[论文解读] A Convolutional Neural Network for gaze preference detection: A potential tool for diagnostics of autism spectrum disorder in children

Dennis Fernandez, Franklin Porras-Barrientos+4 more|arXiv (Cornell University)|Jul 28, 2020

Autism Spectrum Disorder Research参考文献 26被引用 9

一句话总结

该论文提出了一种卷积神经网络（CNN），通过分析儿童观看一分钟长、包含配对社交与抽象场景视频时的眼动追踪数据，检测与自闭症谱系障碍（ASD）相关的注视偏好模式。该模型在不同个体和摄像头条件下均实现了高准确率与强鲁棒性，可实现近实时、低资源的ASD儿童诊断筛查。

ABSTRACT

Early diagnosis of autism spectrum disorder (ASD) is known to improve the quality of life of affected individuals. However, diagnosis is often delayed even in wealthier countries including the US, largely due to the fact that gold standard diagnostic tools such as the Autism Diagnostic Observation Schedule (ADOS) and the Autism Diagnostic Interview-Revised (ADI-R) are time consuming and require expertise to administer. This trend is even more pronounced lower resources settings due to a lack of trained experts. As a result, alternative, less technical methods that leverage the unique ways in which children with ASD react to visual stimulation in a controlled environment have been developed to help facilitate early diagnosis. Previous studies have shown that, when exposed to a video that presents both social and abstract scenes side by side, a child with ASD will focus their attention towards the abstract images on the screen to a greater extent than a child without ASD. Such differential responses make it possible to implement an algorithm for the rapid diagnosis of ASD based on eye tracking against different visual stimuli. Here we propose a convolutional neural network (CNN) algorithm for gaze prediction using images extracted from a one-minute stimulus video. Our model achieved a high accuracy rate and robustness for prediction of gaze direction with independent persons and employing a different camera than the one used during testing. In addition to this, the proposed algorithm achieves a fast response time, providing a near real-time evaluation of ASD. Thereby, by applying the proposed method, we could significantly reduce the diagnosis time and facilitate the diagnosis of ASD in low resource regions.

研究动机与目标

• 开发一种快速、准确且鲁棒的计算机视觉方法，用于检测儿童的注视偏好。
• 通过在临床和低资源环境中实现快速、低专业度评估，减少自闭症谱系障碍（ASD）的诊断延迟。
• 利用自闭症儿童与神经发育正常儿童在注视模式上的差异——特别是对抽象刺激的注意力高于社交刺激——作为检测依据。
• 构建一种可实时部署且校准需求极少的工具，支持可扩展的早期诊断。
• 通过在不同摄像头和未在训练集中出现的个体上验证模型性能，确保其泛化能力。

提出的方法

• 该模型使用卷积神经网络（CNN）处理包含并排社交与抽象场景的1分钟视频刺激中提取的图像。
• 输入图像通过CNN处理，以预测注视方向，重点关注注意力是集中在社交内容还是抽象内容上。
• 网络在受控条件下暴露于视频刺激时收集的眼动追踪数据上进行训练。
• 在未参与训练的不同摄像头和个体数据上评估该方法的鲁棒性。
• 该模型设计用于实时推理，实现在诊断会话期间的近实时注视预测。
• 采用数据增强和交叉验证技术以提升泛化能力并减少过拟合。

实验结果

研究问题

• RQ1 基于一分钟视频的视觉刺激，CNN能否准确预测儿童的注视方向？
• RQ2 当在未参与训练的不同摄像头和个体数据上测试时，该注视预测模型的鲁棒性如何？
• RQ3 该模型在多大程度上可支持儿童自闭症谱系障碍（ASD）的快速、低资源筛查？
• RQ4 该模型能否可靠检测出已知的与ASD相关的注视偏好——即对抽象刺激的注意力高于社交刺激？
• RQ5 该模型能否实现适合临床部署的实时性能？

主要发现

• 所提出的CNN在预测注视方向方面表现出高准确率，即使在测试来自不同摄像头和未参与训练的个体的数据时亦然。
• 该模型在不同成像条件下表现出强鲁棒性，表明其可泛化至多样化的临床环境。
• 该系统可实现近实时评估，与传统工具（如ADOS和ADI-R）相比，显著缩短诊断时间。
• 该方法有效捕捉到与ASD相关的差异性注视偏好——即对抽象刺激的注意力高于社交刺激，支持其诊断相关性。
• 该模型的性能表明其在缺乏专业临床医生的低资源环境中具有部署潜力。
• 该方法为耗时且依赖专业知识的ASD诊断方法提供了一种可扩展、自动化的替代方案。