Klasifikasi Multi-Kelas Kanker Payudara Berdasarkan Citra Mammogram Menggunakan Arsitektur EfficientNetV2
Abstract
Kanker payudara merupakan penyebab utama kematian wanita, di mana deteksi dini menggunakan citra mammogram bersifat krusial namun rentan kesalahan interpretasi manual akibat kelelahan visual dan kualitas citra. Pendekatan deep learning saat ini memiliki keterbatasan berupa kompleksitas komputasi yang tinggi dan umumnya terbatas pada klasifikasi biner. Penelitian ini mengembangkan sistem klasifikasi multikelas menggunakan arsitektur EfficientNetV2 yang efisien untuk mendeteksi lima kondisi, yaitu normal, benign mass, malignant mass, benign calcification, dan malignant calcification pada dataset DDSM dan CBIS-DDSM. Pengembangan model dilakukan melalui pembersihan data dan serangkaian skenario percobaan yang mencakup hyperparameter tuning, penanganan class imbalance dengan undersampling dan augmentasi, serta peningkatan kontras menggunakan CLAHE. Model dievaluasi menggunakan metrik akurasi, macro F1-score, dan weighted F1-score. Hasil penelitian menunjukkan bahwa konfigurasi optimizer AdamW, learning rate 1e-4, dan resolusi asli citra tanpa manipulasi tambahan menghasilkan performa terbaik dengan akurasi 94,71%, macro F1-score 73,87%, dan weighted F1-score 94,69%. Temuan ini mengindikasikan bahwa EfficientNetV2 bekerja dengan efektif pada data asli dan teknik penanganan class imbalance serta peningkatan kontras justru menurunkan kemampuan generalisasi model.
Kata kunci— kanker payudara, mammogram, EfficientNetV2, klasifikasi, class imbalance, CLAHE
References
WHO, “Breast cancer,” 13-Mar-2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/breast-cancer. [Accessed: 20-Apr-2025].
N. Rani, D. K. Gupta, and S. Singh, “Multi-class classification of breast cancer abnormality using transfer learning,” Multimedia Tools and Applications, vol. 83, no. 30, pp. 75085–75100, Feb. 2024, doi: 10.1007/s11042-023-17832-2.
S. S. Boudouh and M. Bouakkaz, “Breast cancer: new mammography dual-view classification approach based on pre-processing and transfer learning techniques,” Multimedia Tools and Applications, vol. 83, no. 8, pp. 24315–24337, Aug. 2023, doi: 10.1007/s11042-023-16431-5.
V. M. Tiryaki, “Deep Transfer Learning to Classify Mass and Calcification Pathologies from Screen Film Mammograms,” Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 12, no. 1, pp. 57–65, Mar. 2023, doi: 10.17798/bitlisfen.1190134.
M. Tan and Q. Le V., “EfficientNet: Rethinking model scaling for convolutional neural networks,” arXiv.org, May 28, 2019. https://arxiv.org/abs/1905.11946.
B. Zoph, V. Vasudevan, J. Shlens, and Q. Le V., “Learning transferable architectures for scalable image recognition,” arXiv.org, Jul. 21, 2017. https://arxiv.org/abs/1707.07012.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for Large-Scale image recognition,” arXiv.org, Sep. 04, 2014. https://arxiv.org/abs/1409.1556.
M. Alruwaili and W. Gouda, “Automated Breast cancer detection models based on transfer learning,” Sensors, vol. 22, no. 3, p. 876, Jan. 2022, doi: 10.3390/s22030876.
N. O. S. Oyebanji et al., “Enhancing breast cancer detection accuracy through transfer learning: A case study using efficient net,” World Journal of Advanced Engineering Technology and Sciences, vol. 13, no. 1, pp. 285–318, Sep. 2024, doi: 10.30574/wjaets.2024.13.1.0415.
W. Ansar, A. R. Shahid, B. Raza, and A. H. Dar, “Breast cancer detection and localization using MobileNet based transfer learning for mammograms,” in Communications in computer and information science, 2020, pp. 11–21. doi: 10.1007/978-3-030-43364-2_2.
