Medical image analysis using artificial intelligence has considerable potential for improving medical diagnoses. One of the largest studies to date has been carried out using AI-assisted image analysis of lymphoma (cancer of the lymphatic system). This adds to the evolving body of evidence in support of AI within the medical field.
Researchers at Chalmers University of Technology in Sweden have developed a computer model that can find signs of lymph node cancer in 90 percent of cases.
To train the AI, the researchers used 17,000 images from more than 5,000 lymphoma patients. These helped to train the system to identify visual signs of cancer in the lymphatic system. Through this the computer model is adjusted so that it gradually gets better and better at determining the diagnosis.
The researchers examined image archives that stretched back more than ten years. They compared the patients’ final diagnosis with scans from positron emission tomography (PET) and computed tomography (CT) taken before and after treatment. This information was then used to help train the AI computer model to detect signs of lymph node cancer in an image.
This led to the creation of the algorithm, named Lars, Lymphoma Artificial Reader System. The AI model is trained to find patterns and features in the image, in order to make the best possible prediction of whether the image is positive or negative.
This development should reduce the workload for radiologists, assist medics with providing a second opinion or helping healthcare facilities to rank which patients need treatment the fastest.
Commenting on the research, lead scientist Ida Häggström extolls the virtues of the new technology: “An AI-based computer system for interpreting medical images also contributes to increased equality in healthcare by giving patients access to the same expertise and being able to have their images reviewed within a reasonable time, regardless of which hospital they are in.”
Furthermore, she adds, the technology should aid detecting fewer common forms of cancer: “Since an AI system has access to much more information, it also makes it easier in rare diseases where radiologists rarely see images”.
The image analysis technology can also assist with assessing other medical conditions, such as cardiovascular disease, stroke and osteoporosis.
The research has been published in the journal The Lancet Digital Health. The paper is titled “Deep learning for [¹⁸F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: a dual-centre retrospective analysis”.