Faster, more efficient searching of medical images

A Danish-led research project has made encouraging progress toward using advanced mathematics as the basis of an improved method for indexing and searching medical images in the huge digital databases of clinics and hospitals.

Completed in November 2005, the DSSCV consortium's long-term goal was to contribute to software tools allowing doctors and hospital technicians to quickly search and match X-rays, magnetic resonance images and computed 3D tomography scans, particularly of the craniofacial region.

"Let's say a doctor has a new patient with a broken bone," says coordinator, Mads Nielsen, a professor of computer science at the IT University of Copenhagen. "He remembers seeing a similar fracture and wants to recall how he treated that patient, but doesn't remember the case number. By inputting the X-ray of the new patient, this computer system would allow finding the relevant, digitally stored image of that kind of fracture."

"Anybody that needs to compare or search images for specific features could use the technology," says Nielsen. However, he estimates that practical use will require five to 10 more years of development.

Funded under the European Commission’s FET (Future and Emerging Technologies) initiative of the IST programme, the DSSCV project gathered mathematicians and computer scientists from four European universities with the objective of developing more efficient algorithms for comparing shapes, in this case images. "A shape is a very complicated thing to describe mathematically," explains Nielsen. "To efficiently compare shapes, you need something that doesn't compare every feature."

The researchers refined the practical application of singularity and scale-space theories to develop algorithms that describe the deep structure of a shape, which Nielsen explains as a collection of details, called singularities. Such an algorithm makes it possible to disregard singularities that do not match the particular shape sought.

"An analogy would be a stadium full of 20,000 spectators, and you want to find your brother”, he says. "You are not going to look at every wrinkle, eyebrow and strand of hair. You eliminate the details that are irrelevant in order to zoom in on your brother."

The team worked with theories of how singularities emerge and disappear in an image. For example, catastrophe theory can explain how one slight change to part of an image can drastically change the overall picture. Says Nielsen, "Zoom in on a tree, and branches and leaves appear. The algorithm we've developed allows such a coarse-to-fine way to break shapes into parts, compare them and determine how they relate to each other."

DSSCV partners have been awarded five grants, for the projects ‘Natural shape’, from the Danish Research Agency; ‘Quantitative shape modelling in biomedical imaging’, from the Danish Technical Research Council; ‘The problem of scale in biomedical image analysis’ and ‘Robust multi-scale methods for optic flow’, from the Dutch Science Foundation; and a grant from the British Research Council for Science and Engineering.

Nielsen says computer vision is still an exploratory field, moving in many different directions. Still, due to pressure from major medical equipment manufacturers, some areas are beginning to standardise—especially in the medical area.

Scientific communication is key to progress, says Nielsen. DSSCV has presented results in several scientific journals and conferences and held an open workshop with participants from the US and Japan. "We gained and provided valuable insights. The feedback has been good."

Looking ahead, Nielsen says, "We've done the deep mathematics. Now we'd like to do another project with other partners more involved in the practical issues, such as doctors and hospitals."

Contact:
Mads Nielsen
IT University of Copenhagen
Rued Langgaards Vej 7
DK-2300 Copenhagen S
Denmark
Tel: +45-72-185075
Fax: +45-72-185001
Email: This email address is being protected from spambots. You need JavaScript enabled to view it.

Source: IST Results

Most Popular Now

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

AI Medical Receptionist Modernizing Doct…

A virtual medical receptionist named "Cassie," developed through research at Texas A&M University, is transforming the way patients interact with health care providers. Cassie is a digital-human assistant created by Humanate...

Using Data and AI to Create Better Healt…

Academic medical centers could transform patient care by adopting principles from learning health systems principles, according to researchers from Weill Cornell Medicine and the University of California, San Diego. In...

AI Tool Set to Transform Characterisatio…

A multinational team of researchers, co-led by the Garvan Institute of Medical Research, has developed and tested a new AI tool to better characterise the diversity of individual cells within...

AI Detects Hidden Heart Disease Using Ex…

Mass General Brigham researchers have developed a new AI tool in collaboration with the United States Department of Veterans Affairs (VA) to probe through previously collected CT scans and identify...

Human-AI Collectives Make the Most Accur…

Diagnostic errors are among the most serious problems in everyday medical practice. AI systems - especially large language models (LLMs) like ChatGPT-4, Gemini, or Claude 3 - offer new ways...

Northern Ireland Completes Nationwide Ro…

Go-lives at Western and Southern health and social care trusts mean every pathology service is using the same laboratory information management system; improving efficiency and quality. An ambitious technology project to...

Highland Marketing Announced as Official…

Highland Marketing has been named, for the second year running, the official communications partner for HETT Show 2025, the UK's leading digital health conference and exhibition. Taking place 7-8 October...

MHP-Net: A Revolutionary AI Model for Ac…

Liver cancer is the sixth most common cancer globally and a leading cause of cancer-related deaths. Accurate segmentation of liver tumors is a crucial step for the management of the...

Groundbreaking TACIT Algorithm Offers Ne…

Researchers at VCU Massey Comprehensive Cancer Center have developed a novel algorithm that could provide a revolutionary tool for determining the best options for patients - both in the treatment...

The Many Ways that AI Enters Rheumatolog…

High-resolution computed tomography (HRCT) is the standard to diagnose and assess progression in interstitial lung disease (ILD), a key feature in systemic sclerosis (SSc). But AI-assisted interpretation has the potential...