Heidelberg – How can camera images be used during a minimally invasive operation to assess whether the operated organ has adequate blood supply or not? Scientists from the German Cancer Research Center and the Municipal Clinic in Karlsruhe have now succeeded in automatically recording the blood flow in the organ during kidney operations and without contrast media, using only the optical properties of the tissue. To do this, they combined a special imaging technique with methods of artificial intelligence. The new procedure has now been used for the first time in patients with kidney tumors.
Minimally invasive surgical techniques, also known as “keyhole surgery”, are increasingly replacing classic open surgery – also in cancer medicine. For example, certain tumors of the internal organs can be removed in the course of a laparoscopy. An instrument called a laparoscope is used, which is a small skin incision is made in the abdomen and the doctor then allows a look at the affected organs.
The video camera connected to the laparoscope supplies an image signal composed of the three color channels red, green and blue (RGB). This color space is also used, for example, in televisions or smartphones. However, it has been shown that the tissue has optical properties that cannot be represented with this image information alone. Lena Maier-Hein (DKFZ) and her team have therefore investigated the use of multispectral imaging systems as part of the “NEURAL spicing” project funded by the European Research Council ERC together with researchers from the Municipal Clinic in Karlsruhe. The camera systems used not only record the three mentioned , but a total of 16 wavelength ranges in the optical spectrum, making it possible to visualize certain functional properties of the tissue that are invisible to conventional camera systems, such as the blood flow through an organ.
This is relevant, for example, in patients with kidney cancer in whom the tumor is to be surgically removed. In this procedure, the blood flow to the affected areas must first be interrupted by pinching off the arteries. However, the blood flow in the tissue can hardly be assessed using the RGB video image of a conventional laparoscope. Only through the use of a fluorescent contrast medium, which is injected into the patient and then accumulates in the tissues supplied with blood, can the doctor see whether the correct segments of the organ have been separated from the blood supply. If this was not successful, the contrast medium must first be washed out for around 30 minutes in order to then be able to repeat the process.
“We were able to show that the blood flow in the kidneys can be displayed in real time with a combination of multispectral imaging and artificial intelligence, even without contrast agents,” says Lena Meier-Hein. The new technology has now been successfully used in a study with ten patients Operations where parts of the kidney had to be removed.”Because our approach allows live observation of the blood flow in the tissue, the clamping of the blood vessels can be corrected immediately if necessary. This reduces the duration of the procedure and makes it safer for the patient and patients,” adds Leonardo Ayala, one of the first authors of the study. The new technology also eliminates the risk of an allergic reaction to the contrast agent.
The acquisition and processing of the image data play a decisive role in this approach. Because the use of multispectral imaging systems in minimally invasive surgery has so far failed, among other things, due to the time that the systems need for these two steps. If it takes several seconds to calculate a new image, the information is practically unusable during the intervention. By using a new multispectral camera technology, the researchers have now been able to solve this problem. Their newly developed system delivers 25 frames per second and thus a smooth video image.
The team also succeeded in recording blood flow for the first time using artificial intelligence (AI) methods that do not rely on large amounts of training data. Instead, the AI relearns with each patient how to distinguish between perfused and non-perfused tissue. “This is necessary because the tissue is not the same in every patient, so the optical properties can also be very different,” explains Leonardo Ayala. At the beginning of an operation, a short video sequence of the kidney of each patient is recorded using the laparoscope. “The algorithm then uses the patient’s individual image data to calculate how the perfusion status affects the optical properties of the tissue so that the degree of perfusion in an area can be displayed during the operation,” says Tim Adler, also the first author of the study.
Comparable procedures could also be used for other surgical issues in the future. Dogu Teber (Städtisches Klinikum Karlsruhe), clinical leader of the study, sees great potential for this new technological approach: “Spectral imaging in combination with new AI-based analysis tools could become an important tool for fast, reliable and safe functional imaging in of minimally invasive surgery.”
Leonardo Ayala, Tim J. Adler, Silvia Seidlitz, Sebastian Wirkert, Christina Engels, Alexander Seitel, Jan Sellner, Alexey Aksenov, Matthias Bodenbach, Pia Bader, Sebastian Baron, Anant Vemuri, Manuel Wiesenfarth, Nicholas Schreck, Diana Mindroc, Minu Tizabi, Sebastian Pirmann, Brittaney Everitt, Annette Kopp-Schneider, Dogu Teber, Lena Maier-Hein: Spectral imaging enables contrast agent-free real-time ischemia monitoring in laparoscopic surgery.
Science Advances (2023) DOI:
An image accompanying the press release is available for download at:
www.dkfz.de/de/presse/pressemitteilungen/2023/bilder/laparoscope.png
Caption: While conventional devices (right) generate an RGB video image, the newly developed laparoscope (left) uses a multispectral camera. This also makes it possible to visualize the functional properties of the fabric.
Notice of use for image material for press releases
Usage is free. The German Cancer Research Center (DKFZ) permits one-off use in connection with reporting on the topic of the press release or on the DKFZ in general. Please indicate as picture credits: “Source: Leonardo Ayala / DKFZ”.
The image material may only be passed on to third parties after prior consultation with the DKFZ press office (Tel. 06221 42 2854, email: [email protected]). Use for commercial purposes is prohibited.
With more than 3,000 employees, the German Cancer Research Center (DKFZ) is the largest biomedical research facility in Germany. More than 1,300 scientists at the DKFZ research how cancer develops, record cancer risk factors and search for new strategies to prevent people from developing cancer. They are developing new methods with which tumors can be diagnosed more precisely and cancer patients can be treated more successfully. At the Cancer Information Service (KID) of the DKFZ, those affected, interested citizens and specialist groups receive individual answers to all questions on the subject of cancer. Together with partners from the university clinics, the DKFZ operates the National Center for Tumor Diseases (NCT) at the Heidelberg and Dresden sites, and the Hopp Children’s Cancer Center KiTZ in Heidelberg. In the German Consortium for Translational Cancer Research (DKTK), one of the six German Centers for Health Research, the DKFZ maintains translation centers at seven university partner locations. The combination of excellent university medicine with the top-class research of a Helmholtz center at the NCT and DKTK locations is an important contribution to transferring promising approaches from cancer research to the clinic and thus improving the chances of cancer patients. The DKFZ is funded 90 percent by the Federal Ministry of Education and Research and 10 percent by the state of Baden-Württemberg and is a member of the Helmholtz Association of German Research Centers.