摘要
Atypical visual attention is a hallmark of autism spectrum disorder (ASD). Identifying the attention features accurately discerning between people with ASD and typically developing (TD) at the individual level remains a challenge. In this study, we developed a new systematic framework combining high accuracy deep learning classification, deep learning segmentation, image ablation and a direct measurement of classification ability to identify the discriminative features for autism identification. Our two-stream model achieved the state-of-the-art performance with a classification accuracy of 0.95. Using this framework, two new categories of features, Food & drink and Outdoor-objects, were identified as discriminative attention features, in addition to the previously reported features including Center-object and Human-faces, etc. Altered attention to the new categories helps to understand related atypical behaviors in ASD. Importantly, the area under curve (AUC) based on the combined top-9 features identified in this study was 0.92, allowing an accurate classification at the individual level. We also obtained a small but informative dataset of 12 images with an AUC of 0.86, suggesting a potentially efficient approach for the clinical diagnosis of ASD. Together, our deep learning framework based on VGG-16 provides a novel and powerful tool to recognize and understand abnormal visual attention in ASD, which will, in turn, facilitate the identification of biomarkers for ASD. [GRAPHICS] .
学科与关键词
- Automatic classification of ASD children using appearance-based features from videosLi, Jing*; Chen, Zejin; Li, Gongfa; Ouyang, Gaoxiang; Li, XiaoliNEUROCOMPUTING, 2022, 470: 40-50.被引 2
- A deep learning algorithm-based visual strategy intervention study for children with autism spectrum disorders-extraction and detection of children's behavioral featuresLin, Y.*European Review for Medical and Pharmacological Sciences, 2023, 27(11): 4914-4928.被引 1
- ADINet: Attention-guided dual-branch integration network for atypical visual saliency predictionWang, Qi; Zhou, Xiaofei*; Zhu, Zunjie; Zhang, Jiyong; Yan, ChenggangJOURNAL OF ELECTRONIC IMAGING, 2023, 32(2): 023047.
