Implementasi Arsitektur U-Net Untuk Segmentasi Tumor Otak Otomatis Pada Citra MRI Dengan Data Pengujian Asli
Abstract
Tumor otak merupakan pertumbuhan sel abnormal yang mengganggu fungsi otak. Deteksi dini penting untuk meningkatkan akurasi diagnosis, namun segmentasi manual citra MRI memerlukan keahlian tinggi. Penelitian ini mengimplementasikan arsitektur U-Net sebagai metode segmentasi otomatis pada citra MRI menggunakan data asli dari Rumah Sakit Islam Jakarta Cempaka Putih. Eksperimen dilakukan dengan variasi epoch (20–100) dan Learning rate (1e-3 dan 1e-4). Konfigurasi terbaik diperoleh pada Learning rate 1e-4 dan 100 epoch dengan Dice Coefficient 0,88 dan IoU 0,78. Sistem U-Net ini dapat meningkatkan efisiensi dan akurasi diagnosis tumor otak. Kata kunci : Tumor otak, MRI, Segmentasi, U-Net, Deep Learning
Downloads
References
[1] I. B. L. M. Suta, M. Sudarma, and I. N. Satya Kumara,
“Segmentasi Tumor Otak Berdasarkan Citra
Magnetic Resonance Imaging Dengan Menggunakan
Metode U-NET,” Maj. Ilm. Teknol. Elektro, vol. 19,
no. 2, p. 151, 2020, doi:
10.24843/mite.2020.v19i02.p05.
[2] Kemenkes, “Panduan Penatalaksanaan Tumor Otak,”
Natl. Cancer Combat Comm., pp. 1–96, 2017,
[Online]. Available:
http://kanker.kemkes.go.id/guidelines.php?id=5.
[3] J. Ferlay et al., “Cancer statistics for the year 2022:
An overview,” Int. J. Cancer, vol. 149, no. 4, pp. 778–
789, 2022, doi: 10.1002/ijc.33588.
[4] N. S. Emril, D. R., Fajri, N., & Rahayu, “The New
Concept of Cancer Pain Management: Should We
Modify the WHO’s Step Ladder? The Challenges Of
Neurological Development In 4.0 Generation Of
Industrial Revolutionary Era,” vol. 3, no. 1, p. 296,
2020.
[5] Mukhlis Akhadi, “Sinar-X Menjawab Masalah
Kesehatan,” Deepublish, 2020.
[6] K. Munir, F. Frezza, and A. Rizzi, “Deep learning for
brain tumor segmentation,” Stud. Comput. Intell., vol.
908, pp. 189–201, 2021, doi: 10.1007/978-981-15-
6321-8_11.
[7] T. A. Soomro et al., “Deep Learning Models for
Retinal Blood Vessels Segmentation: A Review,”
IEEE Access, vol. 7, pp. 71696–71717, 2019, doi:
10.1109/ACCESS.2019.2920616.
[8] J. C. A. Vinay Kumar, Abul K. Abbas, Robbins and
Cotran’s pathologic basis of disease, 9th ed. Elsevier,
2020.
[9] A. Delaidelli and A. Moiraghi, “Recent Advances in
the Diagnosis and Treatment of Brain Tumors,” Brain
Sci., vol. 14, no. 3, 2024, doi:
10.3390/brainsci14030224.
[10]Brain Injury Law of Seattle, “Volumetric Analysis of
the Brain,” Online, 2024.
https://www.braininjurylawofseattle.com/what-is-avolumetric-analysis-of-the-brain/ (accessed Dec. 19,
2024)
[11]P. Prita, I. M. L. Prasetya, and R. Restiana, “Prosedur
Pemeriksaan Magnetic Resonance Imaging (Mri)
Pelvis Menggunakan Kontras Pada Kasus Fistula,” J.
Ilmu Kedokt. dan Kesehat., vol. 10, no. 10, pp. 2955–
2963, 2023, doi: 10.33024/jikk.v10i10.11798.
