Citation: Seol, Y.J.; Park, S.H.; Kim,
Y.J.; Park, Y.-T.; Lee, H.Y.; Kim, K.G.
The Development of an Automatic
Rib Sequence Labeling System on
Axial Computed Tomography Images
with 3-Dimensional Region Growing.
Sensors 2022, 22, 4530. https://
doi.org/10.3390/s22124530
Academic Editors: Andrew W.H. Ip,
Kelvin K.L. Wong, Dhanjoo N. Ghista
and Wenjun (Chris) Zhang
Received: 10 May 2022
Accepted: 10 June 2022
Published: 15 June 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
The Development of an Automatic Rib Sequence Labeling
System on Axial Computed Tomography Images with
3-Dimensional Region Growing
Yu Jin Seol
1,†
, So Hyun Park
2,†
, Young Jae Kim
3
, Young-Taek Park
4
, Hee Young Lee
2,
*
and Kwang Gi Kim
3,5,
*
1
Department of Biomedical Engineering, Gachon University, 191, Hambangmoe-ro, Yeonsu-gu,
Incheon 21936, Korea; tjfwlgns0518@gmail.com
2
Departments of Radiology, Gil Medical Center, College of Medicine, Gachon University, Incheon 21936, Korea;
nnoleeter@gilhospital.com
3
Department of Biomedical Engineering, College of Medicine, Gachon University, 38-13 Docjeom-ro 3 Beon-gil,
Namdong-gu, Incheon 21565, Korea; youngjae@gachon.ac.kr
4
HIRA Research Institute, Health Insurance Review & Assessment Service (HIRA), Wonju-si 26465, Korea;
youngtaek.park@gmail.com
5
Department of Health Sciences and Technology, Gachon Advanced Institute for Health Sciences and
Technology (GAIHST), Gachon University, Seongnam-si 13120, Korea
* Correspondence: lhy0928@gilhospital.com (H.Y.L.); kimkg@gachon.ac.kr (K.G.K.)
† These authors contributed equally to this work.
Abstract:
This paper proposes a development of automatic rib sequence labeling systems on chest
computed tomography (CT) images with two suggested methods and three-dimensional (3D) region
growing. In clinical practice, radiologists usually define anatomical terms of location depending
on the rib’s number. Thus, with the manual process of labeling 12 pairs of ribs and counting their
sequence, it is necessary to refer to the annotations every time the radiologists read chest CT. However,
the process is tedious, repetitive, and time-consuming as the demand for chest CT-based medical
readings has increased. To handle the task efficiently, we proposed an automatic rib sequence labeling
system and implemented comparison analysis on two methods. With 50 collected chest CT images,
we implemented intensity-based image processing (IIP) and a convolutional neural network (CNN)
for rib segmentation on this system. Additionally, three-dimensional (3D) region growing was used
to classify each rib’s label and put in a sequence label. The IIP-based method reported a 92.0% and
the CNN-based method reported a 98.0% success rate, which is the rate of labeling appropriate rib
sequences over whole pairs (1st to 12th) for all slices. We hope for the applicability thereof in clinical
diagnostic environments by this method-efficient automatic rib sequence labeling system.
Keywords: artificial intelligence; image processing; three-dimensional region growing; ribs
1. Introduction
The burden on medical imaging-based diagnosis has been increased gradually with
the demand for radiologic scanning [
1
,
2
]. As the demands for computed tomography
(CT) imaging and reading have been increased, it is noted that research to reduce the
burden on the radiologists while they read and improve the diagnostic process using an
automatic system such as computer-aided diagnosis (CAD) [
3
,
4
]. The chest CT-based
medical is usually read to diagnose diseases occurring in abdominal and design thoracic
surgery, as it is fast and provides anatomical information about general tissues of the upper
body [
5
,
6
]. Accordingly, research on CAD with an automatic system to aid image reading
and diagnosis on chest CT slices has been conducted and published in several fields.
In clinical applications, radiologists check the image with their naked eyes repeatedly
and make a diagnosis decision to increase the reliability of the reading results. Additionally,
Sensors 2022, 22, 4530. https://doi.org/10.3390/s22124530 https://www.mdpi.com/journal/sensors
