The structural neural correlates of atypical facial expression recognition in autism spectrum disorder

Improving facial expression recognition for autism with IDenseNet-RCAformer under occlusions

The term 'autism spectrum disorder' describes a neurodevelopmental illness typified by verbal and nonverbal interaction impairments, repetitive behaviour patterns and poor social interaction. Understanding mental states from FEs is crucial for interpersonal interaction and social interaction. But when there are occlusions like glasses, facial hair or self-occlusion, it becomes harder to identify facial expressions accurately. This research tackles the issue of identifying facial expressions when parts of the face are occluded and suggests an innovative technique to tackle this difficulty. Creating a strong framework for facial expression recognition (FER) that better handles occlusions and increases recognition accuracy is the goal of this research. Therefore, we propose novel Improved DenseNet-based Residual Cross-Attention Transformer (IDenseNet-RCAformer) system to tackle the partial occlusion FER problem in autism patients. The recognition framework's efficacy is assessed using four datasets of facial expressions, and some preprocessing procedures are conducted to increase the expression recognition efficiency. After that, when recognizing expressions, a simple argmax function is applied to get a forecasted landmark position from a heatmap. Then feature extraction phase, local and global representation are captured from preprocessed images by adopting Inception-ResNet-V2 approach, Cross-Attention Transformer, respectively. Moreover, both features are fused by employing the FusionNet method, thereby enhancing system's training speed and precision. After the features are extracted, an improved DenseNet mechanism is applied to efficiently recognize some variety of facial expressions in partially occluded autism patients. A number of performance metrics are determined and analysed to demonstrate the proposed approach's effectiveness, where the IDenseNet-RCAformer performs best with an accuracy of 98.95%. According to the experimental findings, the proposed framework significantly outperforms the prior recognition frameworks in terms of recognition outcomes.

Gray matter microstructure differences in autistic males: A gray matter based spatial statistics study

BACKGROUND

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition. Understanding the brain's microstructure and its relationship to clinical characteristics is important to advance our understanding of the neural supports underlying ASD. In the current work, we implemented Gray-Matter Based Spatial Statistics (GBSS) to examine and characterize cortical microstructure and assess differences between typically developing (TD) and autistic males.

METHODS

A multi-shell diffusion MRI (dMRI) protocol was acquired from 83 TD and 70 autistic males (5-to-21-years) and fit to the DTI and NODDI models. GBSS was performed for voxelwise analysis of cortical gray matter (GM). General linear models were used to investigate group differences, while age-by-group interactions assessed age-related differences between groups. Within the ASD group, relationships between cortical microstructure and measures of autistic symptoms were investigated.

RESULTS

All dMRI measures were significantly associated with age across the GM skeleton. Group differences and age-by-group interactions are reported. Group-wise increases in neurite density in autistic individuals were observed across frontal, temporal, and occipital regions of the right hemisphere. Significant age-by-group interactions of neurite density were observed within the middle frontal gyrus, precentral gyrus, and frontal pole. Negative relationships between neurite dispersion and the ADOS-2 Calibrated Severity Scores (CSS) were observed within the ASD group.

DISCUSSION

Findings demonstrate group and age-related differences between groups in neurite density in ASD across right-hemisphere brain regions supporting cognitive processes. Results provide evidence of altered neurodevelopmental processes affecting GM microstructure in autistic males with implications for the role of cortical microstructure in the level of autistic symptoms.

CONCLUSION

Using dMRI and GBSS, our findings provide new insights into group and age-related differences of the GM microstructure in autistic males. Defining where and when these cortical GM differences arise will contribute to our understanding of brain-behavior relationships of ASD and may aid in the development and monitoring of targeted and individualized interventions.