KYKe Yu

Ke Yu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ke Yu has a total of 37 co-authors. Here are the top co-authors by number of shared publications:

  • Kayhan Batmanghelich

    Boston University

    9 shared publications
  • Li Sun

    Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA

    4 shared publications
  • Christopher Deible

    From the School of Computing and Information, University of Pittsburgh, Pittsburgh, Pa (K.Y., Z.L.); Department of Electrical and Computer Engineering, Boston University, 8 St. Mary’s St, Office 421, Boston, MA 02215 (S.G., K.B.); Department of Radiology, University of Pittsburgh, Pittsburgh, Pa (C.D.); and Chobanian & Avedisian School of Medicine, Boston University, Boston, Mass (C.B.P.).

    2 shared publications
  • Junxiang Chen

    School of Computing and Information Department of Electrical and Computer Engineering Department of Biomedical Informatics Department of Biomedical Informatics Department of Biomedical Informatics Department of Electrical and Computer Engineering University of Pittsburgh Boston University University of Pittsburgh University of Pittsburgh University of Pittsburgh Boston University

    2 shared publications
  • Junxiang Chen

    Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA

    2 shared publications
  • Kayhan Batmanghelich

    School of Computing and Information Department of Electrical and Computer Engineering Department of Biomedical Informatics Department of Biomedical Informatics Department of Biomedical Informatics Department of Electrical and Computer Engineering University of Pittsburgh Boston University University of Pittsburgh University of Pittsburgh University of Pittsburgh Boston University

    2 shared publications

Latest Publications

  • Anatomy-specific Progression Classification in Chest Radiographs via Weakly Supervised Learning

    by Ke Yu, Shantanu Ghosh, Zhexiong Liu, Christopher Deible, Clare B. Poynton, Kayhan Batmanghelich

    “Just Accepted” papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review ...


  • DrasCLR: A self-supervised framework of learning disease-related and anatomy-specific representation for 3D lung CT images

    by Ke Yu, Li Sun, Junxiang Chen, Maxwell Reynolds, Tigmanshu Chaudhary, Kayhan Batmanghelich


  • Open Access

    Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

    by Nihal Murali, Aahlad Puli, Ke Yu, Rajesh Ranganath, Kayhan Batmanghelich

    Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and poses problems when deploying them in safety-critical applications. This paper aims to better understand the effects of spurious features through the lens of the learning dynamics of the internal neurons during the training process. We make the following observations: (1) While previous works highlight the harmful effects of spurious features on the generalization ability of DNNs, we emphasize that not all spurious features are harmful. Spurious features can be "benign" or "harmful" depending on whether they are "harder" or "easier" to learn than the core features for a given model. This definition is model and dataset-dependent. (2) We build upon this premise and use instance difficulty methods (like Prediction Depth (Baldock et al., 2021)) to quantify "easiness" for a given model and to identify this behavior during the training phase. (3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN's early layers. In other words, easy features learned by the initial layers of a DNN early during the training can (potentially) hurt model generalization. We verify our claims on medical and vision datasets, both simulated and real, and justify the empirical success of our hypothesis by showing the theoretical connections between Prediction Depth and information-theoretic concepts like V-usable information (Ethayarajh et al., 2021). Lastly, our experiments show that monitoring only accuracy during training (as is common in machine learning pipelines) is insufficient to detect spurious features. We, therefore, highlight the need for monitoring early training dynamics using suitable instance difficulty metrics.

  • Open Access

    Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling

    by Ke Yu, Stephen Albro, Giulia DeSalvo, Suraj Kothawade, Abdullah Rashwan, Sasan Tavakkol, Kayhan Batmanghelich, Xiaoqi Yin

    Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure. Active learning addresses this challenge by striving for optimum performance with minimal labeling cost by selecting the most informative and representative images for labeling. Despite its potential, active learning has been less explored in instance segmentation compared to other tasks like image classification, which require less labeling. In this study, we propose a post-hoc active learning algorithm that integrates uncertainty-based sampling with diversity-based sampling. Our proposed algorithm is not only simple and easy to implement, but it also delivers superior performance on various datasets. Its practical application is demonstrated on a real-world overhead imagery dataset, where it increases the labeling efficiency fivefold.


  • Considering the Spatial Structure of the Road Network in Pavement Deterioration Modeling

    by Lu Gao, Ke Yu, Pan Lu

    Pavement deterioration modeling is important in providing information with respect to the future state of the road network and in determining the needs of preventive maintenance or rehabilitation treatments. This research incorporated the spatial dependence of the road network into pavement deterioration modeling through a graph neural network (GNN). The key motivation of using a GNN for pavement performance modeling is the ability to easily and directly exploit the rich structural information in the network. This paper explored if considering the spatial structure of the road network will improve the prediction performance of the deterioration models. The data used in this research comprises a large pavement condition dataset with more than a half million observations taken from the Pavement Management Information System maintained by the Texas Department of Transportation. The promising comparison results indicate that pavement deterioration prediction models perform better when the spatial relationship is considered.


