How Neural Networks are used in Medical Imaging
Topic 1: Image Quality Assessment and Enhancement of Fetal Brain Magnetic Resonance Imaging using Convolutional Neural Networks
(Sayeri Lala)
Fetal Brain Magnetic Resonance Imaging (MRI) complements Ultrasound in diagnosing brain pathologies. Despite the utility of fetal brain MRI, the substantial, rapid, and non-periodic nature of fetal motion can severely degrade image quality, often requiring several repeat acquisitions in the clinic.
To improve scan efficiency and diagnostic quality, we investigated Convolutional Neural Networks (CNNs) to perform rapid image quality assessment and enhancement. In a retrospective study, we demonstrated that a CNN for image quality assessment achieves good performance, and observed from saliency maps that the classifier learns relevant criteria. We also showed that on retrospectively undersampled data, a CNN based architecture produces higher quality images compared to traditional reconstruction algorithms. The fast evaluation and reconstruction times of the CNNs suggests their potential to be used during the scan to monitor and enhance image quality.
Topic 2: Deep learning and GAN enable 4x faster scans for clinical radiology (MR, PET and more) (Enhao Gong)
Abstract:
In this talk, Dr. Gong will introduce the research and technology development at Stanford and Subtle Medical on AI-powered medical imaging reconstruction and enhancement. Subtle Medical develops AI/Deep Learning software solution that recently gains FDA clearance and enables faster & safer radiology exams. For faster PET and MRI exams, deep learning algorithms are used to replace the conventional iterative optimization based algorithm. Using ResNet-based recurrent structure and generative adversarial network (GAN) based adversarial loss, the model successfully reconstructs images from low-quality into high-quality with significantly better signal-to-noise ratio and resolution information. Results from clinical partners and deployment sites such as Hoag Hospital and UCSF demonstrate the improvement of clinical workflow and diagnostic quality. The AI inference in deployment is further accelerated with industry frameworks such as NVIDIA tensorRT and Intel OpenVINO. The solutions are currently in clinical usage and commercialization, providing immediate and quantifiable values of AI to hospitals and imaging centers.
In further research work, task-driven GAN and cycle-GAN are used to further improve the performance of DL-based medical image enhancement, demonstrating superior performance for more extreme application of ultra-low-dose PET and 1min-MR scan that will disrupt how radiology is used in healthcare.
Date and Time
Location
Hosts
Registration
- Date: 23 Jul 2019
- Time: 06:30 PM to 09:00 PM
- All times are (UTC-07:00) Pacific Time (US & Canada)
-
Add Event to Calendar
- 2800 Scott Blvd
- Santa Clara, California
- United States 95050
- Building: Nvidia Buliding E
- Click here for Map
- Contact Event Host
- Co-sponsored by dev_bhattacharya@ieee.org
Speakers
Ms. Sayeri Lala
Accurate Sleep Monitoring
Fetal Brain Magnetic Resonance Imaging (MRI) complements Ultrasound in diagnosing brain pathologies. Despite the utility of fetal brain MRI, the substantial, rapid, and non-periodic nature of fetal motion can severely degrade image quality, often requiring several repeat acquisitions in the clinic.
To improve scan efficiency and diagnostic quality, we investigated Convolutional Neural Networks (CNNs) to perform rapid image quality assessment and enhancement. In a retrospective study, we demonstrated that a CNN for image quality assessment achieves good performance, and observed from saliency maps that the classifier learns relevant criteria. We also showed that on retrospectively undersampled data, a CNN based architecture produces higher quality images compared to traditional reconstruction algorithms. The fast evaluation and reconstruction times of the CNNs suggests their potential to be used during the scan to monitor and enhance image quality.
Biography:
Sayeri Lala received her Bachelor’s and Master’s degrees majoring both in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology (MIT). At MIT, she researched machine learning and deep learning techniques for medical image analysis, as well as artificial intelligence algorithms for natural language processing. She also studied machine learning applications through research internships at NASA Ames Data Sciences group, Apple Maps, and other Silicon Valley tech companies. She is also a member of the honor societies of Tau Beta Pi and IEEE Eta Kappa Nu at MIT and is a member of IEEE. She has several publications and was awarded an NSF GRFP honorable mention. As a Ph.D. candidate in Electrical Engineering at Princeton University, she is focusing on Machine Learning, Neuroscience, and Signal Processing.
Mr. Enhao Gong
Deep learning and GAN enable 4x faster scans for clinical radiology (MR, PET and more)
In this talk, Dr. Gong will introduce the research and technology development at Stanford and Subtle Medical on AI-powered medical imaging reconstruction and enhancement. Subtle Medical develops AI/Deep Learning software solution that recently gains FDA clearance and enables faster & safer radiology exams. For faster PET and MRI exams, deep learning algorithms are used to replace the conventional iterative optimization based algorithm. Using ResNet-based recurrent structure and generative adversarial network (GAN) based adversarial loss, the model successfully reconstructs images from low-quality into high-quality with significantly better signal-to-noise ratio and resolution information. Results from clinical partners and deployment sites such as Hoag Hospital and UCSF demonstrate the improvement of clinical workflow and diagnostic quality. The AI inference in deployment is further accelerated with industry frameworks such as NVIDIA tensorRT and Intel OpenVINO. The solutions are currently in clinical usage and commercialization, providing immediate and quantifiable values of AI to hospitals and imaging centers.
In further research work, task-driven GAN and cycle-GAN are used to further improve the performance of DL-based medical image enhancement, demonstrating superior performance for more extreme application of ultra-low-dose PET and 1min-MR scan that will disrupt how radiology is used in healthcare.
Biography:
Enhao Gong is the founder and CEO at Subtle Medical, an AI and radiology startup from Stanford and the winner of 2018 NVIDIA Inception Award at AI+Healthcare. He’s a serial entrepreneur and PhD in electrical engineering at Stanford, with a research focus on applying AI and deep learning to improve reconstruction, analysis, and quantification in medical imaging. His work applies AI to accelerate and reduce doses for MRI and PET and has been the top-downloaded paper in the clinical medical imaging journals and featured in numbers of academic conferences and industry media. Dr. Gong has won several awards, including RSNA research award, Forbes China 2018's and Forbes Asia 2019’s “30 under 30.”
Agenda
Sayeri Lala will present for 20 min and Enhao Gong present for 40 minutes.