2022 JHU Radiology Research Day

By |2022-12-02T20:21:00-05:00November 9th, 2022|

The JHU Radiology Research Day was this past Tuesday (November 8).  It is a place to showcase the research in the Department of Radiology and Radiological Science at JHU.  This year the RAIL lab had 9 posters and Dr Craig Jones was invited to present on AI Applications in Radiology. A huge congratulations on the [...]

New AI Research Grant

By |2022-12-02T20:25:28-05:00November 1st, 2022|

Today we learned of the awarding of a new $310,000 grant from the Department of Defense to Dr Craig Jones and Dr Cliff Weiss to study AI/machine learning-guided treatments for venous malformations.  This includes the design of a neural network segmentation algorithm and texture metric quantification of venous malformations in MRI images.

International Symposium on Visual Computing Presentations

By |2022-12-02T20:29:46-05:00October 20th, 2022|

Sejal Ghate, a past RAIL lab member presented work at the 17th International Symposium on Visual Computing (ISVC'22). This is in collaboration with the Health AI group at Microsoft. The paper was titled: "“Deep Labeling of fMRI Brain Networks Using Cloud Based Processing” Many congratulations to the team: Craig K. Jones, Assistant Research Professor, Computer [...]

Sequential Learning in Azure ML Collaboration with Microsoft

By |2022-07-26T08:15:34-04:00July 26th, 2022|

Dr Craig Jones, Assistant Research Professor in Computer Science (Co-Directory of the Radiology AI Lab) along with Dr Haris Sair (Directory of Neuroradiology) have an exciting new collaboration with Health AI, Microsoft.  Dr Jones along with a graduate student will be implementing a Sequential Learning algorithm for training de-identified medical image data uploaded to Microsoft [...]

Quantifying Uncertainty in Neural Network Segmentation

By |2022-07-26T08:36:27-04:00June 8th, 2022|

Dr Jones and Sair, along with Collaborators in the School of Public Health and the Division of Neuroradiology have designed a method to quantify two types of uncertainty, aleatoric and epistemic, directly from a neural network segmentation algorithm.  Details can be found here: Direct quantification of epistemic and aleatoric uncertainty in 3D U-net segmentation https://doi.org/10.1117/1.JMI.9.3.034002

Go to Top