Erick Costa de Farias (Avtor), Christian Di Noia (Avtor), Changhee Han (Avtor), Evis Sala (Avtor), Mauro Castelli (Avtor), Leonardo Rundo (Avtor)

Povzetek

Robust machine learning models based on radiomic features might allow for accurate diagnosis, prognosis, and medical decision-making. Unfortunately, the lack of standardized radiomic feature extraction has hampered their clinical use. Since the radiomic features tend to be afected by low voxel statistics in regions of interest, increasing the sample size would improve their robustness in clinical studies. Therefore, we propose a Generative Adversarial Network (GAN)-based lesion-focused framework for Computed Tomography (CT) image Super-Resolution (SR); for the lesion (i.e., cancer) patch-focused training, we incorporate Spatial Pyramid Pooling (SPP) into GAN-Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE). At 2x SR, the proposed model achieved better perceptual quality with less blurring than the other considered state-of-the-art SR methods, while producing comparable results at 4x SR. We also evaluated the robustness of our mode's radiomic feature in terms of quantization on a diferent lung cancer CT dataset using Principal Component Analysis (PCA). Intriguingly, the most important radiomic features in our PCA-based analysis were the most robust features extracted on the GAN-super-resolved images. These achievements pave the way for the application of GAN-based image Super-Resolution techniques for studies of radiomics for robust biomarker discovery.

Ključne besede

Ni podatka o ključnih besedah

Podatki

Jezik: Angleški jezik
Leto izida:
Tipologija: 1.01 - Izvirni znanstveni članek
Organizacija: UL EF - Ekonomska fakulteta
UDK: 659.2:004
COBISS: 83224579 Povezava se bo odprla v novem oknu
ISSN: 2045-2322
Št. ogledov: 175
Št. prenosov: 59
Ocena: 0 (0 glasov)
Metapodatki: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Ostali podatki

Sekundarni jezik: Angleški jezik
Vrsta dela (COBISS): Članek v reviji
Strani: str. 1-12
Letnik: ǂVol. ǂ11
Zvezek: ǂart. ǂ21361
Čas izdaje: 2021
DOI: 10.1038/s41598-021-00898-z
ID: 14119237