Image courtesy of RSIP Vision
Precise medical imaging and analysis could enable early detection of lung cancer, help determine its exact size and location, and significantly improve diagnosis and treatment. This is usually done in a process called segmentation, which uses computers to identify the boundaries of the lung from surrounding thoracic tissue on CT images. From this process, a detailed 3-D map of the airways may be generated that can help to plan and navigate a bronchoscopy procedure to obtain biopsy samples and to perform other clinical interventions.
“Until now, this process was very difficult because you need the radiologist, or even the surgeon, to spend much time to understand how to get to the specific place [where the lesion is located]. And this is sometimes prone to error,” said Ron Soferman, founder and CEO of RSIP Vision, in an interview with MD+DI. “It's very critical [to know the precise location] because, if you miss the lesion, you will take a biopsy from some random part of the lung and it will give a negative result.”
RSIP Vision’s fully automated solution uses AI and deep learning technologies to provide a type of road map that can pinpoint the exact location of a suspicious lesion. The AI module uses sophisticated segmentation algorithms and computer vision to divide scanned images into clusters of pixels according to their characteristics. This replaces previous computer vision techniques that offered only a semi-automated airways segmentation, which required several iterations to find the initial seed point.
The procedure is performed in a fixed segmentation time, and it is independent of the quality of the given CT scan. Comparing the lungs with trees that have many branches that get smaller and narrower, Soferman said that this technology enables even the tiniest branches to be more easily located. “Now we can really understand very small airways, detecting them automatically to give you a picture,” he said.
RSIP Vision’s AI module will help surgeons navigate through the lung with greater accuracy, which may help to make possible more minimally invasive procedures that can be performed through the trachea, reducing unnecessary damage to healthy tissues.
The technology is commercially available and has already been used in some procedures, Soferman said, noting that it has received positive feedback from pulmonologists who have performed bronchoscopies with AI’s module.