scispace - formally typeset
P

Pochuan Wang

Researcher at National Taiwan University

Publications -  10
Citations -  223

Pochuan Wang is an academic researcher from National Taiwan University. The author has contributed to research in topics: Internal medicine & Pancreatic cancer. The author has an hindex of 3, co-authored 6 publications receiving 16 citations.

Papers
More filters
Journal ArticleDOI

Federated learning for predicting clinical outcomes in patients with COVID-19.

Ittai Dayan, +103 more
- 15 Sep 2021 - 
TL;DR: In this article, the authors used federated learning to predict future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays.
Journal ArticleDOI

Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study.

TL;DR: The deep learning-based tool developed and validated enabled accurate detection of pancreatic cancer on CT scans, with reasonable sensitivity for tumors smaller than 2 cm.
Posted ContentDOI

Federated Learning used for predicting outcomes in SARS-COV-2 patients

Mona Flores, +97 more
TL;DR: In this paper, the authors used federated learning to predict future oxygen requirements of infected patients using inputs of vital signs, laboratory data, and chest x-rays, constituting the "EXAM" (EMR CXR AI Model) model.
Book ChapterDOI

Automated Pancreas Segmentation Using Multi-institutional Collaborative Deep Learning

TL;DR: In this article, the authors study the use of federated learning between two institutions in a real-world setting to collaboratively train a model without sharing the raw data across national boundaries.
Posted Content

Automated Pancreas Segmentation Using Multi-institutional Collaborative Deep Learning.

TL;DR: This work study the use of federated learning between two institutions in a real-world setting to collaboratively train a model without sharing the raw data across national boundaries and quantitatively compare the segmentation models obtained with federatedLearning and local training alone.