CLINICAL GROUP

ISSN: 2455-8702 DOI: https://dx.doi.org/10.17352/ijcms

Received: 30 October, 2023

Research Article Accepted: 13 November, 2023
Published: 14 November, 2023

Image processing techniques *Corresponding author: Barmak Honarvar Shakibaei

Asli, Centre for Life-Cycle Engineering and Manage-
ment, School of Aerospace, Transport and Manufactur-

for the detection of brain ing, Cranfield University, Cranfield, Bedfordshire MK43
0AL, UK, Tel: +44-0-1234-754599;
E-mail: [email protected]

tumours ORCID: https://orcid.org/0000-0003-1519-9596

Keywords: Brain Tumour; Deblurring; Denoising;

Barmak Honarvar Shakibaei Asli* and Anaëlle Jasmin Classification; Detection

Copyright License: © 2023 Shakibaei Asli BH, et al.

Centre for Life-Cycle Engineering and Management, School of Aerospace, Transport and
This is an open-access article distributed under the
Manufacturing, Cranfield University, Cranfield, Bedfordshire MK43 0AL, UK terms of the Creative Commons Attribution License,
which permits unrestricted use, distribution, and
reproduction in any medium, provided the original
author and source are credited.

https://www.peertechzpublications.org

Abstract
Introduction: This paper is centered around advancing brain image analysis through the introduction and evaluation of advanced methods.

Methods: With the overarching goal of enhancing both image quality and disease classification accuracy, the paper sets out to address crucial aspects of modern
medical imaging. The research's trajectory begins by laying a strong foundation through an in-depth exploration of the principles governing Magnetic Resonance Imaging
(MRI) and Computed Tomography (CT). This understanding serves as a springboard for the subsequent phases, wherein image quality improvement takes center stage.

Results: By employing cutting-edge image processing techniques, the research aims to reduce noise and enhance image clarity, thereby setting the stage for more
reliable and precise analysis. The second phase involves segmentation, a pivotal step in brain image analysis. Various segmentation methods will be assessed to determine
their efficacy in accurately identifying distinct brain structures. Finally, the paper delves into the realm of deep learning, particularly leveraging CNN, to classify brain images
based on disease types. This sophisticated approach holds promise for refining disease identification accuracy by identifying nuanced patterns within the images.

Conclusion: Overall, the research aspires to modernize and elevate the field of brain image analysis, ultimately contributing to improved medical diagnostics and
insights.

Abbreviations 11,400 people diagnosed with a primary brain tumoureach year

in the UK. This highlights the urgent need for advanced medical
MRI: Magnetic Resonance Imaging; IQA: Image Quality imaging techniques to improve the accuracy of diagnosis,
Assessment; CNN: Convolutional Neural Network; SSIM: prognosis, and treatment of brain tumours [1]. Magnetic
Structural Similarity Index; PSNR: Peak Signal-to-Noise Ratio; Resonance Imaging (MRI) and Computed Tomography (CT)
BRISQUE: Blind/Referenceless Image Spatial Quality Evaluator; scans are among the most commonly used medical imaging
PIQE: Perception-based Image Quality Evaluator; NIQE: modalities for brain tumourdetection and diagnosis in the UK.
Naturalness Image Quality Evaluator However, the images produced by these modalities are often
complex and require advanced image processing techniques
Introduction
to extract meaningful information. Medical image processing
Brain tumours have become a major health concern in recent is an interdisciplinary field that combines computer science,
years, affecting people of all ages and nationalities. According physics, mathematics, and medicine to develop techniques
to the Cancer Research UK charity, there are approximately to analyze, manipulate, and visualize medical images. These
004

