Veronika Cheplygina
5 days ago

📝 Read our call for papers here:

#MedicalImaging #MachineLearning #AI #FairAI

If you have any questions please reach out to us via!


Veronika Cheplygina
5 days ago

🚨 Are you interested in the Fairness of Artificial Intelligence for Medical Imaging? Don't miss our next #FAIMI workshop at #MICCAI2023!

⏰Papers due: Jul 21, 2023
📅Workshop: Oct 8, 2023
📍Where: Vancouver 🇨🇦

Check out:

#MedicalImaging #Fairness #MachineLearning 1/3

Veronika Cheplygina
6 days ago

Many people working on #MachineLearning algorithms assume the data is already there, but there's a lot of work behind the scenes! If you want to learn about how some #MedicalImaging challenge datasets were made, join our next "Datasets through the L👀king-Glass" webinar, organized by @amelia

🗓️ Date: 5th June 2023
🕓 4pm CEST
💻 Where: Zoom. Register at



Veronika Cheplygina
1 month ago

The postdoc position #MachineLearning #MedicalImaging #HCI I'm hiring for is finally online! Please reach out if you might be interested, if you happen to be at #CHI2023 physically or virtually we can talk offline or on the Discord channel!

1 month ago

date: 2023-04-20 13:41:22
by: Bartek Papiez

🚨 Fully funded PhD opportunities in AI and medical imaging! 🎓 Join our world-class team and revolutionize healthcare with cutting-edge technology! Apply now ( and take your skills to the next level! 🔬💊 #PhD #AI #MedicalImaging #Healthcare #FullyFunded


cynicalsecurity :cm_2:
2 months ago

[Only one paper so no summary toot]

D. Clunie et al., "Report of the Medical Image De-Identification (MIDI) Task Group -- Best Practices and Recommendations"¹

This report addresses the technical aspects of de-identification of medical images of human subjects and biospecimens, such that re-identification risk of ethical, moral, and legal concern is sufficiently reduced to allow unrestricted public sharing for any purpose, regardless of the jurisdiction of the source and distribution sites. All medical images, regardless of the mode of acquisition, are considered, though the primary emphasis is on those with accompanying data elements, especially those encoded in formats in which the data elements are embedded, particularly Digital Imaging and Communications in Medicine (DICOM). These images include image-like objects such as Segmentations, Parametric Maps, and Radiotherapy (RT) Dose objects. The scope also includes related non-image objects, such as RT Structure Sets, Plans and Dose Volume Histograms, Structured Reports, and Presentation States. Only de-identification of publicly released data is considered, and alternative approaches to privacy preservation, such as federated learning for artificial intelligence (AI) model development, are out of scope, as are issues of privacy leakage from AI model sharing. Only technical issues of public sharing are addressed.

#arXiv #ResearchPapers #MedicalImaging #Privacy #DICOM

2 months ago

Yes, it's an series of #CardiacMRI images of my heart!

Think you're a #radiology genius? Guess what's wrong with me!

If you can read these, you could win a #MedicalImaging no-prize!

It's an MRI of my heart!
Guess what's weird about it.
It's another MRI image, a fraction of a second later.
A third black and white image of human insides, pulsing and jiggling like abstract stained glass.
And on the MRI, the heart refills, ventricle opening.
3 months ago

date: 2023-03-13 08:45:14
by: Claudia Lindner

5 days left to apply!

#PhD opportunity at the intersection of #AI and medicine, involving large and diverse clinical and #MedicalImaging data of patients undergoing knee replacement surgery.

Deadline: 17th March 2023


3 months ago

Save the date!
#Miccai #Brain lesion workshop will be on October 8th 2023 in Vancouver
Program and submission page will be updated soon #medicalimaging #MachineLearning #AI #neuroimaging #braintumor

3 months ago

If you are at SPIE #medicalimaging in SanDiego, check Monika Pytlarz poster on classification of #brain #tumor biopsies TMA via #deeplearning, a work with
@NenckiInstitute. She is up at 6-8 pm (California time)
#glioma #histology #computationalpathology #pathology

4 months ago

We have a new vacancy for a PhD candidate in our group on the topic of federated learning using imaging and other medical data for diagnosis of dementia. #jobalert #PhD #MedicalImaging #ComputerScience #MachineLearning
RT @esther_bron
Vacancy alert: I am looking for a smart, independent and motivated PhD…

I am thrilled to announce that my lab is now officially part of the AIA research group of #UCLouvain that focuses on the algorithmic aspects of artificial intelligence. #MedicalImaging #HealthInformatics

🚨 Paper alert 🚨

Our paper "RegionWise loss for biomedical image segmentation" (w/ @twitter@jussi_tohka) was recently published in Pattern Recognition journal. Link.

Here, we introduce a new stable way to optimize CNNs to account for pixel importance. What does this mean?

#MedicalAI #MedicalImaging #NewPaper


Dave Mackey
4 months ago

current #SearchEngine results are frustratingly poor for "medical imaging", "learn medical imaging", "medical imaging for software engineers", etc.

They tend to focus on commercial companies, paid college degrees, and machine learning.

Yet another reason I'd like to build a better search engine. 🙂

BTW, if you happen to be working in #MedicalImaging with programs such as #VTK or #ITK, I'd love to follow you!

GNU Health
4 months ago

#GNUHealth Dx Imaging reporting in upcoming 4.2 . Very are also very happy to work along the #Orthanc community to deliver the best RIS solution 😎 #MedicalImaging #OpenScience #SocialMedicine #GNU #LibreSoftware

Image shows screenshot of a Medical Imaging study using GNU Health HMIS, along with the generated report.
The two images shown are frontal and lateral chest X-rays and the interpretation:
"Pulmonary aeration is significantly increased bilaterally. There is marked bronchial wall thickening on the right and left in the perihilar zone extending to the lung base in keeping with inflammatory lower airways disease. There are non-segmental patchy lung opacities in the lower lobes bilaterally (right lower lobe posterior basal segment; left lower lobe anterior basal segment; right middle lobe medial segment). There are also increased interstitial markings with lower zone predominance."

Case courtesy of Alborz Jahangiri,, rID: 45781

Fabulous first week in my new job at #ExeterUniversity which included a night away at an amazing research retreat; a really good opportunity to begin planning future collaborations for #research in #MedicalImaging #radiography

South Cloisters building at the university of Exeter
Jens Hannemann
5 months ago

@anton_hilado For me, that's without a doubt the Fourier-Slice Theorem:

It's the basis of medical CT, but more importantly, it's just so darn fundamental and - yes - beautiful, driving home the point that the spatial and spectral domain are completely equivalent representations of information.

#Math #Mathematics #Fourier #Engineering #MedicalImaging

Thomas Schultz
5 months ago

All presentations and keynotes of MICAD 2022 - including my own - are now publicly available via the following YouTube channel:
#machinelearning for #medicalimaging

Santam Chakraborty
5 months ago

Totalsegementator - not only iis the tool open source but also available for 3Dslicer as an extension. Example segmentation of thorax on coarse setting (without GPU and an old Athlon CPU), takes < 5 min.
3D Slicer:
#DeepLearning #TotalSegmentator #OpenSource #RadOnc #MedicalImaging #3DSlicer #Contouring

CT scan image of the thorax showing different organs drawn by an automatic segmentation - showing lung, heart, vertebrea, ribs, great vessels etc.
Brian Casey
5 months ago

In-person registration for #RSNA22 came in at close to 34,000 attendees, according to final registration numbers released by RSNA this week. The final numbers represent a bump up from the preliminary figure of 31,000 in-person registrations released on the first day of RSNA 2022. #radiology #medicalimaging

Andy King
5 months ago

P.S. I discovered this paper because it was mentioned by one of the speakers at the recent #FAIMI event on #fairness of #AI in #medicalimaging - so if you are interested in this research area let me remind you that all FAIMI talks are now available on YouTube:

Two workshops (#MachineLearning for #MedicalImaging and Weakly Supervised Learning) and two tutorials (AI4Code, and Optimization and Learning with Markovian Data) are currently underway.

Screenshot of the ACML virtual conference schedule, showing
Workshop: Machine Learning for Medical Imaging
Tutorial: AI4Code
Tutorial: Optimization and Learning with Markovian Data
Workshop: Weakly Supervised Learning

Also visible are some presenter names.

Stone Web viewer 2.5 is available! This release brings a number of UX improvements. An online demo of the new version is available on our official homepage: #DICOM #WebAssembly #MedicalImaging

I'm quite surprised to see so many papers fine-tuning ImageNet-pretrained models on medical data.

Aside from the major differences in the data, resizing images from, e.g., 2000x2000 to 224x224, to fit, say, a ResNet50, is a huge loss of information. And medical images are very similar within each dataset compared to ImageNet, i.e., their relevant information is likely to be on a few pixels.

#MedicalImaging #MedicalAI

Hi 👋

It's always a good time to explain what is medical image segmentation (MIS) and why it is so important (and cool). I will do this in plain English, and I will also highlight some active research areas. Keep reading if you want to learn more 👇

🧵 #MedicalAI #MedicalImaging

Mark Crowley
6 months ago

Just moved here from the m.s. so let's do an #introduction again.

I'm Mark Crowley (he/him).
I'm an Assoc Prof at the University of #Waterloo.
I'm from Toronto, but I've also lived in Vancouver, Oregon and Germany.

I have a #PhD in #ComputerScience in #ArtificialIntelligence.
My research includes #ReinforcementLearning #DimReduction and #DeepLearning
#AutonomousDriving #AI4Science #ForestWildfire #MedicalImaging

Also talk #startrek, #doctorwho, #science, #philosophy

Sweta Banerjee
6 months ago

Just a couple of hashtags to attract like minded people to hang out on #mastodon :
#deeplearning #MachineLearnning #medicalimaging #BioImageAnalysis #math #statistics .....
Folks, if you work with above topics ( and science in general), I'd love to follow you!

Karolina Wartolowska
6 months ago

Hello! I am a medical doctor turned scientist (Dr^2).

I use MRI in conjunction with other data to measure disease progression and response to treatment in #chronicpain, #stroke, #SVD, and #dementia.

Pet project: outcomes and control groups in #clinicaltrials to account for #placebo / #nocebo

I also run (mostly off-road), take #photos (sometimes while running), drink coffee (mostly asleep), and wine (mostly blinded).

Hashtag collection:

Luis Falcon
6 months ago

Great talk about 3D Slicer by Csaba Pinter at #GHCon2022 #Medicalimaging #LibreSoftware

Bringing maths into the equation to improve medical imaging

Hear from UL's Jason Curran about the importance of maths in improving MRI imaging and patient diagnoses:

#StudyatUL #Research #HigherEducationResearch #MedicalImaging #MedicalDevices #Medicine #Medical #HigherEducation #University #Ireland

A photograph of a man in a checkered white and green shirt. He is stood smiling at the camera, with large cliffs behind him.

@oseymour Hello! Great to meet you! So nice to start seeing some #medicalimaging folks in my network! #AI in medical imaging is an area of interest in the research group I’m joining soon and something I’m hoping to learn more about! Thanks for the link to the dataset, that looks really interesting!

After qualifying as a #radiographer I somehow ended up doing an MSc in #bioinformatics and a PhD looking at #microbial communities followed by a job as a bioinformatician in human #genetics. So, it's fair to say my radiography skills are... rusty! However, in Jan I will be moving to a new job focussing on #MedicalImaging research where I will be able to put my rusty radiography skills back into practice!

One of the things I now need to work on is regaining my HCPC registration as a radiographer, which obviously lapsed whilst I was off playing with microbes! To do this I need to complete a portfolio of a few hundred hours worth of study and practical experience. I'm lucky enough to have access to Exeter uni's library and their medical imaging course material but I am also going to be searching out lots of online resources which will hopefully help me refresh my memory of all things medical imaging! As I find them I will share useful resources on here and as I continue to connect with people who have similar interests I hope they might be useful for others too! 😃

To start with, radiopaedia, a great general radiology site with lots of articles and case studies:

Hello #ScienceMastadon #AcademicMastadon Just wondering if there is anyone else out there who is involved in medical imaging research? I am currently a bioinformatician using RNA-seq data to investigate cellular ageing, but I'm also a qualified diagnostic radiographer and will soon be starting a postdoc in medical imaging. I am especially interested in utilising my quite diverse experience to bring together genetics and imaging to improve medical diagnostics. Would love to connect with anyone who is interested in this area of research or who works in medical imaging in general! 😀 #bioinformatics #genetics #rna #radiography #medicalimaging #medicine

Samuel W. Remedios
7 months ago

Waiting for more of that #twittermigration to link up with more signal processors and #mri and other #medicalimaging folk!

Semi news bot of the Fedi
4 years ago

AI Medical Service raises $42.9 Series B for AI-based software that checks endoscopy scans for signs of cancer #AIMedicalService #Fundings&Exits #medicalimaging #medicaltech #endoscopy #Startups #Health #Japan #tokyo #TC #AI

johannab, cafe proprietor
5 years ago

“To help some of the newcomers make connections: name 5-7 things that interest you but aren't in your profile, as tags so they are searchable. Then boost this post or repeat its instructions so others know to do the same.”