Domain Mapping and Deep Learning from Multiple MRI Clinical Datasets for Prediction of Molecular Subtypes in Low Grade Gliomas
Artikel i vetenskaplig tidskrift, 2020

Brain tumors, such as low grade gliomas (LGG), are molecularly classified which require the surgical collection of tissue samples. The pre-surgical or non-operative identification of LGG molecular type could improve patient counseling and treatment decisions. However, radiographic approaches to LGG molecular classification are currently lacking, as clinicians are unable to reliably predict LGG molecular type using magnetic resonance imaging (MRI) studies. Machine learning approaches may improve the prediction of LGG molecular classification through MRI, however, the development of these techniques requires large annotated data sets. Merging clinical data from different hospitals to increase case numbers is needed, but the use of different scanners and settings can affect the results and simply combining them into a large dataset often have a significant negative impact on performance. This calls for efficient domain adaption methods. Despite some previous studies on domain adaptations, mapping MR images from different datasets to a common domain without affecting subtitle molecular-biomarker information has not been reported yet. In this paper, we propose an effective domain adaptation method based on Cycle Generative Adversarial Network (CycleGAN). The dataset is further enlarged by augmenting more MRIs using another GAN approach. Further, to tackle the issue of brain tumor segmentation that requires time and anatomical expertise to put exact boundary around the tumor, we have used a tight bounding box as a strategy. Finally, an efficient deep feature learning method, multi-stream convolutional autoencoder (CAE) and feature fusion, is proposed for the prediction of molecular subtypes (1p/19q-codeletion and IDH mutation). The experiments were conducted on a total of 161 patients consisting of FLAIR and T1 weighted with contrast enhanced (T1ce) MRIs from two different institutions in the USA and France. The proposed scheme is shown to achieve the test accuracy of 74.81% on 1p/19q codeletion and 81.19% on IDH mutation, with marked improvement over the results obtained without domain mapping. This approach is also shown to have comparable performance to several state-of-the-art methods.

domain mapping

CycleGAN

deep learning

brain tumor

IDH genotype

1p/19q codeletion

Författare

Muhaddisa Barat Ali

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Signalbehandling

Irene Yu-Hua Gu

Chalmers, Elektroteknik

MS Berger

University of California

Johan Pallud

Université Paris-Saclay

Derek Southwell

University of California

Georg Widhalm

Univ Hosp Vienna

Alexandre Roux

Université Paris-Saclay

Tomas Gomez Vecchio

Göteborgs universitet

Asgeir Store Jakola

Göteborgs universitet

Brain Sciences

2076-3425 (eISSN)

Vol. 10 7 463

Ämneskategorier

Elektroteknik och elektronik

Datavetenskap (datalogi)

DOI

10.3390/brainsci10070463

PubMed

32708419

Mer information

Senast uppdaterat

2020-09-17