Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images

TL;DR

This study compares CNN and classical methods for classifying lymph node metastasis in lung cancer from PET/CT images, finding similar performance but highlighting CNN's convenience and potential for improvement with diagnostic features.

Contribution

The paper evaluates CNN against classical methods and human experts, emphasizing CNN's advantages and identifying future integration of diagnostic features as a key research direction.

Findings

CNN performance is comparable to classical methods and doctors.

CNN is more convenient and objective without needing segmentation.

Incorporating diagnostic features could improve CNN accuracy.

Abstract

The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images. Because CNN does not need tumor segmentation or feature calculation, it is more convenient and more objective than the classical methods. However, CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes. Therefore, incorporating the diagnostic features into CNN is a promising direction for future research.