Anais do Workshop de Micro-ondas (ISSN 2675-4460)
Published October 30, 2023 | Version v1
Conference paper Open

SPECIALIZED BRAIN TUMOR DETECTION SYSTEM FOR SUPERIOR VIEW OF CRANIAL MRI USING AI AND TINY ML TECHNIQUES

Authors/Creators

  • 1. Instituto Federal de Educação, Ciência e Tecnologia de São Paulo (IFSP)
  • 2. James Clerk Maxwell Laboratory for Microwaves and Applied Electromagnetism (LABMAX)

Description

With a high mortality rate, brain cancer is considered one of the deadliest cancers in the world and, being the only efficient way of detecting it by doing Cranial Magnetic Resonance Imaging (MRI), new methods and improvements are needed to reduce the number of people that die from this disease. Following this problem, this research seeks to develop an Artificial Intelligence (AI) developed through Edge Impulse© capable of fastening the process of detecting a brain tumor on the MR scan, which can reduce its mortality rate. At the end of the project, the AI could get an F1-Score of 94.5%.

Files

WMO-23-092_R4_P13.pdf

Files (796.5 kB)

Name Size Download all
md5:971f37bdaa1dbb1d281c9c0c2785972a
796.5 kB Preview Download

Additional details

References

  • MONTI, M. M.; LAUREYS, S.; OWEN, A. M. The vegetative state. Bmj, British Medical Journal Publishing Group, v. 341, 2010. DOI: 10.1136/bmj.c3765
  • FERLAY, J.; ERVIK, M.; LAM, F. et al. Global cancer observatory: cancer today. international agency for research on cancer. Lyon, France, 2020
  • DEANGELIS, L. M. Brain tumors. New England journal of medicine, Mass Medical Soc, v. 344, n. 2, p. 114–123, 2001
  • CROSBY, D.; BHATI, S.; BRINDLE, K. M. et al. Early detection of cancer. Science, v. 375, n. 6586, p. eaay9040, 2022. DOI: 10.1126/science.aay9040
  • HALEEM, A.; JAVAID, M.; KHAN, I. H. Current status and applications of artificial intelligence (ai) in medical field: An overview. Current Medicine Research and Practice, v. 9, n. 6, p. 231–237, 2019. ISSN 2352-0817. DOI: 10.1016/j.cmrp.2019.11.005
  • DE CARVALHO, A.; JUSTO, J. F.; ANGéLICO, B. A.; DE OLIVEIRA, A. M.; Da Silva Filho, J. I. Rotary inverted pendulum identification for control by paraconsistent neural network. IEEE Access, v. 9, p. 74155–74167, 2021. DOI: 10.1109/ACCESS.2021.3080176
  • XU, J.; LI, Z.; DU, B.; ZHANG, M.; LIU, J. Reluplex made more practical: Leaky relu. In: 2020 IEEE Symposium on Computers and Communications (ISCC). [S.l.: s.n.], 2020. p. 1–7. DOI: 10.1109/ISCC50000.2020.9219587
  • DIAB, M. S.; RODRIGUEZ-VILLEGAS, E. Performance evaluation of embedded image classification models using edge impulse for application on medical images. In: 44th Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC). [S.l.: s.n.], 2022. p. 2639–2642. DOI: 10.1109/EMBC48229.2022.9871108
  • VOSCO, N. Ai object detection on the edge: Making the right choice. Hailo, 2022
  • SASAKI, Y. et al. The truth of the f-measure. Teach tutor mater, v. 1, n. 5, p. 1–5, 2007
  • REDDY, V. J.; ELIUM, A.; HYMEL, S. et al. Edge impulse: An mlops platform for tiny machine learning. Proceedings of Machine Learning and Systems, v. 5, 2023. DOI: 10.48550/arXiv.2212.03332
  • ADINEGORO, A. F.; SUTAPA, G. N.; GUNAWAN, A. A. N. et al. Classification and segmentation of brain tumor using efficientnet-b7 and u-net. Asian Journal of Research in Computer Science, v. 15, n. 3, p. 1–9, 2023
  • CHERUKUR, R. What is int8 quantization and why is it popular for deep neural networks? Mathworks, 2019
  • ZULFIQAR, F.; BAJWA, U. I.; MEHMOOD, Y. Multi-class classification of brain tumor types from mr images using efficientnets. Biomedical Signal Processing and Control, Elsevier, v. 84, p. 104777, 2023. DOI: 10.1016/j.bspc.2023.104777