Applications and limitations of radiomics

SSF Yip, HJWL Aerts - Physics in Medicine & Biology, 2016 - iopscience.iop.org
Radiomics is an emerging field in quantitative imaging that uses advanced imaging features
to objectively and quantitatively describe tumour phenotypes. Radiomic features have …

False discovery rates in PET and CT studies with texture features: a systematic review

A Chalkidou, MJ O'Doherty, PK Marsden - PloS one, 2015 - journals.plos.org
Purpose A number of recent publications have proposed that a family of image-derived
indices, called texture features, can predict clinical outcome in patients with cancer …

The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis

RTH Leijenaar, G Nalbantov, S Carvalho… - Scientific reports, 2015 - nature.com
FDG-PET-derived textural features describing intra-tumor heterogeneity are increasingly
investigated as imaging biomarkers. As part of the process of quantifying heterogeneity …

Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different …

A Wibmer, H Hricak, T Gondo, K Matsumoto… - European …, 2015 - Springer
Abstract Objectives To investigate Haralick texture analysis of prostate MRI for cancer
detection and differentiating Gleason scores (GS). Methods One hundred and forty-seven …

Tumor texture analysis in 18F-FDG PET: relationships between texture parameters, histogram indices, standardized uptake values, metabolic volumes, and total …

F Orlhac, M Soussan, JA Maisonobe… - Journal of Nuclear …, 2014 - Soc Nuclear Med
Texture indices are of growing interest for tumor characterization in 18F-FDG PET. Yet, on
the basis of results published in the literature so far, it is unclear which indices should be …

Tumor co-segmentation in PET/CT using multi-modality fully convolutional neural network

X Zhao, L Li, W Lu, S Tan - Physics in Medicine & Biology, 2018 - iopscience.iop.org
Automatic tumor segmentation from medical images is an important step for computer-aided
cancer diagnosis and treatment. Recently, deep learning has been successfully applied to …

The crucial role of multiomic approach in cancer research and clinically relevant outcomes

M Lu, X Zhan - EPMA Journal, 2018 - Springer
Cancer with heavily economic and social burden is the hot point in the field of medical
research. Some remarkable achievements have been made; however, the exact …

The impact of image reconstruction settings on 18F-FDG PET radiomic features: multi-scanner phantom and patient studies

I Shiri, A Rahmim, P Ghaffarian, P Geramifar… - European …, 2017 - Springer
Objectives The purpose of this study was to investigate the robustness of different PET/CT
image radiomic features over a wide range of different reconstruction settings. Methods …

Deep learning for variational multimodality tumor segmentation in PET/CT

L Li, X Zhao, W Lu, S Tan - Neurocomputing, 2020 - Elsevier
Positron emission tomography/computed tomography (PET/CT) imaging can simultaneously
acquire functional metabolic information and anatomical information of the human body …

Assessment of intratumoral and peritumoral computed tomography radiomics for predicting pathological complete response to neoadjuvant chemoradiation in patients …

Y Hu, C **e, H Yang, JWK Ho, J Wen, L Han… - JAMA network …, 2020 - jamanetwork.com
Importance For patients with locally advanced esophageal squamous cell carcinoma,
neoadjuvant chemoradiation has been shown to improve long-term outcomes, but the …