2022
DOI: 10.3390/cancers14040946
|View full text |Cite
|
Sign up to set email alerts
|

Quantitative Analysis of Radiation-Associated Parenchymal Lung Change

Abstract: We present a novel classification system of the parenchymal features of radiation-induced lung damage (RILD). We developed a deep learning network to automate the delineation of five classes of parenchymal textures. We quantify the volumetric change in classes after radiotherapy in order to allow detailed, quantitative descriptions of the evolution of lung parenchyma up to 24 months after RT, and correlate these with radiotherapy dose and respiratory outcomes. Diagnostic CTs were available pre-RT, and at 3, 6,… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 58 publications
0
3
0
Order By: Relevance
“…proposed five different RP types, their model presents sophisticated techniques for analyzing RP. Furthermore, it was impossible to classify them intuitively from the CT images ( 26 ). Szejniuk et al.…”
Section: Discussionmentioning
confidence: 99%
“…proposed five different RP types, their model presents sophisticated techniques for analyzing RP. Furthermore, it was impossible to classify them intuitively from the CT images ( 26 ). Szejniuk et al.…”
Section: Discussionmentioning
confidence: 99%
“…In future work we aim to use our classes to investigate if and how tissue changes are linked to RILD pathophysiology. We have already conducted an analysis where we applied the presented classification method to investigate the degree of radiological change [ 44 ]. In that study, the longitudinal data of 24 months follow up were registered to planning scans using a dedicated multi-channel deformable registration method [ 45 ], tailored to deal with large anatomical changes.…”
Section: Discussionmentioning
confidence: 99%
“…The training of NTCP models relies on the classification of patients according to the development of a given toxicity. In this context, the papers by Chandy et al [ 21 ] and Szmul et al [ 22 ] present two automated classification algorithms for the analysis of RT-induced lung damage in NSCLC patients, providing novel insights into the temporal evolution of lung damage and its relationship with global and local dose as well as respiratory outcomes [ 21 ].…”
mentioning
confidence: 99%