Applying 3D U-Net Architecture to the Task of Multi-Organ Segmentation in Computed Tomography
Applied Computer Systems, Vol. 25, No. 1, pp. 43-50
Editorial summary
A modified 3D U-Net segments several abdominal organs directly from CT volumes. Training and testing use a manually assembled scan dataset, with Dice overlap measuring agreement with reference segmentations. The study compares volumetric processing with published multi-organ segmentation results.
Bibliographic reference
Use the publisher’s record for the citation format required by your journal or organisation.
Pavlo Radiuk. "Applying 3D U-Net Architecture to the Task of Multi-Organ Segmentation in Computed Tomography". Applied Computer Systems, Vol. 25, No. 1, pp. 43-50, 2020. https://doi.org/10.2478/acss-2020-0005
Test a method against your business task.
Describe the decision your system needs to support and the data you have. We assess whether a method fits, define a prototype and agree how to measure its quality, response time and operating cost.