Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
Skip to main content
Fig. 1 | BMC Cancer

Fig. 1

From: CausalCervixNet: convolutional neural networks with causal insight (CICNN) in cervical cancer cell classification—leveraging deep learning models for enhanced diagnostic accuracy

Fig. 1

The CausalCervixNet framework begins with a preprocessing step where augmented images are generated using geometric transformations, color space transformations, kernel filters, random erasing, and image mixing. After preprocessing, the augmented images are inputted into a deep learning model, to extract feature maps. Following the final pooling layer, the network progresses through two key phases: 1) constructing a causality map containing estimations of pairwise causal relationships between features, and 2) flattening the feature maps while identifying causal factors associated with the target variable (y) using a novel causal inference scheme. The model's performance is evaluated using unseen test images, and assessed in terms of precision, recall, F1 score, and accuracy

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us