Search

Objectives: This study draws on advances in Doppler ultrasound bubble sizing to investigate whether high volumes of macro-bubbles entering the brain during cardiac surgery increase the risk of new cerebral microbleeds (CMBs), ischemic MR lesions, or post-operative cognitive decline (POCD). Methods: Transcranial Doppler (TCD) ultrasound recordings were analysed to estimate numbers of emboli and macrobubbles (>100 μm) entering the brain during cardiac surgery. Logistic regression was used to explore the hypothesis that emboli characteristics affect the incidence of new brain injuries identified through pre- and post-operative MRI and neuropsychological testing. Results: TCD, MRI, and neuropsychological test data were compared between 28 valve and 18 CABG patients. Although valve patients received over twice as many emboli per procedure [median: 1995 vs. 859, p = .004], and seven times as many macro-bubbles [median: 218 vs. 28, p = .001], high volumes of macrobubbles were not found to be significantly associated with new CMBs, new ischaemic lesions, or POCD. The odds of acquiring new CMBs increased by approximately 5% [95% CI: 1 to 10%] for every embolus detected in the first minute after the release of the aortic cross-clamp (AxC). Logistic regression models also confirmed previous findings that cardiopulmonary bypass time and valve surgery were significant predictors for new CMBs (both p = .03). Logistic regression analysis estimated an increase in the odds of acquiring new CMBs of 6% [95% CI: 1 to 12%] for every minute of bypass time over 91 mins. Conclusions: This small study provides new information about the properties and numbers of bubbles entering the brain during surgery, but found no evidence to substantiate a direct link between large numbers of macrobubbles and adverse cognitive or MR outcome.

Algorithms for fusing information acquired from different imaging modalities have shown to improve the segmentation results of various applications in the medical field. Motivated by recent successes achieved using densely connected fusion networks, we propose a new fusion architecture for the purpose of 3D segmentation in multi-modal brain MRI volumes. Based on a hyper-densely connected convolutional neural network, our network features in promoting a progressive information abstraction process, introducing a new module – ResFuse to merge and normalize features from different modalities and adopting combo loss for handing data imbalances. The proposed approach is evaluated on both an outsourced dataset for acute ischemic stroke lesion segmentation and a public dataset for infant brain segmentation (iSeg-17). The experiment results show our approach achieves superior performances for both datasets compared to the state-of-art fusion network.

In this paper we propose a 2D deep residual Unet with 104 convolutional layers (DR-Unet104) for lesion segmentation in brain MRIs. We make multiple additions to the Unet architecture, including adding the ‘bottleneck’ residual block to the Unet encoder and adding dropout after each convolution block stack. We verified the effect of including the regularization of dropout with small rate (e.g. 0.2) on the architecture, and found a dropout of 0.2 improved the overall performance compared to no dropout, or a dropout of 0.5. We evaluated the proposed architecture as part of the Multimodal Brain Tumor Segmentation (BraTS) 2020 Challenge and compared our method to DeepLabV3+ with a ResNet-V2–152 backbone. We found the DR-Unet104 achieved a mean dice score coefficient of 0.8862, 0.6756 and 0.6721 for validation data, whole tumor, enhancing tumor and tumor core respectively, an overall improvement on 0.8770, 0.65242 and 0.68134 achieved by DeepLabV3+. Our method produced a final mean DSC of 0.8673, 0.7514 and 0.7983 on whole tumor, enhancing tumor and tumor core on the challenge’s testing data. We produce a competitive lesion segmentation architecture, despite only using 2D convolutions, having the added benefit that it can be used on lower power computers than a 3D architecture. The source code and trained model for this work is openly available at https://github.com/jordan-colman/DR-Unet104.

The fusion of multi-modality information has proved effective at improving the segmentation results of targeted regions (e.g., tumours, lesions or organs) of medical images. In particular, layer-level fusion represented by DenseNet has demonstrated a promising level of performance for various medical segmentation tasks. Using stroke and infant brain segmentation as example of ongoing challenging applications involving multi-modal images, we investigate whether it is possible to create a more effective of parsimonious fusion architecture based on the state-of-art fusion network - HyperDenseNet. Our hypothesis is that by fully fusing features throughout the entire network from different modalities, this not only increases network computation complexity but also interferes with the unique feature learning of each modality. Nine new network variants involving different fusion points and mechanisms are proposed. Their performances are evaluated on public datasets including iSeg-2017 and ISLES15-SSIS and an acute stroke lesion dataset collected by medical professionals. The experiment results show that of the nine proposed variants, the ‘mid-dense’ fusion network (named as MidFusNet) is able to achieve a performance comparable to the state-of-art fusion architecture, but with a much more parsimonious network (i.e., ~3.5 million parameters less compared to the baseline network for three modalities).