ANALISIS PERFORMA MODEL CNN MELALUI EVALUASI EKSTERNAL PADA SISTEM KLASIFIKASI CITRA MAMMOGRAFI BERBASIS WEBSITE LOKAL
DOI:
https://doi.org/10.36257/teliska.v19i3.12682Kata Kunci:
Klasifikasi Citra Mammografi, Convolutional Neural Network, Evaluasi Eksternal, Website LokalAbstrak
Kinerja model Convolutional Neural Network (CNN) dalam klasifikasi citra mammografi perlu dievaluasi menggunakan data yang tidak terlibat dalam proses pengembangan model untuk mengetahui kemampuan generalisasinya terhadap data dari sumber berbeda. Penelitian ini bertujuan menganalisis performa model CNN melalui evaluasi eksternal pada sistem klasifikasi citra mammografi berbasis website lokal. Metode yang digunakan adalah menerapkan model EfficientNetB2 yang telah dikembangkan sebelumnya pada 15 citra mammografi klinis sebagai data eksternal. Setiap citra dimasukkan ke dalam sistem untuk memperoleh hasil klasifikasi, kemudian hasil prediksi dibandingkan dengan label diagnosis pada data asli. Pada tahap pengembangan model, EfficientNetB2 menghasilkan accuracy sebesar 72%, precision sebesar 67%, recall sebesar 96% dan F1-score sebesar 79%. Hasil evaluasi eksternal menunjukkan bahwa 13 dari 15 citra menghasilkan prediksi yang sesuai dengan label diagnosis, sedangkan 2 citra menghasilkan prediksi yang tidak sesuai, dengan tingkat kesesuaian prediksi sebesar 86,67%. Berdasarkan confusion matrix, diperoleh accuracy sebesar 86,67%, precision sebesar 80%, recall sebesar 100%, dan F1-score sebesar 88,89%. Hasil evaluasi eksternal memberikan gambaran mengenai kemampuan generalisasi model ketika diterapkan pada data di luar lingkungan pengembangannya melalui sistem berbasis website lokal.
Referensi
S. Brown, S. R. Amend, R. H. Austin, R. A. Gatenby, E. U. Hammarlund, and K. J. Pienta, “Updating the Definition of Cancer.,” Mol. Cancer Res., vol. 21, no. 11, pp. 1142–1147, Nov. 2023, doi: 10.1158/1541-7786.MCR-23-0411.
F. Bray et al., “Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries,” CA. Cancer J. Clin., vol. 74, no. 3, pp. 229–263, 2024, doi: 10.3322/caac.21834.
A. M. Filho et al., “The GLOBOCAN 2022 cancer estimates: Data sources, methods, and a snapshot of the cancer burden worldwide,” Int. J. Cancer, vol. 156, no. 7, pp. 1336–1346, 2025, doi: 10.1002/ijc.35278.
W. H. Organization, “Breast cancer,” World Health Organization. Accessed: Aug. 05, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/breast-cancer
K. Loizidou, R. Elia, and C. Pitris, “Computer-aided breast cancer detection and classification in mammography: A comprehensive review,” Comput. Biol. Med., vol. 153, no. December 2022, p. 106554, 2023, doi: 10.1016/j.compbiomed.2023.106554.
N. Chotai, A. Gadwal, D. Buchireddy, and W. T. Yang, “Why we still miss breast cancers : strategies for improving mammography interpretation,” Insights Imaging, vol. 17, no. 1, p. 8, 2026, doi: 10.1186/s13244-025-02168-2.
L. Wang, “Mammography with deep learning for breast cancer detection,” Front. Oncol., vol. 14, no. February, pp. 1–16, 2024, doi: 10.3389/fonc.2024.1281922.
Z. A. Ansari, M. M. Tripathi, and R. Ahmed, “The role of explainable AI in enhancing breast cancer diagnosis using machine learning and deep learning models,” Discov. Artif. Intell., vol. 5, no. 1, 2025, doi: 10.1007/s44163-025-00307-8.
