Abstract
ObjectiveTo supply the attending doctor’s diagnosis of the persisting of cerebral small vessel disease and speed up their work effectively, we developed a “deep learning system (DLS)” for cerebral small vessel disease predication. The reliability and the disease area segmentation accuracy, of the proposed DLS, was also investigated.MethodsA deep learning model based on the convolutional neural network was designed and trained on 1,010 DWI b1000 images from 1010 patients diagnosed with segmentation of subcortical infarction, 359 T2∗ images from 359 patients diagnosed with segmentation of cerebral microbleed, as well as 824 T1-weighted and T2-FLAIR images from 824 patients diagnosed with segmentation of lacune and WMH. Dicw accuracy, recall, and f1-score were calculated to evaluate the proposed deep learning model. Finally, we also compared the DLS prediction capability with that of 6 doctors with 3 to 18 years’ clinical experience (8 ± 6 years).ResultsThe results support that an appropriately trained DLS can achieve a high-level dice accuracy, 0.598 in the training section over all these four classifications on 30 patients (0.576 for young neuroradiologists), validation accuracy is 0.496 in lacune, 0.666 in WMH, 0.728 in subcortical infarction, and 0.503 in cerebral microbleeds. It is comparable to attending doctor with a few years of experience, regardless of whether the emphasis is placed on the segmentation or detection of lesions with less time-spending compared with manual analysis, about 4.4 s/case, which is dramatically less than doctors about 634 s/case.ConclusionThe results of our comparison lend support to the case that an appropriately trained DLS can be trusted to the same extent as one would trust an attending doctor with a few years of experience, regardless of whether the emphasis is placed on the segmentation or detection of lesions.
Highlights
The Cerebral Small Vessel Disease (CSVD) is an umbrella term covering a variety of abnormalities related to small blood vessels in the brain, which can be caused by many diseases, such as plaque accumulation in the small vessel, small vessel inflammation, and persisted chronic damage in the small vessel (Go et al, 2012; Rincon and Wright, 2014)
It is critical to define the severity of CSVD by a quantitative assessment from magnetic resonance imaging (MRI), which is relevant to the risk of stroke
Considering each of the four CSVD individually, the dice accuracy, as well as region-wise F1 score achieved by our model, is higher than that of the doctors in the segmentation of lacune, white matter hyperintensities (WMH) and subcortical infarction, as can be verified from Table 4 and Figures 5–8
Summary
The Cerebral Small Vessel Disease (CSVD) is an umbrella term covering a variety of abnormalities related to small blood vessels in the brain, which can be caused by many diseases, such as plaque accumulation in the small vessel, small vessel inflammation, and persisted chronic damage in the small vessel (hypertension) (Go et al, 2012; Rincon and Wright, 2014). The CSVD can be diagnosed by medical professionals based on magnetic resonance imaging (MRI) (Noguchi et al, 1997; Greenberg et al, 2009; Debette and Markus, 2010). Signs of CSVD on conventional MRI include lacunes, white matter hyperintensities (WMH), recent small subcortical infarcts, prominent perivascular spaces, cerebral microbleeds, and atrophy (Wardlaw et al, 2013). CSVD has been suggested to be an essential source of morbidity associated with ischaemic and hemorrhagic stroke, dementia, and depression (Pantoni, 2010). It is critical to define the severity of CSVD by a quantitative assessment from MRI, which is relevant to the risk of stroke. The severity of CSVD is mainly evaluated by manual semi-quantitative or qualitative methods at present, which is time-consuming, laborious, and subjective (Rensma et al, 2018)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
