Citation: Gabbar, H.A.; Chahid, A.;
Khan, M.J.A; Adegboro, O.G.;
Samson, M.I. CTIMS: Automated
Defect Detection Framework Using
Computed Tomography. Appl. Sci.
2022, 12, 2175. https://doi.org/
10.3390/app12042175
Academic Editor: Francesco Bianconi
Received: 16 December 2021
Accepted: 14 February 2022
Published: 19 February 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
CTIMS: Automated Defect Detection Framework Using
Computed Tomography
Hossam A. Gabbar
1,2,
* , Abderrazak Chahid
1
, Md. Jamiul Alam Khan
2
, Oluwabukola Grace Adegboro
2
and Matthew Immanuel Samson
3
1
Faculty of Energy Systems and Nuclear Science, Ontario Tech University (UOIT),
Oshawa, ON L1G 0C5, Canada; abderrazak.chahid@ontariotechu.net
2
Faculty of Engineering and Applied Science, Ontario Tech University (UOIT), Oshawa, ON L1G 0C5, Canada;
mdjamiul.khan@ontariotechu.net (M.J.A.K.); oluwabukola.adegboro@ontariotechu.net (O.G.A.)
3
New Vision Systems Canada Inc. (NVS), Scarborough, ON M1S 3L1, Canada; sunnyssj8@gmail.com
* Correspondence: hossam.gaber@ontariotechu.ca
Abstract:
Non-Destructive Testing (NDT) is one of the inspection techniques used in industrial tool
inspection for quality and safety control. It is performed mainly using X-ray Computed Tomogra-
phy (CT) to scan the internal structure of the tools and detect the potential defects. In this paper,
we propose a new toolbox called the CT-Based Integrity Monitoring System (CTIMS-Toolbox) for
automated inspection of CT images and volumes. It contains three main modules: first, the database
management module, which handles the database and reads/writes queries to retrieve or save the
CT data; second, the pre-processing module for registration and background subtraction; third,
the defect inspection module to detect all the potential defects (missing parts, damaged screws,
etc.) based on a hybrid system composed of computer vision and deep learning techniques. This
paper explores the different features of the CTIMS-Toolbox, exposes the performance of its modules,
compares its features to some existing CT inspection toolboxes, and provides some examples of the
obtained results.
Keywords:
computerized tomography (CT); defect inspection; computer vision; image processing;
deep learning; toolbox; image classification
1. Introduction
Electrical energy is one of the major pillars of the global economy. It can be gen-
erated using different resources such as fossil fuels (coal, natural gas, and petroleum),
nuclear energy, and renewable energy sources. For instance, in Canada, the shares of the
different power resources are split as follows: hydro at 60%, nuclear at 15%, coal at 7%,
gas/oil/others at 11%, and non-hydro renewables at 7% [
1
]. As Canada is the world’s
second largest producer of uranium [
2
] and due to the significant share of nuclear power
in the national production, more support is focused on the design as next-generation
nuclear energy systems improve its efficiency, such as the CANDU reactor [
3
]. How-
ever, nuclear-based energy is costly due to the high operation cost and extended reactor
shutdown durations. These outages are usually caused by periodic maintenance, fault
conditions, etc. For instance, the nuclear vault has to stay shut down till all entered objects
are manually checked and identified as complete. Therefore, it is important to reduce
the maintenance-related outage cost (USD 35 per second USD 3
M
per outage) by ac-
celerating the tools’ inspection. Different Non-Destructive Testing (NDT) methods have
been proposed in the literature to perform tool inspection based on different scanning
technologies [4,5]
: thermography imaging, radiography techniques, ultrasonic probes, etc.
Computerized Tomography (CT) imaging is one of the emerging NDT technologies that has
been used in different applications: quality control [
6
,
7
], quantitative material analysis [
8
,
9
],
medicine [10,11]
, and
geosciences [12]
. One of the main challenges in CT-based inspection
Appl. Sci. 2022, 12, 2175. https://doi.org/10.3390/app12042175 https://www.mdpi.com/journal/applsci
