%0 Journal Article
%9 ACL : Articles dans des revues avec comité de lecture répertoriées par l'AERES
%A Darrin, M.
%A Samudre, A.
%A Sahun, M.
%A Atwell, S.
%A Badens, C.
%A Charrier, A.
%A Helfer, E.
%A Viallat, A.
%A Cohen-Addad, V.
%A Giffard-Roisin, Sophie
%T Classification of red cell dynamics with convolutional and recurrent neural networks : a sickle cell disease case study
%D 2023
%L fdi:010087700
%G ENG
%J Scientific Reports - Nature
%@ 2045-2322
%M ISI:000968670400019
%N 1
%P [12 ]
%R 10.1038/s41598-023-27718-w
%U https://www.documentation.ird.fr/hor/fdi:010087700
%> https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2023-06/010087700.pdf
%V 13
%W Horizon (IRD)
%X The fraction of red blood cells adopting a specific motion under low shear flow is a promising inexpensive marker for monitoring the clinical status of patients with sickle cell disease. Its high-throughput measurement relies on the video analysis of thousands of cell motions for each blood sample to eliminate a large majority of unreliable samples (out of focus or overlapping cells) and discriminate between tank-treading and flipping motion, characterizing highly and poorly deformable cells respectively. Moreover, these videos are of different durations (from 6 to more than 100 frames). We present a two-stage end-to-end machine learning pipeline able to automatically classify cell motions in videos with a high class imbalance. By extending, comparing, and combining two state-of-the-art methods, a convolutional neural network (CNN) model and a recurrent CNN, we are able to automatically discard 97% of the unreliable cell sequences (first stage) and classify highly and poorly deformable red cell sequences with 97% accuracy and an F1-score of 0.94 (second stage). Dataset and codes are publicly released for the community.
%$ 050 ; 020