"Software engineers building applications using machine learning need to test models in real-world scenarios before choosing which model performs best. Benchmarks are good preliminary measures but don’t reflect the complexities of real-world scenarios." https://t.co/nSk6shluqP

(Watch the Sharks on @TheASNR Education Connect, coming soon to https://t.co/yruLdUkcu4, and live in San Diego May2025.... 😎 ) @AliTejaniMD @ShahriarFaghani @radiology_ninja @dsmeets https://t.co/n9RT6zHBA8 #neuroradiology #AI #medicaleducation

Using whole body CT scan and #DeepLearning for classifying the stage and #survival of #multiplemyeloma! Today at 10:30, Room 306 #ARRS24! @ARRS_Radiology Especial thanks to my great colleagues and mentors, @ShahriarFaghani @frbaffour, and @Slowvak!

Efficient Health Care: Decreasing MRI Scan Time https://t.co/E7PxjO599B @MayoClinic @ronnie_sebro @MayoRadiology #DeepLearning #MachineLearning #AI

In our recent publication, we explored how adding heterogeneity in the training set helps #glioblastoma tumor #segmentation generalization! https://t.co/4q7PFxbBY7 Thanks to @ShahriarFaghani and @giemmecci and special thanks to my amazing mentor @Slowvak!

Our 1st Yr Residents had a great time attending the @acr annual meeting in Washington, DC. A special thank you to @MNRadSoc for sponsoring! #mayo #acr #radres @MayoRadiology @MayoMN_IRadRes

Enjoyed today's @MayoMrfa poster presentation very much! Ckecked out other great projects happening at @MayoClinic! Mixing #Al with #endometriosis research is something I am truly passionate about!🤩 Special thanks, @Slowvak and @WendalineVB for your great support! @MayoAILab

Commentary on a study testing the robustness of #DeepLearning model to estimate bone age https://t.co/hySvau3wLq @ShahriarFaghani @MayoAILab @Slowvak #MSKRad #PedsRad #MachineLearning

Interested in how to reliably use large language models (#LLMs) & mitigate their hallucinations? Then join @Slowvak, @ShahriarFaghani, & me as we introduce #CONFLARE, our recently proposed technique for measuring the uncertainty of content retrieval with LLMs. #trustworthiness