EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Brain MRI detection and classification: Harnessing convolutional neural networks and multi-level thresholding

Rasool Reddy Kamireddy iD, Rajesh N V P S Kandala iD, Ravindra Dhuli, Srinivasu Polinati, Kamesh Sonti, Ryszard Tadeusiewicz, Paweł Pławiak

PLOS ONE · 01.08.2024 · 19 (8) · e0306492

DOI: 10.1371/journal.pone.0306492 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 01.08.2024. Verfasst von Rasool Reddy Kamireddy und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of ECE, NRI Institute of Technology (Autonomous), Vijayawada, India. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Neural Networks, Computer, Brain Neoplasms, Brain. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Brain tumor detection in clinical applications is a complex and challenging task due to the intricate structures of the human brain. Magnetic Resonance (MR) imaging is widely preferred for this purpose because of its ability to provide detailed images of soft brain tissues, including brain tissue, cerebrospinal fluid, and blood vessels. However, accurately detecting brain tumors from MR images remains an open problem for researchers due to the variations in tumor characteristics such as intensity, texture, size, shape, and location. To address these issues, we propose a method that combines multi-level thresholding and Convolutional Neural Networks (CNN). Initially, we enhance the contrast of brain MR images using intensity transformations, which highlight the infected regions in the images. Then, we use the suggested CNN architecture to classify the enhanced MR images into normal and abnormal categories. Finally, we employ multi-level thresholding based on Tsallis entropy (TE) and differential evolution (DE) to detect tumor region(s) from the abnormal images. To refine the results, we apply morphological operations to minimize distortions caused by thresholding. The proposed method is evaluated using the widely used Harvard Medical School (HMS) dataset, and the results demonstrate promising performance with 99.5% classification accuracy and 92.84% dice similarity coefficient. Our approach outperforms existing state-of-the-art methods in brain tumor detection and automated disease diagnosis from MR images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingNeural Networks, ComputerBrain NeoplasmsBrainHumansImage Processing, Computer-AssistedAlgorithms

Autor:innen und Institutionen

  • Department of ECE, NRI Institute of Technology (Autonomous), Vijayawada, India.
  • School of Electronics Engineering (SENSE), VIT-AP University, Amaravati, Andhra Pradesh, India.
  • Department of ECE, VIEW, Vishakhapatnam, Andhra Pradesh, India.
  • Department of ECE, SVEC, Tadepalligudem, Andhra Pradesh, India.
  • Department of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, Krakow, Poland.
  • Department of Computer Science, Faculty of Computer Science and Telecommunications, Cracow University of Technology, Krakow, Poland.

ORCID-Profile: Rasool Reddy Kamireddy, Rajesh N V P S Kandala

Zitieren

APA

Kamireddy, R. R., Kandala, R. N. V. P. S., Dhuli, R., Polinati, S., Sonti, K., Tadeusiewicz, R., & Pławiak, P. (2024). Brain MRI detection and classification: Harnessing convolutional neural networks and multi-level thresholding. PLOS ONE, 19(8), e0306492. https://doi.org/10.1371/journal.pone.0306492

Vancouver

Kamireddy RR, Kandala RNVPS, Dhuli R, Polinati S, Sonti K, Tadeusiewicz R, et al. Brain MRI detection and classification: Harnessing convolutional neural networks and multi-level thresholding. PLOS ONE. 2024;19(8):e0306492. doi:10.1371/journal.pone.0306492

BibTeX
@article{Kamireddy2024,
  author = {Kamireddy, Rasool Reddy and Kandala, Rajesh N V P S and Dhuli, Ravindra and Polinati, Srinivasu and Sonti, Kamesh and Tadeusiewicz, Ryszard and Pławiak, Paweł},
  title = {Brain MRI detection and classification: Harnessing convolutional neural networks and multi-level thresholding},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {8},
  pages = {e0306492},
  doi = {10.1371/journal.pone.0306492}
}
Kostenlos starten →