MAELi -- Masked Autoencoder for Large-Scale LiDAR Point Clouds

Krispel, Georg; Schinagl, David; Christian, Fruhwirth-Reisinger,; Possegger, Horst; Bischof, Horst

doi:10.48550/arxiv.2212.07207

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This self-supervised training strategy does not depend on data-specific augmentations and is agnostic to the data modality. Starting from its success for natural language models such as BERT [7], it has made its way into vision [9,12,36], 3D data processing [14,16,38], and many other domains [4,10,13,21]. MAE also has been successfully employed in multimodal learning [4,5,11], yet, again they rely on different encoders for each data modality.…”

Section: Related Workmentioning

confidence: 99%

UMAP Based Anomaly Detection for Minimal Residual Disease Quantification within Acute Myeloid Leukemia

Weijler

Kowarsch

Wödlinger

et al. 2022

Cancers

View full text Add to dashboard Cite

Leukemia is the most frequent malignancy in children and adolescents, with acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) as the most common subtypes. Minimal residual disease (MRD) measured by flow cytometry (FCM) has proven to be a strong prognostic factor in ALL as well as in AML. Machine learning techniques have been emerging in the field of automated MRD quantification with the objective of superseding subjective and time-consuming manual analysis of FCM-MRD data. In contrast to ALL, where supervised multi-class classification methods have been successfully deployed for MRD detection, AML poses new challenges: AML is rarer (with fewer available training data) than ALL and much more heterogeneous in its immunophenotypic appearance, where one-class classification (anomaly detection) methods seem more suitable. In this work, a new semi-supervised approach based on the UMAP algorithm for MRD detection utilizing only labels of blast free FCM samples is presented. The method is tested on a newly gathered set of AML FCM samples and results are compared to state-of-the-art methods. We reach a median F1-score of 0.794, while providing a transparent classification pipeline with explainable results that facilitates inter-disciplinary work between medical and technical experts. This work shows that despite several issues yet to overcome, the merits of automated MRD quantification can be fully exploited also in AML.

show abstract