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

techniques are essential in enhancing the quality of medical begin within the brain itself, originating from the various
images, reducing noise, and extracting features that are crucial cells and structures that make up the brain. There are many
for diagnosis and treatment [2]. different types of primary brain tumours, as shown in Table
1. Secondary brain tumours, also known as metastatic brain
Brain tumourdetection and classification can significantly
tumours, are cancers that have spread from other parts of the
benefit from image processing techniques. Image processing
body, such as the lungs, breast, or colon, and have migrated to
can help improve the accuracy of tumourdetection,
the brain through the bloodstream [11].
identification of its location, and determination of its type. It
can also provide valuable information for surgical planning Symptoms
and therapy selection. Image processing techniques can also
help in the early detection of brain tumours, enabling earlier The symptoms of brain tumours can vary depending on the
interventions and better patient outcomes [3]. location, size, and growth rate of the tumour. Common signs
and symptoms may include persistent headaches, seizures,
In the realm of modern healthcare, medical imaging has
cognitive or memory problems, changes in mood or personality,
revolutionized the diagnosis and treatment of various medical
visual or hearing disturbances, balance and coordination
conditions. Among the most crucial applications of medical
issues, nausea, vomiting, and progressive neurological deficits.
imaging techniques are brain imaging modalities such as
However, it is essential to note that these symptoms are not
MRI, CT, and X-rays. These modalities provide invaluable
exclusive to brain tumours and can be associated with various
insights into the intricate workings of the human brain, aiding
other conditions.
clinicians in making accurate diagnoses, planning surgeries,
and monitoring treatment outcomes. Detection
This section explores the definition, types, symptoms, The diagnosis of a brain tumourtypically involves a
detection, and treatment of brain tumours, offering insights combination of medical history evaluation, neurological
into current research and advancements in the field.
examination, imaging techniques such as magnetic resonance

Definition imaging (MRI) or computed tomography (CT) scan, and, in

some cases, a biopsy. Once a brain tumouris diagnosed, further
A brain tumourrefers to an abnormal growth of cells in tests may be conducted to determine the type, grade, and extent
the brain or its surrounding tissues, which can potentially of the tumour, which help guide treatment decisions [21]. A
disrupt the normal functioning of the central nervous system proposed image moments technique applied in the health
[4]. Figure 1 illustrates the different views of brain images monitoring of brain tumours via image analysis procedures
including tumours. [22].

A brain tumouroriginates when there is an uncontrolled Treatment

multiplication of cells within the brain. While the exact causes
of brain tumours are not always clear, certain factors such Treatment options for brain tumours are multifaceted and
as exposure to ionizing radiation, genetic predisposition, depend on several factors, including the type, grade, location,
environmental factors, and certain medical conditions may and size of the tumour, as well as the patient's overall health.
contribute to their development [8]. An overview of current The primary treatment modalities include surgery, radiation
advances in medical image processing and machine learning therapy, and chemotherapy, often used in combination or
techniques for the detection and categorization of brain tumors sequentially. Surgery aims to remove as much of the tumouras
is provided in [9]. Together with these topics, recent research safely possible, while radiation therapy and chemotherapy are
in [10] describes component extraction, Machine Learning employed to target and eliminate remaining cancer cells or
(ML), Transfer Learning (TL), morphology of brain tumors, slow down tumourgrowth.
and available data sets and augmentation techniques.
In addition to conventional treatments, other therapeutic
Types of brain tumours approaches may be utilized in the management of brain
tumours. These can include targeted therapies, immunotherapy,
Brain tumours can be classified into two main categories:
hormone therapy, and supportive care measures to alleviate
primary and secondary. Primary brain tumours are those that
symptoms and enhance the patient's quality of life [23].

Methodology
Brain MRI plays a vital role in the detection of brain tumours.
However, these images often suffer from blurring and noise,
which can hinder accurate tumourdetection. To overcome
this challenge, several techniques are commonly employed
to deblur and denoise brain MRI images. Additionally, post-
Figure 1: Different views of the brain images including tumour: (Left) Axial view of processing techniques are used to enhance the image quality,
a brain with tumour[5] (Middle) Profile view image of a healthy brain [6], and (Right)
segment tumourregions, and classify the presence of tumours.
Top view image of a healthy brain [7].
005

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

Table 1: Definition and image of the different brain tumourtypes.

Type of tumourthat originates in the glial cells of the brain or spinal cord. Glioma [12]

A noncancerous tumourdevelops in the meninges, the protective

Meningioma [13]
membranes surrounding the brain and spinal cord.

A benign tumourthat grows on the vestibulocochlear nerve, which is

Acoustic neuroma [14]
responsible for hearing and balance.

Type of cancer that affects the lymphocytes within the brain, spinal cord, or Primary central nervous system
eyes. lymphoma [15]

A rare, vascular tumourthat typically forms in the cerebellum and is

Haemangioblastoma [16]
associated with a genetic condition called von Hippel-Lindau disease.

