A new AI tool automatically identifies liver tumours on CT scans of patients with colon cancer that has spread to the liver. The tool gives doctors quick insight into the size of tumours, which, among other things, helps chart the effect of chemotherapy on patients.
This is a tool developed by Amsterdam UMC's CAESAR research group, in which surgeons, radiologists, oncologists and data scientists work closely together. Researcher Michiel Zeeuw was involved in the development of the tool. "Bowel cancer is one of the most common cancers. In more than half of patients, metastases are found in the liver and almost all of these patients receive chemotherapy as part of their treatment. Measuring the effect of chemotherapy is crucial," Zeeuw explains on the Amsterdam UMC website.
Less time-consuming and more accurate
The researcher continues: "Until now, these measurements were done manually by radiologists, by manually measuring the difference in diameter of liver tumours on CT scans before and after treatment. This way of working is time-consuming and not always accurate. In addition, only the difference in diameter can be measured and not the difference in tumour volume. The new AI tool will soon be able to do all this and also automatically draw in the tumours on the CT scans."
The software was trained using nearly 100 CT scans of patients. On these, liver tumours were drawn in by hand. The AI model the tool uses was developed by data scientists Jacqueline Bereska and Luuk Wagenaar.
Examined in practice
The AI tool is currently being studied in practice, which Amsterdam UMC calls good news. It points out that many AI tools in practice remain stuck in the development phase, with trajectories often stalled. If, for example, an AI application fails to integrate seamlessly into the existing working methods of doctors and nurses, an AI tool generally does not find its way into daily practice. "A crucial step in the development of this AI tool was therefore the implementation in the software that radiologists use every day to assess examinations," Zeeuw explains.
Amsterdam UMC sees great benefits from deploying the tool. For instance, the AI application is expected to significantly improve patient care. Among other things, by providing radiologists with an accurate and fast way to assess tumours and the effects of chemotherapy. This will enable doctors to make better decisions on the treatments that will provide the best outcome for a specific patient.
No unnecessary treatments
Even if it turns out that a treatment is inadequate, the AI tool benefits patients. This improves the quality of care for patients, who do not have to continue treatment unnecessarily. In time, the researchers hope that the AI tool can also help select patients for surgery. They stress that the tool does not currently offer this possibility.
Author: Wouter Hoeffnagel
Image: Gerd Altmann via Pixabay
