Advanced Algorithms for Treatment Management Applications (AATMA)
Elekta Solutions ABAdvanced Algorithms for Treatment Management Applications (AATMA) is a software library that uses machine-learning convolutional neural networks to automatically segment medical images. It provides derived data sets for use in radiation therapy treatment planning, accessible via an API and intended to help clinicians efficiently generate and review treatment contours from imaging data.
Intended Use
AATMA™ is a medical image processing library intended to produce derived data sets for use as input into radiation therapy treatment planning systems or other intermediate pre-treatment-planning applications.
Technology
The device uses machine-learning convolutional neural networks (auto-segmentation algorithms) with pre-trained models on specific datasets, functioning as a computational engine accessed via API, producing derived datasets in standard formats like DICOM without a user interface.
Performance
Performance testing included software verification, validation, and algorithmic testing on Head & Neck and Male Pelvis models trained on large clinical CT datasets. Testing showed average DICE coefficients of 0.84 and 0.93 respectively, meeting acceptance criteria. No clinical or animal testing was performed; performance was compared to a predicate device showing substantial equivalence.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
7/16/2021
3 months - 2
FDA Approval
10/25/2021
Ready to Sharpen Your Edge?
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.