Neural Network based classification of bone metastasis by primary cacinoma

TL;DR

This paper explores the use of neural networks to classify primary cancers based on multifractal parameters derived from metastatic carcinoma images, aiming to improve diagnostic accuracy.

Contribution

It introduces a neural network-based classification method for primary cancer identification using multifractal analysis, combining two techniques for enhanced diagnostics.

Findings

Neural networks effectively classify primary cancer types.

Multifractal parameters provide valuable features for diagnosis.

The method shows promising accuracy in preliminary tests.

Abstract

Neural networks have been known for a long time as a tool for different types of classification, but only just in the last decade they have showed their entire power. Along with appearing of hardware that is capable to support demanding matrix operations and parallel algorithms, the neural network, as a universal function approximation framework, turns out to be the most successful classification method widely used in all fields of science. On the other side, multifractal (MF) approach is an efficient way for quantitative description of complex structures [1] such as metastatic carcinoma, which recommends this method as an accurate tool for medical diagnostics. The only part that is missing is classification method. The goal of this research is to describe and apply a feed-forward neural network as an auxiliary diagnostic method for classification of multifractal parameters in order to determine primary cancer.