Efficient detection of cerebral microbleeds on 7.0T MR images using the radial symmetry transform

Real-world application of a 3D deep learning model for detecting and localizing cerebral microbleeds

BACKGROUND

Detection and localization of cerebral microbleeds (CMBs) is crucial for disease diagnosis and treatment planning. However, CMB detection is labor-intensive, time-consuming, and challenging owing to its visual similarity to mimics. This study aimed to validate the performance of a three-dimensional (3D) deep learning model that not only detects CMBs but also identifies their anatomic location in real-world settings.

METHODS

A total of 21 patients with 116 CMBs and 12 without CMBs were visited in the neurosurgery outpatient department between January 2023 and October 2023. Three readers, including a board-certified neuroradiologist (reader 1), a resident in radiology (reader 2), and a neurosurgeon (reader 3) independently reviewed SWIs of 33 patients to detect CMBs and categorized their locations into lobar, deep, and infratentorial regions without any AI assistance. After a one-month washout period, the same datasets were redistributed randomly, and readers reviewed them again with the assistance of the 3D deep learning model. A comparison of the diagnostic performance between readers with and without AI assistance was performed.

RESULTS

All readers with an AI assistant (reader 1:0.991 [0.930-0.999], reader 2:0.922 [0.881-0.905], and reader 3:0.966 [0.928-0.984]) tended to have higher sensitivity per lesion than readers only (reader 1:0.905 [0.849-0.942], reader 2:0.621 [0.541-0.694], and reader 3:0.871 [0.759-0.935], p = 0.132, 0.017, and 0.227, respectively). In particular, radiology residents (reader 2) showed a statistically significant increase in sensitivity per lesion when using AI. There was no statistically significant difference in the number of FPs per patient for all readers with AI assistant (reader 1: 0.394 [0.152-1.021], reader 2: 0.727 [0.334-1.582], reader 3: 0.182 [0.077-0.429]) and reader only (reader 1: 0.364 [0.159-0.831], reader 2: 0.576 [0.240-1.382], reader 3: 0.121 [0.038-0.383], p = 0.853, 0.251, and 0.157, respectively). Our model accurately categorized the anatomical location of all CMBs.

CONCLUSIONS

Our model demonstrated promising potential for the detection and anatomical localization of CMBs, although further research with a larger and more diverse population is necessary to establish clinical utility in real-world settings.

Deep-Learning-Based MRI Microbleeds Detection for Cerebral Small Vessel Disease on Quantitative Susceptibility Mapping

BACKGROUND

Cerebral microbleeds (CMB) are indicators of severe cerebral small vessel disease (CSVD) that can be identified through hemosiderin-sensitive sequences in MRI. Specifically, quantitative susceptibility mapping (QSM) and deep learning were applied to detect CMBs in MRI.

PURPOSE

To automatically detect CMB on QSM, we proposed a two-stage deep learning pipeline.

STUDY TYPE

Retrospective.

SUBJECTS

A total number of 1843 CMBs from 393 patients (69 ± 12) with cerebral small vessel disease were included in this study. Seventy-eight subjects (70 ± 13) were used as external testing.

FIELD STRENGTH/SEQUENCE

3 T/QSM.

ASSESSMENT

The proposed pipeline consisted of two stages. In stage I, 2.5D fast radial symmetry transform (FRST) algorithm along with a one-layer convolutional network was used to identify CMB candidate regions in QSM images. In stage II, the V-Net was utilized to reduce false positives. The V-Net was trained using CMB and non CMB labels, which allowed for high-level feature extraction and differentiation between CMBs and CMB mimics like vessels. The location of CMB was assessed according to the microbleeds anatomical rating scale (MARS) system.

STATISTICAL TESTS

The sensitivity and positive predicative value (PPV) were reported to evaluate the performance of the model. The number of false positive per subject was presented.

RESULTS

Our pipeline demonstrated high sensitivities of up to 94.9% at stage I and 93.5% at stage II. The overall sensitivity was 88.9%, and the false positive rate per subject was 2.87. With respect to MARS, sensitivities of above 85% were observed for nine different brain regions.

DATA CONCLUSION

We have presented a deep learning pipeline for detecting CMB in the CSVD cohort, along with a semi-automated MARS scoring system using the proposed method. Our results demonstrated the successful application of deep learning for CMB detection on QSM and outperformed previous handcrafted methods.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 2.

Naïve Bayes classifier assisted automated detection of cerebral microbleeds in susceptibility-weighted imaging brain images

Cerebral microbleeds (CMBs) in the brain are the essential indicators of critical brain disorders such as dementia and ischemic stroke. Generally, CMBs are detected manually by experts, which is an exhaustive task with limited productivity. Since CMBs have complex morphological nature, manual detection is prone to errors. This paper presents a machine learning-based automated CMB detection technique in the brain susceptibility-weighted imaging (SWI) scans based on statistical feature extraction and classification. The proposed method consists of three steps: (1) removal of the skull and extraction of the brain; (2) thresholding for the extraction of initial candidates; and (3) extracting features and applying classification models such as random forest and naïve Bayes classifiers for the detection of true positive CMBs. The proposed technique is validated on a dataset consisting of 20 subjects. The dataset is divided into training data that consist of 14 subjects with 104 microbleeds and testing data that consist of 6 subjects with 63 microbleeds. We were able to achieve 85.7% sensitivity using the random forest classifier with 4.2 false positives per CMB, and the naïve Bayes classifier achieved 90.5% sensitivity with 5.5 false positives per CMB. The proposed technique outperformed many state-of-the-art methods proposed in previous studies.

Automated detection of cerebral microbleeds on MR images using knowledge distillation framework

Introduction

Cerebral microbleeds (CMBs) are associated with white matter damage, and various neurodegenerative and cerebrovascular diseases. CMBs occur as small, circular hypointense lesions on T2*-weighted gradient recalled echo (GRE) and susceptibility-weighted imaging (SWI) images, and hyperintense on quantitative susceptibility mapping (QSM) images due to their paramagnetic nature. Accurate automated detection of CMBs would help to determine quantitative imaging biomarkers (e.g., CMB count) on large datasets. In this work, we propose a fully automated, deep learning-based, 3-step algorithm, using structural and anatomical properties of CMBs from any single input image modality (e.g., GRE/SWI/QSM) for their accurate detections.

Methods

In our method, the first step consists of an initial candidate detection step that detects CMBs with high sensitivity. In the second step, candidate discrimination step is performed using a knowledge distillation framework, with a multi-tasking teacher network that guides the student network to classify CMB and non-CMB instances in an offline manner. Finally, a morphological clean-up step further reduces false positives using anatomical constraints. We used four datasets consisting of different modalities specified above, acquired using various protocols and with a variety of pathological and demographic characteristics.

Results

On cross-validation within datasets, our method achieved a cluster-wise true positive rate (TPR) of over 90% with an average of <2 false positives per subject. The knowledge distillation framework improves the cluster-wise TPR of the student model by 15%. Our method is flexible in terms of the input modality and provides comparable cluster-wise TPR and better cluster-wise precision compared to existing state-of-the-art methods. When evaluating across different datasets, our method showed good generalizability with a cluster-wise TPR >80 % with different modalities. The python implementation of the proposed method is openly available.

Diagnosis of cerebral microbleed via VGG and extreme learning machine trained by Gaussian map bat algorithm

Cerebral microbleed (CMB) is a serious public health concern. It is associated with dementia, which can be detected with brain magnetic resonance image (MRI). CMBs often appear as tiny round dots on MRIs, and they can be spotted anywhere over brain. Therefore, manual inspection is tedious and lengthy, and the results are often short in reproducible. In this paper, a novel automatic CMB diagnosis method was proposed based on deep learning and optimization algorithms, which used the brain MRI as the input and output the diagnosis results as CMB and non-CMB. Firstly, sliding window processing was employed to generate the dataset from brain MRIs. Then, a pre-trained VGG was employed to obtain the image features from the dataset. Finally, an ELM was trained by Gaussian-map bat algorithm (GBA) for identification. Results showed that the proposed method VGG-ELM-GBA provided better generalization performance than several state-of-the-art approaches.

Using transfer learning for automated microbleed segmentation

INTRODUCTION

Cerebral microbleeds are small perivascular hemorrhages that can occur in both gray and white matter brain regions. Microbleeds are a marker of cerebrovascular pathology and are associated with an increased risk of cognitive decline and dementia. Microbleeds can be identified and manually segmented by expert radiologists and neurologists, usually from susceptibility-contrast MRI. The latter is hard to harmonize across scanners, while manual segmentation is laborious, time-consuming, and subject to interrater and intrarater variability. Automated techniques so far have shown high accuracy at a neighborhood ("patch") level at the expense of a high number of false positive voxel-wise lesions. We aimed to develop an automated, more precise microbleed segmentation tool that can use standardizable MRI contrasts.

METHODS

We first trained a ResNet50 network on another MRI segmentation task (cerebrospinal fluid vs. background segmentation) using T1-weighted, T2-weighted, and T2* MRIs. We then used transfer learning to train the network for the detection of microbleeds with the same contrasts. As a final step, we employed a combination of morphological operators and rules at the local lesion level to remove false positives. Manual segmentation of microbleeds from 78 participants was used to train and validate the system. We assessed the impact of patch size, freezing weights of the initial layers, mini-batch size, learning rate, and data augmentation on the performance of the Microbleed ResNet50 network.

RESULTS

The proposed method achieved high performance, with a patch-level sensitivity, specificity, and accuracy of 99.57, 99.16, and 99.93%, respectively. At a per lesion level, sensitivity, precision, and Dice similarity index values were 89.1, 20.1, and 0.28% for cortical GM; 100, 100, and 1.0% for deep GM; and 91.1, 44.3, and 0.58% for WM, respectively.

DISCUSSION

The proposed microbleed segmentation method is more suitable for the automated detection of microbleeds with high sensitivity.

Computer-Aided Extraction of Select MRI Markers of Cerebral Small Vessel Disease: A Systematic Review

Cerebral small vessel disease (CSVD) is a major vascular contributor to cognitive impairment in ageing, including dementias. Imaging remains the most promising method for in vivo studies of CSVD. To replace the subjective and laborious visual rating approaches, emerging studies have applied state-of-the-art artificial intelligence to extract imaging biomarkers of CSVD from MRI scans. We aimed to summarise published computer-aided methods for the examination of three imaging biomarkers of CSVD, namely cerebral microbleeds (CMB), dilated perivascular spaces (PVS), and lacunes of presumed vascular origin. Seventy classical image processing, classical machine learning, and deep learning studies were identified. Transfer learning and weak supervision techniques have been applied to accommodate the limitations in the training data. While good performance metrics were achieved in local datasets, there have not been generalisable pipelines validated in different research and/or clinical cohorts. Future studies could consider pooling data from multiple sources to increase data size and diversity, and evaluating performance using both image processing metrics and associations with clinical measures.

Cerebral Microbleeds Assessment and Quantification in COVID-19 Patients With Neurological Manifestations

It is increasingly acknowledged that Coronavirus Disease 2019 (COVID-19) can have neurological manifestations, and cerebral microbleeds (CMBs) have been observed in this setting. The aim of this study was to characterize CMBs patterns on susceptibility-weighted imaging (SWI) in hospitalized patients with COVID-19 with neurological manifestations. CMBs volume was quantified and correlated with clinical and laboratory parameters. The study included patients who were hospitalized due to COVID-19, exhibited neurological manifestations, and underwent a brain MRI between March and May 2020. Neurological, clinical, and biochemical variables were reported. The MRI was acquired using a 3T scanner, with a standardized protocol including SWI. Patients were divided based on radiological evidence of CMBs or their absence. The CMBs burden was also assessed with a semi-automatic SWI processing procedure specifically developed for the purpose of this study. Odds ratios (OR) for CMBs were calculated using age, sex, clinical, and laboratory data by logistic regression analysis. Of the 1,760 patients with COVID-19 admitted to the ASST Papa Giovanni XXIII Hospital between 1 March and 31 May 2020, 116 exhibited neurological symptoms requiring neuroimaging evaluation. Of these, 63 patients underwent brain MRI and were therefore included in the study. A total of 14 patients had radiological evidence of CMBs (CMBs+ group). CMBs+ patients had a higher prevalence of CSF inflammation (p = 0.020), a higher white blood cell count (p = 0.020), and lower lymphocytes (p = 0.010); the D-dimer (p = 0.026), LDH (p = 0.004), procalcitonin (p = 0.002), and CRP concentration (p < 0.001) were higher than in the CMBs- group. In multivariable logistic regression analysis, CRP (OR = 1.16, p = 0.011) indicated an association with CMBs. Estimated CMBs volume was higher in females than in males and decreased with age (Rho = −0.38; p = 0.18); it was positively associated with CRP (Rho = 0.36; p = 0.22), and negatively associated with lymphocytes (Rho = −0.52; p = 0.07). CMBs are a frequent imaging finding in hospitalized patients with COVID-19 with neurological manifestations and seem to be related to pro-inflammatory status.

Automated detection of cerebral microbleeds via segmentation in susceptibility-weighted images of patients with traumatic brain injury

Cerebral microbleeds (CMBs) are a recognised biomarker of traumatic axonal injury (TAI). Their number and location provide valuable information in the long-term prognosis of patients who sustained a traumatic brain injury (TBI). Accurate detection of CMBs is necessary for both research and clinical applications. CMBs appear as small hypointense lesions on susceptibility-weighted magnetic resonance imaging (SWI). Their size and shape vary markedly in cases of TBI. Manual annotation of CMBs is a difficult, error-prone, and time-consuming task. Several studies addressed the detection of CMBs in other neuropathologies with convolutional neural networks (CNNs). In this study, we developed and contrasted a classification (Patch-CNN) and two segmentation (Segmentation-CNN, U-Net) approaches for the detection of CMBs in TBI cases. The models were trained using 45 datasets, and the best models were chosen according to 16 validation sets. Finally, the models were evaluated on 10 TBI and healthy control cases, respectively. Our three models outperform the current status quo in the detection of traumatic CMBs, achieving higher sensitivity at low false positive (FP) counts. Furthermore, using a segmentation approach allows for better precision. The best model, the U-Net, achieves a detection rate of 90% at FP counts of 17.1 in TBI patients and 3.4 in healthy controls.

Neuropathology of Vascular Brain Health: Insights From Ex Vivo Magnetic Resonance Imaging-Histopathology Studies in Cerebral Small Vessel Disease

Sporadic cerebral small vessel disease (SVD) is a major contributor to vascular cognitive impairment and dementia in the aging human brain. On neuropathology, sporadic SVD is characterized by abnormalities to the small vessels of the brain predominantly in the form of cerebral amyloid angiopathy and arteriolosclerosis. These pathologies frequently coexist with Alzheimer disease changes, such as plaques and tangles, in a single brain. Conversely, during life, magnetic resonance imaging (MRI) only captures the larger manifestations of SVD in the form of parenchymal brain abnormalities. There appears to be a major knowledge gap regarding the underlying neuropathology of individual MRI-detectable SVD abnormalities. Ex vivo MRI in postmortem human brain tissue is a powerful tool to bridge this gap. This review summarizes current insights into the histopathologic correlations of MRI manifestations of SVD, their underlying cause, presumed pathophysiology, and associated secondary tissue injury. Moreover, we discuss the advantages and limitations of ex vivo MRI-guided histopathologic investigations and make recommendations for future studies.

