Classification of colorectal primer carcinoma from normal colon with mid-infrared spectra

TL;DR

This study employs Fourier transform mid-infrared spectroscopy combined with various machine learning models to distinguish between normal colon tissue and colorectal carcinoma in FFPE samples, aiming to improve diagnostic accuracy.

Contribution

It introduces a comprehensive approach using multiple classifiers and data filtering techniques to enhance tissue classification from mid-infrared spectra.

Findings

Random forest achieved highest accuracy

Filtering improved model performance

Deep neural networks performed comparably to traditional classifiers

Abstract

In this project, we used formalin-fixed paraffin-embedded (FFPE) tissue samples to measure thousands of spectra per tissue core with Fourier transform mid-infrared spectroscopy using an FT-IR imaging system. These cores varied between normal colon (NC) and colorectal primer carcinoma (CRC) tissues. We created a database to manage all the multivariate data obtained from the measurements. Then, we applied classifier algorithms to identify the tissue based on its yielded spectra. For classification, we used the random forest, a support vector machine, XGBoost, and linear discriminant analysis methods, as well as three deep neural networks. We compared two data manipulation techniques using these models and then applied filtering. In the end, we compared model performances via the sum of ranking differences (SRD).