  • Open Access

    DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Images

    by Ke Yu, Li Sun, Junxiang Chen, Max Reynolds, Tigmanshu Chaudhary, Kayhan Batmanghelich

    Large-scale volumetric medical images with annotation are rare, costly, and time prohibitive to acquire. Self-supervised learning (SSL) offers a promising pre-training and feature extraction solution for many downstream tasks, as it only uses unlabeled data. Recently, SSL methods based on instance discrimination have gained popularity in the medical imaging domain. However, SSL pre-trained encoders may use many clues in the image to discriminate an instance that are not necessarily disease-related. Moreover, pathological patterns are often subtle and heterogeneous, requiring the ability of the desired method to represent anatomy-specific features that are sensitive to abnormal changes in different body parts. In this work, we present a novel SSL framework, named DrasCLR, for 3D medical imaging to overcome these challenges. We propose two domain-specific contrastive learning strategies: one aims to capture subtle disease patterns inside a local anatomical region, and the other aims to represent severe disease patterns that span larger regions. We formulate the encoder using conditional hyper-parameterized network, in which the parameters are dependant on the anatomical location, to extract anatomically sensitive features. Extensive experiments on large-scale computer tomography (CT) datasets of lung images show that our method improves the performance of many downstream prediction and segmentation tasks. The patient-level representation improves the performance of the patient survival prediction task. We show how our method can detect emphysema subtypes via dense prediction. We demonstrate that fine-tuning the pre-trained model can significantly reduce annotation efforts without sacrificing emphysema detection accuracy. Our ablation study highlights the importance of incorporating anatomical context into the SSL framework.

  • Anatomy-Guided Weakly-Supervised Abnormality Localization in Chest X-rays

    by Ke Yu, Shantanu Ghosh, Zhexiong Liu, Christopher Deible, Kayhan Batmanghelich

    Creating a large-scale dataset of abnormality annotation on medical images is a labor-intensive and costly task. Leveraging weak supervision from readily available data such as radiology reports can compensate lack of large-scale data for anomaly detection methods. However, most of the current methods only use image-level pathological observations, failing to utilize the relevant anatomy mentions in reports. Furthermore, Natural Language Processing (NLP)-mined weak labels are noisy due to label sparsity and linguistic ambiguity. We propose an Anatomy-Guided chest X-ray Network (AGXNet) to address these issues of weak annotation. Our framework consists of a cascade of two networks, one responsible for identifying anatomical abnormalities and the second responsible for pathological observations. The critical component in our framework is an anatomy-guided attention module that aids the downstream observation network in focusing on the relevant anatomical regions generated by the anatomy network. We use Positive Unlabeled (PU) learning to account for the fact that lack of mention does not necessarily mean a negative label. Our quantitative and qualitative results on the MIMIC-CXR dataset demonstrate the effectiveness of AGXNet in disease and anatomical abnormality localization. Experiments on the NIH Chest X-ray dataset show that the learned feature representations are transferable and can achieve the state-of-the-art performances in disease classification and competitive disease localization results. Our code is available at https://github.com/batmanlab/AGXNet.


  • Open Access

    Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN

    by Li Sun, Junxiang Chen, Yanwu Xu, Mingming Gong, Ke Yu, Kayhan Batmanghelich

    Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image. The hierarchical design has two advantages: First, the memory demand for training on high-resolution images is amortized among sub-volumes. Furthermore, anchoring the high-resolution sub-volumes to a single low-resolution image ensures anatomical consistency between sub-volumes. During inference, our model can directly generate full high-resolution images. We also incorporate an encoder with a similar hierarchical structure into the model to extract features from the images. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation. We also demonstrate clinical applications of the proposed model in data augmentation and clinical-relevant feature extraction.

  • Top Cited Papers
    Open Access

    Hierarchical Amortized GAN for 3D High Resolution Medical Image Synthesis

    by Li Sun, Junxiang Chen, Yanwu Xu, Mingming Gong, Ke Yu, Kayhan Batmanghelich

    Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image. The hierarchical design has two advantages: First, the memory demand for training on high-resolution images is amortized among sub-volumes. Furthermore, anchoring the high-resolution sub-volumes to a single low-resolution image ensures anatomical consistency between sub-volumes. During inference, our model can directly generate full high-resolution images. We also incorporate an encoder with a similar hierarchical structure into the model to extract features from the images. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation. We also demonstrate clinical applications of the proposed model in data augmentation and clinical-relevant feature extraction.


  • Missing Pavement Performance Data Imputation Using Graph Neural Networks

    by Lu Gao, Ke Yu, Pan Lu

    Pavement condition data is important for providing information on the current state of the network and determining the needs of preventive maintenance or rehabilitation treatments. However, the condition data set is often incomplete for various reasons such as measurement errors and non-periodic inspection intervals. Missing data, especially when missing systematically, presents loss of information, reduces statistical power, and introduces biased assessment. Existing practices in pavement management systems (PMS) usually discard entire cases with missing data or impute it through data correlation. This paper proposes a graph-based deep learning framework, convolutional graph neural networks, to tackle the missing data problem in PMS. Unlike other variants of neural networks, the proposed approach is able to capture the spatio-temporal relationship in data and to learn and reconstruct the missing data by combining information among neighboring sections. In the case study, pavement condition data from 4,446 sections managed by Texas Department of Transportation were used. Experiments show that the proposed model was able to outperform standard machine learning models when imputing the missing data.