Automated Detection of Candidate Subjects With Cerebral Microbleeds Using Machine Learning

Cerebral microbleeds (CMBs) appear as small, circular, well defined hypointense lesions of a few mm in size on T2^*-weighted gradient recalled echo (T2^*-GRE) images and appear enhanced on susceptibility weighted images (SWI). Due to their small size, contrast variations and other mimics (e.g., blood vessels), CMBs are highly challenging to detect automatically. In large datasets (e.g., the UK Biobank dataset), exhaustively labelling CMBs manually is difficult and time consuming. Hence it would be useful to preselect candidate CMB subjects in order to focus on those for manual labelling, which is essential for training and testing automated CMB detection tools on these datasets. In this work, we aim to detect CMB candidate subjects from a larger dataset, UK Biobank, using a machine learning-based, computationally light pipeline. For our evaluation, we used 3 different datasets, with different intensity characteristics, acquired with different scanners. They include the UK Biobank dataset and two clinical datasets with different pathological conditions. We developed and evaluated our pipelines on different types of images, consisting of SWI or GRE images. We also used the UK Biobank dataset to compare our approach with alternative CMB preselection methods using non-imaging factors and/or imaging data. Finally, we evaluated the pipeline's generalisability across datasets. Our method provided subject-level detection accuracy > 80% on all the datasets (within-dataset results), and showed good generalisability across datasets, providing a consistent accuracy of over 80%, even when evaluated across different modalities.

7-T Magnetic Resonance Imaging in the Management of Brain Tumors

This article provides an overview of the current status of ultrahigh-field 7-T magnetic resonance (MR) imaging in neuro-oncology, specifically for the management of patients with brain tumors. It includes a discussion of areas across the pretherapeutic, peritherapeutic, and posttherapeutic stages of patient care where 7-T MR imaging is currently being exploited and holds promise. This discussion includes existing technical challenges, barriers to clinical integration, as well as our impression of the future role of 7-T MR imaging as a clinical tool in neuro-oncology.

Cerebral Microbleed Detection via Convolutional Neural Network and Extreme Learning Machine

Aim: Cerebral microbleeds (CMBs) are small round dots distributed over the brain which contribute to stroke, dementia, and death. The early diagnosis is significant for the treatment. Method: In this paper, a new CMB detection approach was put forward for brain magnetic resonance images. We leveraged a sliding window to obtain training and testing samples from input brain images. Then, a 13-layer convolutional neural network (CNN) was designed and trained. Finally, we proposed to utilize an extreme learning machine (ELM) to substitute the last several layers in the CNN for detection. We carried out an experiment to decide the optimal number of layers to be substituted. The parameters in ELM were optimized by a heuristic algorithm named bat algorithm. The evaluation of our approach was based on hold-out validation, and the final predictions were generated by averaging the performance of five runs. Results: Through the experiments, we found replacing the last five layers with ELM can get the optimal results. Conclusion: We offered a comparison with state-of-the-art algorithms, and it can be revealed that our method was accurate in CMB detection.

Studying Alzheimer disease, Parkinson disease, and amyotrophic lateral sclerosis with 7-T magnetic resonance

Ultra-high-field (UHF) magnetic resonance (MR) scanners, that is, equipment operating at static magnetic field of 7 tesla (7 T) and above, enable the acquisition of data with greatly improved signal-to-noise ratio with respect to conventional MR systems (e.g., scanners operating at 1.5 T and 3 T). The change in tissue relaxation times at UHF offers the opportunity to improve tissue contrast and depict features that were previously inaccessible. These potential advantages come, however, at a cost: in the majority of UHF-MR clinical protocols, potential drawbacks may include signal inhomogeneity, geometrical distortions, artifacts introduced by patient respiration, cardiac cycle, and motion. This article reviews the 7 T MR literature reporting the recent studies on the most widespread neurodegenerative diseases: Alzheimer's disease, Parkinson's disease, and amyotrophic lateral sclerosis.

Synthetic microbleeds generation for classifier training without ground truth

BACKGROUND AND OBJECTIVE

Cerebral microbleeds (CMB) are important biomarkers of cerebrovascular diseases and cognitive dysfunctions. Susceptibility weighted imaging (SWI) is a common MRI sequence where CMB appear as small hypointense blobs. The prevalence of CMB in the population and in each scan is low, resulting in tedious and time-consuming visual assessment. Automated detection methods would be of value but are challenged by the CMB low prevalence, the presence of mimics such as blood vessels, and the difficulty to obtain sufficient ground truth for training and testing. In this paper, synthetic CMB (sCMB) generation using an analytical model is proposed for training and testing machine learning methods. The main aim is creating perfect synthetic ground truth as similar as reals, in high number, with a high diversity of shape, volume, intensity, and location to improve training of supervised methods.

METHOD

sCMB were modelled with a random Gaussian shape and added to healthy brain locations. We compared training on our synthetic data to standard augmentation techniques. We performed a validation experiment using sCMB and report result for whole brain detection using a 10-fold cross validation design with an ensemble of 10 neural networks.

RESULTS

Performance was close to state of the art (~9 false positives per scan), when random forest was trained on synthetic only and tested on real lesion. Other experiments showed that top detection performance could be achieved when training on synthetic CMB only. Our dataset is made available, including a version with 37,000 synthetic lesions, that could be used for benchmarking and training.

CONCLUSION

Our proposed synthetic microbleeds model is a powerful data augmentation approach for CMB classification with and should be considered for training automated lesion detection system from MRI SWI.

DEEPMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI

Lobar cerebral microbleeds (CMBs) and localized non-hemorrhage iron deposits in the basal ganglia have been associated with brain aging, vascular disease and neurodegenerative disorders. Particularly, CMBs are small lesions and require multiple neuroimaging modalities for accurate detection. Quantitative susceptibility mapping (QSM) derived from in vivo magnetic resonance imaging (MRI) is necessary to differentiate between iron content and mineralization. We set out to develop a deep learning-based segmentation method suitable for segmenting both CMBs and iron deposits. We included a convenience sample of 24 participants from the MESA cohort and used T2-weighted images, susceptibility weighted imaging (SWI), and QSM to segment the two types of lesions. We developed a protocol for simultaneous manual annotation of CMBs and non-hemorrhage iron deposits in the basal ganglia. This manual annotation was then used to train a deep convolution neural network (CNN). Specifically, we adapted the U-Net model with a higher number of resolution layers to be able to detect small lesions such as CMBs from standard resolution MRI. We tested different combinations of the three modalities to determine the most informative data sources for the detection tasks. In the detection of CMBs using single class and multiclass models, we achieved an average sensitivity and precision of between 0.84-0.88 and 0.40-0.59, respectively. The same framework detected non-hemorrhage iron deposits with an average sensitivity and precision of about 0.75-0.81 and 0.62-0.75, respectively. Our results showed that deep learning could automate the detection of small vessel disease lesions and including multimodal MR data (particularly QSM) can improve the detection of CMB and non-hemorrhage iron deposits with sensitivity and precision that is compatible with use in large-scale research studies.

Novel Approaches to Detection of Cerebral Microbleeds: Single Deep Learning Model to Achieve a Balanced Performance

PURPOSE

Cerebral microbleeds (CMBs) are considered essential indicators for the diagnosis of cerebrovascular disease and cognitive disorders. Traditionally, CMBs are manually interpreted based on criteria including the shape, diameter, and signal characteristics after an MR examination, such as susceptibility-weighted imaging or gradient echo imaging (GRE). In this paper, an efficient method for CMB detection in GRE scans is presented.

