Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases

Elisabeth Sartoretti,Sabine Sartoretti-Schefer,Thomas Sartoretti,Luuk Van Smoorenburg,Carolin Reischauer,Manoj Mannil,Christoph A Binkert,Michael Wyss

doi:10.1038/s41598-021-85168-8

Abstract

We sought to evaluate the utility of radiomics for Amide Proton Transfer weighted (APTw) imaging by assessing its value in differentiating brain metastases from high- and low grade glial brain tumors. We retrospectively identified 48 treatment-naïve patients (10 WHO grade 2, 1 WHO grade 3, 10 WHO grade 4 primary glial brain tumors and 27 metastases) with either primary glial brain tumors or metastases who had undergone APTw MR imaging. After image analysis with radiomics feature extraction and post-processing, machine learning algorithms (multilayer perceptron machine learning algorithm; random forest classifier) with stratified tenfold cross validation were trained on features and were used to differentiate the brain neoplasms. The multilayer perceptron achieved an AUC of 0.836 (receiver operating characteristic curve) in differentiating primary glial brain tumors from metastases. The random forest classifier achieved an AUC of 0.868 in differentiating WHO grade 4 from WHO grade 2/3 primary glial brain tumors. For the differentiation of WHO grade 4 tumors from grade 2/3 tumors and metastases an average AUC of 0.797 was achieved. Our results indicate that the use of radiomics for APTw imaging is feasible and the differentiation of primary glial brain tumors from metastases is achievable with a high degree of accuracy.

Highlights

Amide proton transfer weighted (APTw) imaging represents a novel contrast media free molecular MR imaging technique that has recently shown promise in characterizing and differentiating brain neoplasms as well as malignancies in other body regions[1,2,3,4,5,6,7]
The Multilayer Perceptron classifier yielded a sensitivity of 81.3%, a specificity of 81.1%, a recall of 0.81, F-measure 0.81, and an area under the curve (AUC) in receiver operating characteristics (ROC) of 0.836 (Fig. 2) in distinguishing primary brain tumors from metastases
Our results indicate that the application of radiomics to Amide Proton Transfer weighted (APTw) imaging is feasible and allows for the differentiation of these brain neoplasms

Summary

Introduction

Amide proton transfer weighted (APTw) imaging represents a novel contrast media free molecular MR imaging technique that has recently shown promise in characterizing and differentiating brain neoplasms as well as malignancies in other body regions[1,2,3,4,5,6,7]. The APTw signal originates from amide protons in endogeneous proteins and peptides in the parenchyma. The content of mobile proteins and peptides is increased resulting in increased APTw signal intensity v alues[8,9]. With the exception of one s tudy[10], these previous investigations utilized standard histogram analyses techniques at the most to analyse the APTw signal of the tissue at hand only scratching the surface of the information that can potentially be extracted from radiological images[1,2,3]. With recent advances in the field of machine learning (ML), radiomics techniques allowing for the extraction of high-dimensional mineable data from medical images have been developed and introduced to medical imaging enabling in-depth tissue classification and c haracterization[11,12,13,14,15]

Methods

Results

Conclusion