Evaluating synthetic neuroimaging data augmentation for automatic brain tumour segmentation with a deep fully-convolutional network.

Gliomas observed in medical images require expert neuro-radiologist evaluation for treatment planning and monitoring, motivating development of intelligent systems capable of automating aspects of tumour evaluation. Deep learning models for automatic image segmentation rely on the amount and quality of training data. In this study we developed a neuroimaging synthesis technique to augment data for training fully-convolutional networks (U-nets) to perform automatic glioma segmentation. We used StyleGAN2-ada to simultaneously generate fluid-attenuated inversion recovery (FLAIR) magnetic resonance images and corresponding glioma segmentation masks. Synthetic data were successively added to real training data (n = 2751) in fourteen rounds of 1000 and used to train U-nets that were evaluated on held-out validation (n = 590) and test sets (n = 588). U-nets were trained with and without geometric augmentation (translation, zoom and shear), and Dice coefficients were computed to evaluate segmentation performance. We also monitored the number of training iterations before stopping, total training time, and time per iteration to evaluate computational costs associated with training each U-net. Synthetic data augmentation yielded marginal improvements in Dice coefficients (validation set +0.0409, test set +0.0355), whereas geometric augmentation improved generalization (standard deviation between training, validation and test set performances of 0.01 with, and 0.04 without geometric augmentation). Based on the modest performance gains for automatic glioma segmentation we find it hard to justify the computational expense of developing a synthetic image generation pipeline. Future work may seek to optimize the efficiency of synthetic data generation for augmentation of neuroimaging data.

A simultaneous EEG-fNIRS dataset of the visual cognitive motivation study in healthy adults.

This article described a publicly available dataset of the visual cognitive motivation study in healthy adults. To gain an in-depth understanding and insights into motivation, Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) were measured simultaneously at shared locations while participants performed a visual cognitive motivation task. The participants' choices in the cognitive motivation task were recorded. The effects of their motivation were identified in the recognition test afterward. This dataset comprised EEG and fNIRS data from sixteen healthy adults (age: 21- 37 years; 14 males and 2 females) during the cognitive motivation task with visual scenic stimuli. In addition, the motivation and the corresponding motivation effect were also provided. This dataset provides understanding and analyzing opportunities for the process of attention and decision while the brain undergoes an induced motivated state and its effect on the recognition performance.

Decoding violated sensory expectations from the auditory cortex of anaesthetised mice: Hierarchical recurrent neural network depicts separate 'danger' and 'safety' units.

The ability to respond appropriately to sensory information received from the external environment is among the most fundamental capabilities of central nervous systems. In the auditory domain, processes underlying this behaviour are studied by measuring auditory-evoked electrophysiology during sequences of sounds with predetermined regularities. Identifying neural correlates of ensuing auditory novelty responses is supported by research in experimental animals. In the present study, we reanalysed epidural field potential recordings from the auditory cortex of anaesthetised mice during frequency and intensity oddball stimulation. Multivariate pattern analysis (MVPA) and hierarchical recurrent neural network (RNN) modelling were adopted to explore these data with greater resolution than previously considered using conventional methods. Time-wise and generalised temporal decoding MVPA approaches revealed previously underestimated asymmetry between responses to sound-level transitions in the intensity oddball paradigm, in contrast with tone frequency changes. After training, the cross-validated RNN model architecture with four hidden layers produced output waveforms in response to simulated auditory inputs that were strongly correlated with grand-average auditory-evoked potential waveforms (r2 > .9). Units in hidden layers were classified based on their temporal response properties and characterised using principal component analysis and sample entropy. These demonstrated spontaneous alpha rhythms, sound onset and offset responses and putative 'safety' and 'danger' units activated by relatively inconspicuous and salient changes in auditory inputs, respectively. The hypothesised existence of corresponding biological neural sources is naturally derived from this model. If proven, this could have significant implications for prevailing theories of auditory processing.

More evidence for a long-latency mismatch response in urethane-anaesthetised mice.

