Terms of Use

Home

Registration

Login/Download

SIEMENS

Siemens Medical Solutions USA

Computer Aided Detection (CAD)

Soarian Quality Measures

KDD 2008

KDD CUP 2008

Background on Breast Cancer

Data Description

Challenge Description

Hints

Workshop on Mining Medical Data

Important Dates

Contact/FAQ  

Announcement about test labels

KDD Cup 2008 Announces Top 10 submissions!

Challenge 1

1. PMG-IBM-Research
Team Members: Claudia Perlich, Prem Melville, Grzegorz Swirszcz, Yan Liu, Saharon Rosset, Richard Lawrence.
Affiliation: IBM Research

2. Hung-Yi Lo
Team Members: Hung-Yi Lo, Chun-Min Chang, Tsung-Hsien Chiang, Cho-Yi Hsiao, Anta Huang, Tsung-Ting Kuo, Wei-Chi Lai, Ming-Han Yang, Jung-Jung Yeh, Chun-Chao Yen and Shou-De Lin
Affiliation: National Taiwan University

3. yazhene
Team Members: Yazhene Krishnaraj and Chandan K. Reddy
Affiliation: Wayne State University

Challenge 2

1. PMG-IBM-Research
Team Members: Claudia Perlich, Prem Melville, Grzegorz Swirszcz, Yan Liu, Saharon Rosset, Richard Lawrence.
Affiliation: IBM Research

2. TZTeam
Team Members: Didier Baclin
Affiliation:

3. Hung-Yi Lo
Team Members: Hung-Yi Lo, Chun-Min Chang, Tsung-Hsien Chiang, Cho-Yi Hsiao, Anta Huang, Tsung-Ting Kuo, Wei-Chi Lai, Ming-Han Yang, Jung-Jung Yeh, Chun-Chao Yen and Shou-De Lin
Affiliation: National Taiwan University

KDD Cup 2008 and the Workshop on Mining Medical Data

KDD Cup is the first and the oldest data mining competition, and is an integral part of the annual ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). Based on data provided by Siemens Medical Solutions USA, this year's KDD Cup competition focuses on the early detection of breast cancer from X-ray images of the breast. No image processing skills are needed for participating in the competition.

We are looking forward to an interesting competition and your participation. We particularly encourage the participation of students. There are two different and parallel options for participating.

1. Submit entries to the KDD Cup 2008 competition.
2. Paper submissions for the associated Workshop on Mining Medical Data.

Medical Data Mining products from Siemens Medical Solutions

Siemens Medical Solutions USA is proud to provide data for the KDD Cup 2008. The CAD & Knowledge solutions group (CKS Group) of Siemens Medical Solutions is responsible for research and development in three main categories of products designed to: (a) improve early detection of diseases from imaging studies; (b) support therapy planning; and (c) help improve the therapy received by patients. In the first category, computer aided detection (CAD) products assist clinicians, for example, in the detection of breast cancer in mammography examinations or the identification of early stage lung cancer in chest CT images. In the second category, products are developed to assist physicians in planning the optimal schedule of radiation and chemotherapy for patients with lung cancer. In the third category, our quality measurement products mine all available data from physician dictations, medical images, billing databases, and other structured and non-structured data sources. The data is organized to identify patients who may need additional therapy according to established medical guidelines.

Machine Learning Research in the CKS group

The CKS Group brings together a world class team of scientists with expertise in various aspects of statistical pattern recognition, optimization, natural language processing, Bayesian inference, computer vision, bioinformatics, medical imaging and image processing. The algorithms developed and prototyped by these scientists are coded, tested and commercialized by a strong international team of software engineers. Since machine learning (ML) is crucial to the development of our products, it is a core-research area for the group. We are interested in many problems such as supervised/semi-supervised classification, feature selection, active learning, structured prediction of correlated output variables, large-scale inference with Bayes Nets, multiple instance learning and collaborative learning. Further, the improvement of our products also poses many novel and interesting research questions, which can only be solved by creative researchers who are eager to tackle complex machine learning problems from first principles. We have opportunities at both junior and senior levels for machine learning, NLP and Bioinformatics researchers. We also have opportunities for student internships.