Journal of the Korean Society of Radiology (한국방사선학회논문지)

The Korean Society of Radiology (한국방사선학회)
권호 표지
DOI QR코드

DOI QR Code

Detection and Segmentation of Tumors in Brain MR Images

뇌 MR 영상에서 종양의 검출과 분할

  • Hwunjae Lee (YUHS-KRIBB Medical Convergence Research Institute, Yonsei University College of Medicine)
  • 이훈재 (연세대학교 의과대학 연의-생공연 메디컬융합연구소)
  • Received : 2024.10.09
  • Accepted : 2024.11.30
  • Published : 2024.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Brain tumors arise from various complex factors, including genetic, environmental, immunological, and biochemical influences. They can be classified as primary or metastatic, differing in their origin and location. Brain tumors significantly impact the quality of life, leading to symptoms such as headaches, seizures, cognitive decline, and motor function impairment, depending on the tumor's size and location. Early diagnosis of brain tumors is crucial for improving quality of life. Timely detection allows for prompt treatment initiation, which can prevent tumor growth and the worsening of symptoms. Diagnosis typically involves neurological examinations, imaging examinations, tissue biopsies, and blood tests. In particular, MRI provides high-resolution images of the brain's detailed structure, clearly depicting the location, size, shape, and surrounding tissues of the tumor. This study proposes a method for detecting and segmenting brain tumors in MRI images, utilizing a dataset constructed for this purpose, named "BrainTumors_1.0.zip." Experimental results demonstrate that filtering the input images enhances image quality and enables accurate tumor detection. Future research will focus on enhancing algorithm generalization, diversifying the dataset, developing automated methodologies, and assessing clinical utility to establish an effective tool for the diagnosis and treatment of brain tumors.

뇌종양은 유전적, 환경적, 면역학적, 생화학적 요인을 포함한 다양한 복합적인 요인에서 발생한다. 뇌종양은 원발성과 전이성으로 분류되며, 이들은 발생 원인과 위치에서 차이를 보인다. 뇌종양은 삶의 질에 상당한 영향을 미치며, 종양의 크기와 위치에 따라 두통, 발작, 인지 기능 저하, 운동 기능 장애와 같은 증상이 나타날 수 있다. 뇌종양의 조기 진단은 삶의 질을 향상시키는 데 매우 중요하다. 적시의 발견은 신속한 치료를 가능하게 하여 종양의 성장과 증상의 악화를 예방할 수 있다. 진단 과정은 일반적으로 신경학적 검사, 영상 검사, 조직 검사, 혈액 검사를 포함한다. 특히, MRI는 뇌의 상세한 구조를 고해상도로 제공하여 종양의 위치, 크기, 형태 및 주변 조직을 명확하게 나타낸다. 본 연구에서는 MRI 영상에서 뇌종양을 탐지하고 분할하는 방법을 제안하며, 이를 위해 "BrainTumors_1.0.zip"이라는 이름의 데이터 세트를 구축하였다. 실험 결과는 입력 영상을 필터링함으로써 이미지 품질을 향상시키고 정확한 종양 탐지를 가능하게 함을 보여주었다. 향후 연구는 알고리즘의 일반화, 데이터 세트의 다양화, 자동화된 방법론 개발, 그리고 임상적 유용성을 평가하여 뇌종양 진단과 치료를 위한 도구로 확립하는 것이다.

Keywords

Acknowledgement

This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(Grant number_RS-2023-00248763).

