A clear vision | The current of UCSB


Good vision is essential for everyday life, but about 12 million Americans ages 40 and older live with visual impairment, 1 million of whom are legally blind, according to the Centers for Disease Control and Prevention. Although some affected individuals can be treated with surgery or medication, and recent advances in gene and stem cell therapies show promise, there is no effective treatment for many people blinded by severe degeneration or damage to retina, optic nerve or cortex. In such cases, an electronic visual prosthesis, or bionic eye, may be the only option.

Michael Beyeler, an assistant professor of computer science and psychological and brain sciences at UC Santa Barbara, aims to bring an AI-powered bionic eye that can generate artificial vision to the general public, with the goal of improving quality life of patients who are blind or visually impaired.

“I envision an intelligent bionic eye that could find misplaced keys on a counter, read drug labels, notify a user of people’s gestures and facial expressions during social interactions, and warn a user of nearby obstacles and chart safe paths,” he said.

For his project, “Towards an Intelligent Bionic Eye: AI-Powered Computer Vision for the Treatment of Incurable Blindness,” Beyeler was shortlisted for the National Institutes of Health (NIH) Director’s New Innovator Award. The five-year, $1.5 million grant was one of 103 awarded this week by the NIH to enable exceptionally creative early-career scientists to push the boundaries of biomedical science and pursue high-impact projects. that aim to advance knowledge and improve health.

“I offer my heartfelt congratulations to Professor Beyeler on being recognized for his innovative research by the prestigious NIH Director’s New Innovator Award,” said Tresa Pollock, Acting Dean of the College of Engineering and Alcoa Distinguished Professor of Materials. “His new approach of using recent advances in computer vision, AI and neuroscience has enormous potential to uncover new insights and provide millions of people with useful vision through an intelligent bionic eye.”

“I am extremely honored and thrilled to receive this award,” said Beyeler, who has previously received the NIH Pathway to Independence Award. “As part of the NIH’s high-risk, high-reward research program, this award will enable my group to explain the science behind bionic technologies that may one day restore useful vision to millions of people living with blindness. incurable.”

Bionic eyes, as we know them, transform light, captured by a front camera, into electrical impulses which are delivered by a network of microelectrodes implanted in the eye or the visual cortex, which are then interpreted by the brain as visual perceptions, or phosphenes. Although current devices generally offer a better ability to differentiate light from dark backgrounds and see motion, the vision they provide is blurry, distorted and often difficult to interpret.

A major challenge for scientists trying to develop visual prostheses is therefore to predict what implant recipients “see” when they use their devices. Instead of seeing focal points of light, current retinal implant users perceive heavily distorted phosphenes that often fail to assemble into more complex objects of perception. Consequently, the vision generated by current prostheses has been widely described as “fundamentally different” from natural vision, and does not improve over time.

Beyeler takes a different approach. Rather than aiming to make bionic vision as natural as possible, he suggests focusing on how to create practical and useful objects. artificial vision that would be based on artificial intelligence (AI)-based scene understanding and would be adapted to specific real-world tasks that affect the quality of life of a blind person, such as facial recognition, navigation in outdoors and personal care.

His new multidisciplinary strategy for this project will study the neural code of vision, studying how to translate electrode stimulation into code that the human brain can understand.

“We want to address fundamental questions at the intersection of neuroscience, computing and human-computer interaction to enable the development of a Smart Bionic Eye, a visual neuroprosthesis that functions as a visual aid powered by AI for the blind,” Beyeler said. .

To enable technology that provides signals to the visually impaired, much like a computer vision system communicates with a self-driving car, Beyeler must first understand how visual prostheses interact with the human visual system to shape perception. He said a common misconception in the field is that each electrode in a device’s microelectrode array can be thought of as a pixel in an image, or a tiny area of ​​illumination on a display screen, and that to generate a complex visual experience, one simply needs to activate the right combination of pixels. His research shows, however, that the visual experience provided by current prostheses is highly distorted and unrelated to the number of electrodes.

“Current devices do not have sufficient image resolution to transmit a complex natural scene. Therefore, it is necessary to simplify the scene,” Beyeler said.

According to Beyeler, one way to simplify the visual scene and create useful machine vision is to use deep learning-based computer vision, which can be used to highlight nearby obstacles or remove clutter by background. Computer vision is a field of AI that allows computers and systems to derive important information from digital images, videos, and other visual input, and take action or make recommendations based on it. of this information. Computer vision relies on cameras, data, and algorithms, rather than retinas, optic nerves, and visual cortex.

He said his project will be patient-centered, involving people at all stages of the design process to test his group’s theoretical predictions. Patients will be provided by its collaborators at four universities across the country and in Spain. Beyeler’s team will design experiments that probe the potential of an implant to support functional vision for real-world tasks involving object recognition, scene understanding, and mobility. This method deviates from the typical vision tests performed in clinics that measure acuity, contrast sensitivity and orientation discrimination.

Due to the unique demands of working with recipients of bionic eyes, such as constant assistance, setup time, and travel, experimentation remains time-consuming and expensive. Beyeler offers an interim solution.

“A more cost-effective and increasingly popular alternative could be to rely on an immersive virtual reality (VR) prototype based on simulated prosthetic vision (SPV),” Beyeler explained.

The classic SPV method relies on sighted subjects wearing a head-mounted VR display (HMD). The subjects are then deprived of natural vision and allowed to perceive only the phosphenes displayed in the HMD. This approach allows sighted participants to “see” through the eyes of the bionic eye user as they explore a virtual environment. The visual scene can then be manipulated by researchers according to any desired image processing or visual enhancement strategy.

“The challenge in the field is less about devising new augmentation strategies and more about finding effective visual representations to support practical, everyday tasks,” Beyeler said. “That’s why in my project we’re using a prototyping system that allows us to explore different strategies and find out what works before implanting devices in patients.”

In the future, he said, the Smart Bionic Eye could be combined with GPS to give directions, warn users of impending dangers in their immediate surroundings, or even extend the range of visible light with the use of an infrared sensor, providing what he describes as “bionic night vision”. But before any of that can happen, Beyeler said, fundamental scientific questions must be addressed.

“The success of this project would result in a potential new treatment option for incurable blindness, which affects nearly 40 million people worldwide,” said Beyeler, who plans to put all software, tools and anonymized data from his group at the disposal of the scientific community. “Overall, this will be a fantastic opportunity for my lab to contribute substantially to the field of sight restoration and make a difference in the world.”


About Author

Comments are closed.