Open position in Image Analysis

Uppsala University hereby declares the following position open for application:

Postdoctoral Research Position in Image Analysis for Cancer Diagnosis

at the Department of Information Technology, Division of Visual Information and Interaction, Centre for Image Analysis, starting as soon as possible, with application no later than June 15, 2013.

The Department of Information Technology has a leading position in research as well as teaching. The Department employs a staff of about 250, including 100 senior faculty and 100 PhD students. More than 3000 students are enrolled in one or more courses annually. More information can be found at

The Centre for Image Analysis (CBA) is a joint research effort between Uppsala University and the Swedish University of Agricultural Sciences. CBA was established for research and development in digital image analysis and scientific visualization. More information can be found at

Prostate cancer is the leading cause of cancer deaths in men. Diagnosis is based on Gleason grading, which is the most widely used system for determining the severity of prostate cancer from tissue samples. However, Gleason grading is highly subjective with significant variation between experienced pathologists. An improved prostate cancer grading system will both prolong lives and reduce medical costs significantly.

We are working on replacing subjective diagnosis of prostate cancer with automatic malignancy grading using a combination of new tissue stains and image analysis. We have developed staining methods that identify cancerous and non-cancerous glands and also use a larger part of the color spectrum than conventional stains facilitating more reliable image segmentation. This staining method combined with our novel color decomposition method, which is robust to variations in tissue staining, will be the basis for pattern recognition and machine learning algorithms that identify morphological features from prostate tissue in a reproducible manner.

Using biopsy and prostatectomy material with a consensus Gleason grade, we will use pattern recognition and statistical methods to find the features that correlate well with the grade. We will also develop new classifiers for cancer grading that reliably identify malignancy relative to disease end points. By training the classifiers on the disease outcome rather than on the Gleason grade, we aim for better prognostication than currently possible.

Position: We are seeking a postdoctoral researcher to develop algorithms and software in this project to facilitate automatic malignancy grading and to develop new classifiers for better prognostication of prostate cancer.
The position may also include teaching at all levels and supervision of masters and graduate students. The position is for one year with the possibility for a one year extension.

Prerequisites: A PhD in computer science, engineering, or mathematics, with focus on pattern recognition and machine learning. Experience in statistics, image processing, and signal processing is highly valued, as is previous experience with tissue analysis. Programming experience is essential. The department is striving to achieve a more equal gender balance and female candidates are particularly invited to apply.

Application: The application should contain a CV, college and graduate school transcripts, letters of recommendation, and a letter describing why you want to become a postdoctoral researcher with us and why this line of research appeals to you.

For further information, please contact
Professor Ingrid Carlbom via email,, or by phone, + 46-18-471 7004, or
Professor Ewert Bengtsson via e-mail,, or phone, +46-18-471 3467.

Union representatives are Anders Grundström, Saco, phone +46-18-471 5380, Carin Söderhäll, TCO/ST, phone +46-18-471 1996, Stefan Djurström, Seko, phone +46-18-471 3315.

Please submit your application no later than date June 15 2013, UFV-PA 2013/1361. Use the link below to access the application form.

Postdoctoral Research Position in Image Analysis for Cancer Diagnosis.

In case of disagreement between the English and the Swedish version of this announcement, the Swedish version takes precedence.