A malignant brain tumourthat primarily affects children and arises in the

Medulloblastoma [17]
cerebellum, often causing symptoms related to balance and coordination.

The tumouroccurs in the pineal gland, which is located deep within the brain
Pineal region tumour [18]
and plays a role in regulating sleep-wake cycles and hormone production.

A tumourdevelops in the pituitary gland, a small gland at the base of the

Pituitary tumour [19]
brain that controls various hormonal functions in the body.

A benign tumourtypically arises near the pituitary gland and originates from
Craniopharyngioma tumour [20]
remnants of tissue left over from fetal development.

006

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

Image acquisition 

f  x, y  *h  x, y   ∬f  u , v  h  x  u , y  v  dudv,
In the pursuit of advancing medical imaging technology

and improving the detection and diagnosis of brain tumours, (2)
researchers often rely on publicly available datasets for their
studies. To avoid this complex calculation, the Fourier transform
can be applied:
The Kaggle Brain MRI Images dataset consists of a
comprehensive collection of brain magnetic resonance imaging G  u, v   F  u, v   H  u, v   N  u, v  . (3)
(MRI) scans, encompassing both tumour and non-tumor cases,
as shown in Table 2 [24] (Note that this research complies Eq. (3) is the easiest way to understand the presence of
with data protection regulations, ethical guidelines, and noise and blur on a captured image.
privacy concerns using Kaggle datasets). It provides a diverse
Fourier transform is a mathematical tool that decomposes
range of brain images, allowing to explore various imaging
a signal or image into its constituent frequencies, represented
characteristics associated with brain tumours.
as complex numbers, providing insights into the presence and
This dataset includes a substantial number of MRI images, strength of different frequency components for deblurring and
representing different slices and orientations of the brain. Each image enhancement applications [28,29].
image is labeled to indicate the presence or absence of a tumour,
Results
and also the type of tumour, facilitating the development and
evaluation of tumour detection algorithms. The pre-processing stage focused on mitigating the effects
of blurring and noise in brain MRI images. A combination of
Pre-processing techniques
advanced image processing techniques was employed to achieve
In the field of image processing and analysis, images are this goal. The pre-processing pipeline included Gaussian blur,
often regarded as 2D signals, subject to noise and blurring total variation filtering, Wiener filtering, and Lucy-Richardson
during the acquisition or transmission process. Figure 2 shows filtering. Each technique was applied to a sample of tumorous
the imaging system which is modeled the acquired image in brain MRI images.

terms of the original image by convolving it with a point-spread

The Gaussian blur was employed to reduce image noise
function (PSF) and added noise. These inherent challenges and create smoother image contours. The total variation filter,
can significantly impact the accuracy of classification tasks. known for its ability to preserve edges while denoising images,
Therefore, to improve the performance of image classification helped enhance the contrast of the tumourregions. The Wiener
algorithms, it is essential to undertake pre-processing and
processing techniques to mitigate noise and blur, enabling
more robust and reliable image classification results [25-27].

Here is the equation of the captured image

g ( x, y )  f ( x, y ) * h( x, y )  n( x, y ), (1)

x and Y refer to the image pixels. f is the original view, h

refers to the blur, and n to the noise. G is the final 2D signal,
the captured image.

The convolution of f by h corresponds to the following

calculation:
Figure 2: Imaging system model of pre-processing techniques (noise and blur).

Table 2: Sample of the datasets of brain MRI images [24].

