276 citations · 714 across the 20 of their papers we have counts for
20 papers
Consistency-guided Meta-Learning for Bootstrapping Semi-Supervised Medical Image Segmentation
Qingyue Wei, Lequan Yu, Xianhang Li +4
Medical imaging has witnessed remarkable progress but usually requires a large amount of high-quality annotated data which is time-consuming and costly to obtain. To alleviate this…
Learning Image Representations for Content Based Image Retrieval of Radiotherapy Treatment Plans
Charles Huang, Varun Vasudevan, Oscar Pastor-Serrano +7
Objective: Knowledge based planning (KBP) typically involves training an end-to-end deep learning model to predict dose distributions. However, training end-to-end methods may be a…
Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging
Rui Yan, Liangqiong Qu, Qingyue Wei +5
The collection and curation of large-scale medical datasets from multiple institutions is essential for training accurate deep learning models, but privacy concerns often hinder da…
L2B: Learning to Bootstrap Robust Models for Combating Label Noise
Yuyin Zhou, Xianhang Li, Fengze Liu +6
Deep neural networks have shown great success in representation learning. However, when learning with noisy labels (LNL), they can easily overfit and fail to generalize to new data…
Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels
Varun Vasudevan, Maxime Bassenne, Md Tauhidul Islam +1
Prior studies using graph neural networks (GNNs) for image classification have focused on graphs generated from a regular grid of pixels or similar-sized superpixels. In the latter…
SSDL: Self-Supervised Dictionary Learning
Shuai Shao, Lei Xing, Wei Yu +3
The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the labe…
MDFM: Multi-Decision Fusing Model for Few-Shot Learning
Shuai Shao, Lei Xing, Rui Xu +3
In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i…
RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR
Yuyin Zhou, Shih-Cheng Huang, Jason Alan Fries +8
Despite the routine use of electronic health record (EHR) data by radiologists to contextualize clinical history and inform image interpretation, the majority of deep learning arch…
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
Yang Song, Liyue Shen, Lei Xing +1
Reconstructing medical images from partial measurements is an important inverse problem in Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). Existing solutions based o…
Metal Artifact Reduction in 2D CT Images with Self-supervised Cross-domain Learning
Lequan Yu, Zhicheng Zhang, Xiaomeng Li +3
The presence of metallic implants often introduces severe metal artifacts in the X-ray CT images, which could adversely influence clinical diagnosis or dose calculation in radiatio…
CIM: Class-Irrelevant Mapping for Few-Shot Classification
Shuai Shao, Lei Xing, Yixin Chen +3
Few-shot classification (FSC) is one of the most concerned hot issues in recent years. The general setting consists of two phases: (1) Pre-train a feature extraction model (FEM) wi…
MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
Shuai Shao, Lei Xing, Yan Wang +4
Few-shot learning (FSL) aims to address the data-scarce problem. A standard FSL framework is composed of two components: (1) Pre-train. Employ the base data to generate a CNN-based…
NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction
Liyue Shen, John Pauly, Lei Xing
Image reconstruction is an inverse problem that solves for a computational image based on sampled sensor measurement. Sparsely sampled image reconstruction poses addition challenge…
A Geometry-Informed Deep Learning Framework for Ultra-Sparse 3D Tomographic Image Reconstruction
Liyue Shen, Wei Zhao, Dante Capaldi +2
Deep learning affords enormous opportunities to augment the armamentarium of biomedical imaging, albeit its design and implementation have potential flaws. Fundamentally, most deep…
CateNorm: Categorical Normalization for Robust Medical Image Segmentation
Junfei Xiao, Lequan Yu, Zongwei Zhou +4
Batch normalization (BN) uniformly shifts and scales the activations based on the statistics of a batch of images. However, the intensity distribution of the background pixels ofte…
A Mean-Field Theory for Learning the Schönberg Measure of Radial Basis Functions
Masoud Badiei Khuzani, Yinyu Ye, Sandy Napel +1
We develop and analyze a projected particle Langevin optimization method to learn the distribution in the Schönberg integral representation of the radial basis functions from train…
Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications
Hyunseok Seo, Masoud Badiei Khuzani, Varun Vasudevan +5
In recent years, significant progress has been made in developing more accurate and efficient machine learning algorithms for segmentation of medical and natural images. In this re…
A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
Masoud Badiei Khuzani, Liyue Shen, Shahin Shahrampour +1
We propose a novel supervised learning method to optimize the kernel in the maximum mean discrepancy generative adversarial networks (MMD GANs), and the kernel support vector machi…
On Sample Complexity of Projection-Free Primal-Dual Methods for Learning Mixture Policies in Markov Decision Processes
Masoud Badiei Khuzani, Varun Vasudevan, Hongyi Ren +1
We study the problem of learning policy of an infinite-horizon, discounted cost, Markov decision process (MDP) with a large number of states. We compute the actions of a policy tha…
A Distributionally Robust Optimization Method for Adversarial Multiple Kernel Learning
Masoud Badiei Khuzani, Hongyi Ren, Md Tauhidul Islam +1
We propose a novel data-driven method to learn a mixture of multiple kernels with random features that is certifiabaly robust against adverserial inputs. Specifically, we consider…