Citation: Baghdadi, N.; Maklad, A.S.;
Malki, A.; Deif, M.A. Reliable
Sarcoidosis Detection Using Chest
X-rays with EfficientNets and
Stain-Normalization Techniques.
Sensors 2022, 22, 3846. https://
doi.org/10.3390/s22103846
Academic Editor: Christophoros
Nikou
Received: 13 April 2022
Accepted: 17 May 2022
Published: 19 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Reliable Sarcoidosis Detection Using Chest X-rays
with EfficientNets and Stain-Normalization Techniques
Nadiah Baghdadi
1
, Ahmed S. Maklad
2,3,
* , Amer Malki
2
and Mohanad A. Deif
4
1
Nursing Management and Education Department, College of Nursing, Princess Nourah Bint
Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia; nabaghdadi@pnu.edu.sa
2
Computer Science Department, College of Computer Science and Engineering in Yanbu, Taibah University,
Medina 42353, Saudi Arabia; asamalki@taibahu.edu.sa
3
Information Systems Department, Faculty of Computers and Artificial Intelligence, Beni-Suef University,
Beni-Suif 62521, Egypt
4
Department of Bioelectronics, Modern University of Technology and Information (MTI University),
Cairo 12055, Egypt; mohand.deif@eng.mti.edu.eg
* Correspondence: amaklad@taibahu.edu.sa; Tel.: +966-56121-6639
Abstract:
Sarcoidosis is frequently misdiagnosed as tuberculosis (TB) and consequently mistreated
due to inherent limitations in radiological presentations. Clinically, to distinguish sarcoidosis from
TB, physicians usually employ biopsy tissue diagnosis and blood tests; this approach is painful
for patients, time-consuming, expensive, and relies on techniques prone to human error. This
study proposes a computer-aided diagnosis method to address these issues. This method examines
seven EfficientNet designs that were fine-tuned and compared for their abilities to categorize X-
ray images into three categories: normal, TB-infected, and sarcoidosis-infected. Furthermore, the
effects of stain normalization on performance were investigated using Reinhard’s and Macenko’s
conventional stain normalization procedures. This procedure aids in improving diagnostic efficiency
and accuracy while cutting diagnostic costs. A database of 231 sarcoidosis-infected, 563 TB-infected,
and 1010 normal chest X-ray images was created using public databases and information from
several national hospitals. The EfficientNet-B4 model attained accuracy, sensitivity, and precision
rates of 98.56%, 98.36%, and 98.67%, respectively, when the training X-ray images were normalized
by the Reinhard stain approach, and 97.21%, 96.9%, and 97.11%, respectively, when normalized
by Macenko’s approach. Results demonstrate that Reinhard stain normalization can improve the
performance of EfficientNet -B4 X-ray image classification. The proposed framework for identifying
pulmonary sarcoidosis may prove valuable in clinical use.
Keywords:
pulmonary sarcoidosis; sarcoidosis detection; tuberculosis; chest X-rays; EfficientNets;
stain normalization
1. Introduction
Tuberculosis (TB) is an infectious disease and one of the top 10 causes of death world-
wide [
1
,
2
]. Despite major advances in tuberculosis control methods, such as improved
vaccines and novel treatments, there are still difficulties in the development of quick and
accurate TB testing procedures [
3
]. Multidrug-resistant tuberculosis (MDR TB) has emerged
as the most difficult disease to treat, and it is spreading fast, demonstrating the pathogen’s
adaptability [
4
]. Around 23% of the world’s population has latent tuberculosis [
4
,
5
]. In the
developing world, tuberculosis is still a major, life-threatening disease, particularly in
countries with high population density and poor sanitation. Tuberculosis elimination has
become a major public health concern, and the urgency of the effort has been compounded
by the advent of new tuberculosis bacillus strains that are resistant to standard medicines [
6
].
Extrapulmonary tuberculosis (EPTB) occurs when tuberculosis spreads outside of the lungs.
Tuberculosis of the lungs (PTB) and EPTB may coexist. Asymptomatic people account for
15 to 20% of the population [7].
Sensors 2022, 22, 3846. https://doi.org/10.3390/s22103846 https://www.mdpi.com/journal/sensors