Brain tumours Without tumour With tumour

MRI images

007

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

filter, which aims to remove noise from images, contributed to accurate diagnosis and treatment planning. The pre-processed
further noise reduction in the pre-processed MRI scans. Lastly, images from Table 4, play an essential role in improving the
the Lucy-Richardson filter, a popular deblurring technique, performance and reliability of the subsequent image analysis
effectively restored lost details and improved the overall image and classification algorithms, enabling medical professionals
quality as shown in Table 3. to make more informed decisions in the context of brain
tumour detection and treatment.
Poisson noise is commonly encountered in low-light
imaging conditions, such as in certain types of medical imaging Image quality assessment results
equipment. It appears as random variations in pixel intensities
and can introduce unwanted artifacts into the image. By Several Image Quality Assessment (IQA) methods,
simulating Poisson noise and then applying Poisson noise including Blind/Referenceless Image Spatial Quality Evaluator
removal techniques, the images were effectively restored to (BRISQUE), Perception-based Image Quality Evaluator (PIQE),
reduce the impact of noise on the accuracy of tumour detection. Naturalness Image Quality Evaluator (NIQE) [30], Structural
Similarity Index (SSIM), and Peak Signal-to-Noise Ratio
Similarly, salt and pepper noise was artificially added (PSNR) [31], were employed to evaluate the quality of the pre-
to the images to simulate the presence of random black and processed brain MRI images, as shown in Figure 3. These IQA
white pixels that can occur due to various factors, such as data methods are essential for objectively measuring and comparing
corruption during transmission or errors in image acquisition. the performance of different pre-processing techniques, as
Techniques for salt and pepper noise reduction were then well as for assessing the impact of various noise reduction and
applied to eliminate these noisy pixels, improving the clarity deblurring algorithms on image quality.
of the images and facilitating more precise tumour region
identification. Figure 3 shows that, based on the BRISQUE metric as a
no-reference method, the total variation filter and Poisson
The non-local mean filtering and wavelet thresholding
noise have a significantly good impact on the original image.
techniques were also utilized in conjunction with Poisson
However, Gaussian blur and Salt and pepper degrade the quality
noise and salt and pepper noise removal to further enhance
of the original image. On the other hand, as SSIM is based on a
the quality of the pre-processed brain MRI images. These
comparison and full-reference approach, the Non-local mean
combined algorithms effectively addressed noise and other
(NLM) image is the closest to the original one. Salt and pepper
artifacts while preserving critical image features, resulting in
noise is the method that generates the furthest image from the
clearer and more reliable images for subsequent analysis and
original one.
interpretation.
Detection results
By carefully incorporating these pre-processing
techniques, the brain MRI images were optimized for tumour Building upon meticulous segmentation, the detection
detection and classification, providing a solid foundation for phase introduces refined visualizations that emphasize the

Table 3: Pre-processed image of a tumorous brain with blurring and deblurring methods.

Original Image Gaussian blur Total variation filter Wiener filter Lucy-Richardson filter

Table 4: Pre-processed image of a tumourous brain with noising and denoising methods.

Poisson noise Salt & Pepper noise Non-local mean filter (NLM) Wavelet threshold
008

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

Figure 3: No-reference methods (Top) and Full-reference methods image quality assessment results (Bottom).

tumour's localization and shape. The integration of a bounding

box around the tumouroffers a precise spatial representation of
the anomaly within the brain MRI image, as shown in Figure
4. This bounding box not only encapsulates the tumour's
spatial extent but also enhances the visibility of its location.
Further enhancing the detection process, the intricate outline
of the tumouris crafted using techniques such as dilation and
erosion. The result is a finely detailed representation of the
tumour's contours, facilitating a deeper understanding of its
characteristics and boundaries. Through this comprehensive
Figure 4: Tumourarea with bounding box (left). Defined tumourboundary (right).
detection process, medical professionals can accurately assess
the tumour's presence and develop targeted approaches for
further analysis.

Classification results

The integration of deep learning-based classification

techniques adds a layer of sophistication to the analysis,
allowing for the identification of the tumortype from the MRI
data. This pivotal phase involves training a neural network
to distinguish between different tumor categories, such as
meningioma, glioma, or pituitary tumour. Convolutional
Neural Network (CNN) provides a segmentation-free approach
that does away with the requirement for labor-intensive Figure 5: Tumouris outlined in the original image.
feature extractor techniques. Because of this, we used various
CNN designs for brain tumor detection and classification [32-
34]. The classification output holds significant clinical value, as between images with tumours and those without. This figure
it provides crucial information about the tumour's underlying displays key training metrics and their evolution over training
nature. By leveraging machine learning algorithms, medical epochs, reflecting how effectively the model is learning to make
practitioners can efficiently categorize tumours, enabling accurate classifications. The X-axis represents the training
them to make timely and informed decisions about treatment epochs, while the Y-axis shows the values of the training
strategies. This classification outcome augments the diagnostic metrics, which may include accuracy, loss, and validation
process by offering insights into the tumour's potential metrics. This graphical representation provides valuable
behavior and guiding personalized medical care. Figure 5 insights into the model's learning curve and its performance in
shows the original image with the outline of the tumour, as distinguishing between brain images with tumours and those
well as the type of tumor which is displayed in the figure title. deemed tumour-free.

