PuSH - Publikationsserver des Helmholtz Zentrums München

Sadafi, A. ; Makhro, A.* ; Livshits, L.* ; Navab, N.* ; Bogdanova, A.* ; Albarqouni, S. ; Marr, C.

Sickle cell disease severity prediction from percoll gradient images using graph convolutional networks.

In: (3rd MICCAI Workshop on Domain Adaptation and Representation Transfer, DART 2021, 27 September-01 October 2021, Virtual, Online). Berlin [u.a.]: Springer, 2021. 216-225 (Lect. Notes Comput. Sc. ; 12968 LNCS)
Sickle cell disease (SCD) is a severe genetic hemoglobin disorder that results in premature destruction of red blood cells. Assessment of the severity of the disease is a challenging task in clinical routine, since the causes of broad variance in SCD manifestation despite the common genetic cause remain unclear. Identification of biomarkers that would predict the severity grade is of importance for prognosis and assessment of responsiveness of patients to therapy. Detection of the changes in red blood cell (RBC) density by means of separation of Percoll density gradients could be such a marker as it allows to resolve intercellular differences and follow the most damaged dense cells prone to destruction and vasoocclusion. Quantification and interpretation of the images obtained from the distribution of RBCs in Percoll gradients is an important prerequisite for establishment of this approach. Here, we propose a novel approach combining a graph convolutional network, a convolutional neural network, fast Fourier transform, and recursive feature elimination to predict the severity of SCD directly from a Percoll image. Two important but expensive laboratory blood test parameters are used for training the graph convolutional network. To make the model independent from such tests during prediction, these two parameters are estimated by a neural network from the Percoll image directly. On a cohort of 216 subjects, we achieve a prediction performance that is only slightly below an approach where the groundtruth laboratory measurements are used. Our proposed method is the first computational approach for the difficult task of SCD severity prediction. The two-step approach relies solely on inexpensive and simple blood analysis tools and can have a significant impact on the patients’ survival in low resource regions where access to medical instruments and doctors is limited.
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Graph Convolutional Networks ; Percoll Gradients ; Severity Prediction ; Sickle Cell Disease
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel 3rd MICCAI Workshop on Domain Adaptation and Representation Transfer, DART 2021
Konferzenzdatum 27 September-01 October 2021
Konferenzort Virtual, Online
Quellenangaben Band: 12968 LNCS, Heft: , Seiten: 216-225 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]