no code implementations • 12 Oct 2022 • Zhenyu Yang, Kyle Lafata, Eugene Vaios, Zongsheng Hu, Trey Mullikin, Fang-Fang Yin, Chunhao Wang
The SPU-Net model was compared with (1) the classic U-Net model with test-time augmentation (TTA) and (2) linear scaling-based U-Net (LSU-Net) segmentation models in terms of both segmentation accuracy (Dice coefficient, sensitivity, specificity, and accuracy) and segmentation uncertainty (uncertainty map and uncertainty score).
no code implementations • 1 Mar 2022 • Zhenyu Yang, Zongsheng Hu, Hangjie Ji, Kyle Lafata, Scott Floyd, Fang-Fang Yin, Chunhao Wang
Methods: By hypothesizing that deep feature extraction can be modeled as a spatiotemporally continuous process, we designed a novel deep learning model, neural ODE, in which deep feature extraction was governed by an ODE without explicit expression.
no code implementations • 19 Jul 2021 • Zongsheng Hu, Zhenyu Yang, Kyle J. Lafata, Fang-Fang Yin, Chunhao Wang
To develop a deep-learning model that integrates radiomics analysis for enhanced performance of COVID-19 and Non-COVID-19 pneumonia detection using chest X-ray image, two deep-learning models were trained based on a pre-trained VGG-16 architecture: in the 1st model, X-ray image was the sole input; in the 2nd model, X-ray image and 2 radiomic feature maps (RFM) selected by the saliency map analysis of the 1st model were stacked as the input.