Dataset Information

A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics.

ABSTRACT: The application of machine learning approaches to imaging flow cytometry (IFC) data has the potential to transform the diagnosis of hematological diseases. However, the need for manually labeled single-cell images for machine learning model training has severely limited its clinical application. To address this, we present iCellCnn, a weakly supervised deep learning approach for label-free IFC-based blood diagnostics. We demonstrate the capability of iCellCnn to achieve diagnosis of Sézary syndrome (SS) from patient samples on the basis of bright-field IFC images of T cells obtained after fluorescence-activated cell sorting of human peripheral blood mononuclear cell specimens. With a sample size of four healthy donors and five SS patients, iCellCnn achieved a 100% classification accuracy. As iCellCnn is not restricted to the diagnosis of SS, we expect such weakly supervised approaches to tap the diagnostic potential of IFC by providing automatic data-driven diagnosis of diseases with so-far unknown morphological manifestations.

SUBMITTER: Otesteanu CF

PROVIDER: S-EPMC9017143 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics.

Otesteanu Corin F CF Ugrinic Martina M Holzner Gregor G Chang Yun-Tsan YT Fassnacht Christina C Guenova Emmanuella E Stavrakis Stavros S deMello Andrew A Claassen Manfred M

Cell reports methods 20211025 6

The application of machine learning approaches to imaging flow cytometry (IFC) data has the potential to transform the diagnosis of hematological diseases. However, the need for manually labeled single-cell images for machine learning model training has severely limited its clinical application. To address this, we present iCellCnn, a weakly supervised deep learning approach for label-free IFC-based blood diagnostics. We demonstrate the capability of iCellCnn to achieve diagnosis of Sézary syndr ...[more]

PMID: 35474892

Similar Datasets

Project description:Impedance flow cytometry (IFC) is a versatile lab-on-chip technology which enables fast and label-free analysis of pollen grains in various plant species, promising new research possibilities in agriculture and plant breeding. Hazelnut is a monoecious, anemophilous species, exhibiting sporophytic self-incompatibility. Its pollen is dispersed by wind in midwinter when temperatures are still low and relative humidity is usually high. Previous research found that hazelnut can be characterized by high degrees of pollen sterility following a reciprocal chromosome translocation occurring in some cultivated genotypes. In this study, IFC was used for the first time to characterize hazelnut pollen biology. IFC was validated via dye exclusion in microscopy and employed to (i) follow pollen hydration over time to define the best pre-hydration treatment for pollen viability evaluation; (ii) test hazelnut pollen viability and sterility on 33 cultivars grown in a collection field located in central Italy, and two wild hazelnuts. The accessions were also characterized by their amount and distribution of catkins in the tree canopy. Pollen sterility rate greatly varied among hazelnut accessions, with one main group of highly sterile cultivars and a second group, comprising wild genotypes and the remaining cultivars, producing good quality pollen. The results support the hypothesis of recurring reciprocal translocation events in Corylus avellana cultivars, leading to the observed gametic semi-sterility. The measured hazelnut pollen viability was also strongly influenced by pollen hydration (R adj2 = 0.83, P ≤ 0.0001) and reached its maximum at around 6 h of pre-hydration in humid chambers. Viable and dead pollen were best discriminated at around the same time of pollen pre-hydration, suggesting that high humidity levels are required for hazelnut pollen to maintain its functionality. Altogether, our results detail the value of impedance flow cytometry for high throughput phenotyping of hazelnut pollen. Further research is required to clarify the causes of pollen sterility in hazelnut, to confirm the role of reciprocal chromosome translocations and to investigate its effects on plant productivity.

Dataset Information

A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics.

Publications

A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets