HongweiLi

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Mr. Hongwei Li (Bran)

bran.jpeg

  • Email: hongwei.li@tum.de ; Phone: 0049017647358115
  • Office: In open space of IMETUM close to the printing room (lots of drones in my desk).

My English name is Bran. I am a Ph.D. candidate supervised by Prof. Bjoern Menze starting from Sep. 2017.
My research interests focus on devoloping machine-learning algorithms in the field of medical image analysis,
especially in weakly-supervised learning and multi-view learning for image segmentation.

My program includes several projects:

  • Automatic segmentation of white matter hyperintensities (WMH) and multiple sclerosis (MS) lesions in MR images;
  • Automated algorithms for classification of pancreas cysts using multi-modal computed tomography (CT);
  • Brain structures segmentation including Claustrum in brain MR images;
For more details about my research, please have a look at my Curriculum Vitae, Google scholar profile and GitHub.

Available Projects for Undergraduates and Master Students

I enjoy working with students who are interested in machine learning and medical image analysis.
Please feel free to contact me and Prof. Bjoern Menze if you want to do research on relevant topics, especially:

1. Weakly-supervised learning / one-shot learning in medical image analysis.
2. Deep learning's application on segmentation of lesion in MR images and lesion subtype classification using CT images.

News

Winner (Team Name:sysu_media) of WMH Segmentation Challenge in MICCAI 2017!
Detailed description of our method is submitted to NeuroImage Journal and now published!

Selected Publications (first author)

1. Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images, NeuroImage (08/2018)
2. Multi-Scale Convolutional-Stack Aggregation for Robust White Matter Hyperintensities Segmentation, MICCAI Brain Lesion Workshop (08/2018)
3. Automatic Brain Structures Segmentation Using Deep Residual Dilated U-Net, MICCAI Brain Lesion Workshop (08/2018)
4. HEp-2 specimen classification via deep CNNs and pattern histogram, International Conference on Pattern Recognition (ICPR 2016)
5. HEp-2 cells staining patterns classification via wavelet scattering network and random forest, Asian Conference on Pattern Recognition (ACPR 2015)

Other Interests

Amateur indoor volleyball player, now playing for VfR Garching Men's volleyball team (national league games);

Reading and writing fairy tales.


updated on 31/12/2018



Edit | Attach | Refresh | Diffs | More | Revision r1.66 - 21 Jan 2019 - 13:51 - HongweiLi

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif