Thanks for visiting Scientific Computing World.

You're trying to access an editorial feature that is only available to logged in, registered users of Scientific Computing World. Registering is completely free, so why not sign up with us?

By registering, as well as being able to browse all content on the site without further interruption, you'll also have the option to receive our magazine (multiple times a year) and our email newsletters.

Automated image analysis aids biomarker screening

Share this on social media:

A feasibility study for the evaluation of the Her2/neu protein in breast cancer biopsies has been conducted by a leading pharmaceutical company and Munich-based Definiens, an image analysis software developer. The study's results suggest that utilising automated image analysis technology in biomarker screening can have a positive impact on clinical trial outcomes and the diagnosis and treatment of breast cancer.

The study involved 1,800 tumour cases from patients enrolled in a multi-centre clinical trial for a breast cancer targeted therapy. It compared results obtained using manual pathology scoring methods to those obtained via Definiens' computerised image analysis approach for evaluating Her2/neu objectively, on a cell-by-cell basis. The comparison indicated that Definiens XD – the company's platform for multi-dimensional image analysis – provided improved scoring accuracy of 30 per cent, compared to manual results from a panel of six pathologists.

'The results of this feasibility study are very compelling,' said Manfred Voglmaier, vice president of business development for Definiens' Life Sciences division. 'Our approach to image analysis and biomarker quantification demonstrates enormous potential for facilitating better treatment decisions for a variety of cancer types. We are currently seeking cancer centre and bio-pharmaceutical partners to collaborate with in the development of tissue-based cancer diagnostics applications.'

Currently, the tasks of tumour biopsy grading and biomarker assessment are performed largely by manually applying classical pathology techniques. This process is time consuming and subjective, and may lead to delayed or inaccurate diagnostic and treatment decisions. Definiens technology enables accurate, rapid quantitative assessment of biological images from multiple image acquisition platforms.

Definiens is also evaluating the application of its image analysis platform for Her2/neu assessment in stomach cancer biopsies; the grading of non-small cell lung cancer, breast cancer and prostate cancer; and tumour volumetric assessment post-Avastin, Sutent, and Sorafenib treatment.