Variable Kernel Feature Fusion and Transfer Learning for Pap Smear Image-Based Cervical Cancer Classification DOI Open Access

S. Priya,

V. Mary Amala Bai

International Journal of Electronics and Communication Engineering, Journal Year: 2024, Volume and Issue: 11(11), P. 228 - 243

Published: Nov. 30, 2024

Cervical cancer, a malignant tumour that forms in the cervix, significantly contributes to cancer-related mortality among women globally, making early diagnosis crucial for effective treatment. Pap smear images, which are microscopic images of cervical cells, commonly used detection abnormal cells may lead cancer. This study introduces novel classification approach, Variable Kernel Feature Fusion-CNN (VKFF-CNN), improves performance by fusing multi-scale features using convolutional layers with 3x3, 4x4, and 5x5 kernels. architecture captures diverse set features, enhancing ability model accurately classify cells. With an average accuracy 98.03%, precision 97.83%, recall 97.11%, F1 score 98.23%, VKFF-CNN exhibited outstanding outcomes on Herlev Smear dataset. These results demonstrate outperforms traditional machine learning models. The model's confusion matrix indicated fewer misclassifications, underscoring its robustness effectiveness. Including batch normalization softmax activation function further enhanced stability accurate classification. Overall, presents promising advancement automated cancer screening, providing highly reliable detection.

Language: Английский

Variable Kernel Feature Fusion and Transfer Learning for Pap Smear Image-Based Cervical Cancer Classification DOI Open Access

S. Priya,

V. Mary Amala Bai

International Journal of Electronics and Communication Engineering, Journal Year: 2024, Volume and Issue: 11(11), P. 228 - 243

Published: Nov. 30, 2024

Cervical cancer, a malignant tumour that forms in the cervix, significantly contributes to cancer-related mortality among women globally, making early diagnosis crucial for effective treatment. Pap smear images, which are microscopic images of cervical cells, commonly used detection abnormal cells may lead cancer. This study introduces novel classification approach, Variable Kernel Feature Fusion-CNN (VKFF-CNN), improves performance by fusing multi-scale features using convolutional layers with 3x3, 4x4, and 5x5 kernels. architecture captures diverse set features, enhancing ability model accurately classify cells. With an average accuracy 98.03%, precision 97.83%, recall 97.11%, F1 score 98.23%, VKFF-CNN exhibited outstanding outcomes on Herlev Smear dataset. These results demonstrate outperforms traditional machine learning models. The model's confusion matrix indicated fewer misclassifications, underscoring its robustness effectiveness. Including batch normalization softmax activation function further enhanced stability accurate classification. Overall, presents promising advancement automated cancer screening, providing highly reliable detection.

Language: Английский

Citations

0