Radiomics Feature Activation Maps as a New Tool for Signature Interpretability.

Details

Ressource 1Download: Radiomics_fonc-10-578895.pdf (1909.35 [Ko])
State: Public
Version: Final published version
License: CC BY 4.0
Serval ID
serval:BIB_F93AA20EEB4E
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Radiomics Feature Activation Maps as a New Tool for Signature Interpretability.
Journal
Frontiers in oncology
Author(s)
Vuong D., Tanadini-Lang S., Wu Z., Marks R., Unkelbach J., Hillinger S., Eboulet E.I., Thierstein S., Peters S., Pless M., Guckenberger M., Bogowicz M.
ISSN
2234-943X (Print)
ISSN-L
2234-943X
Publication state
Published
Issued date
2020
Peer-reviewed
Oui
Volume
10
Pages
578895
Language
english
Notes
Publication types: Journal Article
Publication Status: epublish
Abstract
In the field of personalized medicine, radiomics has shown its potential to support treatment decisions. However, the limited feature interpretability hampers its introduction into the clinics. Here, we propose a new methodology to create radiomics feature activation maps, which allows to identify the spatial-anatomical locations responsible for signature activation based on local radiomics. The feasibility of this technique will be studied for histological subtype differentiation (adenocarcinoma versus squamous cell carcinoma) in non-small cell lung cancer (NSCLC) using computed tomography (CT) radiomics.
Pre-treatment CT scans were collected from a multi-centric Swiss trial (training, n=73, IIIA/N2 NSCLC, SAKK 16/00) and an independent cohort (validation, n=32, IIIA/N2/IIIB NSCLC). Based on the gross tumor volume (GTV), four peritumoral region of interests (ROI) were defined: lung_exterior (expansion into the lung), iso_exterior (expansion into lung and soft tissue), gradient (GTV border region), GTV+Rim (GTV and iso_exterior). For each ROI, 154 radiomic features were extracted using an in-house developed software implementation (Z-Rad, Python v2.7.14). Features robust against delineation variability served as an input for a multivariate logistic regression analysis. Model performance was quantified using the area under the receiver operating characteristic curve (AUC) and verified using five-fold cross validation and internal validation. Local radiomic features were extracted from the GTV+Rim ROI using non-overlapping 3x3x3 voxel patches previously marked as GTV or rim. A binary activation map was created for each patient using the median global feature value from the training. The ratios of activated/non-activated patches of GTV and rim regions were compared between histological subtypes (Wilcoxon test).
Iso_exterior, gradient, GTV+Rim showed good performances for histological subtype prediction (AUC <sub>training</sub> =0.68-0.72 and AUC <sub>validation</sub> =0.73-0.74) whereas GTV and lung_exterior models failed validation. GTV+Rim model feature activation maps showed that local texture feature distribution differed significantly between histological subtypes in the rim (p=0.0481) but not in the GTV (p=0.461).
In this exploratory study, radiomics-based prediction of NSCLC histological subtypes was predominantly based on the peritumoral region indicating that radiomics activation maps can be useful for tracing back the spatial location of regions responsible for signature activation.
Keywords
computed tomography, interpretability, local radiomics, lung cancer, peritumoral radiomics, radiomics activation maps
Pubmed
Web of science
Open Access
Yes
Create date
11/01/2021 9:44
Last modification date
19/11/2021 7:15
Usage data