Kiran Vaidhya Venkadesh
@kiranvaidhya93
Followers
527
Following
5K
Media
134
Statuses
1K
Co-founder, CTO at Plain Medical
Nijmegen, Netherlands
Joined June 2013
⏳Our AI algorithm predicts lung cancer risk by incorporating prior CT scans, which provide valuable temporal information to clinicians, such as changes in nodule size or appearance. #lungcancer #radiology #ai. Performance icon created by @freepik @flaticon.
1
0
4
RT @fchollet: When you talk to young folks, they think that the belief in imminent AGI was caused by the rise of LLMs. In reality, this bel….
0
223
0
Our recent study on using CT exams from previous years to enhance AI predictions of lung cancer risk got covered by RSNA News.
"Early-stage lung cancer can manifest as small pulmonary nodules, with CT examinations highly effective at depicting these nodules. @jacobscolin1 @kiranvaidhya93
0
0
4
Actually the first thing I picked up when I switched from Windows to Mac.
The most unknown most common shortcut I use on my MacBook is:. - Command+Option+Shift+4 to select a small part of the screen and copy it into clipboard as an image.- Command+Shift+4 to do the same, but save it as a file on Desktop as png. Life-changing.
0
0
0
RT @MaxCRoser: This shows the share of global electricity production coming from solar and wind. • In 2012, it was just 3%. • Five years l….
0
341
0
My first visit to @RSNA, after having had to give two scientific talks online during corona. Chicago is a beautiful city. 💙 . Looking forward to seeing the progress so far in #RadiologyAI #RSNA2023
1
0
12
RT @lungradiologist: A 20-year Follow-up of the International Early Lung Cancer Action Program (I-ELCAP) | Radiology. 89 404 participants.….
pubs.rsna.org
The estimated cure rate of 80% using the 10-year lung cancer–specific survival of 484 International Early Lung Cancer Action Program (I-ELCAP) participants reported in 2006 has persisted after 20 y...
0
7
0
RT @gradientpub: How can we capture classical computation with neural networks? @PetarV_93 writes:.
thegradient.pub
In this article, we will talk about classical computation: the kind of computation typically found in an undergraduate Computer Science course on Algorithms and Data Structures [1]. Think shortest...
0
19
0
I couldn't agree more with @_jasonwei here. Manual inspection of data is by far the most effective way of understanding a task and solving it with deep learning. And it has such a low entry barrier, which is a mark of how easy it is to build deep learning algorithms now.
One pattern I noticed is that great AI researchers are willing to manually inspect lots of data. And more than that, they build infrastructure that allows them to manually inspect data quickly. Though not glamorous, manually examining data gives valuable intuitions about the.
0
0
0
RT @radiology_rsna: An AI prediction uncertainty quantification metric consistently identified reduced AI performance in cancer diagnosis a….
0
6
0
RT @BcalvesNatlia: Our latest paper has just been published in @radiology_rsna!.We show that uncertainty quantification can identify patien….
0
7
0
RT @gradientpub: In the world of generative AI, a new phenomenon has emerged: AI now generates 3D CAD models from text. However, it also pr….
thegradient.pub
In the realm of AI-powered text-to-CAD, there's promise, but also a surge in subpar designs. Can we steer this technology towards better outcomes?
0
2
0
🔗 To know more about our research, please check out our recent publication in @radiology_rsna:
pubs.rsna.org
A deep learning algorithm trained to estimate 3-year malignancy risk of screening-detected pulmonary nodules using current and prior low-dose CT examinations outperformed validated models that used...
0
0
0
My awesome colleague will be hosting the popular #RadAIchat today.
We all know that no AI algorithm will work for every single patient. But what if there was a way to know which cases AI will perform well and which cases it's most likely giving a wrong prediction? Curious? Join our #RadAIchat tonight to find out more!
0
0
3
RT @waitbutwhy: The Earth is 4.5 billion years old and is expected to be swallowed by the sun in about 5 billion years, when Earth is 9.5 b….
0
963
0
RT @radiology_rsna: In this editorial, Drs. Horst and Nishino discuss the implications of the deep learning study by Venkadesh et al for pu….
0
1
0
Our latest research, which centers on leveraging prior CT scans to bolster AI predictions of #lungcancer risk, is now published in @radiology_rsna.🙃.
A deep learning algorithm trained to estimate 3-year malignancy risk for screening-detected pulmonary nodules using current and prior low-dose CT scans outperformed validated models that used a single CT scan. @kiranvaidhya93 @jacobscolin1 @radboudumc
1
0
8
Remember watching a highly impressive presentation by @joeranbosma, who was defending his Master's thesis back then. Happy to see this work published in @Radiology_AI.
Semisupervised learning guided by clinical reports achieved similar csPCa detection performance with supervised learning while significantly reducing annotation burden @anindox8 @MaartendeRooij @radboudumc #Semisupervised #ML #MachineLearning
0
0
2