Machine learning trial to detect sex differences in simple sticker arts of 1606 preschool children.

BACKGROUND: Previous studies suggested that drawings made by preschool boys and girls show distinguishable differences. However, children's drawings on their own are too complexly determined and inherently ambiguous to be a reliable indicator. In the present study, we attempted to develop a machine learning algorithm for classification of sex of the subjects using children's artworks. METHODS: We studied three types of simple sticker artworks from 1606 Japanese preschool children aged 51-83 months (803 boys and 803 girls). Those artworks were processed into digitalized data. Simulated data based on the original data were also generated. Logistic regression approach was applied to each dataset to make a classifier, and run on each dataset in a stratified ten-fold cross-validation with hyperparameter tuning. A probability score was calculated in each sample and utilized for sex classification. Prediction performance was evaluated using accuracy, recall, and precision scores, as well as learning curves. RESULTS: Two models created from the original and simulated data showed comparably low metrics. The distributions of probability scores in the samples from boys and girls mostly overlapped and were indistinguishable. Learning curves of the models showed an extremely under-fitted pattern. CONCLUSIONS: Our machine learning algorithm was unable to distinguish simple sticker arts created by boys and girls. More complex tasks will enable to develop an accurate classifier.

Dynamic monitoring of brain activation under visual stimulation using fMRI--the advantage of real-time fMRI with sliding window GLM analysis.

An fMRI technique based on real-time analysis was applied to evaluate the advantages of dynamic monitoring of the t-statistics based on a general linear model. The temporal change of the t-statistics in V1 and V4 under four conditions of visual stimuli covering different visual fields with or without coloring was estimated using an incremental analysis and a sliding window analysis (SWA). The SWA not only visualized the dynamic change of the activation in response to the task conditions and switching, but also enabled us to evaluate the temporal correlation of the t-statistics among the four visual areas. It was suggested that the activity in the V4 was bilaterally organized, and the altering color stimuli gave stronger stimulation to the V1 than did the black and white stimuli. Although the activation map at each time point represents the brain activity during several task and rest blocks, a SWA will be useful to evaluate the transition of neuronal activation in response to several sequential task conditions. An incremental analysis will be useful to monitor the ongoing activation in real-time during the scan, since it gives a higher t-value according to the accumulation of volume data. These two methods will be complementary.

An fMRI study of temporal sequencing of motor regulation guided by an auditory cue--a comparison with visual guidance.

The neuronal system to process and transfer auditory information to the higher motor areas was investigated using fMRI. Two different types of internal modulation of auditory pacing (1 Hz) were combined to design a 2x2 condition experiment, and the activation was compared with that under a visual guidance. The bilateral anterior portion of the BA22 (ant-BA22) and the left BA41/42 were more extensively activated by the combined modulation condition under the auditory cue than that under the visual cue. Among the four auditory conditions with or without the two types of internal modulation, the activation in the ant-BA22 was augmented only on the left side by the combined modulation condition. The left ant-BA22 may be especially involved in integrating the external auditory cue with internal modulation, while the activation on the right side did not depend on the complexity. The role of the left BA41/42 in motor regulation may be more specific to the processing of an auditory cue than that on the right side. These two areas in the left temporal lobe may be organized as a subsystem to handle the timing of complex movements under auditory cues, while the higher motor areas in the frontal lobe support both sensory modalities for the cue. This architecture may be considered as 'audio-motor control', which is similar to the visuo-motor control of the front-parietal network.

An fMRI study of tool-use gestures: body part as object and pantomime.

A body part as object (BPO) gesture is one of the error patterns in apraxia. In the BPO gesture, people represent objects by their hands. To clarify the neuronal background of the BPO gesture, we compared the brain activation during the BPO gesture with that during ordinary pantomime in normal subjects using functional magnetic resonance imaging. Both the BPO gesture and the pantomime induced activation in the left parietal areas (Brodmann's area (BA) 7, 40), irrespective of the hand used. These areas might be activated by a common process of tool-related gestures. The BPO gesture also activated the right supramarginal gyrus (BA 40). This activation might reflect the characteristic process of BPO, the correlation of hands with tools by their forms and movements.