MATERIALS AND METHODS

The proposed framework consists of the following phases: (1) pre-processing (skull extraction), (2) the first training with the ground truth labeled using CMB, (3) the second training with the ground truth labeled with CMB mimicking the same subjects, and (4) post-processing (cerebrospinal fluid (CSF) filtering). The proposed technique was validated on a dataset of 1133 CBMs that consisted of 5284 images for training and 1737 images for testing. We applied a two-stage approach using a region-based CNN method based on You Only Look Once (YOLO) to investigate a novel CMB detection technique.

RESULTS

The sensitivity, precision, F1-score and false positive per person (FP_avg) were evaluated as 80.96, 60.98, 69.57 and 6.57, 59.69, 62.70, 61.16 and 4.5, 66.90, 79.75, 72.76 and 2.15 for YOLO with a single label, YOLO with double labels, and YOLO + CSF filtering, respectively, and YOLO + CSF filtering showed the highest precision performance, F1-score and lowest FP_avg.

CONCLUSIONS

Using proposed framework, we developed an optimized CMB learning model with low false positives and a balanced performance in clinical practice.

Detecting cerebral microbleeds via deep learning with features enhancement by reusing ground truth

BACKGROUND AND OBJECTIVES

Cerebral microbleeds (CMBs) are cerebral small vascular diseases and are often used to diagnose symptoms such as stroke and dementia. Manual detection of cerebral microbleeds is a time-consuming and error-prone task, so the application of microbleed detection algorithms based on deep learning is of great significance. This study presents the feature enhancement technology applying to improve the performances of detecting CMBs. The primary purpose of the feature enhancement is emphasizing the meaningful features, leading deep learning network easier and correctly to optimize.

METHOD

In this study, we applied feature enhancement in detecting CMBs from brain MRI images. Feature enhancement enhanced specific intervals and suppressed the useless intervals of the feature map. This method was applied in SSD-512 and SSD-300 algorithm, using VGG architecture pre-trained in the ImageNet dataset.

RESULTS

The proposed method was applied in SSD-512. Moreover, the model was trained and tested on the sequence of SWAN images of brain MRI images. The results of the experiment demonstrate that our method effectively improves the detection performance of the SSD network in detecting CMBs. We train SSD-512 120000 iterations and test results on the test datasets, by applying the feature enhancement layer, improving the precision with 3.3% and the mAP of 2.3%. In the same way, we trained SSD-300, improving the mAP of 2.0%. 2.8% and 7.4% precision are improved by applying feature enhancement layer In ResNet-34 and MobileNet.

CONCLUSIONS

The proposed method achieved more effective performance, demonstrated that feature enhancement can be a helpful algorithm to enhance the deep learning model.

Detection of Cerebral Microbleeds With Venous Connection at 7-Tesla MRI

OBJECTIVE

Cerebral microbleeds (MBs) are a common finding in patients with cerebral small vessel disease (CSVD) and Alzheimer disease as well as in healthy elderly people, but their pathophysiology remains unclear. To investigate a possible role of veins in the development of MBs, we performed an exploratory study, assessing in vivo presence of MBs with a direct connection to a vein.

METHODS

7-Tesla (7T) MRI was conducted and MBs were counted on quantitative susceptibility mapping (QSM). A submillimeter resolution QSM-based venogram allowed identification of MBs with a direct spatial connection to a vein.

RESULTS

A total of 51 people (mean age [SD] 70.5 [8.6] years, 37% female) participated in the study: 20 had CSVD (cerebral amyloid angiopathy [CAA] with strictly lobar MBs [n = 8], hypertensive arteriopathy [HA] with strictly deep MBs [n = 5], or mixed lobar and deep MBs [n = 7], 72.4 [6.1] years, 30% female) and 31 were healthy controls (69.4 [9.9] years, 42% female). In our cohort, we counted a total of 96 MBs with a venous connection, representing 14% of all detected MBs on 7T QSM. Most venous MBs (86%, n = 83) were observed in lobar locations and all of these were cortical. Patients with CAA showed the highest ratio of venous to total MBs (19%) (HA = 9%, mixed = 18%, controls = 5%).

CONCLUSION

Our findings establish a link between cerebral MBs and the venous vasculature, pointing towards a possible contribution of veins to CSVD in general and to CAA in particular. Pathologic studies are needed to confirm our observations.

Automated detection of cerebral microbleeds on T2*-weighted MRI

Cerebral microbleeds, observed as small, spherical hypointense regions on gradient echo (GRE) or susceptibility weighted (SWI) magnetic resonance imaging (MRI) sequences, reflect small hemorrhagic infarcts, and are associated with conditions such as vascular dementia, small vessel disease, cerebral amyloid angiopathy, and Alzheimer’s disease. The current gold standard for detecting and rating cerebral microbleeds in a research context is visual inspection by trained raters, a process that is both time consuming and subject to poor reliability. We present here a novel method to automate microbleed detection on GRE and SWI images. We demonstrate in a community-based cohort of older adults that the method is highly sensitive (greater than 92% of all microbleeds accurately detected) across both modalities, with reasonable precision (fewer than 20 and 10 false positives per scan on GRE and SWI, respectively). We also demonstrate that the algorithm can be used to identify microbleeds over longitudinal scans with a higher level of sensitivity than visual ratings (50% of longitudinal microbleeds correctly labeled by the algorithm, while manual ratings was 30% or lower). Further, the algorithm identifies the anatomical localization of microbleeds based on brain atlases, and greatly reduces time spent completing visual ratings (43% reduction in visual rating time). Our automatic microbleed detection instrument is ideal for implementation in large-scale studies that include cross-sectional and longitudinal scanning, as well as being capable of performing well across multiple commonly used MRI modalities.

Automated detection of cerebral microbleeds in MR images: A two-stage deep learning approach

Cerebral Microbleeds (CMBs) are small chronic brain hemorrhages, which have been considered as diagnostic indicators for different cerebrovascular diseases including stroke, dysfunction, dementia, and cognitive impairment. However, automated detection and identification of CMBs in Magnetic Resonance (MR) images is a very challenging task due to their wide distribution throughout the brain, small sizes, and the high degree of visual similarity between CMBs and CMB mimics such as calcifications, irons, and veins. In this paper, we propose a fully automated two-stage integrated deep learning approach for efficient CMBs detection, which combines a regional-based You Only Look Once (YOLO) stage for potential CMBs candidate detection and three-dimensional convolutional neural networks (3D-CNN) stage for false positives reduction. Both stages are conducted using the 3D contextual information of microbleeds from the MR susceptibility-weighted imaging (SWI) and phase images. However, we average the adjacent slices of SWI and complement the phase images independently and utilize them as a two-channel input for the regional-based YOLO method. This enables YOLO to learn more reliable and representative hierarchal features and hence achieve better detection performance. The proposed work was independently trained and evaluated using high and low in-plane resolution data, which contained 72 subjects with 188 CMBs and 107 subjects with 572 CMBs, respectively. The results in the first stage show that the proposed regional-based YOLO efficiently detected the CMBs with an overall sensitivity of 93.62% and 78.85% and an average number of false positives per subject (FPavg) of 52.18 and 155.50 throughout the five-folds cross-validation for both the high and low in-plane resolution data, respectively. These findings outperformed results by previously utilized techniques such as 3D fast radial symmetry transform, producing fewer FPavg and lower computational cost. The 3D-CNN based second stage further improved the detection performance by reducing the FPavg to 1.42 and 1.89 for the high and low in-plane resolution data, respectively. The outcomes of this work might provide useful guidelines towards applying deep learning algorithms for automatic CMBs detection.