V. K. V., A. N. Nayak, and T. R. Arunkumar, “Sensitivity-Based Breast Cancer Characterization on CBIS-DDSM Mammography Dataset Using Fine-Tuned EfficientNet-B2 Model,” Int. J. Adv. Electr. Comput. Eng., vol. 15, no. 1S, pp. 365–371, 2026, doi: 10.65521/ijaece.v15i1s.1380.
J. Logan, P. J. Kennedy, and D. Catchpoole, “A review of the machine learning datasets in mammography, their adherence to the FAIR principles and the outlook for the future,” Sci. Data, vol. 10, no. 1, pp. 1–11, 2023, doi: 10.1038/s41597-023-02430-6.
A. Mračko, L. Vanovčanová, and I. Cimrák, “Mammography Datasets for Neural Networks—Survey,” J. Imaging, vol. 9, no. 5, 2023, doi: 10.3390/jimaging9050095.
H. R. Fajrin and S. D. Min, “From Machine Learning to Ensemble Approaches: A Systematic Review of Mammogram Classification Methods,” Diagnostics, vol. 15, no. 22, pp. 1–30, 2025, doi: 10.3390/diagnostics15222829.
D. P. Sari, M. Arya, and C. Putra, “Implementasi Pengenalan Wajah Berbasis CNN dan RFID untuk Area Akses Aman di Fasilitas Polsri dengan Hosting Lokal,” J. Teliska, vol. 17, no. II, pp. 23–31, 2024, doi: 10.5281/zenodo.13047545.
A. C. Yu, B. Mohajer, and J. Eng, “External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic Review,” Radiol. Artif. Intell., vol. 4, no. 3, pp. 1–9, 2022, doi: 10.1148/ryai.210064.
M. U. Suleman et al., “Assessing the generalizability of artificial intelligence in radiology: a systematic review of performance across different clinical settings,” Ann. Med. Surg., vol. 87, no. 12, pp. 8803–8811, 2025, doi: 10.1097/ms9.0000000000004166.
S. Matta et al., “A systematic review of generalization research in medical image classification,” Comput. Biol. Med., vol. 183, 2024, doi: 10.1016/j.compbiomed.2024.109256.
S. Chakravarthy et al., “Multi-class Breast Cancer Classification Using CNN Features Hybridization,” Int. J. Comput. Intell. Syst., vol. 17, no. 1, 2024, doi: 10.1007/s44196-024-00593-7.
D. Moslemi, S. M. Hassan Hosseini, E. Jafarian, and M. Jamshidi, “Benchmarking Deep Learning Algorithms for Breast Cancer Detection: A Comprehensive Review and Evaluation Across Public Imaging Datasets,” Infosci. Trends, vol. 2, no. 4, pp. 11–24, 2025, doi: 10.61186/ist.202502.04.02.
G. W. Purnama, A. Aan, J. Permana, and N. Ketut, “Klasifikasi Citra Medis Mamografi Berbasis Multi-View Convolutional Neural Networks,” J. Pendidik. Teknol. dan Kejuru., vol. 22, no. 2, pp. 162–171, 2025, doi: 10.23887/jptk-undiksha.v22i2.94691.
M. Tan and Q. V Le, “EfficientNet : Rethinking Model Scaling for Convolutional Neural Networks,” in Proceedings of the 36th International Conference on Machine Learning, Proceedings of Machine Learning Research (PMLR), 2019, pp. 6105–6114. [Online]. Available: https://proceedings.mlr.press/v97/tan19a.html
N. I. Fardana, R. R. Isnanto, and O. D. Nurhayati, “Pneumothorax Detection System in Thoracic Radiography Images Using CNN Method,” Sci. J. Informatics, vol. 11, no. 4, pp. 981–990, 2025, doi: 10.15294/sji.v11i4.16635.
Template Jurnal TELISKA 
