National Taiwan University Hospital (NTUH) is collaborating with the U.S.- based Artificial Intelligence (AI) solution provider to develop the first-ever AI-powered tumour auto-contouring solution. To treat brain cancer, doctors must first precisely map out where the tumours are in the brain, in a process called contouring.
Using traditional manual contouring takes several hours, while the AI device can shorten the process to just a few minutes. It ensures precision mapping of brain tumours with closer cuts and the ability to identify additional lesions that may be missed by the human eye.
NTUH has been used the AI device for the past 18 months as part of clinical trials and helped doctors treat more than 100 patients with brain tumours, including a terminally ill woman whose lung cancer metastasised to her brain.
A doctor and researcher from NTUH said that he had successfully identified nine tumours in the female patient based on her imaging testing, but the AI device later detected two more. As a result, the patient received radiation therapy targeting the 11 tumours, saving her both time and money spent on a second treatment in the event the two tumours were not initially identified.
An oncologist and researcher from NTUH said that 10% of tiny brain tumours, mostly malicious brain metastases, can be missed with manual contouring. He also estimated that using the AI device cuts the time spent on tumour contouring by 50%, which enables patients to receive the treatment they need as soon as possible.
The director of the NTUH Department of Oncology said with the AI device, even tiny tumours can be treated precisely thereby ensuring patients experience fewer side effects. In addition, it also means doctors have time to help additional patients or engage in more discussions with existing patients
According to a page, The AI device has received clearance from the U.S. Food and Drug Administration (FDA). This is the first time the FDA has cleared an AI device for tumour auto-contouring in radiation therapy. Devices to receive FDA clearance before are specific to normal organ auto-contouring.
The research on this AI device has been published in the world’s leading medical journal. The researchers conducted a randomised, cross-modal, multi-reader, multi-speciality, multi-case study to evaluate the impact of AI device on brain tumour (Stereotactic Radiosurgery) SRS.
A state-of-the-art auto-contouring algorithm, built on multi-modality imaging and ensemble neural networks, was integrated into the clinical workflow. Nine medical professionals contoured the same case series in two reader modes (assisted or unassisted) with a memory washout period of 6 weeks between each section.
The case series consisted of ten algorithm-unseen cases, including five cases of brain metastases, three of meningiomas and two of acoustic neuromas. Among the nine readers, three experienced experts determined the ground truths of tumour contours.
The clinical findings indicated clinicians assisted by VBrain demonstrated 12.2% higher sensitivity for lesion detection, and less experienced clinicians improved contouring accuracy with the added help. The efficiency in AI device also decreased treatment planning time at a median of 30.8%.
Less-experienced clinicians gained prominent improvement on contouring accuracy but less benefit in reduction of working hours. By contrast, SRS specialists had a relatively minor advantage in DSC, but greater timesaving with the aid of AI.
CEO of the U.S. AI solution provider said that he was thrilled to bring the AI device to their partners across the U.S. and Taiwan. Receiving unique FDA clearance for this solution allows the company to further its commitment to transforming radiotherapy workflows through developing full-body auto-contouring solutions. The future of AI is near, bringing a second set of eyes and hands to assist clinicians in analysing and segmenting medical scans and further improving patient cancer care.
