Kvasir-Instruments and Polyp Segmentation Using UNet
DOI:
https://doi.org/10.5617/nmi.9130Emneord (Nøkkelord):
UNet, segmentation, deep learning, polyp, instrumentationSammendrag
This paper aims to describe the methodology used to develop, fine-tune and analyze a UNet model for creating masks for two datasets: Polyp Segmentation and Instrument Segmentation, which are part of MedAI challenge. For training and validation, we have used same methodology on both tasks and finally on
the hidden testing dataset the model resulted with accuracy of 0.9721, dice score of 0.7980 for the instrumentation task, and the accuracy of 0.5646 and a dice score of 0.4100 was achieved for the Polyp Segmentation.
Nedlastinger
Publisert
2021-11-01 — Oppdatert 2021-12-09
Versjoner
- 2021-12-09 (2)
- 2021-11-01 (1)
Utgave
Seksjon
NMI Challenge
Lisens
Opphavsrett 2021 Nordic Machine Intelligence
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
Dette verket er lisensiert under Creative Commons Attribution 4.0 International License.