Ensemble-Based CNN Approach for Gastric Cancer Classification in Histopathological Images
Resumo
Gastric cancer is one of the leading causes of cancer-related deaths worldwide and is often diagnosed at advanced stages. Histopathological analysis is essential for diagnosis but heavily relies on the specialist’s expertise and is prone to human error. This study presents the development of a model based on Convolutional Neural Networks (CNNs) for identifying gastric cancer in histopathological images. The approach incorporates transfer learning, data augmentation, cross-validation, and an ensemble combining ResNet101, MobileNet, and EfficientNetB3. The model achieved an accuracy of 95.09% and a Kappa score of 89.72%. The results highlight the model’s strong potential for practical application in supporting medical diagnosis.
Referências
W. Ribeiro, O. Santiago, S. Oliveira, J. Souza, B. Fassarella, Y. Almeida, D. Jesus, R. Pontes, Q. França, M. Fassarella, L. Santos, and F. Neves, “Câncer de estômago: fatores de risco, prevenção e tratamento,” Brazilian Journal of Implantology and Health Sciences, vol. 5, pp. 1098–1120, 2023.
E. C. Smyth, M. Nilsson, H. I. Grabsch, N. C. Van Grieken, and F. Lordick, “Gastric cancer,” Lancet, vol. 396, no. 10251, pp. 635–648, 2020.
X. Fu, S. Liu, C. Li, and J. Sun, “Mclnet: A multidimensional convolutional lightweight network for gastric histopathology image classification,” Biomedical Signal Processing and Control, vol. 80, p. 104319, 2023.
M. Kato, T. Nishida, K. Yamamoto et al., “Scheduled endoscopic surveillance controls secondary cancer after curative endoscopic resection for early gastric cancer: a multicentre retrospective cohort study by osaka university esd study group,” Gut, vol. 62, pp. 1425–1432, 2013.
Y. Zhao, B. Hu, Y. Wang, X. Yin, Y. Jiang, and X. Zhu, “Identification of gastric cancer with convolutional neural networks: a systematic review,” Multimedia Tools and Applications, vol. 81, no. 8, pp. 11 717–11 736, 2022.
H. Sharma, N. Zerbe, I. Klempert, O. Hellwich, and P. Hufnagl, “Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology,” Computerized Medical Imaging and Graphics, 2017. [Online]. DOI: 10.1016/j.compmedimag.2017.06.001
Y. Li, X. Li, X. Xie, and L. Shen, “Deep learning based gastric cancer identification,” in Proceedings of the IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA, 2018, pp. 182–185. [Online]. DOI: 10.1109/ISBI.2018.8363550
W. Hu, C. Li, X. Li, M. M. Rahaman, J. Ma, Y. Zhang, H. Chen, W. Liu, C. Sun, Y. Yao, H. Sun, and M. Grzegorzek, “Gashissdb: A new gastric histopathology image dataset for computer aided diagnosis of gastric cancer,” Computers in Biology and Medicine, vol. 142, p. 105207, 2022.
M. P. Yong, Y. C. Hum, K. W. Lai, Y. L. Lee, C. H. Goh, W. S. Yap, and Y. K. Tee, “Histopathological gastric cancer detection on gashissdb dataset using deep ensemble learning,” Diagnostics, vol. 13, no. 1793, 2023. [Online]. DOI: 10.3390/diagnostics13101793
A. Mumuni and F. Mumuni, “Data augmentation: A comprehensive survey of modern approaches,” Array, vol. 16, p. 100258, 2022.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016, [link].
N. Tajbakhsh, J. Y. Shin, S. R. Gurudu, R. T. Hurst, C. B. Kendall, M. B. Gotway, and J. Liang, “Convolutional neural networks for medical image analysis: full training or fine tuning?” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1299–1312, 2016.
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009, pp. 248–255.
TensorFlow Developers, “tf.keras.applications: Models with pre-trained weights,” [link], 2024, acessado em 29 de junho de 2025.
M. M. Taba, G. B. Junior, and R. M. de Souza, “A comparative study of shallow and deep fine-tuning for medical image classification,” Journal of Digital Imaging, vol. 35, pp. 456–468, 2022.
