Italian researchers have completed a systematic literature review which was published this month in APL Bioengineering, by AIP Publishing. The review’s aim was to develop better understanding around artificial intelligence (AI) and its ability to be used as a treatment for brain disease. After gathering 2,696 different results, the researchers closed in on the top 154 most cited papers.
AI is able to process massive amounts of data, and it can do so very quickly. This, along with different approaches like machine learning, computer vision, and neural networks help create an environment where AI technology is an effective tool against many of the world’s biggest health problems.
However, there are many challenges surrounding the technology and its uses within these fields, specifically within diagnosis, surgical treatment, and brain disease monitoring. The new study could help develop new methods, which are constantly pushing the field forward.
One of the major points of the review was the use of a generative adversarial network in order to synthetically develop an aged brain. This allowed experts to study the progression of disease over time.
Alice Segato was the author of the paper detailing the review.
“The use of artificial techniques is gradually bringing efficient theoretical solutions to a large number of real-world clinical problems related to the brain,” Segato said. “Especially in recent years, thanks to the accumulation of relevant data and the development of increasingly effective algorithms, it has been possible to significantly increase the understanding of complex brain mechanisms.”
The study was focused on a few main areas of brain care, such as examining AI methods that are responsible for processing information about structure and connectivity characteristics of the brain, as well as surgical candidate assessment. The others included image data for studying brain disease, identifying issues and problem areas, predicting disease and outcomes, and intraoperative assistance.
Some of the image data that is used to study brain disease includes 3D data like magnetic resonance imaging, diffusion tensor imaging, positron emission tomography, and computed tomography imaging. Computer vision AI techniques can be used to analyze all of these types of image data.
In the published study, the researchers advocate for “explainable algorithms.” This means clearly detailed pathways to solutions, instead of the very vague “black box” that is often relied on.
“If humans are to accept algorithmic prescriptions or diagnosis, they need to trust them,” Segato said. “Researchers’ efforts are leading to the creation of increasingly sophisticated and interpretable algorithms, which could favor a more intensive use of ‘intelligent’ technologies in practical clinical contexts.”
This advocacy also comes during a time when international scientists are calling for more transparency in AI research. The group of scientists included members from top institutions like Princess Margaret Cancer Centre, University of Toronto, Stanford University, Johns Hopkins, Harvard School of Public Health, and Massachusetts Institute of Technology (MIT). According to the scientists, more transparent findings and methods could help lead to better cancer treatment based on the research.
- Humayun Sheikh, CEO of Fetch.ai – Interview Series
- Research Team Aims to Create Explainable AI for Nuclear Nonproliferation and Nuclear Security
- Pieter VanIperen, Founder & Managing Partner of PWV Consultants – Cybersecurity Interviews
- Advance in Microchips Brings Us Closer to AI Edge Computing
- AI Researchers Create Video Game Playing Model That Can Remember Past Events