TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Machine Learning for MRI Image Reconstruction

79 pointsby raffihotterover 3 years ago

6 comments

tqiover 3 years ago
&gt; This makes it hard to predict when and how deep learning methods will fail (there are no theoretical guarantees that deep learning will work).<p>I actually think we know fairly well how deep learning methods work (and what the shortcomings are), we just have no way to interpret the models it produces. Wouldn&#x27;t ML techniques to reduce scan times fail at the most critical moments, ie when patients had unusual or unexpected ailments? Using ML in on downsampled MRI images feels akin to having an artist with a lot of familiarity of human anatomy touch up a scan.
评论 #29775714 未加载
评论 #29779938 未加载
评论 #29776143 未加载
olliejover 3 years ago
Things like MRIs are the last thing you want to be using ML to invent detail in.<p>This proposal basically says using ML we can quarter the number of frequencies we sample and still get good <i>looking</i> scans. But the full resolution is made by inventing details based on statistics from a biased input (most MRIs are taken due to something being wrong).<p>Again, as with super resolution, ML cannot add detail that isn’t there, anything it creates is simply based on the statistical model it formed from the training set.
评论 #29775773 未加载
评论 #29776364 未加载
vitorsrover 3 years ago
&gt; Though compressed sensing can improve the image quality relative to a vanilla inverse Fourier transform, it still suffers from artifacts.<p>Odd remark. FDA approves compressed sensing products (e.g., [1], [2], [3], [4]) precisely because it is possible (and provably so) to quantify and&#x2F;or characterize such “artifacts” up to substantial equivalence.<p>[1] <a href="https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn.cfm?ID=K162722" rel="nofollow">https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn...</a><p>[2] <a href="https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn.cfm?ID=K163312" rel="nofollow">https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn...</a><p>[3] <a href="https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn.cfm?ID=K173079" rel="nofollow">https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn...</a><p>[4] <a href="https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn.cfm?ID=K173617" rel="nofollow">https:&#x2F;&#x2F;www.accessdata.fda.gov&#x2F;scripts&#x2F;cdrh&#x2F;cfdocs&#x2F;cfpmn&#x2F;pmn...</a>
评论 #29784264 未加载
01acheruover 3 years ago
Can’t wait to do an MRI and hear the doc say “You’re all set, good to go!”, only to discover that I actually had a tumor but that really clever ML algorithm thought that it was noise and should’ve been smoothed out…<p>I don’t want to be part of it, thanks
评论 #29776212 未加载
评论 #29780051 未加载
评论 #29776050 未加载
londons_exploreover 3 years ago
Could this be taken one step further... Use the ML in-the-loop during an MRI scan, to look at the data collected so far, then decide which frequency should be measured next to most improve the quality of the result?<p>This can also all be simulated offline without an MRI machine to test on with just access to a few full scans... So could be a good weekend project for someone here on HN, and your technique might even be in use by the time you need an MRI scan and will mean your doctor can get results slightly quicker and you get better healthcare, together with hundreds of millions of other people!
nik282000over 3 years ago
Need training data? Offer scans at half price in America if they agree to hand over their images!