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY: Springer, 2009.
D. M. Powers, “Evaluation: From precision, recall and f-factor to roc, informedness, markedness correlation,” School of Informatics and Engineering, Flinders University, Adelaide, Australia, Tech. Rep., 2007.
E. C. Smyth, M. Nilsson, H. I. Grabsch, N. C. Van Grieken, and F. Lordick, “Gastric cancer,” Lancet, vol. 396, no. 10251, pp. 635–648, 2020.
X. Fu, S. Liu, C. Li, and J. Sun, “Mclnet: A multidimensional convolutional lightweight network for gastric histopathology image classification,” Biomedical Signal Processing and Control, vol. 80, p. 104319, 2023.
M. Kato, T. Nishida, K. Yamamoto et al., “Scheduled endoscopic surveillance controls secondary cancer after curative endoscopic resection for early gastric cancer: a multicentre retrospective cohort study by osaka university esd study group,” Gut, vol. 62, pp. 1425–1432, 2013.
Y. Zhao, B. Hu, Y. Wang, X. Yin, Y. Jiang, and X. Zhu, “Identification of gastric cancer with convolutional neural networks: a systematic review,” Multimedia Tools and Applications, vol. 81, no. 8, pp. 11 717–11 736, 2022.
H. Sharma, N. Zerbe, I. Klempert, O. Hellwich, and P. Hufnagl, “Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology,” Computerized Medical Imaging and Graphics, 2017. [Online]. DOI: 10.1016/j.compmedimag.2017.06.001
Y. Li, X. Li, X. Xie, and L. Shen, “Deep learning based gastric cancer identification,” in Proceedings of the IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA, 2018, pp. 182–185. [Online]. DOI: 10.1109/ISBI.2018.8363550
W. Hu, C. Li, X. Li, M. M. Rahaman, J. Ma, Y. Zhang, H. Chen, W. Liu, C. Sun, Y. Yao, H. Sun, and M. Grzegorzek, “Gashissdb: A new gastric histopathology image dataset for computer aided diagnosis of gastric cancer,” Computers in Biology and Medicine, vol. 142, p. 105207, 2022.
M. P. Yong, Y. C. Hum, K. W. Lai, Y. L. Lee, C. H. Goh, W. S. Yap, and Y. K. Tee, “Histopathological gastric cancer detection on gashissdb dataset using deep ensemble learning,” Diagnostics, vol. 13, no. 1793, 2023. [Online]. DOI: 10.3390/diagnostics13101793
A. Mumuni and F. Mumuni, “Data augmentation: A comprehensive survey of modern approaches,” Array, vol. 16, p. 100258, 2022.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016, [link].
N. Tajbakhsh, J. Y. Shin, S. R. Gurudu, R. T. Hurst, C. B. Kendall, M. B. Gotway, and J. Liang, “Convolutional neural networks for medical image analysis: full training or fine tuning?” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1299–1312, 2016.
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009, pp. 248–255.
TensorFlow Developers, “tf.keras.applications: Models with pre-trained weights,” [link], 2024, acessado em 29 de junho de 2025.
M. M. Taba, G. B. Junior, and R. M. de Souza, “A comparative study of shallow and deep fine-tuning for medical image classification,” Journal of Digital Imaging, vol. 35, pp. 456–468, 2022.
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY: Springer, 2009.
D. M. Powers, “Evaluation: From precision, recall and f-factor to roc, informedness, markedness correlation,” School of Informatics and Engineering, Flinders University, Adelaide, Australia, Tech. Rep., 2007.
Publicado
30/09/2025
Como Citar
SILVA, Camilly L. C.; VERAS, Rodrigo M. S.; BORGES, Rodrigo N.; SILVA, Ivan S.; MACHADO, Vinicius P.; BARBOSA, François F. R..
Ensemble-Based CNN Approach for Gastric Cancer Classification in Histopathological Images. In: WORKSHOP ON DIGITAL AND COMPUTATIONAL PATHOLOGY - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 38. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 382-385.
