Deep learning ResNet34 model-assisted diagnosis of sickle cell disease <i>via</i> microcolumn isoelectric focusing-Reference-Cited by-同舟云学术

Deep learning ResNet34 model-assisted diagnosis of sickle cell disease via microcolumn isoelectric focusing

Published:2024 Issue: Volume: Page:
ISSN:1759-9660
Container-title:Analytical Methods
language:en
Short-container-title:Anal. Methods

Author:

Sani Ali¹^ORCID,Tian Youli¹,Shah Saud¹,Khan Muhammad Idrees¹,Abdurrahman Hafiz Rabiu²,Zha Genhan¹,Zhang Qiang¹,Liu Weiwen¹,Abdullahi Ibrahim Lawal³,Wang Yuxin⁴,Cao Chengxi¹

Affiliation:

1. School of Sensing Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

2. Department of Hematology, Aminu Kano Teaching Hospital, Kano, 3462, Nigeria

3. Department of Biological Sciences, Faculty of Life Sciences, Bayero University, Kano, 3011, Nigeria

4. School of Physics and Astronomy, Shanghai Jiao Tong University, Shanghai, 200240, China

Abstract

The study proposes a ResNet34 DL model for automated SCD diagnosis using mIEF for Hb S, achieving 90.1% accuracy in classifying Hb variants. The model's precision suggests it could reduce costs and the reliance on the need for expert diagnosis.

Funder

National Natural Science Foundation of China

Publisher

Royal Society of Chemistry (RSC)

Link

http://pubs.rsc.org/en/content/articlepdf/2024/AY/D4AY01005A

Reference77 articles.

1. Global epidemiology of haemoglobin disorders and derived service indicators

2. Sickle Cell Disease in Africa

3. Sickle Hemoglobin (Hb S) Allele and Sickle Cell Disease: A HuGE Review

4. Physiology of haemoglobin

5. HemoTypeSC point-of-care testing shows high sensitivity with alkaline cellulose acetate hemoglobin electrophoresis for screening hemoglobin SS and SC genotypes