An Enhanced U-Net and CNN-based Tumor Edge Detection Technique in MR Images: U-Net & CNN for Tumor Detection in MRI

Muhammad Faris; Tariq Javid; Khalid  Mahmood; Danish  Aziz; Mir Farooq Ali; Muhamad Mansoor  Mughal

Authors

Muhammad Faris Department of Biomedical Engineering, Hamdard University, Karachi, Pakistan
Tariq Javid Department of Biomedical Engineering, Hamdard University, Karachi, Pakistan https://orcid.org/0000-0001-7476-8862
Khalid Mahmood Department of Biomedical Engineering, Hamdard University, Karachi, Pakistan
Danish Aziz Analog Devices, Munich, Germany
Mir Farooq Ali Marche, Polytechnic University, Ancona, Italy
Muhamad Mansoor Mughal Hamdard University/University of Houston

Keywords:

Cancer diagnosis, Deep learning, Medical image processing, Spatial resolution, Tumor edge detection

Abstract

Tumor edge detection and segmentation are crucial in cancer diagnosis and monitoring. Existing methods are limited to detecting complex tumour edges because of their low spatial resolution. This results in inaccurate detection of tumour boundaries. Deep learning (DL) based approaches have recently emerged as a promising solution for improving the accuracy of tumour detection. We propose an ensemble DL-based U-net and CNN model for tumour edge detection, segmentation, and classification. The model uses Leaky ReLU instead of ReLU and dice loss as a function. It was evaluated on the BraTS 2020 dataset of a diverse range of MR images. It achieves an accuracy of 0.9928, precision of 0.9935, sensitivity of 0.991, and specificity of 0.9978 on BraTS 2020. The algorithm was deployed on a Linux-based embedded Edge AI system combining the processing powers of Nvidia Jetson Nano and Google Coral USB AI Accelerator for faster computation than regular desktops. It is a portable, low-powered, cost-effective, and time-efficient system.

DOI: https://doi.org/10.59564/amrj/03.01/019

Author Biographies

Muhammad Faris, Department of Biomedical Engineering, Hamdard University, Karachi, Pakistan

Assistant Professor

Tariq Javid, Department of Biomedical Engineering, Hamdard University, Karachi, Pakistan

Professor

Khalid Mahmood, Department of Biomedical Engineering, Hamdard University, Karachi, Pakistan

Service Engineer

Danish Aziz, Analog Devices, Munich, Germany

Field Service Engineer, Technical Support

Mir Farooq Ali, Marche, Polytechnic University, Ancona, Italy

PhD Scholar, Department of Information Engineering

Muhamad Mansoor Mughal, Hamdard University/University of Houston

Sr. Lecturer/PhD Scholar, Department of Electrical and Computer Engineering

References

R. Bryan, C. Kagadis, Introduction to the Science of Medical Imaging, Medical Physics 2011;

DOI: https://doi.org/10.1017/CBO9780511994685.008

T. Vlaardingerbroek, A. Boer, Magnetic resonance imaging: theory and practice. Springer Science & Business Media, 2013; D

DOI: https://doi.org/10.1007/978-3-662-05252-5

C. Dickerson, Advances in functional magnetic resonance imaging: technology and clinical applications, Neurotherapeutics, 2007; DOI:10.1016/B978-0-323-91842-8.22001-6

H. Mohammad, A. David, A. Aaron, Y. Bengio, C. Pal, P. Jodoin, H. Larochelle, Brain tumor segmentation with deep neural networks, Medical image analysis. 2017; 35:

DOI: https://doi.org/10.1016/j.media.2016.05.004

M. Sbaraglia, E. Bellan, P. Angelo, The 2020 WHO classification of soft tissue tumours: news and perspectives, Pathologica 2021;

DOI: https://doi.org/10.32074/1591-951X-213

K. Haaf, Informing Patient Surveillance for the Growing Number of Survivors of Lung Cancer, Journal of Thoracic Oncology 2022;

DOI: https://doi.org/10.1016/j.jtho.2021.12.003

D. Hanahan, Hallmarks of cancer: new dimensions, Cancer discovery, 2022:

DOI: https://doi.org/10.1158/2159-8290.CD-21-1059

R. Baghban, L. Roshangar, R. Jahanban-Esfahlan, K. Seidi, A. Ebrahimi-Kalan, M. Jaymand, S. Kolahian, T. Javaheri, P. Zare, Tumor microenvironment complexity and therapeutic implications at a glance, Cell Communication and Signaling, 2020:

DOI: https://doi.org/10.1186/s12964-020-0530-4

M. Arabahmadi, R. Farahbakhsh, J. Rezazadeh, Deep learning for smart Healthcare—A survey on brain tumor detection from medical imaging, Sensors, 2022:

DOI: https://doi.org/10.3390/s22051960

WL. Bi, A. Hosny, MB. Schabath, ML. Giger, NJ. Birkbak, A. Mehrtash, T. Allison et al., Artificial intelligence in cancer imaging: clinical challenges and applications, CA: a cancer journal for clinicians, 2019.