Long-latency mismatch responses to oddball stimuli have recently been observed from anaesthetised rodents. This electrophysiological activity is viewed through 200 to 700 ms post-stimulus; a window that is typically obstructed from analysis by the response to subsequent stimuli in the auditory paradigm. A novel difference waveform computation using two adjoining evoked responses has enabled visualisation of this activity over a longer window than previously available. In the present study, this technique was retroactively applied to data from 13 urethane-anaesthetised mice. Oddball paradigm waveforms were compared with those of a many-standards control sequence, confirming that oddball stimuli evoked long-latency potentials that did not arise from standard or control stimuli. Statistical tests were performed to identify regions of significant difference. Oddball-induced mismatch responses were found to display significantly greater long-latency potentials than identical stimuli presented in an equal-probability context. As such, it may be concluded that long-latency potentials were evoked by the oddball condition. How this feature of the anaesthetised rodent mismatch response relates to human mismatch negativity is unclear, although it may be tentatively linked to the human P3a component, which emerges downstream from mismatch negativity under certain conditions. These results demonstrate that the time dynamics of mismatch responses from anaesthetised rodents are more extensive than previously considered.

Multiscale Entropy as a New Feature for EEG and fNIRS Analysis.

The present study aims to apply multiscale entropy (MSE) to analyse brain activity in terms of brain complexity levels and to use simultaneous electroencephalogram and functional near-infrared spectroscopy (EEG/fNIRS) recordings for brain functional analysis. A memory task was selected to demonstrate the potential of this multimodality approach since memory is a highly complex neurocognitive process, and the mechanisms governing selective retention of memories are not fully understood by other approaches. In this study, 15 healthy participants with normal colour vision participated in the visual memory task, which involved the making the executive decision of remembering or forgetting the visual stimuli based on his/her own will. In a continuous stimulus set, 250 indoor/outdoor scenes were presented at random, between periods of fixation on a black background. The participants were instructed to make a binary choice indicating whether they wished to remember or forget the image; both stimulus and response times were stored for analysis. The participants then performed a scene recognition test to confirm whether or not they remembered the images. The results revealed that the participants intentionally memorising a visual scene demonstrate significantly greater brain complexity levels in the prefrontal and frontal lobe than when purposefully forgetting a scene; p < 0.05 (two-tailed). This suggests that simultaneous EEG and fNIRS can be used for brain functional analysis, and MSE might be the potential indicator for this multimodality approach.

Investigating the Effect of Intrinsic Motivation on Alpha Desynchronization Using Sample Entropy.

The effect of motivation and attention could play an important role in providing personalized learning services and improving learners toward smart education. These effects on brain activity could be quantified by EEG and open the path to analyze the efficiency of services during the learning process. Many studies reported the appearance of EEG alpha desynchronization during the attention period, resulting in better cognitive performance. Motivation was also found to be reflected in EEG. This study investigated the effect of intrinsic motivation on the alpha desynchronization pattern in terms of the complexity of time series data. The sample entropy method was used to quantify the complexity of event-related spectral perturbation (ERSP) of EEG data. We found that when participants can remember the stimulus, ERSP was significantly less complex than when they cannot. However, the effect of intrinsic motivation cannot be defined by using sample entropy directly. ERSP's main effect showed that motivation affects the complexity of ERSP data; longer continuous alpha desynchronization patterns were found when participants were motivated. Therefore, we introduced an algorithm to identify the longest continuous alpha desynchronization pattern. The method allowed us to understand that intrinsic motivation has an effect on recognition at the frontal and left parietal area directly.

Measuring brain activation by using baseline-normalized event-related spectral perturbation in working memory task.

Understanding the cognitive function of human brain is an important step in providing scientific evidence which could help us improve the condition of memory disorders, slow down its progress or at least help the patients retain some important matters. In this study, we aimed to provide additional scientific evidence with more insight on how the brain functions at a good/bad cognitive state than the usual statistical analysis. We introduced the brain activation measurement using baseline-normalized ERSP to determine the activation of EEG data from stimuli. These active points over a period of time could reflect brain synchronization due to stimuli. We also demonstrated the use of proposed measure on attention working memory data. The results indicate the potential of using the proposed measurement in categorizing the brain cognitive state and identifying some important factors to provide additional evidence to the field in the future.