Sorry, you need to enable JavaScript to visit this website.

ASSESSING THE PROGNOSTIC IMPACT OF 3D CT IMAGE TUMOUR RIND TEXTURE FEATURES ON LUNG CANCER SURVIVAL MODELLING

Citation Author(s):
Alanna Vial, David Stirling, Matthew Field, Montserrat Ros, Christian Ritz, Martin Carolan, Lois Hollowayn, Alexis A. Miller
Submitted by:
Alanna Vial
Last updated:
11 December 2017 - 5:01pm
Document Type:
Presentation Slides
Document Year:
2017
Event:
Presenters:
Alanna Vial
Paper Code:
1284
 

In this paper we examine a technique for developing prognostic image characteristics, termed radiomics, for non-small cell lung cancer based on a tumour edge region-based analysis. Texture features were extracted from the rind of the tumour in a publicly available 3D CT data set to predict two-year survival. The derived models were compared against the previous methods of training radiomic signatures that are descriptive of the whole tumour volume. Radiomic features derived solely from regions external, but neighbouring, the tumour were shown to also have prognostic value. By using additional texture features a marked increase in accuracy, of 7%, is shown over previous approaches for predicting two-year survival, upon examining the outside rind including the volume compared to the volume without the rind. This conflicts with the clinical view that the centre of the tumour is the main target for radiotherapy treatment, yet is characteristic of this type of cancer.

up
0 users have voted: