Case Study: TensorFlow in Medicine - Retinal Imaging (TensorFlow Dev Summit 2017)
ฝัง
- เผยแพร่เมื่อ 5 ก.ค. 2024
- Explore this illuminating ML medical case study where Lily Peng dives into the realm of diabetic retinopathy, the fastest growing cause of blindness linked to diabetes. Witness how the power of machine learning was trained to meticulously analyze retinal fundus images for precise diagnosis. Lily Peng guides you through the pivotal project phases, from acquiring a dataset, training a deep network, and evaluating the results.Embark on this journey to uncover the seamless fusion of ML and medicine, unraveling new possibilities in the realm of healthcare.
Chapters:
0:00 - Introduction
3:42 - Training a model
5:15 - Demo
5:59 - Development and Validation of Deep Learning Algorithm for Detection of diabetic Retinopathy in Retinal Fundus Photographs
7:16 - Why we used TensorFlow
9:52 - Session wrap up
Visit the TensorFlow website for all session recordings: goo.gl/bsYmza Subscribe to the Google Developers channel at goo.gl/mQyv5L
#ML #medicialtechnology
event: TensorFlow Dev Summit 2017; re_ty: Publish; - วิทยาศาสตร์และเทคโนโลยี
Awesome work ! One of the main points that Lily Peng pointed out was about data and its validity in general. As far as I know, DRIVE, STARE and Kaggle datasets are the best ones out there for deep-learning enabled Diabetic Retinopathy research. I am also amazed by how versatile Inception architecture is. She also pointed out that the network is pre-trained on ImageNet and thus got better results. Impressive work by the team ! Kudos guys !
Arun Das thanks for those references. Very useful.
one of the biggest obstacles of any product commercialisation is economics, in addition to politics of industry. having overcome the technical aspects (which in itself is another major obstacle), I hope this gets out to better the lives of many. thanks
The best statement " In the previous life I was a doctor and have been repurposed as Google Product manager" :-)
Exciting work with the potential to prevent so much suffering. The integration of the hardware, ML, and clinical experience is powerful. Thanks for sharing!
This is awesome!
A real case study where you show how AI can benefit humanity.
Outstanding job! Thanks.
Excellent. Keep up the good work
This is really great!
so much to do, so many possibilities!!
I really like all related to vision or image science, but it is hard to get into bioinformatics (or computer vision related) field even with computer science degree. Any advice if someone here has the answer on question 'How other people do this?' is valuable for me, so please share your thought!
Is data available to public??
What is now the best implementation of this in a modern app in 2021?
Are the images using the same type/quality imaging machine? if not, you've introduce image quality as a noncontrolled variable which is the one control that needs to be tight (exact same tolerances for precise validation) with this development.
9:28
How was the website created?
09:23 Nikon is not a little company, it's a huge DSLR maker LOL (I'm only saying this for a laugh)
I work on healthcare data and this is exciting news and inspiration to me
Everyone is small compared to Google I guess :-)
I thought about that too, but hmm... I still think that was not the smartest thing to say, at least out loud LOL
To me, that was clearly a joke (of the understatement kind).
Carlos Chau I think she meant Verily.
03:33 she says that for the two images all grades are classified. This is not correct. For the lower image there is no blue (no DR). Also no orange (severe) in the upper image?!
Anjeng
If you are so concerned about diabetic retinopathy, make your dataset open-source.
Is Nikon a little company? :) Good for now but I say India and other nations should invest in education, and produce more ophthalmologist in the long run.
this girl is sweet
We are thankful that Tensorflow will augment the intelligence lost
its my taste
That idiotic rising tone makes me sick