• Publications
  • Influence
Learning to Map Nearly Anything
TLDR
We propose a cross-modal distillation strategy to learn to predict the distribution of fine-grained properties from overhead imagery, without requiring any manual annotation. Expand
  • 3
  • 1
  • PDF
Inconsistent Performance of Deep Learning Models on Mammogram Classification.
TLDR
We evaluated six deep learning models on four mammogram data sets, including three public (Digital Database for Screening Mammography, INbreast, and Mammographic Image Analysis Society) and one private data set (UKy). Expand
  • 12
Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees
TLDR
The purpose of this study was to investigate the use of deep learning for coniferous/deciduous classification of individual trees from airborne LiDAR data. Expand
  • 14
  • PDF
GANai: Standardizing CT Images using Generative Adversarial Network with Alternative Improvement
TLDR
We present a new GAN model called GANai to mitigate the differences in radiomic features across CT images captured using non-standard imaging protocols, which poses a fundamental challenge in large-scale cross-center CT image analysis. Expand
  • 2
Joint 2D-3D Breast Cancer Classification
TLDR
We propose an innovative convolutional neural network architecture for breast cancer classification, which uses both 2D and 3D mammograms, simultaneously. Expand
  • 5
  • PDF
2D Convolutional Neural Networks for 3D Digital Breast Tomosynthesis Classification
TLDR
We propose a novel deep 2D convolutional neural network architecture for DBT classification that enables us to use pre-trained 2D CNNs. Expand
  • 4
  • PDF
Mitigation of Coagulation by Removing Clotting Factors Part 1: In Vitro Feasibility Study
Heparin is associated with adverse effects in some patients during extracorporeal circulation. A potential alternate anticoagulation strategy explored in this investigation involved mitigation ofExpand
  • 2
Defense-PointNet: Protecting PointNet Against Adversarial Attacks
TLDR
We propose Defense-PointNet to enhance the robustness of PointNet, which is one of the most widely used 3D point clouds. Expand
  • 2
  • PDF
Polypharmacology Within the Full Kinome: a Machine Learning Approach
TLDR
Protein kinases generate nearly a thousand different protein products and regulate the majority of cellular pathways and signal transduction. Expand
  • 1