Computer Aided Diagnosis (CAD) systems

The recent boom of digital medical imaging has made the support of computers in

assisting doctors in image interpretation of unsurmountable importance.

Specifically, modern imaging techniques yield a great deal of information that doctors must analyze and evaluate comprehensively in a short time. CAD is an interdisciplinary technology combining elements of artificial intelligence and computer vision with radiological and pathology image processing to develop methods to assist doctors in the interpretation of medical images, giving a second-opinion and aiding the final diagnosis decision. Our research group has many years’ experience in this field, allowing for the acquisition of a deep know-how for the completely automatic extraction of the main quantitative aspects in CAD systems: 

  1. The accurate segmentation of lesions and/or the principal tissues;
  2. Their characterization through the calculation of numerous quantitative features which are then used for the discrimination between healthy and diseased tissues.

Our research in this area includes, but is not limited to, the analysis of ultrasound images in cardiovascular and musculoskeletal applications and thyroid nodule staging, the study of MRI images for prostate and breast cancer detection, and the analysis of histopathological images for an automatic scoring. Moreover, in the last few years we applied clustering techniques for MRI and CT images segmentation to overcome the limitations of supervised approaches.

ERC Sector:

  • PE7_11 Components and systems for applications
  • LS7_1 Medical engineering and technology
  • LS7_2 Diagnostic tools (e.g. genetic, imaging)
  • PE6_11 Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)

Keywords:

  • Computer aided diagnosis
  • Machine intelligence
  • Segmentation
  • Classification

Research groups