Getting your Trinity Audio player ready...
|
The All-India Institute of Medical Science (AIIMS) has joined forces with the Indian Institute of Technology Delhi (IIT-Delhi) to create an artificial intelligence (AI)-powered simulator intended for the training and assessment of aspiring neurosurgeons in the proficiency of minimally invasive microscopic and endoscopic surgical techniques.
According to specialists, it aims to revolutionise the observation and evaluation of neurosurgical skills, crucial factors influencing outcomes in brain surgery. This system significantly alleviates the evaluation responsibilities of neurosurgeons and sets a benchmark for training and assessment protocols in the field.
Dr Ashish Suri, the principal investigator of the neuro-engineering facility and the unit head of the neurosurgery department at AIIMS Delhi, highlighted that in the existing apprenticeship model, neurosurgeons acquire skills through observation and assisting experts in the operating room. However, this traditional approach is becoming increasingly prohibitive due to the lack of efficient training. To address the challenges and deliver more effective coaching, intelligent smart surgical simulators offer a viable alternative.
He mentioned the crucial role played by 3D printing and AI in the creation of neurosurgical simulators and the assessment of surgical skills in the domain of brain surgery. 3D printing facilitates the production of intricately detailed and personalised brain models, allowing surgeons to practice procedures on lifelike anatomical structures. AI, employing deep learning and machine learning algorithms, can assess a surgeon’s performance in terms of precision, speed, and decision-making during these simulations, providing real-time feedback.
The institute hopes that this pioneering initiative has the potential to reshape the method of educating upcoming surgeons. A key participant in this project and the head of the computer science department at IIT-Delhi, Professor Prem Kumar Kalra, expressed that the partnership between IIT-Delhi and AIIMS in this project has produced noteworthy outcomes in automating the assessment of skills in microscopic and endoscopic neurosurgery training through the application of computer vision and AI/ML. This progress is expected to stimulate additional research in the development of technology for medical education and training.
In a parallel scenario showcasing the accelerated advancement of medical procedures through AI/ML, researchers at the Indian Institute of Science (IISc) in Bengaluru developed an AI tool proficient in identifying the median nerve in ultrasound videos, facilitating the diagnosis of carpal tunnel syndrome (CTS). OpenGov Asia had previously reported, CTS manifests when the median nerve, which traverses from the forearm to the hand, experiences compression at the wrist’s carpal tunnel, resulting in sensations of numbness, tingling, or pain.
Presently, physicians use ultrasound for visualising the median nerve and assessing factors such as its size, shape, and potential irregularities. However, distinguishing details in ultrasound images and videos is challenging compared to X-rays and MRI scans.
Precise tracking of the median nerve holds significant importance, particularly in medical interventions that entail the administration of local anesthesia to the forearm or the blockade of the median nerve to relieve pain.
In developing their tool, the team employed a machine learning model with a transformer architecture, like the technology powering ChatGPT. Initially designed to recognise multiple objects in an online video-sharing and social media platform, the team refined the model by removing computationally intensive components and honing its focus to track a specific object—the median nerve in this case.