Synthetic medical image generator for data augmentation and anonymisation based on generative adversarial network for glioblastoma tumors growth prediction. Issue 16 (24th February 2021)

• Record Type: Journal Article
• Authors: Kamli, Adel; Saouli, Rachida; Batatia, Hadj; Naceur, Mostefa Ben; Youkana, Imane
• Is Part Of: IET image processing. Volume 14:Issue 16(2020)
• Page Start: 4248
• Page End: 4257
• Publication Date: 2021-02-24
• Subjects: data privacy -- tumours -- neural nets -- cancer -- medical image processing; medical data -- synthetic medical image generator -- generative adversarial network -- anonymised data -- glioblastoma multiform tumour growth -- tumour growth predictor -- end convolution neural network architecture -- cancer imaging archive -- generated synthetic data -- data augmentation tool -- data size -- TCIA data -- valuable tumour growth prediction accuracy -- anonymisation -- glioblastoma tumors growth prediction -- prediction methods -- glioblastoma tumours growth; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.1141
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Prediction methods of glioblastoma tumours growth constitute a hard task due to the lack of medical data, which is mostly related to the patients' privacy, the cost of collecting a large medical data set, and the availability of related notations by experts. In this study, the authors propose a synthetic medical image generator (SMIG) with the purpose of generating synthetic data based on the generative adversarial network in order to provide anonymised data. In addition, to predict the glioblastoma multiform tumour growth the authors developed a tumour growth predictor based on end to end convolution neural network architecture that allows training on a public data set from the cancer imaging archive (TCIA), combined with the generated synthetic data. The authors also highlighted the impact of implicating a synthetic data generated using SMIG as a data augmentation tool. Despite small data size provided by TCIA data set, the obtained results demonstrate valuable tumour growth prediction accuracy.