IEM Seminar Series: Innovative Neurotechnologies for Brain Disorder Treatment: Merging Efficiency and Intelligence
Event details
| Date | 19.11.2024 |
| Hour | 16:15 › 17:00 |
| Speaker | Prof Mahsa Shoaran, Integrated Neurotechnologies Laboratory (INL), IEM and NeuroX |
| Location | Online |
| Category | Conferences - Seminars |
| Event Language | English |
Abstract
The field of neural interface technology holds great promise for developing new therapies for brain disorders that do not respond to conventional treatments. Today, neurotechnology is experiencing rapid growth, with several key trends shaping the future of the field. The push for denser electrode arrays is creating opportunities for higher-resolution neural data acquisition, benefiting applications from basic neuroscience to brain-machine interfaces (BMIs) and clinical treatments. However, this progress comes with substantial challenges in data processing and system integration. Current devices are limited by their recording and stimulation capacities, bulky designs, and insufficient embedded processing, leaving them unable to meet the needs of complex neurological conditions.
At the Integrated Neurotechnologies Laboratory (INL), we tackle critical challenges in low-power circuit design, medical devices, and edge intelligence, aiming to improve the accuracy, efficiency, and scalability of implantable and wearable devices. Bridging multiple disciplines, our lab has pioneered ML-enabled neural microchips that set new benchmarks in miniaturization, channel density, and efficient real-time processing.
In this talk, I will outline how we address these challenges through innovative neural interface designs. I will discuss our development of high-channel-count Systems-on-Chip (SoCs) that integrate novel circuit techniques and machine learning for real-time symptom management and movement control, significantly improving the capabilities of brain implants for epilepsy, movement disorders, and BMIs. Highlights include the NeuralTree SoC, a high-density closed-loop neuromodulation system with exceptional energy efficiency; the MiBMI chipset, a breakthrough brain-to-text interface that decodes complex neural signals with high accuracy and sub-mW power; and our closed-loop neural connectivity processors for psychiatric disorders. Finally, I will present our advances in wireless transmitter technology to push the boundaries of high-density, distributed brain implants. These innovations promise to reshape treatment paradigms and improve the performance of future neural devices.
Bio
Mahsa Shoaran is currently a Tenure-Track Assistant Professor in Electrical and Micro Engineering and NeuroX at EPFL and Director of the Integrated Neurotechnologies Laboratory (INL). From 2017 to 2019, she was an Assistant Professor of Electrical and Computer Engineering at Cornell University. Prior to that, she was a Postdoctoral Scholar in Electrical and Medical Engineering at Caltech, working in the Mixed-mode Integrated Circuits and Systems Lab from 2015 to 2017. Mahsa received her PhD from EPFL in 2015 and her B.Sc. and M.Sc. from Sharif University of Technology. Dr. Shoaran is a recipient of the ERC Starting Grant (2021) and the Google Faculty Research Award in Machine Learning and Data Mining (2018). Her team received the IEEE SSCS–Brain Best Paper Award in 2022 for their work on NeuralTree. She was named a Rising Star in EECS by MIT in 2015. Her research interests include low-power IC design for neural interfaces and BMIs, machine learning hardware, and neuromodulation therapies for neurological and psychiatric disorders. Dr. Shoaran serves on the Technical Program Committee of the International Solid-State Circuits Conference (ISSCC), as an Associate Editor for IEEE Transactions on Biomedical Circuits and Systems (TBioCAS), on the ISSCC Student Research Preview (SRP) committee, and as a Scientific Advisor to the NeuroTec Center in Bern. She has served on the Technical Program Committee of the IEEE Custom Integrated Circuits Conference (CICC), as an Editor for Current Opinion in Biotechnology and IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE).
The field of neural interface technology holds great promise for developing new therapies for brain disorders that do not respond to conventional treatments. Today, neurotechnology is experiencing rapid growth, with several key trends shaping the future of the field. The push for denser electrode arrays is creating opportunities for higher-resolution neural data acquisition, benefiting applications from basic neuroscience to brain-machine interfaces (BMIs) and clinical treatments. However, this progress comes with substantial challenges in data processing and system integration. Current devices are limited by their recording and stimulation capacities, bulky designs, and insufficient embedded processing, leaving them unable to meet the needs of complex neurological conditions.
At the Integrated Neurotechnologies Laboratory (INL), we tackle critical challenges in low-power circuit design, medical devices, and edge intelligence, aiming to improve the accuracy, efficiency, and scalability of implantable and wearable devices. Bridging multiple disciplines, our lab has pioneered ML-enabled neural microchips that set new benchmarks in miniaturization, channel density, and efficient real-time processing.
In this talk, I will outline how we address these challenges through innovative neural interface designs. I will discuss our development of high-channel-count Systems-on-Chip (SoCs) that integrate novel circuit techniques and machine learning for real-time symptom management and movement control, significantly improving the capabilities of brain implants for epilepsy, movement disorders, and BMIs. Highlights include the NeuralTree SoC, a high-density closed-loop neuromodulation system with exceptional energy efficiency; the MiBMI chipset, a breakthrough brain-to-text interface that decodes complex neural signals with high accuracy and sub-mW power; and our closed-loop neural connectivity processors for psychiatric disorders. Finally, I will present our advances in wireless transmitter technology to push the boundaries of high-density, distributed brain implants. These innovations promise to reshape treatment paradigms and improve the performance of future neural devices.
Bio
Mahsa Shoaran is currently a Tenure-Track Assistant Professor in Electrical and Micro Engineering and NeuroX at EPFL and Director of the Integrated Neurotechnologies Laboratory (INL). From 2017 to 2019, she was an Assistant Professor of Electrical and Computer Engineering at Cornell University. Prior to that, she was a Postdoctoral Scholar in Electrical and Medical Engineering at Caltech, working in the Mixed-mode Integrated Circuits and Systems Lab from 2015 to 2017. Mahsa received her PhD from EPFL in 2015 and her B.Sc. and M.Sc. from Sharif University of Technology. Dr. Shoaran is a recipient of the ERC Starting Grant (2021) and the Google Faculty Research Award in Machine Learning and Data Mining (2018). Her team received the IEEE SSCS–Brain Best Paper Award in 2022 for their work on NeuralTree. She was named a Rising Star in EECS by MIT in 2015. Her research interests include low-power IC design for neural interfaces and BMIs, machine learning hardware, and neuromodulation therapies for neurological and psychiatric disorders. Dr. Shoaran serves on the Technical Program Committee of the International Solid-State Circuits Conference (ISSCC), as an Associate Editor for IEEE Transactions on Biomedical Circuits and Systems (TBioCAS), on the ISSCC Student Research Preview (SRP) committee, and as a Scientific Advisor to the NeuroTec Center in Bern. She has served on the Technical Program Committee of the IEEE Custom Integrated Circuits Conference (CICC), as an Editor for Current Opinion in Biotechnology and IEEE Transactions on Neural Systems and Rehabilitation Engineering (TNSRE).
Practical information
- General public
- Free
Contact
- Prof. Jean-Philippe Thiran, IEM Director