Segmentation of multiple myeloma plasma cells in microscopy images with noisy labels
In person: 22 February 2022 • 11:50 AM - 12:10 PM PST
A key component towards an improved cancer diagnosis is the development of computer-assisted tools. In this article, we present the solution that won the SegPC-2021 competition for the segmentation of multiple myeloma plasma cells in microscopy images. The labels in the competition dataset were generated semi-automatically and presented noise. To deal with it, new labels were generated from existing ones, heavy image augmentation was carried out and predictions were combined by a custom ensemble strategy. These techniques, along with state-of-the-art feature extractors and instance segmentation architectures, resulted in a mean Intersection-over-Union of 0.9389 on the SegPC-2021 final test set.
Álvaro García Faura
XLAB d.o.o. (Slovenia)
Mr. Álvaro García Faura received his M. Sc. degree in Telecommunication Engineering from the Escuela Técnica Superior de Ingenieros de Telecomunicación at Universidad Politécnica de Madrid in 2018. He started collaborating with the Speech Technology Group, from the Electronic Engineering Department (UPM) in 2015, where he mainly researched on computational models for image and video aesthetic assessment as part of the project ESITUR, founded by the Spanish Ministry of Economy and Competitiveness. He joined XLAB in March, 2020, where he is working as a Data Scientist.