cited by 8 publications

References 15 publications

An Efficient False-Positive Reduction System for Cerebral Microbleeds Detection

An Efficient False-Positive Reduction System for Cerebral Microbleeds Detection

Intracranial Hemorrhage Rate and Lesion Burden in Patients With Familial Cerebral Cavernous Malformation

Advanced computational and statistical multiparametric analysis of Susceptibility-Weighted Imaging to characterize gliomas and brain metastases

Contact Info

Product

Resources

About