Sat, Aug 23, 2025
[Archive]
Volume 17, Issue 2 (June-2025 2025)
Iranian Journal of Blood and Cancer 2025, 17(2): 34-45 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Porkar P, Mehrabipour F, Pourasad M H, Movassagh A A, nazari K, Porkar P, et al . Enhancing Cancer Zone Diagnosis in MRI Images: A Novel SOM Neural Network Approach with Block Processing in the Presence of Noise. Iranian Journal of Blood and Cancer 2025; 17 (2) :34-45
URL: http://ijbc.ir/article-1-1706-en.html
URL: http://ijbc.ir/article-1-1706-en.html
Payam Porkar1 
, Faranak Mehrabipour2 , Mohammad Hossein Pourasad3 , Ali Akbar Movassagh4 , Kobra Nazari5 , Pasha Porkar6 , Mustafa Ghaderzadeh *7 , Mehdi Gheisari8 , Cirruse Salehnasab9 , Sohrab Almasi10
, Faranak Mehrabipour2 , Mohammad Hossein Pourasad3 , Ali Akbar Movassagh4 , Kobra Nazari5 , Pasha Porkar6 , Mustafa Ghaderzadeh *7 , Mehdi Gheisari8 , Cirruse Salehnasab9 , Sohrab Almasi10
1- Institute of Artificial Intelligence, Shaoxing University, Zhejiang, China.
2- Computer Department, Islamic Azad University, Damavand Branch, Damavand, Iran.
3- School of paramedical, Kermanshah University of Medical Sciences, Kermanshah, Iran.
4- Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
5- Department of mathematics, Vali-E-Asr university of Rafsanjani, Rafsanjani, Iran.
6- Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven 5600 MB, Netherlands.
7- Boukan Faculty of Medical Sciences, Urmia University of Medical Sciences, Urmia, Iran. ,Mustaf.ghaderzadeh@sbmu.ac.ir
8- Institute of Artificial Intelligence, Shaoxing University, Zhejiang, China. & Department of R&D, Shenzhen BKD Co LTD, Shenzhen, China.
9- Assistant Professor of Medical Informatics, Social Determinants of Health Research Center, Yasuj University of Medical Sciences, Yasuj, Iran.
10- National Center for Health Insurance Research, Tehran, Iran.
2- Computer Department, Islamic Azad University, Damavand Branch, Damavand, Iran.
3- School of paramedical, Kermanshah University of Medical Sciences, Kermanshah, Iran.
4- Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
5- Department of mathematics, Vali-E-Asr university of Rafsanjani, Rafsanjani, Iran.
6- Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven 5600 MB, Netherlands.
7- Boukan Faculty of Medical Sciences, Urmia University of Medical Sciences, Urmia, Iran. ,
8- Institute of Artificial Intelligence, Shaoxing University, Zhejiang, China. & Department of R&D, Shenzhen BKD Co LTD, Shenzhen, China.
9- Assistant Professor of Medical Informatics, Social Determinants of Health Research Center, Yasuj University of Medical Sciences, Yasuj, Iran.
10- National Center for Health Insurance Research, Tehran, Iran.
Abstract: (262 Views)
Background: Brain tumors are a specific disease that directly affects the brain. Magnetic Resonance Imaging (MRI) is considered the most effective imaging technique for diagnosing brain tumors, providing crucial information about tumor size, location, and type. However, accurately segmenting and extracting the tumor region from MRI images is a challenging task for radiologists and physicians, impacting the overall accuracy of diagnosis.
Methods: This research focuses on addressing the challenges of brain tumor detection and segmentation in MRI images. In line with the recent trend of big data analysis, neuroimaging data, including MRI images, are considered an important subset of big data due to their volume, velocity, and variety. The proposed approach utilizes the Self Organizing Maps (SOM) Neural Network, a powerful concept in image processing, to handle noise and artifacts in brain MRI.
Results: The proposed method employs image segmentation to focus on smaller parts of the brain and utilizes the SOM neural network for noise reduction, enhancing the processing of noisy brain images. The approach incorporates block processing to effectively approximate the suspected cancer zone, facilitating accurate medical diagnosis. The algorithm achieves precise specification of brain image zones by learning the unique SOM algorithm and setting an edge detection threshold. Experimental results demonstrate the superior performance of the proposed method, surpassing previous approaches, with a precision of over 10% in diagnosing abnormal brain areas.
Conclusion: The study highlights the importance of MRI in brain tumor diagnosis and the challenges associated with accurate tumor segmentation. The proposed approach using the SOM Neural Network effectively addresses these challenges by reducing noise, enabling block processing, and enhancing the precision of tumor detection. Results indicate the potential of the proposed method to significantly improve brain tumor diagnosis and contribute to advancements in medical imaging for neuroimaging applications.
Methods: This research focuses on addressing the challenges of brain tumor detection and segmentation in MRI images. In line with the recent trend of big data analysis, neuroimaging data, including MRI images, are considered an important subset of big data due to their volume, velocity, and variety. The proposed approach utilizes the Self Organizing Maps (SOM) Neural Network, a powerful concept in image processing, to handle noise and artifacts in brain MRI.
Results: The proposed method employs image segmentation to focus on smaller parts of the brain and utilizes the SOM neural network for noise reduction, enhancing the processing of noisy brain images. The approach incorporates block processing to effectively approximate the suspected cancer zone, facilitating accurate medical diagnosis. The algorithm achieves precise specification of brain image zones by learning the unique SOM algorithm and setting an edge detection threshold. Experimental results demonstrate the superior performance of the proposed method, surpassing previous approaches, with a precision of over 10% in diagnosing abnormal brain areas.
Conclusion: The study highlights the importance of MRI in brain tumor diagnosis and the challenges associated with accurate tumor segmentation. The proposed approach using the SOM Neural Network effectively addresses these challenges by reducing noise, enabling block processing, and enhancing the precision of tumor detection. Results indicate the potential of the proposed method to significantly improve brain tumor diagnosis and contribute to advancements in medical imaging for neuroimaging applications.
Keywords: Brain Tomur, Magnetic Resonance Imaging, Edge detection, Image processing, Segmentation, Self-Organizing Maps, Neural network
: Original Article |
Subject:
AI in Medicine
Received: 2025/04/22 | Accepted: 2025/06/14 | Published: 2025/06/30
Received: 2025/04/22 | Accepted: 2025/06/14 | Published: 2025/06/30
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
- Iranian Journal of Blood and Cancer
- Journal Tel: +989369936116
- Publisher Tel: +982122275917
- Mail: Info@ijbc.ir