[12]Y. Yu et al., “Techniques and Challenges of Image
Segmentation: A Review,” Electron., vol. 12, no. 5,
2023, doi: 10.3390/electronics12051199.
[13]M. A. I. Fahim and S. A. Tumpa, “Image
Augmentation Techniques: Enhancing Deep Learning
Performance,” no. June, pp. 1–7, 2023, doi:
10.13140/RG.2.2.17295.97448.
[14]G. Kaur, P. S. Rana, and V. Arora, State-of-the-art
techniques using pre-operative brain MRI scans for
survival prediction of glioblastoma multiforme
patients and future research directions, vol. 10, no. 4.
Springer International Publishing, 2022.
[15]M. Karlık and B. Karlik, “Prediction of Student’s
Performance with Deep Neural Networks,” Int. J.
Artif. Intell. Expert Syst., vol. 9, no. 2, pp. 39–47,
2020.
[16]A. ANHAR and R. A. PUTRA, “Perancangan dan
Implementasi Self-Checkout System pada Toko Ritel
menggunakan Convolutional Neural Network
(CNN),” ELKOMIKA J. Tek. Energi Elektr. Tek.
Telekomun. Tek. Elektron., vol. 11, no. 2, p. 466,
2023, doi: 10.26760/elkomika.v11i2.466.
[17]N. Siddique, S. Paheding, C. P. Elkin, and V.
Devabhaktuni, “U-Net and Its Variants for Medical
Image Segmentation: A Review of Theory and
Applications,” IEEE Access, vol. 9, no. January 2021,
pp. 82031–82057, 2021, doi:
10.1109/ACCESS.2021.3086020.
[18]Y. Ding, F. Chen, Y. Zhao, Z. Wu, C. Zhang, and D.
Wu, “A Stacked Multi-Connection Simple Reducing
Net for Brain Tumor Segmentation,” IEEE Access,
vol. 7, pp. 104011–104024, 2019, doi:
10.1109/ACCESS.2019.2926448.
[19]J. Jordan, “Evaluating image segmentation models.,”
Jeremy Jordan Data Science, 2018.
https://www.jeremyjordan.me/evaluating-imagesegmentation-models/ (accessed Dec. 19, 2024).
[20]R. Padilla, S. L. Netto, and E. A. B. Silva,
“Proceedings of the 2020 International Conference on
Systems, Signals and Image Processing, IWSSIP
2020,” Int. Conf. Syst. Signals, Image Process., vol.
2020-July, pp. 237–242, 2020.
[21]C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and
M. Jorge Cardoso, “Generalised Dice overlap as a
deep learning Loss function for highly unbalanced
segmentations,” Lect. Notes Comput. Sci. (including
Subser. Lect. Notes Artif. Intell. Lect. Notes
Bioinformatics), vol. 10553 LNCS, pp. 240–248,
2017, doi: 10.1007/978-3-319-67558-9_28.
[22]H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I.
Reid, and S. Savarese, “Generalized intersection over
union: A metric and a Loss for bounding box
regression,” Proc. IEEE Comput. Soc. Conf. Comput.
Vis. Pattern Recognit., vol. 2019-June, pp. 658–666,
2019, doi: 10.1109/CVPR.2019.00075.
[23]D. W. Ayu and G. A. Pradipta, “Analisis Performansi
Parameter pada Arsitektur U-Net untuk Segmentasi
Nukleus pada Citra Kanker Serviks,” J. Sist. dan
Inform., vol. 18, no. 2, pp. 131–138, 2024, doi:
10.30864/jsi.v18i2.607.
[24]S. Jadon, “A survey of Loss functions for semantic
segmentation,” 2020 IEEE Conf. Comput. Intell.
Bioinforma. Comput. Biol. CIBCB 2020, 2020, doi:
10.1109/CIBCB48159.2020.9277638.
