Events Add an event Speakers Talks Collections
 
Duration 02:59
16+
Video

C21 Denoising stimulated Raman histology using weak supervision to improve label-free optical...

Esteban Urias
Research Assistant-Laboratory of Cell and Carbohydrate Engineering at Johns Hopkins University
+ 4 speakers
  • Video
  • Table of contents
  • Video
Machine Learning for Healthcare
August 8, 2020, Online, Los Angeles, CA, USA
Machine Learning for Healthcare
Request Q&A
Machine Learning for Healthcare
From the conference
Machine Learning for Healthcare
Request Q&A
Video
C21 Denoising stimulated Raman histology using weak supervision to improve label-free optical...
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Add to favorites
106
I like 0
I dislike 0
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
  • Description
  • Transcript
  • Discussion

About speakers

Esteban Urias
Research Assistant-Laboratory of Cell and Carbohydrate Engineering at Johns Hopkins University
Christian Freudiger
Co-Founder and Vice President, R&D at Invenio Imaging Inc.
Daniel Orringer
Associate Professor at NYU Langone Health
Honglak Lee
Senior Vice President and Chief Scientist of Artificial Intelligence at LG AI Research
Todd Hollon
Neurosurgeon at University of Michigan

Esteban Urias was raised in the southern border region between El Paso, TX and Ciudad Juarez, Mexico. Through a strong personal drive and family ties, he was able to overcome the several obstacles encountered during the peak of the violence in the border region. He was awarded the Gates Millenium Scholarship and completed a degree in Biomedical Engineering from Johns Hopkins University. He is currently a second year medical student at University of Michigan Medical School and plans on becoming a neurosurgeon.

View the profile

Chris Freudiger is an accomplished spectroscopist and the co-inventor of Stimulated Raman Scattering microscopy. He co-founded Invenio and has lead the development and commercialization of multiple generations of imaging systems. He enjoys working with customers to improve our products and developing new applications of technology that can positively impact the treatment of patients and reduce healthcare costs. Chris grew up in Munich, Germany and came to the United States on a Fulbright Fellowship and obtained his PhD in Physics from Harvard University.

View the profile

I am a board-certified neurosurgeon specializing in the care of primary and secondary tumors of the brain and spinal cord. The goal of my research is to leveraging advances in molecular imaging technology, such as stimulated Raman scattering microscopy, to improve the safety and accuracy of brain tumor surgery. I am the primary medical advisor to Invenio Imaging Inc., a Santa Clara startup devoted to the commercialization of stimulated Raman histology, a technique capable of simplifying the process of cancer diagnosis during surgery.

View the profile

I am a Senior VP and Chief Scientist at LG AI Research and also an Associate Professor of Computer Science and Engineering at the University of Michigan, Ann Arbor. Prior to joining LG AI Research, I worked as a Research Scientist at Google Brain. I received my Ph.D. from Computer Science Department at Stanford University in 2010, advised by Prof. Andrew Ng. My primary research interests lie in machine learning, in particular deep learning. Specific topics include representation learning, reinforcement learning, unsupervised, semi-supervised, and supervised learning, transfer learning, graphical models, and optimization. I also work on application problems in computer vision, control, text processing, and audio recognition. My work received best paper awards at ICML (2009) and CEAS (2005). I have served as a guest editor of IEEE TPAMI Special Issue on Learning Deep Architectures, as well as area chairs and senior program committee of ICML, NIPS, ICCV, AAAI, IJCAI, and ICLR. I received the Google Faculty Research Award (2011), NSF CAREER Award (2015), and was selected as one of AI's 10 to Watch by IEEE Intelligent Systems (2013) and a research fellow by Alfred P. Sloan Foundation (2016).

View the profile

Dr. Todd Hollon is a neurosurgeon specializing in the treatment of brain tumors. He grew up in Ionia, MI and attended the University of Michigan for his undergraduate degree. He then earned his Doctor of Medicine from Ohio State University, graduating with High Honors. Dr. Hollon’s clinical interests include the diagnosis and treatment of skull base and malignant brain tumors, including pituitary adenomas, meningiomas, and gliomas. Dr. Hollon is the principal investigator of the Machine Learning in Neurosurgery Laboratory (MLiNS) at Michigan Medicine. His research includes the use of computer science and artificial intelligence to improve the diagnosis and treatment of patients with brain tumors. Currently, his work focuses on using advanced intraoperative imaging methods to improve the speed and accuracy of tumor diagnosis and detection of tumor margins. Dr. Hollon has published extensively in peer-reviewed journals, including Nature Medicine, Nature Biomedical Engineering, Neuro-Oncology, Cancer Research, Journal of Neurosurgery, and Neurosurgery.

View the profile
Share

Hello. My name is this the one who dies? And I'm student researcher at the University of Michigan medical school. Today, I'll be talkin about using week supervision machine learning to remove noise from stimulator. Remind me images of human brain stimulator. Remind histology labeled free Optical Imaging method, that produces high-resolution, histologic images of tissue, different wavelengths of the remind shifts. This modalities able to catch a CH 3 signal corresponding to protein in the ch3 ch2 signal corresponding two nuclei combine. These three

signals into a 3 Channel. RGB image, reduce an image like the one shown below. Unfortunately, for microscope laser aberrations in the Bible chemical properties of damaged specimens images. On top of high-quality images of all the images in the bottom are low-quality images that have lost features essential for diagnosis. We propose a solution to the problem of denoising, SRH images are using a training algorithm the Churches with supervision based on perceptual image quality ratings. In other words, we want to restore low-quality images by training a deep Learning

Network with our own pair of data set from my party images. Artists are each day to see it was split into three groups based on their perceptual quality is average and low. For now, we'll focus on the high-quality images that were used to generate a pair Training Day, to sit to pray that they decide the original. High quality images, copied and noise from a gaussian distribution with variants randomly ranging between 20 and 80 is added this noisy image startes as the input to the network and its corresponding high quality image search with the target. That's creating a week supervision

training base of a unit, convolutional network with down, sampling and coder and up. Sampling decoder region, Strong by skip, to next level 3 edition. We compare a network to a traditional denoising out in quarter, in a not learning, denoising Agra than call non-local meet. Some of the most important features with high diagnostic power are the nuclei of cells and accent, light structure. As you can see, our network has restored, many of the Lost features of the noisy image. And it's almost indistinguishable from the original image quality. HD images generated by the other men,

when tested our Network outperformed, the other methods with higher SSI and mostly higher PC in our sport which represent her image quality Leslie. You should train Network, did you know if the low party images from our data set have you can see our new Natok, perform, all the other message, the Human Show improve, perceptual quality of diagnostic features and the average risk was using 1000 Pages. Were also lower using our Network, which is consistent with higher quality of the images. Over all our Network, outperformed the other learning and not learning, be noisy

method, possibly created a pipeline that generates paired data sets, use for semi-supervised training. Thank you.

Cackle comments for the website

Buy this talk

Access to the talk “C21 Denoising stimulated Raman histology using weak supervision to improve label-free optical...”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Ticket

Get access to all videos “Machine Learning for Healthcare”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Ticket

Interested in topic “Artificial Intelligence and Machine Learning”?

You might be interested in videos from this event

February 4 - 5, 2021
Online
26
106
ai, application, bot, chatbot, conversation, data, design, healthcare, ml

Similar talks

Besmira Nushi
Principal Researcher at Microsoft
+ 1 speaker
Byron Wallace
Associate Professor at Northeastern University
+ 1 speaker
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Ariane Marelli
Professor of Medicine at McGill University
+ 10 speakers
Chao Chao Li
E. B. Eddy Professor and Canada Research Chair at McGill University
+ 10 speakers
Aihua Liu
Psychologist at McGill University
+ 10 speakers
Hanh Nguyen
Рsychologist at McGill University
+ 10 speakers
James Brophy
Professor at McGill University
+ 10 speakers
Liming Guo
Research at McGill University
+ 10 speakers
David Buckeridge
Professor at McGill University
+ 10 speakers
Jian Tang
Assistant Professor at HEC Montreal
+ 10 speakers
Joelle Pineau
Associate Professor at McGill University
+ 10 speakers
Yi Yang
Associate Professor of Statistics at McGill University
+ 10 speakers
Yue Li
Assistant Professor at McGill University
+ 10 speakers
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Richard Peters
Technology Innovation Lead, Assistant Professor Population Health at Dell Medical School at the University of Texas at Austin
+ 4 speakers
Ali Lotfi Rezaabad
Machine Learning Researcher at Bosch Center for Artificial Intelligence (BCAI)
+ 4 speakers
Matthew Sither
Lead Software Engineer at Dell Medical School at The University of Texas at Austin
+ 4 speakers
Abhishek Shende
Co-Founder/ ML Engineer at BrilliantMD
+ 4 speakers
Sriram Vishwanath
President and Co-Founder at GenXComm
+ 4 speakers
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Buy this video

Video
Access to the talk “C21 Denoising stimulated Raman histology using weak supervision to improve label-free optical...”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Conference Cast

With ConferenceCast.tv, you get access to our library of the world's best conference talks.

Conference Cast
949 conferences
37757 speakers
14408 hours of content
Esteban Urias
Christian Freudiger
Daniel Orringer
Honglak Lee
Todd Hollon