Type: User
Company: Rensselaer Polytechnic Institute
Bio: We focus on advancing the understanding, visualization and application of medical images using machine learning and computer vision techniques.
Blog: https://dial.rpi.edu/
dial-rpi's Projects
Source code for BOWDANet
Predicting ICU admission based on initial CT images and non-imaging data.
A deep learning model (Tri2D-Net) for predicting cardiovascular disease risks from lung cancer screening LDCT
A python (PyTorch) implementation of federated multi-encoding U-Net (Fed-MENU) method for federated learning-based multi-organ segmentation with inconsistent labels.
2D Ultrasound Frame to 3D Ultrasound Volume Registration (FVReg) pipeline.
Source code for DCL-Net, a deep learning model for sensorless freehand 3D ultrasound volume reconstruction.
Image augmentation for machine learning experiments.
Deep learning for mortality prediction from low-dose CT images
PIPO-FAN for multi organ segmentation over partial labeled datasets using pytorch
A python (PyTorch) implementation of Polar Transform Network (PTN) method for prostate ultrasound segmentation
Tensors and Dynamic neural networks in Python with strong GPU acceleration
The website for PyTorch
A loss function originated for regression tasks to learn a representation manifold that is isometric to the label space.
A python (PyTorch) implementation of Shadow-consistent Semi-supervised Learning (SCO-SSL) method for prostate ultrasound segmentation
Unsupervised Cross-domain Adversarial Training