@danielthuff

PhD @wiscmedphys | ML/AI methods in medical imaging | https://xitter.cf/t.co/Dx51yxiLLO | he/him

 WA
Joined January 2021
  • Tweets23
  • Following100
  • Followers43
10Media
5/ Lesion matching is a harder task (for both 👩‍⚕️and 🤖) in subjects with higher disease burden. Here are IRV metrics as a function of lesion count – plots look similar if you compare automated to physician consensus.
1
1
65
6/ The big win for automated 🤖matching is in time savings. Automated matching took up to 11 minutes (on a typical desktop workstation – no NASA supercomputer here!), while clinicians took up to 130 minutes (⌛️!!) for the highest burden cases.
1
1
58
7/ big thanks to coauthors @victor_santoro, @aj_weisman, @TimothyGPerk, @jeraj_lab, and support from @aiq_solutions!!
1
71
3/ In our study, two #nucmed physicians matched lesions between pairs of #PETCT images of cancer pts. Then, we used an automated 🤖approach to do the same. We assess differences between clinicians 👨‍⚕️ and differences between physician consensus 👨‍⚕️👩‍⚕️ and automated🤖
1
1
66
4/ Automated matching met the benchmark of IRV in all study cohorts – meaning the variability between 🤖 and 👩‍⚕️ was similar to variability between 👨‍⚕️ and 👩‍⚕️
1
1
48
1/ Excited to share our latest paper! 🧵 Performance of an automated registration-based method for longitudinal lesion matching and comparison to inter-reader variability doi.org/10.1088/1361-6560/ac… via @ioppublishing
1
2
3
184
2/ Inter-reader variability (IRV) has been widely studied in image segmentation contexts, but another task clinicians 👩‍⚕️👨‍⚕️ perform is longitudinal comparison of multiple images to track lesions in time and determine change. This task is critical in determining tx. response!
1
1
58
Daniel Huff retweeted
JNM@JournalofNucMed13 Jan 2023
Learn about the future of oncology and therapy: ow.ly/5BcK50Mogfc #MolecularImaging and #Theranostics = Precision Oncology #Cancer #NuclearMedicine #JNuclMed
16
2
30
3,892
Join us next Monday at #RSNA22. AIQ's Eric Horler will give a presentation sponsored by @OneMedNet. We hope to see you there, and please contact us if you'd like to connect in Chicago.
3
1
6
Join us for our free, upcoming #webinar in partnership with @ConferenceForum. Register here to save your spot: theconferenceforum.org/confe… #ai #ImageAnalysis
3
2
5
This month has been pretty cool - I defended my PhD on imaging #immunotherapy response using #PET from ⁦@wiscmedphys⁩, and am now starting as a research scientist at ⁦@aiq_solutions⁩. Excited for new challenges! 😄
2
1
1
8
Are you a @UWMadGSEd student or @Badgerdocs / @UWPostdocOffice researcher interested in science careers? Join us at @DiscoveryBldg May 19 to chat with scientists who have careers in the communications space. Registration requested. warf.org/event/careers-and-b…
4
3
hey look its me😅
Parola Analytics@ParolaAnalytics1 Feb 2022
.@WARF_News's #patent filing is a way to monitor organ health during #cancer treatments. ➡️ Read more: bit.ly/3EByOQe
2
4
1/ A belated xmas present - our latest article detecting #immunotherapy toxicity on FDG PET was published in #EJNMMI. Elevated uptake in thyroid, lung, and bowel can indicate toxicity in those organs! Read the deets at: link.springer.com/article/10…
2
4
16
more replies
3/ Zooming out to all pts, things get messier - but general trend is elevated organ uptake at time of clinical toxicity dx (or sometimes before!). Worth noting that organ PET quantification here is automatic thanks to #AI-based organ segmentation.
1
1
4/ Early detection+monitoring of toxicity is critical for keeping pts on #immunotherapy! Our work suggests #PETimaging can play a role here, but big limitation is when scans are acquired after tx start.
1
Check out our new paper in BPEX using #AI to ID side-effects of #immunotherapy on FDG PET! w/ @grozomah @MauroNamias @HamidEmamekhoo @JerajLab Image intensity histograms as imaging biomarkers: application to immune-related colitis. doi.org/10.1088/2057-1976/ac… via @IOPscience
4
1
4
Check out our most recent paper towards a more quantitative understanding of treatment response for metastatic cancer patients. Development and validation of a longitudinal soft-tissue metastatic lesion matching algorithm doi.org/10.1088/1361-6560/ac… via @IOPscience
3
4
Is this how it's supposed to feel???
1
3
Load more