See you in two years!
11-16 April 2026
Conference 13006 > Paper 13006-52
Paper 13006-52

Cervical pre-cancer detection through wavelet denoising and random forest classification

10 April 2024 • 16:50 - 17:10 CEST | Etoile B, Niveau/Level 1

Abstract

We report a multi-class classification model built using random forest (RF) and synthetic minority oversampling technique (SMOTE) applied to extracted intrinsic fluorescence (IF) data to detect normal, pre-cancer, and cancer samples. Important features in the fluorescence signal often get suppressed by the noise which makes denoising an essential pre-processing step. The proposed algorithm implements a wavelet-based denoising technique as a pre-processing step before data analysis which utilizes the “coif3” mother wavelet function to denoise IF data. Synthetic minority oversampling technique (SMOTE) is utilized to generate a balanced dataset. We achieved the best classification for the denoised balanced dataset with accuracy, sensitivity, and specificity above 90% for normal/pre-cancer and precancer/cancer groups. Further, the receiver operating curve (ROC) shows a clear distinction among three grades with the area under curve (AUC) of 0.96 for normal and precancer samples and 1.00 for cancer samples. The python script prepared for this study is available on GitHub and Signal Science Lab.

Presenter

Gyana Ranjan Sahoo
Cornell Univ. (United States)
Gyana Ranjan Sahoo is working as Postdoctoral fellow in the Department of Chemistry & Chemical Biology, Cornell University. His research interests include signal processing, wavelet analysis, image segmentation, machine learning, optical spectroscopy and imaging diagnostics. Dr. Gyana Ranjan Sahoo received his Ph.D. degree in physics from Indian Institute of Technology Kanpur, India in 2020, and MSc. in Physics from Utkal University, Bhubaneswar, India in 2013.
Application tracks: AI/ML
Presenter/Author
Gyana Ranjan Sahoo
Cornell Univ. (United States)
Author
Indian Institute of Technology Kanpur (India)
Author
Cornell Univ. (United States)
Author
Asima Pradhan
Indian Institute of Technology Kanpur (India)