Web-Based Implementation of a Logistic Regression Model for Rapid FNA Cytopathology Image Analysis in Breast Cancer Detection

Animesh Sahu*
Periodicity:April - June'2025

Abstract

Early detection of breast cancer significantly improves patient prognosis. Fine Needle Aspiration (FNA) cytopathology is a common diagnostic procedure, but its interpretation can be subjective and time-consuming. Machine learning (ML) models have shown promise in aiding this process. This paper details the design and implementation of a user-friendly, web-based application that leverages a pre-trained Logistic Regression model for the preliminary analysis of FNA cytopathology images. The system accepts a JPG image of an FNA slide, performs automated image segmentation and feature extraction, and subsequently feeds these parameters into the classification model to predict whether the sample indicates a benign or malignant tumor. The underlying Logistic Regression model, trained on the Wisconsin Breast Cancer Dataset, demonstrated a high accuracy of 97.07% on its test set. The web application, with its frontend deployed on GitHub Pages and backend on Render, provides an accessible platform for demonstrating the potential of ML in cytopathology, simplifying the input process to a single image upload and providing an immediate, interpretable result. This work highlights the practical application of existing ML research, making sophisticated analysis tools more accessible for educational, demonstrational, or preliminary assessment purposes. The complete source code is publicly available on GitHub.

Keywords

Breast Cancer, FNA Cytopathology, Machine Learning, Logistic Regression, Web Application, Image Analysis, Computer-Aided Diagnosis, Wisconsin Breast Cancer Dataset.

How to Cite this Article?

References

If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 15 15 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.