CHENG Li

Automated Image Based Prominent Nucleoli Detection

Published date : 23 Jun 2015

Nucleolar changes in cancer cells are one of the cytologic features important to the tumor pathologist in cancer assessments of tissue biopsies. However, inter-observer variability and the manual approach to this work hamper the accuracy of the assessment by pathologists. In this paper, we propose a computational method for prominent nucleoli pattern detection. Materials and Methods: Thirty-five hematoxylin and eosin stained images were acquired from prostate cancer, breast cancer, renal clear cell cancer and renal papillary cell cancer tissues.

type
Journal Paper
journal
Journal of Pathology Informatics 2015, Vol. 6, Issue 1,doi: 10.4103/2153-3539.159232

Contrasting expression patterns of coding and noncoding parts of the human genome upon oxidative stress

Published date : 29 May 2015

Oxidative stress (OS) is caused by an imbalance between pro- and anti-oxidant reactions leading to accumulation of reactive oxygen species within cells. We here investigate the effect of OS on the transcriptome of human fibroblasts. OS causes a rapid and transient global induction of transcription characterized by pausing of RNA polymerase II (PolII) in both directions, at specific promoters, within 30 minutes of the OS response.

type
Journal Paper
journal
Scientific Reports 5,Article no: 9737, 2015, doi: 10.1038/srep09737

author

GHand: A GPU algorithm for realtime hand pose estimation using depth camera

Published date : 04 May 2015

We present GHand, a GPU algorithm for markerless hand pose estimation from a single depth image obtained from a commodity depth camera. Our method uses a dual random forest approach: the first forest estimates position and orientation of hand in 3D, while the second forest determines the joint angles of the kinematic chain of our hand model. GHand runs entirely on GPU, at a speed of 64 FPS with an average 3D joint position error of 20mm. It can detect complex poses with interlocked and occluded fingers and hidden fingertips.

type
Conference Paper/Poster
journal
EuroGraphics 2015, 4th - 8th May 2015, Kongresshaus Zurich, Switzerland

STOCS: An Efficient Self-Tuning Multiclass Classification Approach

Published date : 29 Apr 2015

A simple, efficient, and parameter-free approach is proposed for the problem of multiclass classification, and is especially useful when dealing with large-scale datasets in the presence of label noise. Grown out of one-class SVM, our approach enjoys several distinct features: First, its decision boundary is learned based on both positive and negative examples; Second, the internal parameters and especially the kernel bandwidth are self-tuned.

type
Book/Book Chapter
journal
Advances in Artificial Intelligence, Volume 9091 of the series LNCS pp 291-306

Estimate Hand Poses Efficiently from Single Depth Images

Published date : 19 Apr 2015

This paper aims to tackle the practically very challenging problem of efficient and accurate hand pose estimation from single depth images. A dedicated two-step regression forest pipeline is proposed: Given an input hand depth image, step one involves mainly estimation of 3D location and in-plane rotation of the hand using a pixel-wise regression forest. This is utilized in step two which delivers final hand estimation by a similar regression forest model based on the entire hand image patch. Moreover, our estimation is guided by internally executing a 3D hand kinematic chain model.

type
Journal Paper
journal
International Journal of Computer Vision (IJCV), Vol. 112, No. 3, May 2015, pp.1-25
Impact Factor
3.81

Integrated Foreground Segmentation and Boundary Matting for Live Videos

Published date : 15 Feb 2015

The objective of foreground segmentation is to extract the desired foreground object from input videos. Over the years, there have been significant amount of efforts on this topic. Nevertheless, there still lacks a simple yet effective algorithm that can process live videos of objects with fuzzy boundaries (e.g., hair) captured by freely moving cameras. This paper presents an algorithm toward this goal.

type
Journal Paper
journal
IEEE Transaction on Image Processing (TIP), Vol. 24, No. 4, April 2015 Pg 1356-70
Impact Factor
3.625

Semi-supervised Domain Adaptation on Manifolds

Published date : 20 Nov 2014

In real-life problems, the following semi-supervised domain adaptation scenario is often encountered: we have full access to some source data, which is usually very large; the target data distribution is under certain unknown transformation of the source data distribution; meanwhile, only a small fraction of the

type
Journal Paper
journal
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), (25)12:2240-2249, 2014

author

Tracing Retinal Blood Vessels by Matrix-Forest Theorem of Directed Graphs

Published date : 14 Sep 2014

This paper aims to trace retinal blood vessel trees in fundus images. This task is far from being trivial as the crossover of vessels are commonly encountered in image-based vessel networks. Meanwhile it is
often crucial to separate the vessel tree structures in applications such as diabetic retinopathy analysis. In this work, a novel directed graph based approach is proposed to cast the task as label propagation over directed graphs, such that the graph is to be partitioned into disjoint sub-graphs,

type
Conference Paper/Poster
journal
The 17th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2014) 14-18 Sept, Boston USA

A retinal vessel boundary tracking method based on Bayesian theory and multi-scale line detection

Published date : 05 Jun 2014

A retinal vessel tracking method based on Bayesian theory and multi-scale line detection is proposed in this paper. The optic disk is located by a PCA method and the initial points of tracking are identified. In each step, candidate points for vessel edges are selected on a semi-ellipse. Three types of vessel structure are considered in the tracking: normal vessel, branching, and crossing. To determine the new pair of edge points, the characteristics of the vessel intensity profiles along both the cross section and the longitudinal direction are considered in the tracking.

type
Journal Paper
journal
Computerized Medical Imaging and Graphics, Volume 38, Issue 6, Pages 517–525, September 2014