Pengfei Chen

Pengfei Chen

Auto-generated profile, based on publicly available information

Pengfei Chen

Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 May 2019 in Nature Communications
Verified
Journal Article
Open access
PDF file
QGQiang Geng
Qiang Geng
DWDien Wang
Dien Wang
PCPengfei Chen
Pengfei Chen
SCShih-Chi Chen
Shih-Chi Chen
Two-photon polymerization (TPP) is the most precise 3-D printing process that has been used to create many complex structures for advanced photonic and nanoscale applications. However, to date the technology still remains a laboratory tool due to its high operation cost and limited fabrication rate, i.e., serial laser scanning process. Here we present a revolutionary laser nanofabrication process based on TPP and an ultrafast random-access digital micromirror device (DMD) scanner. By exploiting binary holography, the DMD scanner can simultaneously generate and individually control one to tens of laser foci for parallel nanofabrication at 22.7 kHz. Complex 3-D trusses and woodpile structures have been fabricated via single or multi-focus processes, showing a resolution of ~500 nm. The nanofabrication system may be used for largescale nano-prototyping or creation of complex structures, e.g., overhanging structures, that cannot be easily fabricated via conventional raster-scanning-based systems, bringing significant impact to the world of nanomanufacturing.

4 January 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
CXCheng Xue
Cheng Xue
LYLequan Yu
Lequan Yu
PCPengfei Chen
Pengfei Chen
QDQi Dou
Qi Dou
PHPheng-Ann Heng
Pheng-Ann Heng
Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some noisy-labeled images, the network training procedure would suffer from difficulties, leading to a sub-optimal classifier. This problem is even more severe in the medical image analysis field, as the annotation quality of medical images heavily relies on the expertise and experience of annotators. In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high quality annotated medical data. Specifically, we employ the self-ensemble model with a noisy label filter to efficiently select the clean and noisy samples. Then, the clean samples are trained by a collaborative training strategy to eliminate the disturbance from imperfect labeled samples. Notably, we further design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples in a self-supervised manner. We evaluated our proposed robust learning strategy on four public medical image classification datasets with three types of label noise, i.e. , random noise, computer-generated label noise, and inter-observer variability noise. Our method outperforms other learning from noisy label methods and we also conducted extensive experiments to analyze each component of our method.