EUVIMEDEUVIMED entdecken
Crossref

2D Brain Tumor Classification Using CNN and SVM

Ayush kumar Ayush kumar

International Journal of Scientific Research in Engineering and Management · 2026-06 · 10 (6)

DOI: 10.55041/ijsrem64901 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Engineering and Management, 2026-06. Verfasst von Ayush kumar Ayush kumar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the contemporary era, the doctor-to-patient ratio is notably insufficient.In the year 2020, an approximate 251,329 individuals globally succumbed to primary cancerous brain and central nervous system tumors.Analyzing the vast array of magnetic resonance imaging (MRI) images and manually identifying a brain tumor is an arduous and error-prone endeavor.Timely detection of tumors holds paramount significance in preserving a patient's life.However, this becomes a time-consuming process when dealing with extensive datasets.The visual resemblance between normal tissue and brain tumor cells complicates the segmentation of tumor regions, posing a formidable challenge.Consequently, there arises a crucial need for a highly accurate automatic tumor detection method.In this study, we introduce a novel algorithm designed for the classification of brain tumors using 2D Magnetic Resonance Imaging (MRI) scans.Our approach involves the utilization of a convolutional neural network (CNN) in conjunction with a support vector machine (SVM).To ensure the robustness of our model, we curated a diverse dataset encompassing MRI images featuring varying tumor sizes, locations, shapes, and intensity levels.The classification process involves the application of the CNN model, followed by classification using the SVM classifier.The implementation of our proposed method is carried out using the "TensorFlow" and "Keras" libraries in the "Python" programming language, chosen for its efficiency in facilitating rapid and effective computational tasks.During our research endeavors, the model achieved an impressive training accuracy of 99.55% and a commendable testing accuracy of 98.47%.These results surpass the previously achieved stateof-the-art outcomes in this field.Our system enables doctors to precisely identify brain tumors in MRI images, significantly reducing the time required for diagnosis.This, in turn, accelerates the treatment process, ensuring a faster response to medical needs.

Zitieren

APA

kumar, A. K. A. (2026). 2D Brain Tumor Classification Using CNN and SVM. International Journal of Scientific Research in Engineering and Management, 10(6). https://doi.org/10.55041/ijsrem64901

Vancouver

kumar AKA. 2D Brain Tumor Classification Using CNN and SVM. International Journal of Scientific Research in Engineering and Management. 2026;10(6). doi:10.55041/ijsrem64901

BibTeX
@article{kumar2026,
  author = {kumar, Ayush kumar Ayush},
  title = {2D Brain Tumor Classification Using CNN and SVM},
  journal = {International Journal of Scientific Research in Engineering and Management},
  year = {2026},
  volume = {10},
  number = {6},
  doi = {10.55041/ijsrem64901}
}
Kostenlos starten →