Figure 6 visually presents the training progress of a brain As shown in Figure 7, one of the datasets contained over
image classification model specifically designed to differentiate 2200 figures of brain MRI, tumorous and non-tumorous.

009

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

Figures 6 and 8 show the training progress of a brain image by accurately delineating the region of interest. Moving to the
classification model specifically designed to differentiate detection phase, the process is evidenced through an image
between tumourtypes. depicting the tumourarea with a bounding box and another
image highlighting the defined tumourboundary. These
Discussion visualizations intricately outline the localized tumourand
precisely define its boundaries, emphasizing the efficacy of the
The results presented encompass a comprehensive analysis
of brain MRI images to detect and characterize tumorous detection process in identifying and visualizing the presence

regions. The analysis pipeline consists of four key phases: of tumours. In the classification phase, the tumouroutlined
pre-processing, segmentation, detection, and classification. in the original image is showcased, demonstrating how
The pre-processing phase serves as the initial step, involving a deep neural network trained to classify tumourtypes as
techniques such as contrast adjustment, anisotropic diffusion, meningioma, glioma, or pituitary tumourcan be applied. The
and resizing. These techniques contribute to refining image amalgamation of these phases is illustrated by the interplay
quality, minimizing noise, and ensuring uniform dimensions of various images, representing different stages of analysis
across the dataset. In the segmentation phase, the generation and underlining the methodology's comprehensive nature. By
of a tumoursegmentation mask effectively isolates the seamlessly integrating techniques spanning pre-processing,
tumorous region from the brain's anatomical structures. This image segmentation, and neural network-based classification,
foundational step lays the groundwork for subsequent analyses this approach offers a robust framework for accurate brain

Figure 6: Plot of the training progress for brain image classification (Tumour/No tumour).

Figure 7: Distribution of the brain images based on the classes: Tumourand No tumour.

010

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

Figure 8: Plot of the training progress for brain tumourtypes classification (Meningioma, Glioma, and Pituitary).

tumouranalysis. This approach not only advances diagnostic comprehensive evaluation of the model's applicability.
accuracy but also lays the groundwork for future advancements Integrating additional data modalities, such as functional
in medical image analysis and diagnosis. MRI or diffusion tensor imaging, could enrich the analysis
and potentially lead to more holistic insights into brain
There are many challenges in brain tuomour detection
health. Furthermore, the pre-processing phase could benefit
such as complexity and heterogeneity of tumours, small
from advancements in noise reduction techniques and more
lesion detection, imaging modalities, and interpretability
advanced image restoration methods, potentially enhancing
and explainability of neural networks and deep learning
image quality and subsequently improving downstream
algorithms. Moreover, Limited Availability of Labeled Data and
analysis.
computational resources could be considered as limitations of
this study. References
Conclusion 1. NHS. Brain tumours. https://www.nhs.uk/conditions/brain-tumours/.

The foundational understanding of MRI principles 2. Beucler N, Dagain A, Sellier A. Duret Brainstem Hemorrhage Secondary to
enabled a robust start to this research, allowing for informed Large Supratentorial Meningioma. World Neurosurg. 2023 May 24;177:1-2.
doi: 10.1016/j.wneu.2023.05.067. Epub ahead of print. PMID: 37236310.
decisions throughout the research. The pre-processing phase,
involving noise reduction and image clarity enhancement, 3. Solanki S, Singh UP, Chouhan SS, Jain S. Brain tumor detection and
substantially improved image quality, making subsequent classification using intelligence techniques: An overview. IEEE Access. 2023.
analysis more reliable. The exploration and comparison of
4. Kurdi SZ, Ali MH, Jaber MM, Saba T, Rehman A, Damaševičius R. Brain
different segmentation methods provided valuable insights
Tumor Classification Using Meta-Heuristic Optimized Convolutional Neural
into accurately identifying brain structures. Networks. J Pers Med. 2023 Jan 20;13(2):181. doi: 10.3390/jpm13020181.
PMID: 36836415; PMCID: PMC9965936.
The primary highlight of this research lies in the successful
implementation of CNNs for brain image classification. The 5. Li G. AI matches humans at diagnosing brain cancer from tumourbiopsy
utilization of CNN architecture showcased the potential of deep images. 2020. https://www.newscientist.com/article/ 2229306-ai-matches-
learning in extracting complex features and patterns from humans-at-diagnosing-brain-cancer-from-tumour/ /-biopsy-images

brain images. The results demonstrated improved accuracy in

6. Profile view of a brain. https://pngimg.com/image/86579.
classifying brain images based on disease types, a significant
achievement in medical image analysis. 7. Top view of a brain. https://pngimg.com/image/86597.

