Cerebral Microbleed Automatic Detection System Based on the “Deep Learning”

Abstract

ObjectiveTo validate the reliability and efficiency of clinical diagnosis in practice based on a well-established system for the automatic segmentation of cerebral microbleeds (CMBs).MethodThis is a retrospective study based on Magnetic Resonance Imaging-Susceptibility Weighted Imaging (MRI-SWI) datasets from 1,615 patients (median age, 56 years; 1,115 males, 500 females) obtained between September 2018 and September 2019. All patients had been diagnosed with cerebral small vessel disease (CSVD) with clear cerebral microbleeds (CMBs) on MRI-SWI. The patients were divided into training and validation cohorts of 1,285 and 330 patients, respectively, and another 30 patients were used for internal testing. The model training and validation data were labeled layer by layer and rechecked by two neuroradiologists with 15 years of work experience. Afterward, a three-dimensional convolutional neural network (CNN) was applied to the MRI data from the training and validation cohorts to construct a deep learning system (DLS) that was tested with the 72 patients, independent of the aforementioned MRI cohort. The DLS tool was used as a segmentation program for these 72 patients. These results were evaluated and revised by five neuroradiologists and subjected to an output analysis divided into the missed label, incorrect label, and correct label. The interneuroradiologists DLS agreement rate, which was assessed using the interrater agreement kappas test, was used for the quality analysis.ResultsIn the detection and segmentation of the CMBs, the DLS achieved a Dice coefficient of 0.72. In the evaluation of the independent clinical data, the neuroradiologists reported that more than 90% of the lesions were directly detected and less than 10% of lesions were incorrectly labeled or the label was missed by our DLS. The kappa value for interneuroradiologist DLS agreement reached 0.79 on average.ConclusionBased on the results, the automatic detection and segmentation of CMBs are feasible. The proposed well-trained DLS system might represent a trusted tool for the segmentation and detection of CMB lesions.

Construction of a Medical Micro-Object Cascade Network for Automated Segmentation of Cerebral Microbleeds in Susceptibility Weighted Imaging

“…In a comparison of automated segmentation studies ( Duan et al, 2020 ), implemented CMB segmentation in non-SWI sequences, but a DSC of only 50.30% was achieved. Fan et al (2022) implemented 3D segmentation for CMBs, but a DSC of only 72.00% was achieved. There have also been studies on brain vessels ( Dang et al, 2022 ), haemorrhage strokes ( Li et al, 2021a ) and white matter hyperintensities ( Li et al, 2018 ).…”

Deep learning applications in vascular dementia using neuroimaging

“…They found that CMBs were significantly associated with greater WMH and lower total white matter fractional anisotropy. Additionally, researchers also applied deep learning on SWI for the CMBs segmentation in patients diagnosed with CSVD [36].…”

Risk of intracranial hemorrhage in patients using anticoagulant therapy for atrial fibrillation after cerebral microbleeds combined with acute ischemic stroke: a meta-analysis

“…CMBs are usually caused by CSVD (generally 2-5 mm, up to 10 mm diameter) or hemosiderin deposition in brain tissue. On imaging, CMBs manifest as round or oval scattered low signal shadows using gradient recalled echo (GRE) T2-magnetic resonance imaging (MRI) or susceptibility weighted imaging (SWI) (2,3). A 9 years follow-up study showed that CMBs did not disappear with time (4), although prevalence increased with age.…”