Microbleeds colocalize with enlarged juxtacortical perivascular spaces in amnestic mild cognitive impairment and early Alzheimer's disease: A 7 Tesla MRI study

MRI-visible perivascular spaces (PVS) in the semioval centre are associated with cerebral amyloid angiopathy (CAA), but it is unknown if PVS co-localize with MRI markers of CAA. To examine this, we assessed the topographical association between cortical cerebral microbleeds (CMBs) - as an indirect marker of CAA - and dilatation of juxtacortical perivascular spaces (jPVS) in 46 patients with amnestic mild cognitive impairment (aMCI) or early Alzheimer's disease (eAD). The degree of dilatation of jPVS <1 cm around each cortical CMBs was compared with a similar reference site (no CMB) in the contralateral hemisphere, using a 4-point scale. Also, jPVS dilatation was compared between patients with and without cortical CMBs. Eleven patients (24%) had cortical CMBs [total=35, median=1, range=1-14] of whom five had >1 cortical CMBs. The degree of jPVS dilatation was higher around CMBs than at the reference sites [Wilcoxon signed rank test, Z = 2.2, p = 0.03]. Patients with >1 cortical CMBs had a higher degree of jPVS dilation [median=2.2, IQR = 1.8-2.3] than patients without cortical CMBs [median=1.4, IQR = 1.0-1.8], p = 0.02. We found a topographical association between a high degree of jPVS dilatation and cortical CMBs, supporting a common underlying pathophysiology - most likely CAA.

European Ultrahigh-Field Imaging Network for Neurodegenerative Diseases (EUFIND)

INTRODUCTION

The goal of European Ultrahigh-Field Imaging Network in Neurodegenerative Diseases (EUFIND) is to identify opportunities and challenges of 7 Tesla (7T) MRI for clinical and research applications in neurodegeneration. EUFIND comprises 22 European and one US site, including over 50 MRI and dementia experts as well as neuroscientists.

METHODS

EUFIND combined consensus workshops and data sharing for multisite analysis, focusing on 7 core topics: clinical applications/clinical research, highest resolution anatomy, functional imaging, vascular systems/vascular pathology, iron mapping and neuropathology detection, spectroscopy, and quality assurance. Across these topics, EUFIND considered standard operating procedures, safety, and multivendor harmonization.

RESULTS

The clinical and research opportunities and challenges of 7T MRI in each subtopic are set out as a roadmap. Specific MRI sequences for each subtopic were implemented in a pilot study presented in this report. Results show that a large multisite 7T imaging network with highly advanced and harmonized imaging sequences is feasible and may enable future multicentre ultrahigh-field MRI studies and clinical trials.

DISCUSSION

The EUFIND network can be a major driver for advancing clinical neuroimaging research using 7T and for identifying use-cases for clinical applications in neurodegeneration.

Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network

Cerebral microbleeds, which are small focal hemorrhages in the brain that are prevalent in many diseases, are gaining increasing attention due to their potential as surrogate markers of disease burden, clinical outcomes, and delayed effects of therapy. Manual detection is laborious and automatic detection and labeling of these lesions is challenging using traditional algorithms. Inspired by recent successes of deep convolutional neural networks in computer vision, we developed a 3D deep residual network that can distinguish true microbleeds from false positive mimics of a previously developed technique based on traditional algorithms. A dataset of 73 patients with radiation-induced cerebral microbleeds scanned at 7 T with susceptibility-weighted imaging was used to train and evaluate our model. With the resulting network, we maintained 95% of the true microbleeds in 12 test patients and the average number of false positives was reduced by 89%, achieving a detection precision of 71.9%, higher than existing published methods. The likelihood score predicted by the network was also evaluated by comparing to a neuroradiologist's rating, and good correlation was observed.

A user-guided tool for semi-automated cerebral microbleed detection and volume segmentation: Evaluating vascular injury and data labelling for machine learning

Background and purpose

With extensive research efforts in place to address the clinical relevance of cerebral microbleeds (CMBs), there remains a need for fast and accurate methods to detect and quantify CMB burden. Although some computer-aided detection algorithms have been proposed in the literature with high sensitivity, their specificity remains consistently poor. More sophisticated machine learning methods appear to be promising in their ability to minimize false positives (FP) through high-level feature extraction and the discrimination of hard-mimics. To achieve superior performance, these methods require sizable amounts of precisely labelled training data. Here we present a user-guided tool for semi-automated CMB detection and volume segmentation, offering high specificity for routine use and FP labelling capabilities to ease and expedite the process of generating labelled training data.

Materials and methods

Existing computer-aided detection methods reported by our group were extended to include fully-automated segmentation and user-guided CMB classification with FP labelling. The algorithm's performance was evaluated on a test set of ten patients exhibiting radiotherapy-induced CMBs on MR images.

Results

The initial algorithm's base sensitivity was maintained at 86.7%. FP's were reduced to inter-rater variations and segmentation results were in 98% agreement with ground truth labelling. There was an approximate 5-fold reduction in the time users spent evaluating CMB burden with the algorithm versus without computer aid. The Intra-class Correlation Coefficient for inter-rater agreement was 0.97 CI[0.92,0.99].

Conclusions

This development serves as a valuable tool for routine evaluation of CMB burden and data labelling to improve CMB classification with machine learning. The algorithm is available to the public on GitHub (https://github.com/LupoLab-UCSF/CMB_labeler).

Clinical vascular imaging in the brain at 7T

Stroke and related cerebrovascular diseases are a major cause of mortality and disability. Even at standard-field-strengths (1.5T), MRI is by far the most sensitive imaging technique to detect acute brain infarctions and to characterize incidental cerebrovascular lesions, such as white matter hyperintensities, lacunes and microbleeds. Arterial time-of-flight (TOF) MR angiography (MRA) can depict luminal narrowing or occlusion of the major brain feeding arteries, and this without the need for contrast administration. Compared to 1.5T MRA, the use of high-field strength (3T) and even more so ultra-high-field strengths (7T), enables the visualization of the lumen of much smaller intracranial vessels, while adding a contrast agent to TOF MRA at 7T may enable the visualization of even more distal arteries in addition to veins and venules. Moreover, with 3T and 7T, the arterial vessel walls beyond the circle of Willis become visible with high-resolution vessel wall imaging. In addition, with 7T MRI, the brain parenchyma can now be visualized on a submillimeter scale. As a result, high-resolution imaging studies of the brain and its blood supply at 7T have generated new concepts of different cerebrovascular diseases. In the current article, we will discuss emerging clinical applications and future directions of vascular imaging in the brain at 7T MRI.

MRI for in vivo diagnosis of cerebral amyloid angiopathy: Tailoring artifacts to image hemorrhagic biomarkers

Cerebral amyloid angiopathy (CAA) is a frequent age-related small vessel disease (SVD) with cardinal magnetic resonance imaging (MRI) signatures that are hemorrhagic in nature, and include the presence of strictly lobar (superficial) cerebral microbleeds and intracerebral hemorrhages as well as cortical superficial siderosis. When investigating a patient with suspected CAA in the context of intracranial hemorrhage (parenchymal or subarachnoid) or cognitive dysfunction, various MRI parameters influence the optimal detection and characterization (and prognostication) of this frequent SVD. The present report describes the influence of imaging techniques on the detection of the key hemorrhagic CAA imaging signatures in clinical practice, in research studies, and the imaging parameters that must be understood when encountering a CAA patient, as well as reviewing CAA literature.