M. Tan and Q. V. Le, “EfficientNetV2: Smaller models and faster training,” arXiv (Cornell University), Apr. 2021, doi: 10.48550/arxiv.2104.00298.
M. Hasan, “Deep Learning for Breast Cancer Detection: Comparative Analysis of ConvNeXT and EfficientNet,” pp. 1387–1391, Dec. 2024, doi: https://doi.org/10.1109/iccit64611.2024.11021905.
O. A. Abioye, A. E. Evwiekpaefe, and A. J. Awujoola, “Performance Evaluation of EfficientNetV2 Models on the Classification of Histopathological Benign Breast Cancer Images,” Science Journal of University of Zakho, vol. 12, no. 2, pp. 208–214, May 2024, doi: 10.25271/sjuoz.2024.12.2.1261.
E. A. Scuccimarra, “DDSM Mammography,” 2018. [Online]. Available: https://www.kaggle.com/datasets/skooch/ddsm-mammography/data. [Accessed: 01-May-2025].
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv (Cornell University), Dec. 2014, doi: 10.48550/arxiv.1412.6980.
M. C. Mukkamala and M. Hein, “Variants of RMSProp and Adagrad with Logarithmic Regret Bounds,” arXiv (Cornell University), pp. 2545–2553, Jun. 2017, doi: 10.48550/arxiv.1706.05507.
A. Brutzkus, A. Globerson, E. Malach, and S. Shalev-Shwartz, “SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data,” arXiv (Cornell University), Oct. 2017, doi: 10.48550/arxiv.1710.10174.
I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” arXiv.org, Nov. 14, 2017. https://arxiv.org/abs/1711.05101.
J. M. Johnson and T. M. Khoshgoftaar, “The Effects of Data Sampling with Deep Learning and Highly Imbalanced Big Data,” Information Systems Frontiers, vol. 22, no. 5, pp. 1113–1131, Jun. 2020, doi: 10.1007/s10796- 020-10022-7.
S. Yang, W. Xiao, M. Zhang, S. Guo, J. Zhao, and F. Shen, “Image Data augmentation for Deep Learning: A survey,” arXiv (Cornell University), Apr. 2022, doi: 10.48550/arxiv.2204.08610.
K. Zuiderveld, “Contrast limited adaptive histogram equalization,” in Graphics Gems IV, 1994, pp. 474–485.
M. Heath, K. Bowyer, D. Kopans, R. Moore, and W. P. Kegelmeyer, “The Digital Database for Screening Mammography,” in Proc. 5th Int. Workshop on Digital Mammography, M. J. YaZe, Ed. Madison, WI: Medical Physics Publishing, 2001, pp. 212–218, ISBN 1-930524-00-5.
R. S. Lee, F. Gimenez, A. Hoogi, K. K. Miyake, M. Gorovoy, and D. L. Rubin, “A curated mammography data set for use in computer-aided detection and diagnosis research,” Scientific Data, vol. 4, no. 1, p. 170177, Dec. 2017, doi: 10.1038/sdata.2017.177.
R. C. Gonzalez and R. E. Woods, Digital Image Processing. 2018.
J. L. Pech-Pacheco, G. Cristóbal, J. Chamorro-Martínez, and J. Fernández-Valdivia, “Diatom autofocusing in brightfield microscopy: a comparative study,” in Proc. 15th Int. Conf. Pattern Recognit. (ICPR), vol. 3, pp. 314–317, Sept. 2000.
S. Vajapeyam, “Understanding Shannon’s Entropy metric for Information,” arXiv.org, Mar. 24, 2014. https://arxiv.org/abs/1405.2061.
H. M and S. MN, “A review on Evaluation Metrics for Data Classification Evaluations,” International Journal of Data Mining & Knowledge Management Process, vol. 5, no. 2, pp. 01–11, Mar. 2015, doi: 10.5121/ijdkp.2015.5201.
M. C. H. Lee, J. Braet, and J. Springael, “Performance Metrics for multilabel emotion Classification: Comparing micro, macro, and weighted F1-Scores,” Applied Sciences, vol. 14, no. 21, p. 9863, Oct. 2024, doi: 10.3390/app14219863.
