9/ Read the full article in @Radiology_RSNA at:
📖 pubs.rsna.org/doi/epdf/10.11…
#Radiology #Tweetorial #BreastImaging
60
8/
🧠The authors suggest regular review sessions of AI-flagged cases to help radiologists build intuition around AI decisions. Trust in AI comes from understanding.
1
82
7/
👀 Interesting twist: Unlike automation bias, where humans tend to over-trust AI, this study found that the consensus panel (which had access to both human & AI opinions) was more likely to disagree with the AI than the radiologist.
1
10
6/
💡So what does this mean?
Cases flagged by radiologists were more likely to be recalled than those flagged by AI. But… the AI-flagged recalls had a higher PPV.
#AIvsHuman
1
8
5/
📈 Key results:
--1 radiologist: recall rate = 14.2%, PPV = 3.4%
--AI only: recall rate = 4.6%, PPV = 22%
--2 radiologists: recall rate = 57.2%, PPV = 2.5%
--1 radiologist + AI: recall rate = 38.6%, PPV = 25%
--2 radiologists + AI: recall rate = 82.6%, PPV = 34.2%
1
9
4/
📌The authors did a secondary analysis comparing consensus outcomes of mammograms flagged by one reader (radiologist or AI), two readers (two radiologists or one radiologist + AI), and three readers. Key question: What happens at consensus discussion for those flagged cases?
1
13
3/
🔙 In 2023 the ScreenTrustCADtrial published its promising results, compared with standard-of-care radiologist double reading, replacing one radiologist with AI for independent reading resulted in a 4% higher noninferior cancer detection.
1
12
2/
📊 In this prospective study of 54,991 women, screening mammograms were read independently by two radiologists and one AI CAD reader. If at least one reader flagged the examination it went to a consensus panel for recall decisions.
1
18
1/ New insights from the ScreenTrustCAD trial!
How do radiologists interact with AI in breast cancer screening and what are the consequences for recall rates and positive predictive values (PPV)? Let's dive in. 👇 #Radiology #AI #breastcancer
1
108
Our PhD candidate Alma Hoxhaj used fruits and vegetables to test contrast-enhanced conebeam CT-guided biopsy.
Interested? Her work was presented at #ecr2023 and was recently featured on auntminnie.com.
auntminnie.com/index.aspx?Se…
#internationalwomensday #breastcancer
1
140
AXTI Lab retweeted
Proud of our colleague and friend @danielledok from the @LRCB_NL! Congrats for being awarded the Best Presentation on Professional Matters and Education and Training at #ECMP2022 of @EFOMP_org! Well done!
EFOMP :: The Best Presentations and Posters award | ECMP2022, Dublin, Ireland:efomp.org/index.php?r=news/v… Congratulations to all the winners
and indeed all who contributed their excellent work to the congress, the standards were very high👋👋👋
Today, Mireille Broeders gave a inaugural lecture for her full professor title ceremony at @Radboud_Uni. We are very proud and happy to be working with her to improve personalised breast cancer screening
AXTI Lab retweeted
.@IoannisNL .....presents the 'new' @EFOMP_org @aapmHQ dosimetry for mammography and 'magic 🪄' phantom @ECMP2022 – at Dublin City, Ireland
AXTI Lab retweeted
It was great speaking to group that included #medphys #ethicist #socialogist and #patientadvocate on how to develop tools to evaluate #AI products for in equities @euramed1 , day before @ECMP2022 begins. Diverse opinions on key topic such as #AI in health care is very helpful – at Dublin City, Ireland
AXTI Lab retweeted
1 day before the @ECMP2022 begins, the @euramed1 workshop on 'Digital resolutionðical challenges for medical applications' were organised.
☘️ @ECMP2022👇
✅Download the Event APP
✅Be ready to show QR code at the registration desk
😀Find some discount codes to our social tab
AXTI Lab retweeted
Replying to @ECMP2026
@ECMP2022 | EFOMP School for Medical Physics Experts (ESMPE) editions "EFOMP protocol for QC of Digital Breast tomosynthesis" with Ioannis Sechopoulos started (NL)!
#medicalphysics #breasttomosynthesis #european #congress
An associate editor is responsible for finding reviewers for papers, monitoring their work and making the final decision on the verdict of a paper. Marco will play a key role in the peer review process and will help ensure that high quality research will keep being provided.
1
Congratulations to our Post-Doc Marco Caballo who is now an Associate Editor for Medical Physics of @aapmHQ.
#AcademicTwitter #medicalphysics
We are #hiring!
Are you interested in applying deep learning on highly relevant breast cancer imaging problems, come find us!
You will be part of a very active and social lab and we look forward to welcoming you!
linkedin.com/jobs/view/30719…