Brain lesion segmentation through image synthesis and outlier detection

Cerebral small vessel disease (SVD) can manifest in a number of ways. Many of these result in hyperintense regions visible on T2-weighted magnetic resonance (MR) images. The automatic segmentation of these lesions has been the focus of many studies. However, previous methods tended to be limited to certain types of pathology, as a consequence of either restricting the search to the white matter, or by training on an individual pathology. Here we present an unsupervised abnormality detection method which is able to detect abnormally hyperintense regions on FLAIR regardless of the underlying pathology or location. The method uses a combination of image synthesis, Gaussian mixture models and one class support vector machines, and needs only be trained on healthy tissue. We evaluate our method by comparing segmentation results from 127 subjects with SVD with three established methods and report significantly superior performance across a number of metrics.

7T MRI for neurodegenerative dementias in vivo: a systematic review of the literature

The spatial resolution of 7T MRI approaches the scale of pathologies of interest in degenerative brain diseases, such as amyloid plaques and changes in cortical layers and subcortical nuclei. It may reveal new information about neurodegenerative dementias, although challenges may include increased artefact production and more adverse effects. We performed a systematic review of papers investigating Alzheimer's disease (AD), Lewy body dementia (LBD), frontotemporal dementia (FTD) and Huntington's disease (HD) in vivo using 7T MRI. Of 19 studies identified, 15 investigated AD (the majority of which examined hippocampal subfield changes), and 4 investigated HD. Ultrahigh resolution revealed changes not visible using lower field strengths, such as hippocampal subfield atrophy in mild cognitive impairment. Increased sensitivity to susceptibility-enhanced iron imaging, facilitating amyloid and microbleed examination; for example, higher microbleed prevalence was found in AD than previously recognised. Theoretical difficulties regarding image acquisition and scan tolerance were not reported as problematic. Study limitations included small subject groups, a lack of studies investigating LBD and FTD and an absence of longitudinal data. In vivo 7T MRI may illuminate disease processes and reveal new biomarkers and therapeutic targets. Evidence from AD and HD studies suggest that other neurodegenerative dementias would also benefit from imaging at ultrahigh resolution.

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

PURPOSE

Familial cerebral cavernous malformation (CCM) patients present with multiple lesions that can grow both in number and size over time and are reliably detected on susceptibility-weighted imaging (SWI). Manual counting of lesions is arduous and subject to high variability. We aimed to develop an automated algorithm for counting CCM microbleeds (lesions <5 mm in diameter) on SWI images.

METHODS

Fifty-seven familial CCM type-1 patients were included in this institutional review board-approved study. Baseline SWI (n = 57) and follow-up SWI (n = 17) were performed on a 3T Siemens MR scanner with lesions counted manually by the study neuroradiologist. We modified an algorithm for detecting radiation-induced microbleeds on SWI images in brain tumor patients, using a training set of 22 manually delineated CCM microbleeds from two random scans. Manual and automated counts were compared using linear regression with robust standard errors, intra-class correlation (ICC), and paired t tests. A validation analysis comparing the automated counting algorithm and a consensus read from two neuroradiologists was used to calculate sensitivity, the proportion of microbleeds correctly identified by the automated algorithm.

RESULTS

Automated and manual microbleed counts were in strong agreement in both baseline (ICC = 0.95, p < 0.001) and longitudinal (ICC = 0.88, p < 0.001) analyses, with no significant difference between average counts (baseline p = 0.11, longitudinal p = 0.29). In the validation analysis, the algorithm correctly identified 662 of 1325 microbleeds (sensitivity=50%), again with strong agreement between approaches (ICC = 0.77, p < 0.001).

CONCLUSION

The automated algorithm is a consistent method for counting microbleeds in familial CCM patients that can facilitate lesion quantification and tracking.

Determination of detection sensitivity for cerebral microbleeds using susceptibility-weighted imaging

Cerebral microbleeds (CMBs) are small brain hemorrhages caused by the break down or structural abnormalities of small vessels of the brain. Owing to the paramagnetic properties of blood degradation products, CMBs can be detected in vivo using susceptibility-weighted imaging (SWI). SWI can be used not only to detect iron changes and CMBs, but also to differentiate them from calcifications, both of which may be important MR-based biomarkers for neurodegenerative diseases. Moreover, SWI can be used to quantify the iron in CMBs. SWI and gradient echo (GE) imaging are the two most common methods for the detection of iron deposition and CMBs. This study provides a comprehensive analysis of the number of voxels detected in the presence of a CMB on GE magnitude, phase and SWI composite images as a function of resolution, signal-to-noise ratio (SNR), TE, field strength and susceptibility using in silico experiments. Susceptibility maps were used to quantify the bias in the effective susceptibility value and to determine the optimal TE for CMB quantification. We observed a non-linear trend with susceptibility for CMB detection from the magnitude images, but a linear trend with susceptibility for CMB detection from the phase and SWI composite images. The optimal TE values for CMB quantification were found to be 3 ms at 7 T, 7 ms at 3 T and 14 ms at 1.5 T for a CMB of one voxel in diameter with an SNR of 20: 1. The simulations of signal loss and detectability were used to generate theoretical formulae for predictions. Copyright © 2016 John Wiley & Sons, Ltd.

7-T MRI in Cerebrovascular Diseases: Challenges to Overcome and Initial Results

Magnetic resonance imaging (MRI) plays a key role in the investigation of cerebrovascular diseases. Compared with computed tomography (CT) and digital subtraction angiography (DSA), its advantages in diagnosing cerebrovascular pathology include its superior tissue contrast, its ability to visualize blood vessels without the use of a contrast agent, and its use of magnetic fields and radiofrequency pulses instead of ionizing radiation. In recent years, ultrahigh field MRI at 7 tesla (7 T) has shown promise in the diagnosis of many cerebrovascular diseases. The increased signal-to-noise ratio (SNR; 2.3x and 4.7x increase compared with 3 and 1.5 T, respectively) and contrast-to-noise ratio (CNR) at this higher field strength can be exploited to obtain a higher spatial resolution and higher lesion conspicuousness, enabling assessment of smaller brain structures and lesions. Cerebrovascular diseases can be assessed at different tissue levels; for instance, changes of the arteries feeding the brain can be visualized to determine the cause of ischemic stroke, regional changes in brain perfusion can be mapped to predict outcome after revascularization, and tissue damage, including old and recent ischemic infarcts, can be evaluated as a marker of ischemic burden. For the purpose of this review, we will discriminate 3 levels of assessment of cerebrovascular diseases using MRI: Pipes, Perfusion, and Parenchyma (3 Ps). The term Pipes refers to the brain-feeding arteries from the heart and aortic arch, upwards to the carotid arteries, vertebral arteries, circle of Willis, and smaller intracranial arterial branches. Perfusion is the amount of blood arriving at the brain tissue level, and includes the vascular reserve and perfusion territories. Parenchyma refers to the acute and chronic burden of brain tissue damage, which includes larger infarcts, smaller microinfarcts, and small vessel disease manifestations such as white matter lesions, lacunar infarcts, and microbleeds. In this review, we will describe the key developments in the last decade of 7-T MRI of cerebrovascular diseases, subdivided for these 3 levels of assessment.

Perivascular spaces on 7 Tesla brain MRI are related to markers of small vessel disease but not to age or cardiovascular risk factors

Cerebral perivascular spaces (PVS) are small physiological structures around blood vessels in the brain. MRI visible PVS are associated with ageing and cerebral small vessel disease (SVD). 7 Tesla (7T) MRI improves PVS detection. We investigated the association of age, vascular risk factors, and imaging markers of SVD with PVS counts on 7 T MRI, in 50 persons aged ≥ 40. The average PVS count ± SD in the right hemisphere was 17 ± 6 in the basal ganglia and 71 ± 28 in the semioval centre. We observed no relation between age or vascular risk factors and PVS counts. The presence of microbleeds was related to more PVS in the basal ganglia (standardized beta 0.32; p = 0.04) and semioval centre (standardized beta 0.39; p = 0.01), and white matter hyperintensity volume to more PVS in the basal ganglia (standardized beta 0.41; p = 0.02). We conclude that PVS counts on 7T MRI are high and are related SVD markers, but not to age and vascular risk factors. This latter finding may indicate that due to the high sensitivity of 7T MRI, the correlation of PVS counts with age or vascular risk factors may be attenuated by the detection of "normal", non-pathological PVS.

