paper_authors: Tapan Ganatma Nakkina, Adithyaa Karthikeyan, Yuhao Zhong, Ceyhun Eksin, Satish T. S. Bukkapatnam
for: automatic detection of surface defects in highly textured backgrounds
methods: graph Fourier analysis and convolutional neural network (1D-CNN)
results: classification accuracy of 99.4% and explainable AI method using SHAP to analyze the trained 1D-CNN modelHere’s the full text in Simplified Chinese:
for: 本研究旨在自动检测生产过程中的表面问题，特别是在高度文化背景下。
methods: Graph Fourier分析和卷积神经网络(1D-CNN)。
results: 对于具有高度文化背景的图像进行自动检测，以获得99.4%的准确率和可解释的AI方法使用SHAP来分析训练好的1D-CNN模型，并发现低频率的graph傅立叶波形在精确地local化表面问题中发挥重要作用。Abstract
In the realm of industrial manufacturing, product inspection remains a significant bottleneck, with only a small fraction of manufactured items undergoing inspection for surface defects. Advances in imaging systems and AI can allow automated full inspection of manufactured surfaces. However, even the most contemporary imaging and machine learning methods perform poorly for detecting defects in images with highly textured backgrounds, that stem from diverse manufacturing processes. This paper introduces an approach based on graph Fourier analysis to automatically identify defective images, as well as crucial graph Fourier coefficients that inform the defects in images amidst highly textured backgrounds. The approach capitalizes on the ability of graph representations to capture the complex dynamics inherent in high-dimensional data, preserving crucial locality properties in a lower dimensional space. A convolutional neural network model (1D-CNN) was trained with the coefficients of the graph Fourier transform of the images as the input to identify, with classification accuracy of 99.4%, if the image contains a defect. An explainable AI method using SHAP (SHapley Additive exPlanations) was used to further analyze the trained 1D-CNN model to discern important spectral coefficients for each image. This approach sheds light on the crucial contribution of low-frequency graph eigen waveforms to precisely localize surface defects in images, thereby advancing the realization of zero-defect manufacturing.
摘要
在工业生产领域，产品检测仍然是一个重要的瓶颈，只有一小部分生产item进行表面检测。技术进步和人工智能可以自动检测全部生产表面的瑕疵。然而，even the most contemporary imaging and machine learning methods perform poorly for detecting defects in images with highly textured backgrounds, which stem from diverse manufacturing processes.这篇论文提出了一种基于图 Fourier分析的方法，可以自动识别瑕疵图像，以及图像中的关键图 Fourier 约束 coefficient。这种方法利用图表示法 capture高维数据中的复杂动态特性，保留图像中的重要地方性质。一种基于1D-CNN的卷积神经网络模型被训练使用图 Fourier 约束的图像 coefficients 作为输入，可以准确地判断图像是否包含瑕疵。使用 SHAP 方法进行解释的 AI 方法可以进一步分析训练好的 1D-CNN 模型，以便了解每个图像中关键的spectral coefficient。这种方法显示了低频图 eigen waveforms 在准确地Localiza表面瑕疵图像中的重要贡献，从而推进零瑕疵生产的实现。
A Novel Deep Clustering Framework for Fine-Scale Parcellation of Amygdala Using dMRI Tractography
results: 研究结果表明，使用提议的方法可以在腾脑囊中分割出九个独特的 parcels，这些 parcels 在不同的主题中具有good correspondence。Abstract
The amygdala plays a vital role in emotional processing and exhibits structural diversity that necessitates fine-scale parcellation for a comprehensive understanding of its anatomico-functional correlations. Diffusion MRI tractography is an advanced imaging technique that can estimate the brain's white matter structural connectivity to potentially reveal the topography of the amygdala for studying its subdivisions. In this work, we present a deep clustering pipeline to perform automated, fine-scale parcellation of the amygdala using diffusion MRI tractography. First, we incorporate a newly proposed deep learning approach to enable accurate segmentation of the amygdala directly on the dMRI data. Next, we design a novel streamline clustering-based structural connectivity feature for a robust representation of voxels within the amygdala. Finally, we improve the popular joint dimensionality reduction and k-means clustering approach to enable amygdala parcellation at a finer scale. With the proposed method, we obtain nine unique amygdala parcels. Experiments show that these parcels can be consistently identified across subjects and have good correspondence to the widely used coarse-scale amygdala parcellation.
摘要
《amygdala的多样性和其相关功能的研究》Introduction:The amygdala is a crucial structure involved in emotional processing, and its anatomical diversity has made it challenging to study its function. Recent advances in diffusion MRI tractography have enabled the estimation of white matter structural connectivity, which can potentially reveal the topography of the amygdala and its subdivisions. In this study, we propose a deep clustering pipeline to perform automated, fine-scale parcellation of the amygdala using diffusion MRI tractography.Methodology:1. Deep Learning Approach: We incorporate a newly proposed deep learning approach to accurately segment the amygdala directly on the dMRI data.2. Streamline Clustering-based Structural Connectivity Feature: We design a novel streamline clustering-based structural connectivity feature to robustly represent voxels within the amygdala.3. Improved Joint Dimensionality Reduction and k-Means Clustering: We improve the popular joint dimensionality reduction and k-means clustering approach to enable amygdala parcellation at a finer scale.Results:With the proposed method, we obtain nine unique amygdala parcels that can be consistently identified across subjects and have good correspondence to the widely used coarse-scale amygdala parcellation.Conclusion:Our proposed method provides a fine-scale parcellation of the amygdala, which can help researchers better understand the anatomical and functional diversity of this structure and its role in emotional processing.