While this research has paved the way for advanced brain 8. DeAngelis LM. Brain tumors. N Engl J Med. 2001 Jan 11;344(2):114-23. doi:
10.1056/NEJM200101113440207. PMID: 11150363.
image analysis, several avenues for future exploration remain
open. Firstly, further investigation into incorporating more 9. Kandimalla SY, Vamsi DM, Bhavani S, VM M. Recent Methods and Challenges
intricate deep learning architectures, such as ResNet-50 or in Brain Tumor Detection Using Medical Image Processing. Recent Patents on
more recent variations, could yield even higher classification Engineering. 2023; 17(5): pp.8-23.
accuracy. Exploring ensembles of CNN models and transfer
10. Solanki S, Singh UP, Chouhan SS, Jain S. Brain Tumor Detection and
learning from large datasets might contribute to enhancing the
Classification using Intelligence Techniques: An Overview. IEEE Access. 2023.
robustness and generalizability of the model.
11. Thust SC, van den Bent MJ, Smits M. Pseudoprogression of brain tumors. J
Additionally, extending the research to a broader range Magn Reson Imaging. 2018 May 7;48(3):571–89. doi: 10.1002/jmri.26171.
of diseases and medical conditions could provide a more Epub ahead of print. PMID: 29734497; PMCID: PMC6175399.

011

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140
 https://www.peertechzpublications.org/journals/imaging-journal-of-clinical-and-medical-sciences

12. Nelson SJ, Cha S. Imaging glioblastoma multiforme. Cancer J. 2003 Mar- approaches to the treatment of metastatic brain tumours. Nat Rev Clin Oncol.
Apr;9(2):134-45. doi: 10.1097/00130404-200303000-00009. PMID: 12784879. 2014 Apr;11(4):203-22. doi: 10.1038/nrclinonc.2014.25. Epub 2014 Feb 25.
PMID: 24569448; PMCID: PMC4041037.
13. Maggio I, Franceschi E, Tosoni A, Nunno VD, Gatto L, Lodi R, Brandes AA.
Meningioma: not always a benign tumor. A review of advances in the treatment 24. Chakrabarty N. Brain MRI images for Brain tumor detection, Kaggle. 2019.
of meningiomas. CNS Oncol. 2021 Jun 1;10(2):CNS72. doi: 10.2217/cns- https://www.kaggle.com/datasets/navoneel/brain-mri-images-for-brain-
2021-0003. Epub 2021 May 21. PMID: 34015955; PMCID: PMC8162186. tumor-detection (Accessed: 10 November 2023).

14. Dr Louis Hofmeyr. Acoustic neuroma (vestibular schwannoma).2023. https:// 25. Honarvar Shakibaei B, Jahanshahi P. Image deconvolution by means of
lmhofmeyr.co.za/conditions/conditions-we-specialise-in/ acoustic-neuroma/ frequency blur invariant concept. ScientificWorldJournal. 2014;2014:951842.
doi: 10.1155/2014/951842. Epub 2014 Aug 12. PMID: 25202743; PMCID:
15. Karia SJ, McArdle DJT. AIDS-related primary CNS lymphoma. Lancet. 2017 PMC4147381.
Jun 3;389(10085):2238. doi: 10.1016/S0140-6736(17)30056-9. Epub 2017
Apr 6. PMID: 28392104. 26. Shakibaei BH, Flusser J. Image deconvolution in the moment domain.
Moments and Moment Invariants—Theory and Applications. 2014; 1:111-125.
16. Prontera A, Puzzolante A, Carpeggiani P, Pavesi G. Symptomatic anterior
cerebral artery vasospasm after brainstem hemangioblastoma resection. A 27. Kumar A, Paramesran R, Shakibaei BH. Moment domain representation
case report. Neuroradiol J. 2014 Apr;27(2):186-90. doi: 10.15274/NRJ-2014- of nonblind image deblurring. Appl Opt. 2014 Apr 1;53(10):B167-71. doi:
10019. Epub 2014 Apr 18. PMID: 24750707; PMCID: PMC4202852. 10.1364/AO.53.00B167. PMID: 24787200.