References

  1. J. H. Sampson, M. D. Gunn, P. E. Fecci, D. M. Ashley, "Brain immunology and immunotherapy in brain tumours", Nature Reviews Cancer, Vol. 20, No 1, pp. 12-25, 2020. http://dx.doi.org/10.1038/s41568-019-0224-7
  2. K. M. Reilly, "Brain Tumor Susceptibility: the Role of Genetic Factors and Uses of Mouse Models to Unravel Risk", Brain Pathology, Vol. 19, No. 1, pp. 121-131, 2009. http://dx.doi.org/10.1111/j.1750-3639.2008.00236.x
  3. S. Li, C . Wang, J. C hen, Y. Lan, W. Zhang, Z. Kang, Y. Zheng, R. Zhang, J. Yu, W. Li, "Signaling pathways in brain tumors and therapeutic interventions", Signal Transduction and Targeted Therapy, Vol. 8, No. 1, 2023. http://dx.doi.org/10.1038/s41392-022-01260-z
  4. T. N. Seyfried1, L. C. Huysentruyt, "On the Origin of Cancer Metastasis", Critical Reviews™ in Oncogenesis, Vol. 18, No. 1-2, pp. 43-73, 2013. https://doi.org/10.1615/critrevoncog.v18.i1-2.40
  5. R. Liu, M. Page, K. Solheim, S. Fox, S. M. Chang, "Quality of life in adults with brain tumors: Current knowledge and future directions", Neuro-Oncology, Vol. 11, No. 3, pp. 330-339, 2009. https://doi.org/10.1215/15228517-2008-093
  6. G. Thenuwara, J. Curtin, F. Tian, "Advances in diagnostic tools and therapeutic approaches for gliomas: a comprehensive review", Sensors, Vol. 23, No. 24, pp. 9842, 2023. http://dx.doi.org/10.3390/s23249842
  7. NEJM, URL; https://www.nejm.org/image-challenge?startPage=1
  8. auntminnie, URL; https://my.auntminnie.com/cases/
  9. springer, URL; H. H. Sultan, N. M. Salem, W. Al-Atabany, "Multi-Classification of Brain Tumor Images Using Deep Neural Network", IEEE Access, Vol. 7, pp. 69215-69225, 2019. http://dx.doi.org/10.1109/ACCESS.2019.2919122
  10. medscape, URL; https://emedicine.medscape.com/article/779664-overview?_gl=1*1otq4tg*_gcl_au*MTczMTA0NTk1NC4xNzMxOTAzNjAw&form=fpf
  11. Radiology cases, URL; Gaillard F, Sharma R, Spires R, et al., "Brain tumors", Radiopaedia, 2024. https://doi.org/10.53347/rID-4986
  12. Radiopaedia, URL; Smith D, Sharma R, Bell D, et al. "Intracranial tumors (summary)", Radiopaedia, 2024. https://doi.org/10.53347/rID-34338
  13. data-visualization, URL; https://kr.mathworks.com/discovery/data-visualization.html
  14. L. Li, W. Ding, L. Huang, Xi. Zhuang, V. Grau, "Multi-modality cardiac image computing: A survey", Medical Image Analysis, Vol. 88, No. 102869, 2023. https://doi.org/10.1016/j.media.2023.102869
  15. MATLAB®, The Language of Technical Computing, From:https://www.mn.uio.no/astro/english/services/it/help/mathematics/matlab/matlab_prog.pdf
  16. M. Martucci, R. Russo, F. Schimperna, G. D'Apolito, M. Panfili, A. Grimaldi, "Magnetic Resonance Imaging of Primary Adult Brain Tumors: State of the Art and Future Perspectives", Biomedicines, Vol. 11, No. 2, pp. 364, 2023. https://doi.org/10.3390/biomedicines11020364
  17. M. M. Badza, M. C. Barjaktarovic, "Segmentation of Brain Tumors from MRI Images Using Convolutional Autoencoder", Applied Sciences, Vol. 11, No. 9, 2021. https://doi.org/10.3390/app11094317
  18. P. Jyothi, A. R. Singh, "Deep learning models and traditional automated techniques for brain tumor segmentation in MRI: a review", Artificial Intelligence Review, Vol. 56, pp. 2923-2969 2023. https://doi.org/10.1007/s10462-022-10245-x
  19. S. Maqsood, R. Damasevicius, R. Maskeliunas, "Multi-Modal Brain Tumor Detection Using Deep Neural Network and Multiclass SVM", Medicina (Kaunas, Lithuania), Vol. 58, No. 8, pp. 1090, 2022. https://doi.org/10.3390/medicina58081090
  20. A. M. Mostafa, M. Zakariah, E. A. Aldakheel, "Brain tumor segmentation using deep learning on MRI images", Diagnostics, Vol. 13, No. 9, 1562, 2023. https://doi.org/10.3390/diagnostics13091562