Interpretable spiculation quantification for lung cancer screening Conference Paper


Authors: Choi, W.; Nadeem, S.; Riyahi, S.; Deasy, J. O.; Tannenbaum, A.; Lu, W.
Title: Interpretable spiculation quantification for lung cancer screening
Conference Title: International Workshop on Shape in Medical Imaging (ShapeMI 2018)
Abstract: Spiculations are spikes on the surface of pulmonary nodule and are important predictors of malignancy in lung cancer. In this work, we introduced an interpretable, parameter-free technique for quantifying this critical feature using the area distortion metric from the spherical conformal (angle-preserving) parameterization. The conformal factor in the spherical mapping formulation provides a direct measure of spiculation which can be used to detect spikes and compute spike heights for geometrically-complex spiculations. The use of the area distortion metric from conformal mapping has never been exploited before in this context. Based on the area distortion metric and the spiculation height, we introduced a novel spiculation score. A combination of our spiculation measures was found to be highly correlated (Spearman’s rank correlation coefficient with the radiologist’s spiculation score. These measures were also used in the radiomics framework to achieve state-of-the-art malignancy prediction accuracy of 88.9% on a publicly available dataset. © 2018, Springer Nature Switzerland AG.
Keywords: medical imaging; diagnosis; pulmonary nodules; biological organs; diseases; lung cancer screening; conformal mapping; critical features; conformal factors; distortion metrics; prediction accuracy; rank correlation coefficient; spiculation scores
Journal Title Lecture Notes in Computer Science
Volume: 11167
Conference Dates: 2018 Sep 20
Conference Location: Granada, Spain
ISBN: 0302-9743
Publisher: Springer  
Date Published: 2018-01-01
Start Page: 38
End Page: 48
Language: English
DOI: 10.1007/978-3-030-04747-4_4
PROVIDER: scopus
DOI/URL:
Notes: Part of "Shape in Medical Imaging" (ISBN: 978-3-030-04746-7) -- Export Date: 2 January 2019 -- Conference Paper -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Joseph Owen Deasy
    524 Deasy
  2. Wei   Lu
    70 Lu
  3. Wookjin   Choi
    21 Choi
  4. Saad Nadeem
    50 Nadeem