1/1

Digitized Thin Blood Films for Sickle Cell Disease Detection

dataset
posted on 01.07.2020 by Petru Manescu, Bendkowski Christopher, Remy Claveau, Muna Elmi, Vijay Pawar, Biobele J Brown, Mike Shaw, Delmiro Fernandez-Reyes
If you plan on using this dataset, please cite : P. Manescu, C. Bendkowski, R. Claveau, M. Elmi, B.J. Brown, V. Pawar, M. Shaw and D. Fernandez-Reyes, A weakly supervised deep learning approach for detecting malaria and sickle cells in blood films , MICCAI (2020).

Image acquistion
Images were captured with custom built brightfield microscope fitted with a 100X/1.4NA objective lens, a motorized x-y sample positioning stage and a color camera.
z-stacks were projected onto a single (xy) plane using a wavelet-based Extended Depth of Field (EDoF) algorithm.

Clinical diagnosis
Hemoglobin electrophoresis was used to obtain the haemoglobin phenotype and test patients for Sickle Cell Disease (SCD). sickle_slides_new_march.txt contains the corresponding labels.

Ethical Statement.
The internationally recognized ethics committee at the Institute for Advanced Medical Research and Training (IAMRAT) of the College of Medicine, University of Ibadan (COMUI) approved this research with permit numbers: UI/EC/10/0130, UI/EC/19/0110. Parents and/or guardians of study participants gave informed written consent in accordance with the World Medical Association ethical principles for research involving human subjects.


Funding

This work was supported by the College of Medicine of the University of Ibadan, Ibadan, Nigeria; the UK Medical Research Council (MC_U117585869); Department of Computer Science, Faculty of Engineering Sciences of University College London, United Kingdom and UK Engineering and Physical Sciences Research Council (EP/P028608/1).

History

Exports