AUTHORS: Marcadent S, Hofmeister J, Preti MG, Martin S, Van De Ville D, Montet X

Radiology: Artificial Intelligence, 2(3): , May 2020

ABSTRACT

A generative adversarial network accurately translates texture between manufacturers at image level on chest radiographs, reduces the intermanufacturer variability of radiomic features, and improves radiomic diagnostic accuracy, allowing for improving retrospective and multicenter radiomic studies.

Purpose

To assess the contribution of a generative adversarial network (GAN) to improve intermanufacturer reproducibility of radiomic features (RFs).

Materials and Methods

The authors retrospectively developed a cycle-GAN to translate texture information from chest radiographs acquired using one manufacturer (Siemens) to chest radiographs acquired using another (Philips), producing fake chest radiographs with different textures. The authors prospectively evaluated the ability of this texture-translation cycle-GAN to reduce the intermanufacturer variability of RFs extracted from the lung parenchyma. This study assessed the cycle-GAN’s ability to fool several machine learning (ML) classifiers tasked with recognizing the manufacturer on the basis of chest radiography inputs. The authors also evaluated the cycle-GAN’s ability to mislead radiologists who were asked to perform the same recognition task. Finally, the authors tested whether the cycle-GAN had an impact on radiomic diagnostic accuracy for chest radiography in patients with congestive heart failure (CHF).

Results

RFs, extracted from chest radiographs after the cycle-GAN’s texture translation (fake chest radiographs), showed decreased intermanufacturer RF variability. Using cycle-GAN–generated chest radiographs as inputs, ML classifiers categorized the fake chest radiographs as belonging to the target manufacturer rather than to a native one. Moreover, cycle-GAN fooled two experienced radiologists who identified fake chest radiographs as belonging to a target manufacturer class. Finally, reducing intermanufacturer RF variability with cycle-GAN improved the discriminative power of RFs for patients without CHF versus patients with CHF (from 55% to 73.5%, P < .001).

Conclusion

Both ML classifiers and radiologists had difficulty recognizing the chest radiographs’ manufacturer. The cycle-GAN improved RF intermanufacturer reproducibility and discriminative power for identifying patients with CHF. This deep learning approach may help counteract the sensitivity of RFs to differences in acquisition.

BibTex

Module: