We are excited to let you know that our lab is developing an educational website to help you learn how to apply deep learning methods to medical images.
An electronic textbook combined with actual code to learn about
#Deep_Learning
!
#MIDeL_Book
.
During the eclipse, our lab meeting turned into a stellar viewing party!
๐๐๐
The best way to shed light on our research is watching the sun hide!๐
๐ Congratulations,
@ShahriarFaghani
, on winning the title of the most valuable JDI reviewer! ๐ Your hard work, dedication, and expertise have earned you this honor. Well-deserved recognition for your outstanding contributions!
@SIIM_Tweets
@MayoRadiology
#SIIM23
We are the artificial intelligence (AI) lab at Mayo Clinic: a multidisciplinary lab dedicated to developing innovative machine learning tools for medical imaging analysis.
#Artificialintelligene
#Radiology
Our Thursday meeting this week also doubled as a farewell event for two exceptional summer interns โ Cooper Gamble (
@thecoopergamble
) and Ajay Misra (
@tamperable
).
Wishing you both a brilliant future ahead! Best of luck!
You have heard of
#DALLE2
, the model that creates realistic photos based on text prompts! This is an example of "denoising diffusion probabilistic models".
#DDPMs
Check out the video by
@PRouzrokh
&
@khosravi_bardia
to learn more about them and their applications in medicine!
If you are interested to learn how to apply
#DeepLearning
on
#Medicalimaging
FOR FREE, you can check out "Medical Image Deep Learning" (MIDeL) Massive open online course(MOOC)!
Before starting, check out Dr. Erickson's introduction to the
#MIDeLMOOC
!
โจ Want to know how synthetic data can be useful in healthcare research?
๐ Check our lab's recent paper, published
@JArthroplast
. In this work, we show how
#GenerativeAI
can help with increasing model robustness in source domain:
๐ Honored to receive the Best Research Paper Award at
#SIIM23
! ๐
Huge thanks to the amazing team, esp.
@PRouzrokh
who deserves equal recognition for his invaluable contributions. ๐
Grateful to
@Slowvak
&
@CodyWyles
for their exceptional support.
@SIIM_Tweets
โ Dr. Shahriar Faghani from
@MayoAILab
will deliver a digital presentation at
#RSNA2022
on โUncertainty Quantification in COVID-19 Detection Using Evidential Deep Learningโ.
๐ Join the discussion session tomorrow, 9:00 am at the learning center.
#UQ
@ShahriarFaghani
We hope you are all having a nice relaxing 4th of July (at least those of you in the US). It is important to take time to enjoy life and the people around you. Our lab recently had an evening of sand volleyball to help take a break.
#Radiology
#4thOfJuly
Missing MRI sequences is a common bottleneck in applying
#AI
models. A solution was provided by
@Giemmecci
by synthesizing the missing MRI sequences using
#GAN
. You can find more information in our paper published in
#Radiology
.
We are proud to announce that our lab provided a collection on bias in
#MachineLearning
studies in 3 parts; data handling, model development, and performance evaluation.
Please find the papers in the following link:
#AIbias
#Radiology
@Radiology_AI
For this new
@Radiology_AI
initiative, our lab director Dr. Brad Erickson
@Slowvak
introduces the concepts of probability, model calibration, and uncertainty quantification.
Here is the link to the video:
In our latest study, we found that the pancreas fat distribution is highly heterogeneous, which means that the typical clinical practice of just looking at fat in small spots could be flawed!
To learn more about this check out the paper:
#deeplearning
#AI
โ Dr. Shanli Vahdati from
@MayoAILab
will deliver a digital presentation at
#RSNA2022
on โA multi-view Deep Learning-based Architecture for Thyroid Nodules
Detection and Characterizationโ.
๐ Join the discussion session Today, 12:15 PM at the learning center.
@shanlivahdati
โ Dr. Bardia Khosravi from
@MayoAILab
will deliver a digital presentation at
#RSNA2022
on a deep learning based pipeline for post-arthroplasty risk prediction from pre-op radiographs.
๐ Join the discussion session Today, 9:00am at the learning center.
@khosravi_bardia
@ShahriarFaghani
will be presenting an intriguing study on Uncertainty Quantification in Radiology. Be sure to join him at Room 9, Level 3 4:15 to stay up-to-date with the latest advancements in science.
@SIIM
Tweets
#SIIM23
If you're attending
#SIIM23
, don't miss
@ShahriarFaghani
oral presentation on AI in Enterprise Research Abstracts Sessions. Join him at Room 9, Level 3 from 10:00 to 10:45 AM.
@SIIM_Tweets
Interested in applying diffusion models to generate a radiology time machine?๐
Then Join
@prouzrokh
in his poster presentation on Friday at 9:30 AM to see how a highly valid and realistic post-arthroplasty pelvis Xray could be generated from a patientโs preop Xray๐
#SIIM23
Delighted to share that this year, 3 of our team members(
@giemmecci
,
@ShahriarFaghani
,
@ManaMSF94
) will present their projects about
#Gliobalstoma
survival, MGMT, pseudoprogression, and
#MRI
missing sequences at 27th annual meeting of the society of neuro-oncology
#SNO
in Tampa!
โ Dr. Shahriar Faghani form
@MayoAILab
will deliver an oral presentation at
#RSNA2022
on โA deep learning model for detection of multiple myeloma lesions using whole body CT-scanโ.
๐Join his talk on Sunday, 9 AM at E451B.
@ShahriarFaghani
Thought-provoking conversations we had and lasted for 2 hours!
The new paper released by
@nvidia
team!
Mixing imaging with prompts! What will be the use in
#medicalimaging
?
Great presentation
@PRouzrokh
!
โ Dr. Mana Moassefi form
@MayoAILab
will deliver an oral presentation at
#RSNA2022
on โA Multi-modal Deep Learning Model for Discriminating True Progression from Pseudoprogression in Glioblastoma
Patients".
๐Join her talk on Monday, 1:30 PM at N226.
@ManaMSF94
Our team has developed a "Multitask Brain Tumor Inpainting tool with Diffusion Models"!
Just a lede to what is going to come out tomorrow!
It's gonna be legen..(wait for it)...dary!
#GenerativeAdversarialNetworks
#inpainting
#DDPMs
โ Dr. Pouria Rouzrokh form
@MayoAILab
and
@Mayo_OSAIL
will deliver an oral presentation at
#RSNA2022
on โApplying Deep Learning to Establish a Total Hip Arthroplasty Radiography Registry: A Stepwise Approachโ.
๐Join his talk on Sunday, 9 AM at E451B.
@PRouzrokh
โ Dr. Gian Marco Conte will deliver an oral presentation at
#RSNA2022
on โA Validation of Conditional and Super-Resolution Generative Adversarial Networks to Synthesize Brain MRI Sequences to Use for Volumetric Analysis of Brain Gliomasโ.
๐Tuesday, 3 PM at E353C.
@giemmecci
โจInterested in learning how to detect objects in medical imaging data using artificial intelligence?
โ Then feel free to attend Dr. Pouria Rouzrokh's two workshop sessions at RSNA2022 to learn about object detection models.
๐November 29 and 30, 10 - 11 AM, Learning Center
Join us at
#SIIM23
for
@khosravi_bardia
's presentation on anonymizing radiographs. Learn about why this is important (beyond patient privacy) and how we tackle this important challenge. Don't miss this opportunity!
โฐ June 14th, 4:15 PM CST
๐ข R9 / L3
@SIIM_Tweets
โจ Want to learn about generative adversarial networks (
#GAN
) and their application in
#radiology
research?
๐ฉ๐ปโ๐ป Don't miss this
@RSNA
deep learning lab by
@Slowvak
and
@khosravi_bardia
๐ Tuesday 11:30-12:30; "Deep Learning Lab" area
#RSNA22
This year, At
#SIIM22
our lab received several awards and honors:
Dr. Bradley Erickson
@Slowvak
received the "Gold Medal of The Society Award" which is the highest award of the society for his outstanding accomplishments and achievements!
Congratulations to our amazing mentor!
Great news!
Dr. Singh (
@yashbir143
), our team member, will be presenting at
@NYASciences
conference this year. His
#DL
model, predicting liver decompensation over time in patients with primary sclerosing cholangitis
#PSC
has shown promising results.
@Slowvak
@ShahriarFaghani
Want to challenge your deep learning understanding and how good you are at avoiding bias in AI?
Then join DL-GEM deep learning lab, where
@PRouzrokh
&
@khosravi_bardia
will invite you to a fun, challenging, and simulated educational game.
๐ June 16th
โฐ1 PM, Level 3, Room 6
To get some answers about clinical applications of
#AI
, you can check out this link to the expert panel discussion at the
@MayoClinic
Platform Conference:
Dr.
@ShahriarFaghani
won the "2022 Helen and Paul Chang Foundation New Investigator Travel Award" for presenting several impactful projects in the field of radiology and informatics!
Congratulations to our great team member
@ShahriarFaghani
!
Congrats to Dr.
@PRouzrokh
, Dr.
@khosravi_bardia
and other colleagues from our lab and
@Mayo_OSAIL
who have developed a
#DeepLearning
pipeline to organize over 800,000 radiographs. Feel free to read their work at the prestigious Journal of Bone and Joint Surgery,
@jbjs
.
Congratulations, Dr. Yashbir Singh, on your remarkable achievement of winning the prestigious travel award! Additionally, it is with great pleasure that we acknowledge your appointment as Assistant Professor of Radiology at
@MayoClinic
!
Excited to announce I received a travel grant from
@NYASciences
for the New Wave of AI in Healthcare Meeting 2023! Grateful for the opportunity to explore the latest advancements in AI and its impact on healthcare.
#AIinHealthcare
#NYAS
#Grateful
At the
#CMIMI22
event Dr. Erickson (
@Slowvak
) delivered a great talk about
#AI
; probability, calibration, certainty, and finally
#UncertaintyQuantification
, which are the topics that our lab is actively working on these days.
If curious watch minutes 1-15:
Check out Dr. Bradley Erickson's latest interview with
@RSNA
regarding our new publication on mitigating bias in data handling phase of
#MachineLearning
studies.
@Slowvak
With the increasing use of AI in radiology, it is critical to minimize bias within machine learning systems before implementing their use in real-world clinical scenarios.
#RadAI
Congratulationsย to Dr. Jaidip Jagtap, Ph.D., and Dr. Fred Nugen, Ph. D. of
@MayoClinic
Radiology Research, on being appointed as Assistant Professor of Radiology by Mayo Clinic's Academic Appointments and Promotions Committee.ย Wish you success in this new role!
#AcademicPromotion
A recent excellent publication by
@ShahriarFaghani
on applying
#deeplearning
for Barret's esophagus diagnosis!
The following link will take you to the full paper:
Generate MRI images with
#glioblastoma
(
#GBM
) tumors!
Remove the already existing tumors from the
#MRI
!
Watch this demo, to learn more about our team's newly-released app!
Thrilled and honored to have been selected as a Trainee Editorial Board member for
@Radiology_AI
#TEB
.
Looking forward to learning from experienced mentors of the field of radiology and Al over the next two years! Thank you
@judywawira
and
@cekahn
for this valuable opportunity.
Please watch this short video from
@pair_medicine
to learn about one of our recent publications at
@Radiology_AI
, first authored by Dr.
@khosravi_bardia
.
This study uses
#DeepLearning
to predict the risk of implant dislocation following total hip arthroplasty.
One of our team members,
@yashbir143
, had an excellent presentation in the "Novelties in Hepatobiliary Imaging" session at the recent European Congress of Radiology
#ECR2022
held by
@myESR
.
Congratulations and great work,
@yashbir143
!
Dr. Gian Marco Conte's paper (
@giemmecci
) received an honorable mention for the "Best Student Paper Award". His amazing work using
#radiomics
on
#glioblastomas
is fantastic and highly appreciated.
Congrats to our fantastic lab member,
@giemmecci
!
We applied denoising diffusion probabilistic models(
#DDPMs
) to develop a "Multitask
#BrainTumor
#Inpainting
Tool"
You can
#generate
necrotic, enhancing, and non-enhancing components and edema with the size that you choose!
Try it with the link below:
@ShahriarFaghani
presented his model at
#CMIMI22
for predicting GBM overall survival based on post-operative brain
#MRI
which showed secondary progression after the first tumor resection.
Interesting work!