Dice vs Dice Loss
The dice loss in a special case of the dice coefficient but physically they are the same. Read this arrticle for more details
August 5, 2026
Guides, project breakdowns, and lessons learned from building medical imaging platforms — written by the PYCAD team.
The dice loss in a special case of the dice coefficient but physically they are the same. Read this arrticle for more details
RADAR is a new multimodal benchmark testing whether AI can review and improve draft radiology reports against 3D imaging studies — and why it matters for medical imaging product teams.
A session-based radiology reporting workflow: read naturally in the viewer, narrate findings, and turn the review into a structured draft report.
Merlin shows how CT-native vision-language foundation models could shape radiology AI, with released code, model weights, and dataset access for researchers.
PadChest-GR brings grounded, bilingual evaluation to chest X-ray report generation. Learn why this benchmark matters for trustworthy radiology AI and medical imaging workflows.
ABRA introduces a more realistic way to evaluate radiology AI by testing how models function inside real DICOM workflows with OHIF, Orthanc, and structured reporting tools.
We build custom medical imaging platforms — advanced DICOM viewers, AI segmentation, and the clinical systems around them.
Copyright © 2026 PYCAD. All Rights Reserved.