COMPARISON OF RESNET-50 AND DENSENET-121 CNNARCHITECTURES FOR MALARIA IMAGE CLASSIFICATION
Abstract
Abstract: Malaria remains a major global health problem, particularly in tropical countries such as Indonesia. Accurate early diagnosis is essential for reducing malaria-related morbidity and mortality. Conventional microscopic examination is time-consuming, highly dependent on expert personnel, and prone to human error. This study compares the performance of two Convolutional Neural Network (CNN) architectures, ResNet-50 and DenseNet-121, for malaria image classification. The Cell Images for Malaria dataset provided by the National Institutes of Health (NIH) through Kaggle was used, consisting of 27,558 microscopic blood cell images categorized into Parasitized and Uninfected classes. The dataset was divided into 80% training data and 20% testing data. Image preprocessing included resizing to 224 × 224 pixels, normalization, labeling, and data augmentation using RandomFlip, RandomRotation, RandomZoom, and RandomContrast. Experimental results showed that the ResNet-50 model trained for 100 epochs achieved the highest performance, with an accuracy of 95.54% and precision, recall, and F1-score of 0.96. The confusion matrix indicated 5,272 correctly classified images out of 5,510 testing samples. These findings demonstrate that ResNet-50 outperformed DenseNet-121 and has strong potential for supporting accurate, reliable, and efficient computer-aided malaria diagnosis based on microscopic blood smear images.
Keywords: computer-aided diagnosis; convolutional neural network (CNN); densenet-121; early detection; image classification; malaria; microscopic blood smear images; resnet-50;
Abstrak : Malaria masih menjadi masalah kesehatan global yang serius, terutama di negara tropis seperti Indonesia. Diagnosis dini yang akurat sangat penting untuk menurunkan angka morbiditas dan mortalitas. Metode konvensional berupa pemeriksaan mikroskopis memiliki keterbatasan karena memerlukan waktu yang relatif lama, bergantung pada tenaga ahli, dan berpotensi menimbulkan kesalahan manusia. Penelitian ini bertujuan membandingkan kinerja arsitektur Convolutional Neural Network (CNN) yaitu ResNet-50 dan DenseNet-121 dalam klasifikasi citra malaria. Dataset yang digunakan berasal dari Cell Images for Malaria yang disediakan oleh National Institutes of Health (NIH) melalui platform Kaggle, terdiri dari 27.558 citra dengan pembagian 80% data latih, 20% data validasi. Tahap praproses meliputi cleaning, resizing citra menjadi 224×224 piksel, normalisasi, labeling, serta data augmentasi menggunakan RandomFlip, RandomRotation, RandomZoom, dan RandomContrast. Hasil pengujian menunjukkan bahwa model ResNet-50 pada epoch 100 memperoleh akurasi sebesar 95,54% dengan nilai precision, recall, dan F1-score masing-masing sebesar 0,96. Confusion matrix menunjukkan jumlah prediksi benar sebanyak 5.272 dari total 5.510 data uji. Hasil ini menunjukkan bahwa arsitektur CNN mampu mengklasifikasikan citra malaria dengan tingkat akurasi yang tinggi dan memiliki kemampuan generalisasi yang baik terhadap data baru. Penelitian ini memberikan kontribusi dalam evaluasi performa arsitektur CNN untuk mendukung pengembangan sistem diagnosis malaria berbasis citra mikroskopis yang lebih cepat dan akurat.
Kata kunci: convolutional neural network (CNN); citra mikroskopis hapusan darah; densenet-121; diagnosis berbantuan komputer; deteksi dini; klasifikasi citra; malaria; resnet-50
References
N. Huda, S. Y. Prayogi, M. A. Ahmad, and A. Y. Dewi, “Klasifi kasi Malaria Menggunakan Meto de Image Processing Dari Sel Darah Merah Dengan Algoritma Convolutional Neural Network,” JOINS (Journal Inf. Syst., vol. 7, no. 2, pp. 166–177, 2022, doi: 10.33633/joins.v7i2.7068.
WHO, “Kasus malaria di indone sia,” 2021, [Online]. Available: https://www.who.int/indonesia/news/campaign/world-malaria-day-2021#:~:text=Berdasarkan data World Malaria Report,) menjadi 658.000 (2019).
A. Loddo, C. Fadda, and C. Di Ruberto, “An Empirical Evalua tion of Convolutional Networks for Malaria Diagnosis,” J. Imag ing, vol. 8, no. 3, 2022, doi: 10.3390/jimaging8030066.
R. A. Hasyani, S. M. Simbolon, Y. Mufida, Y. Ester, and B. Ritonga, “Klasifikasi Malaria melalui Penggunaan Convolutio nal Neural Network pada Citra Sel Darah,” Student Res. J., vol. 1, no. 6, 2023, [Online]. Available: https://doi.org/10. 55606/srjyappi.v1i6.853
N. K. C. PRATIWI, N. IBRAHIM, Y. N. FU’ADAH, and S. RIZAL, “Deteksi Parasit Plasmodium pada Citra Mikrosko pis Hapusan Darah dengan Metode Deep Learning,” ELKO MIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 9, no. 2, p. 306, 2021, doi: 10.26760/elkomika.v9i2.306.
T. Jameela, K. Athota, N. Singh, V. K. Gunjan, and S. Kahali, “Deep Learning and Transfer Learning for Malaria Detection,” vol. 2022, 2022.
A. Yusuf, Y. Azhar, and Z. Sari, “Deteksi Penyakit Malaria Meng gunakan Klasifikasi Berbasis CNN,” Syntax Lit. ; J. Ilm. Indo nes., vol. 9, no. 1, pp. 168–177, 2024, doi: 10.36418/syntax-literate.v9i1.14771.
J. G. Purnomo, S. Birowo, and M. A. Maulana, “Identifikasi Malaria Pada Citra Darah Dengan Convolutional Neural Network,” vol. 7, no. 2, pp. 0–6, 2024, doi: 10.32877/bt.v7i2.18 28.
K. Hemachandran et al., “Performance Analysis of Deep Learning Algorithms in Diagnosis of Malaria Disease,” Diagnostics, vol. 13, no. 3, 2023, doi: 10.3390/diagnostics13030534.
Aris Muhandisin and Y. Azhar, “Malaria Blood Cell Image Classi fication using Transfer Learning with Fine-Tune ResNet50 and Data Augmentation,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 5, pp. 891–897, 2022, doi: 10.29207 /resti.v6i5.4322.
A. Kareem, H. Liu, and V. Velisa vljevic, “A Privacy-Preserving Approach to Effectively Utilize Distributed Data for Malaria Image Detection,” Bioengineering, vol. 11, no. 4, 2024, doi: 10.3390/bioengineering11040340.
A. A. Laghari, W. Muhammad, M. L. Memon, A. Hussain, and A. Kumar, “Malaria Parasite Cell Classification Using Transfer Learning with State-of-the-Art CNN Architectures,” pp. 1–21, 2025.