DOI: https://doi.org/10.3322/caac.21552

B. Amreen, B. Yung-Cheol, Brain tumor detection with integrating traditional and computational intelligence approaches across diverse imaging modalities-Challenges and future directions, Computers in Biology and Medicine, 2024.

DOI: https://doi.org/10.1016/j.compbiomed.2024.108412

N. Neelum, S. Palaniappan, A. Qayyum, I. Ahmad, M. Imran, M. Shoaib, A deep learning model based on concatenation approach for the diagnosis of brain tumor. IEEE Access 2020; 8:55135-55144.

DOI: https://doi.org/10.1109/ACCESS.2020.2978629

I. Lauriola, A. Lavelli, F. Aiolli, An introduction to deep learning in natural language processing: Models, techniques, and tools, Neurocomputing 2022;

DOI: https://doi.org/10.1016/j.neucom.2021.05.103.

G. Mudasir, M. Hu, A. Malik, M. Tanveer, P. Suganthan, Ensemble deep learning: A review. Engineering Applications of Artificial Intelligence. 2022;

DOI: https://doi.org/10.1016/j.engappai.2022.105151

K. Charnpreet, U. Garg, Artificial intelligence techniques for cancer detection in medical image processing: A review. Materials Today, Proceedings. 2023;

DOI: https://doi.org/10.1016/j.matpr.2021.04.241

A. Asra, E. Khan, M. Sufyan, Improved edge detection algorithm for brain tumor segmentation. Procedia Computer Science. 2015;

DOI: https://doi.org/10.1016/j.procs.2015.08.057

Jagannadham, S. L., Nadh, K. L., and Sireesha, M. (2021, November). Brain Tumour Detection Using CNN 2021, Fifth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud). 2021;

Kim, M., and Lee, B. D. 2021. A simple generic method for effective boundary extraction in medical image segmentation. IEEE Access, 9. 2021;

DOI: https://doi.org/10.1109/ACCESS.2021.3099936

H. Mawaddah, A. Mahmud, S. Singh, S. Singh, S. DP Situmorang, J. Saputra, Comparative analysis of deep learning approach for detection and segmentation of brain tumor. In 2022 IEEE International Conference of Computer Science and Information Technology (ICOSNIKOM), IEEE. 2022;

DOI: https://doi.org/10.1109/icosnikom56551.2022.10034876

B. Neha, M. Sood, S. Gill, Deep learning framework using CNN for brain tumor classification. 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT), 2022:

DOI:https://doi.org/10.1109/IMPACT55510.2022.10029043

A. Muhammad, Z. Rahman, Z. Dayo, W. Abro, M. Uddin, I. Khan, A. Imran, A deep learning approach for brain tumor classification using MRI images. Computers and Electrical Engineering. 2022;

DOI: https://doi.org/10.1016/j.compeleceng.2022.108105

Y. Ayesha, L. Qiang, C. Nyatega, M. Jajere, H. Kawuwa. Brain tumor analysis using deep learning and VGG-16 ensembling learning approaches. Applied Sciences, 2022;

DOI: https://doi.org/10.3390/app12147282

P. Suraj, D. Kirange, Ensemble of deep learning models for brain tumor detection. Procedia Computer Science. 2023;

DOI: https://doi.org/10.1016/j.procs.2023.01.222

P. Rao, B. Rao, K. Patro, J. Allam, M.Jamjoom, N. Samee, A novel approach for brain tumour detection using deep learning based technique. Biomedical Signal Processing and Control, 2023;

DOI: https://doi.org/10.1016/j.bspc.2022.104549

E. Omar, Y. Hmamouche, A. Idrissi, B. Khamlichi, A. Seghrouchni, Refined edge detection with cascaded and high-resolution convolutional network. Pattern Recognition. 2023;

DOI: https://doi.org/10.1016/j.patcog.2023.109361