Automatic cerebral microbleeds detection from MR images via Independent Subspace Analysis based hierarchical features

With the development of susceptibility weighted imaging (SWI) technology, cerebral microbleed (CMB) detection is increasingly essential in cerebrovascular diseases diagnosis and cognitive impairment assessment. Clinical CMB detection is based on manual rating which is subjective and time-consuming with limited reproducibility. In this paper, we propose a computer-aided system for automatic detection of CMBs from brain SWI images. Our approach detects the CMBs within three stages: (i) candidates screening based on intensity values (ii) compact 3D hierarchical features extraction via a stacked convolutional Independent Subspace Analysis (ISA) network (iii) false positive candidates removal with a support vector machine (SVM) classifier based on the learned representation features from ISA. Experimental results on 19 subjects (161 CMBs) achieve a high sensitivity of 89.44% with an average of 7.7 and 0.9 false positives per subject and per CMB, respectively, which validate the efficacy of our approach.

Evaluating the Role of Reduced Oxygen Saturation and Vascular Damage in Traumatic Brain Injury Using Magnetic Resonance Perfusion-Weighted Imaging and Susceptibility-Weighted Imaging and Mapping

The cerebral vasculature, along with neurons and axons, is vulnerable to biomechanical insult during traumatic brain injury (TBI). Trauma-induced vascular injury is still an underinvestigated area in TBI research. Cerebral blood flow and metabolism could be important future treatment targets in neural critical care. Magnetic resonance imaging offers a number of key methods to probe vascular injury and its relationship with traumatic hemorrhage, perfusion deficits, venous blood oxygen saturation changes, and resultant tissue damage. They make it possible to image the hemodynamics of the brain, monitor regional damage, and potentially show changes induced in the brain's function not only acutely but also longitudinally following treatment. These methods have recently been used to show that even mild TBI (mTBI) subjects can have vascular abnormalities, and thus they provide a major step forward in better diagnosing mTBI patients.

Reproducibility and variability of quantitative magnetic resonance imaging markers in cerebral small vessel disease

Brain imaging is essential for the diagnosis and characterization of cerebral small vessel disease. Several magnetic resonance imaging markers have therefore emerged, providing new information on the diagnosis, progression, and mechanisms of small vessel disease. Yet, the reproducibility of these small vessel disease markers has received little attention despite being widely used in cross-sectional and longitudinal studies. This review focuses on the main small vessel disease-related markers on magnetic resonance imaging including: white matter hyperintensities, lacunes, dilated perivascular spaces, microbleeds, and brain volume. The aim is to summarize, for each marker, what is currently known about: (1) its reproducibility in studies with a scan-rescan procedure either in single or multicenter settings; (2) the acquisition-related sources of variability; and, (3) the techniques used to minimize this variability. Based on the results, we discuss technical and other challenges that need to be overcome in order for these markers to be reliably used as outcome measures in future clinical trials. We also highlight the key points that need to be considered when designing multicenter magnetic resonance imaging studies of small vessel disease.

Automated detection of cerebral microbleeds in patients with Traumatic Brain Injury

In this paper a Computer Aided Detection (CAD) system is presented to automatically detect Cerebral Microbleeds (CMBs) in patients with Traumatic Brain Injury (TBI). It is believed that the presence of CMBs has clinical prognostic value in TBI patients. To study the contribution of CMBs in patient outcome, accurate detection of CMBs is required. Manual detection of CMBs in TBI patients is a time consuming task that is prone to errors, because CMBs are easily overlooked and are difficult to distinguish from blood vessels.

This study included 33 TBI patients. Because of the laborious nature of manually annotating CMBs, only one trained expert manually annotated the CMBs in all 33 patients. A subset of ten TBI patients was annotated by six experts. Our CAD system makes use of both Susceptibility Weighted Imaging (SWI) and T1 weighted magnetic resonance images to detect CMBs. After pre-processing these images, a two-step approach was used for automated detection of CMBs. In the first step, each voxel was characterized by twelve features based on the dark and spherical nature of CMBs and a random forest classifier was used to identify CMB candidate locations. In the second step, segmentations were made from each identified candidate location. Subsequently an object-based classifier was used to remove false positive detections of the voxel classifier, by considering seven object-based features that discriminate between spherical objects (CMBs) and elongated objects (blood vessels). A guided user interface was designed for fast evaluation of the CAD system result. During this process, an expert checked each CMB detected by the CAD system.

A Fleiss' kappa value of only 0.24 showed that the inter-observer variability for the TBI patients in this study was very large. An expert using the guided user interface reached an average sensitivity of 93%, which was significantly higher (p = 0.03) than the average sensitivity of 77% (sd 12.4%) that the six experts manually detected. Furthermore, with the use of this CAD system the reading time was substantially reduced from one hour to 13 minutes per patient, because the CAD system only detects on average 25.9 false positives per TBI patient, resulting in 0.29 false positives per definite CMB finding.

•

We present an automated detection system for microbleeds in MRIs of trauma patients.

•

When using the system, detection time goes down from one hour to 13 min.

•

The system enables the user to detect a significantly higher number of CMBs.

•

The inter-observer variability for detecting CMBs is very large in TBI patients.

Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks

Cerebral microbleeds (CMBs) are small haemorrhages nearby blood vessels. They have been recognized as important diagnostic biomarkers for many cerebrovascular diseases and cognitive dysfunctions. In current clinical routine, CMBs are manually labelled by radiologists but this procedure is laborious, time-consuming, and error prone. In this paper, we propose a novel automatic method to detect CMBs from magnetic resonance (MR) images by exploiting the 3D convolutional neural network (CNN). Compared with previous methods that employed either low-level hand-crafted descriptors or 2D CNNs, our method can take full advantage of spatial contextual information in MR volumes to extract more representative high-level features for CMBs, and hence achieve a much better detection accuracy. To further improve the detection performance while reducing the computational cost, we propose a cascaded framework under 3D CNNs for the task of CMB detection. We first exploit a 3D fully convolutional network (FCN) strategy to retrieve the candidates with high probabilities of being CMBs, and then apply a well-trained 3D CNN discrimination model to distinguish CMBs from hard mimics. Compared with traditional sliding window strategy, the proposed 3D FCN strategy can remove massive redundant computations and dramatically speed up the detection process. We constructed a large dataset with 320 volumetric MR scans and performed extensive experiments to validate the proposed method, which achieved a high sensitivity of 93.16% with an average number of 2.74 false positives per subject, outperforming previous methods using low-level descriptors or 2D CNNs by a significant margin. The proposed method, in principle, can be adapted to other biomarker detection tasks from volumetric medical data.

