How researchers are using Datamint right now.
A look at real medical imaging AI projects using Datamint to improve workflow, collaboration, and reproducibility — before results are finalized.
Our active research projects.
Across universities, hospitals, and research labs
Fabiana Almeida is an oral maxillofacial radiologist and clinical researcher passionate about diagnosis. She is deeply committed to improving children’s arthritis diagnosis and to reducing the pain and long-term facial changes caused by undiagnosed TMJ (Temporomandibular Joint) arthritis. Identifying arthritis in the TMJ through imaging is difficult, requiring specialized training for radiologists or rheumatologists.
“AI can help health professionals to identify TMJ issues, improving the diagnosis process and potentially avoiding life-changing problems for children. Datamint has been instrumental in streamlining data and annotation workflows, which will let me get to solid results faster”.
%20(1).jpg)
What these research teams have in common.
-
Complex, evolving datasets
-
Multi-role collaboration
-
High expectations for reproducibility
-
Long-term research continuity
.png)
Why we’re sharing these projects early.
Because progress matters as much as outcomes.
-
Medical AI research is iterative and non-linear
-
Most value comes from workflow structure and continuity
-
These stories highlight progress and process—not final publications (yet)
How Datamint supports active research.
A flexible, non-linear workflow designed for real-world medical imaging research.
Data Intake
Annotation & Review
Model Training
Evaluation & Insight
Publication & Continuity
Refinement
Retraining
Bring structure to your research workflows.
No sales pressure — just a walkthrough of how Datamint supports real research workflows.