Abstract
Cerebral microbleeds (CMB) are increasingly present with aging and can reveal vascular pathologies associated with neurodegeneration. Deep learning-based classifiers can detect and quantify CMB from MRI, such as susceptibility imaging, but are challenging to train because of the limited availability of ground truth and many confounding imaging features, such as vessels or infarcts. In this study, we present a novel generative adversarial network (GAN) that has been trained to generate three-dimensional lesions, conditioned by volume and location. This allows one to investigate CMB characteristics and create large training datasets for deep learning-based detectors. We demonstrate the benefit of this approach by achieving state-of-the-art CMB detection of real CMB using a convolutional neural network classifier trained on synthetic CMB. Moreover, we showed that our proposed 3D lesion GAN model can be applied on unseen dataset, with different MRI parameters and diseases, to generate synthetic lesions with high diversity and without needing laboriously marked ground truth.
Highlights
Cerebral microbleeds (CMB) are small hypointense spots on brain MRI susceptibility-weighted imaging (SWI), known as chronic blood products in normal brain tissues (Greenberg et al, 2009)
The main contribution of this paper is twofold: (1) we investigated whether a new generative adversarial network (GAN) model could create synthetic CMB on SWI conditioned on location and volume and (2) we investigated whether synthetic lesions generalize to a new unseen dataset with a different population, MRI parameters, and pathologies
We investigated whether using the proposed synthetic CMB (sCMB) for training could improve the performance of the classifier for detecting real lesions compared to other recent data augmentation approaches
Summary
Cerebral microbleeds (CMB) are small hypointense spots on brain MRI susceptibility-weighted imaging (SWI), known as chronic blood products in normal (or near-normal) brain tissues (Greenberg et al, 2009). Most automated CMB detections use machine learning (Barnes et al, 2011; Bian et al, 2013; Fazlollahi et al, 2015; Roy et al, 2015), including deep learning methods, achieving superior performance by increasing the sensitivity to 95.8 and reducing the number of false positives to 1.6 (Dou et al, 2016; Zhang et al, 2017; Liu et al, 2019; Faryna et al, 2021).
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.