Automated segmentation of chronic stroke lesions using LINDA: Lesion identification with neighborhood data analysis

The gold standard for identifying stroke lesions is manual tracing, a method that is known to be observer dependent and time consuming, thus impractical for big data studies. We propose LINDA (Lesion Identification with Neighborhood Data Analysis), an automated segmentation algorithm capable of learning the relationship between existing manual segmentations and a single T1-weighted MRI. A dataset of 60 left hemispheric chronic stroke patients is used to build the method and test it with k-fold and leave-one-out procedures. With respect to manual tracings, predicted lesion maps showed a mean dice overlap of 0.696 ± 0.16, Hausdorff distance of 17.9 ± 9.8 mm, and average displacement of 2.54 ± 1.38 mm. The manual and predicted lesion volumes correlated at r = 0.961. An additional dataset of 45 patients was utilized to test LINDA with independent data, achieving high accuracy rates and confirming its cross-institutional applicability. To investigate the cost of moving from manual tracings to automated segmentation, we performed comparative lesion-to-symptom mapping (LSM) on five behavioral scores. Predicted and manual lesions produced similar neuro-cognitive maps, albeit with some discussed discrepancies. Of note, region-wise LSM was more robust to the prediction error than voxel-wise LSM. Our results show that, while several limitations exist, our current results compete with or exceed the state-of-the-art, producing consistent predictions, very low failure rates, and transferable knowledge between labs. This work also establishes a new viewpoint on evaluating automated methods not only with segmentation accuracy but also with brain-behavior relationships. LINDA is made available online with trained models from over 100 patients.

Computer-aided detection of cerebral microbleeds in susceptibility-weighted imaging

Susceptibility-weighted imaging (SWI) is recognized as the preferred MRI technique for visualizing cerebral vasculature and related pathologies such as cerebral microbleeds (CMBs). Manual identification of CMBs is time-consuming, has limited reliability and reproducibility, and is prone to misinterpretation. In this paper, a novel computer-aided microbleed detection technique based on machine learning is presented: First, spherical-like objects (potential CMB candidates) with their corresponding bounding boxes were detected using a novel multi-scale Laplacian of Gaussian technique. A set of robust 3-dimensional Radon- and Hessian-based shape descriptors within each bounding box were then extracted to train a cascade of binary random forests (RF). The cascade consists of consecutive independent RF classifiers with low to high posterior probability constraints to handle imbalanced training sets (CMBs and non-CMBs), and to progressively improve detection rates. The proposed method was validated on 66 subjects whose CMBs were manually stratified into "possible" and "definite" by two medical experts. The proposed technique achieved a sensitivity of 87% and an average false detection rate of 27.1 CMBs per subject on the "possible and definite" set. A sensitivity of 93% and false detection rate of 10 CMBs per subject was also achieved on the "definite" set. The proposed automated approach outperforms state of the art methods, and promises to enhance manual expert screening. Benefits include improved reliability, minimization of intra-rater variability and a reduction in assessment time.

Susceptibility Weighted Imaging and Mapping of Micro-Hemorrhages and Major Deep Veins after Traumatic Brain Injury

Micro-hemorrhages are a common result of traumatic brain injury (TBI), which can be quantified with susceptibility weighted imaging and mapping (SWIM), a quantitative susceptibility mapping approach. A total of 23 TBI patients (five women, 18 men; median age, 41.25 years old; range, 21.69-67.75 years) with an average Glasgow Coma Scale score of 7 (range, 3-15) at admission were recruited at mean 149 d (range, 57-366) after injury. Susceptibility-weighted imaging data were collected and post-processed to create SWIM images. The susceptibility value of small hemorrhages (diameter ≤10 mm) and major deep veins (right septal, left septal, central septal, right thalamostriate, left thalamostriate, internal cerebral, right basal vein of Rosenthal, left basal vein of Rosenthal, and pial veins) were evaluated. Different susceptibility thresholds were tested to determine SWIM's sensitivity and specificity for differentiating hemorrhages from the veins. A total of 253 deep veins and 173 small hemorrhages were identified and evaluated. The mean susceptibility of hemorrhages was 435±206 parts per billion (ppb) and the mean susceptibility of deep veins was 108±56 ppb. Hemorrhages showed a significantly higher susceptibility than all deep veins (p<0.001). With different thresholds (250, 227 and 200 ppb), the specificity was 97%, 95%, and 92%, and the sensitivity was 84%, 90%, and 92%, respectively. These results show that SWIM could be used to differentiate hemorrhages from veins in TBI patients in a semi-automated manner with reasonable sensitivity and specificity. A larger cohort will be needed to validate these findings.

Cerebral microvascular lesions on high-resolution 7-Tesla MRI in patients with type 2 diabetes

Cerebral small vessel disease, including microvascular lesions, is considered to play an important role in the development of type 2 diabetes mellitus (T2DM)-associated cognitive deficits. With ultra-high field MRI, microvascular lesions (e.g., microinfarcts and microbleeds) can now be visualized in vivo. For the current study, 48 nondemented older individuals with T2DM (mean age 70.3 ± 4.1 years) and 49 age-, sex-, and education-matched control subjects underwent a 7-Tesla brain MRI scan and a detailed cognitive assessment. The occurrence of cortical microinfarcts and cerebral microbleeds was assessed on fluid-attenuated inversion recovery and T1-weighted and T2*-weighted images, respectively, compared between the groups, and related to cognitive performance. Microinfarcts were found in 38% of control subjects and 48% of patients with T2DM. Microbleeds were present in 41% of control subjects and 33% of patients (all P > 0.05). The presence and number of microinfarcts or microbleeds were unrelated to cognitive performance. This study showed that microvascular brain lesions on ultra-high field MRI are not significantly more common in well-controlled patients with T2DM than in control subjects.

Semi-Automated Detection of Cerebral Microbleeds on 3.0 T MR Images

Cerebral microbleeds are associated with vascular disease and dementia. They can be detected on MRI and receive increasing attention. Visual rating is the current standard for microbleed detection, but is rater dependent, has limited reproducibility, modest sensitivity, and can be time-consuming. The goal of the current study is to present a tool for semi-automated detection of microbleeds that can assist human raters in the rating procedure. The radial symmetry transform is originally a technique to highlight circular-shaped objects in two-dimensional images. In the current study, the three-dimensional radial symmetry transform was adapted to detect spherical microbleeds in a series of 72 patients from our hospital, for whom a ground truth visual rating was made by four raters. Potential microbleeds were automatically identified on T2*-weighted 3.0 T MRI scans and the results were visually checked to identify microbleeds. Final ratings of the radial symmetry transform were compared to human ratings. After implementing and optimizing the radial symmetry transform, the method achieved a high sensitivity, while maintaining a modest number of false positives. Depending on the settings, sensitivities ranged from 65%-84% compared to the ground truth rating. Rating of the processed images required 1-2 minutes per participant, in which 20-96 false positive locations per participant were censored. Sensitivities of individual raters ranged from 39%-86% compared to the ground truth and required 5-10 minutes per participant per rater. The sensitivities that were achieved by the radial symmetry transform are similar to those of individual experienced human raters, demonstrating its feasibility and usefulness for semi-automated microbleed detection.

Computer-aided detection of radiation-induced cerebral microbleeds on susceptibility-weighted MR images

Recent interest in exploring the clinical relevance of cerebral microbleeds (CMBs) has motivated the search for a fast and accurate method to detect them. Visual inspection of CMBs on MR images is a lengthy, arduous task that is highly prone to human error because of their small size and wide distribution throughout the brain. Several computer-aided CMB detection algorithms have recently been proposed in the literature, but their diagnostic accuracy, computation time, and robustness are still in need of improvement. In this study, we developed and tested a semi-automated method for identifying CMBs on minimum intensity projected susceptibility-weighted MR images that are routinely used in clinical practice to visually identify CMBs. The algorithm utilized the 2D fast radial symmetry transform to initially detect putative CMBs. Falsely identified CMBs were then eliminated by examining geometric features measured after performing 3D region growing on the potential CMB candidates. This algorithm was evaluated in 15 patients with brain tumors who exhibited CMBs on susceptibility-weighted images due to prior external beam radiation therapy. Our method achieved heightened sensitivity and acceptable amount of false positives compared to prior methods without compromising computation speed. Its superior performance and simple, accelerated processing make it easily adaptable for detecting CMBs in the clinic and expandable to a wide array of neurological disorders.