17. Trieu EQ, Huang SY, Yang JY. Medulloblastoma: Clinical challenges and 28. Asli BHS, Flusser J, Zhao Y, Erkoyuncu JA, Krishnan KB, Farrokhi Y, Roy R.
emerging molecular discoveries,” in Neurooncology-Newer Developments. Ultrasound image filtering and reconstruction using DCT/IDCT filter structure.
IntechOpen. 2016. IEEE Access. 2020; 8:141342-141357.

18. Rastogi M, Gupta MK, Revannasiddaiah S, Seam RK. The lack of sleep, the pineal 29. Honarvar Shakibaei Asli B, Zhao Y, Erkoyuncu JA. Motion blur invariant for
gland and breast cancer. BMJ Case Rep. 2012 Sep 17;2012:bcr2012006763. estimating motion parameters of medical ultrasound images. Sci Rep. 2021
doi: 10.1136/bcr-2012-006763. PMID: 22987906; PMCID: PMC4543568. Jul 12;11(1):14312. doi: 10.1038/s41598-021-93636-4. PMID: 34253807;
PMCID: PMC8275601.
19. Raeesa F, Mahale A, Vinay B S. A curious case of vanishing pituitary
adenoma. Radiol Case Rep. 2020 May 19;15(7):1050-1053. doi: 10.1016/j. 30. Mittal A, Moorthy AK, Bovik AC. No-reference image quality assessment in the
radcr.2020.04.021. PMID: 32461776; PMCID: PMC7240058. spatial domain. IEEE Trans Image Process. 2012 Dec;21(12):4695-708. doi:
10.1109/TIP.2012.2214050. Epub 2012 Aug 17. PMID: 22910118.
20. Drapeau A, Walz PC, Eide JG, Rugino AJ, Shaikhouni A, Mohyeldin A, Carrau
RL, Prevedello DM. Pediatric craniopharyngioma. Childs Nerv Syst. 2019 31. Chen MJ, Bovik AC. Fast structural similarity index algorithm.Journal of Real-
Nov;35(11):2133-2145. doi: 10.1007/s00381-019-04300-2. Epub 2019 Aug 5. Time Image Processing. 2011; 6:281-287.
PMID: 31385085.
32. Aggarwal M, Khullar V, Goyal N, Singh A, Tolba A, Thompson EB, Kumar S. Pre-
21. Butowski NA. Epidemiology and diagnosis of brain tumors. Continuum Trained Deep Neural Network-Based Features Selection Supported Machine
(Minneap Minn). 2015 Apr;21(2 Neuro-oncology):301-13. doi: 10.1212/01. Learning for Rice Leaf Disease Classification. Agriculture. 2023; 13(5):936.
CON.0000464171.50638.fa. PMID: 25837897.
33. Sharma N, Gupta S, Mohamed HG, Anand D, Mazón JLV, Gupta D, Goyal
22. Honarvar Shakibaei Asli B, Wang Y. Moment-based image enhancement for N. Siamese convolutional neural network-based twin structure model for
brain tumor health monitoring. In: 11th International Conference on Through- independent offline signature verification. Sustainability. 2022; 14(18):11484.
life Engineering Services - TESConf2022, 8-9 November 2022, Cranfield, UK,
Paper number 3405. 2022. 34. Singh TP, Gupta S, Garg M, Gupta D, Alharbi A, Alyami H, Anand D, Ortega-
Mansilla A, Goyal N. Visualization of Customized Convolutional Neural Network
23. Owonikoko TK, Arbiser J, Zelnak A, Shu HK, Shim H, Robin AM, Kalkanis SN, for Natural Language Recognition. Sensors (Basel). 2022 Apr 8;22(8):2881.
Whitsett TG, Salhia B, Tran NL, Ryken T, Moore MK, Egan KM, Olson JJ. Current doi: 10.3390/s22082881. PMID: 35458866; PMCID: PMC9026827.

https://www.peertechzpublications.org/submission

012

Citation: Shakibaei Asli BH, Jasmin A (2023) Image processing techniques for the detection of brain tumours. Imaging J Clin Medical Sci 10(1): 004-012.
DOI: https://dx.doi.org/10.17352/2455-8702.000140