Integration of DCNN Model for Brain Tumor Detection with PPIR Simulator

Authors

  • Dafina Xhako Polytechnic University of Tirana, Albania
  • Elda Spahiu Institute of Applied Physics, Tirana, Albania
  • Niko Hyka University of Medicine, Tirana, Albania
  • Suela Hoxhaj Polytechnic University of Tirana, Albania
  • Partizan Malkaj Polytechnic University of Tirana, Albania

Keywords:

ANN, cancer, Convolutional Deep Neural Nets, medical imaging, PPIR, forecast, training, simulation

Abstract

For several years we are focused in use of simulation in radiotherapy in Matlab environment establishing the first module for called PPIR 2014. This program uses Matlab to implement a number of simulation and computation techniques and applications in radiation and medical imaging. Important features for processing, visualizing, and calculating medical pictures in radiotherapy are offered by this program. With an emphasis on estimating the tumor normal tissue complication probability through the analysis of radiation interactions with individual tumor cells using virtual simulations and control probability, we enhanced the Eudmodel for histogram of dose and volume, in 2019. The 2019 release of the PPIR previews gave students additional chances to do realistic simulations of a fractioned treatment, based on the radiation sensitivity of tumor cells, tumor volume, cell density, and number of fractions. In 2023, under the project “Development of simulation and forecasting models and integration with the TCIA database of medical images”, we created a DCNN model that includes a thorough ontology of the various kinds of the most prevalent cancer types. In this work we represent the DCNN model and its applications on dataset loading, preparation for training, regularization, and other parameters. We integrated the PPIR 2023 adding the DCNN module as integral part of PPIR. The process of creation of the DCNN structure, reading the data, training, displaying the results and performance evaluation of the trained, using the validation dataset, is performed through PPIR GUI which can be enabling easy use by students, imaging technicians and radiological medicine professionals. The model that we proposed with DCNN, is adapted to function with large number of input data which are medical images taken with CT, MRI and PET technics. We offer a technique to facilitate the brain tumor detection simulation by altering the network's architecture. However, we seek to further the application of artificial neural networks in clinical diagnosis and decision-making.

Downloads

Download data is not yet available.

References

Joseph O Deasy, (2003); “A computational environment for radiotherapy research”, Med Phys. May; 30 (5): 979-85.

Brad Warkentin (2004), A TCP-NTCP estimation module using DVHs and known radiobiological models and parameter sets. University of Alberta, 11560 University Ave., Edmonton, AlbertaT6G IZ2 Canada

M. Goitein (1985), Calculation of the uncertainty in the dose delivered during radiation therapy, Medical Physics, Volume12, Issue5, September, Pages 608-612.

M. Zaider, L. Hanin, Med Phys. 38(2), 574-583 (2011).

Niko Hyka; Dafina Xhako, New method to calculate the tumor control probability for PPIR, https://doi.org/10.1063/1.5135450.

Niko Hyka et.al (2023), Using deep convolutional neural network to create a DCNN model for brain tumor detection, European Chemical Bulletin (ISSN 2063-5346), Volume -12, Special Issue-7: Page: 4979-4989.

Xhako, D., & Hyka, N. (2022). Artificial neural networks application in medical images. International Journal of Health Sciences, 6(S2), 10632–10639. https://doi.org/10.53730/ijhs.v6nS2.7829.

Jinming Zou, Yi Han, Sung-Sau So. Overview of Artificial Neural Networks, PubMed, January 2009, Methods in molecular biology (Clifton, N.J.) 458:14-22, DOI: 10.1007/978-1-60327-101-1_2.

Niko, H. et al. “Calculation Methods in Radiotherapy Using MATLAB.” Journal of International Environmental Application and Science 9 (2014): 205-210.

Dafina Hyka (Xhako), Niko Hyka, Developing numerical methods and simulations for trainings in radiotherapy. Science & Technologies, Nautical and environmental studies, Volume VIII, 2018, Number 2:

Nyoman Abiwinanda et al, Brain Tumor Classification Using Convolutional Neural Network, DOI: 10.1007/978-981-10-9035-6_33

Louis, David N et al. “The 2021 WHO Classification of Tumors of the Central Nervous System: a summary.” Neuro-oncology vol. 23,8 (2021): 1231-1251. doi:10.1093/neuonc/noab106

Clark, K., Vendt, B., Smith, K. et al. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. J Digit Imaging 26, 1045–1057 (2013). https://doi.org/10.1007/s10278-013-9622-7

Aggarwal, M., Tiwari, A.K., Sarathi, M. et al. An early detection and segmentation of Brain Tumor using Deep Neural Network. BMC Med Inform Decis Mak 23, 78 (2023). https://doi.org/10.1186/s12911-023-02174-8

Manu BN (2023). Brain MRI Tumor Detection and Classification. https://www.mathworks.com/matlabcentral/fileexchange/55107-brain-mri-tumor-detection-and-classification), MATLAB Central File Exchange. Retrieved AI4MED (2023) Artificial intelligence for medicine, https://ai4med.net

Dhabliya, D., Ugli, I.S.M., Murali, M.J., Abbas, A.H.R., Gulbahor, U. Computer Vision: Advances in Image and Video Analysis (2023) E3S Web of Conferences, 399, art. no. 04045, .

Tonk, A., Dhabliya, D., Sheril, S., Abbas, A.H.R., Dilsora, A. Intelligent Robotics: Navigation, Planning, and Human-Robot Interaction (2023) E3S Web of Conferences, 399, art. no. 04044, .

Downloads

Published

13.12.2023

How to Cite

Xhako, D. ., Spahiu, E. ., Hyka, N. ., Hoxhaj, S. ., & Malkaj, P. . (2023). Integration of DCNN Model for Brain Tumor Detection with PPIR Simulator . International Journal of Intelligent Systems and Applications in Engineering, 12(8s), 534–538. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/4184

Issue

Vol. 12 No. 8s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.

Most read articles by the same author(s)