Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Automatic detection of spiculation of pulmonary nodules in computed tomography images

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

DOI

  1. Computed tomography synthesis from magnetic resonance images in the pelvis using multiple random forests and auto-context features

    Publikation: Bidrag til tidsskriftKonferenceabstrakt i tidsskriftForskningpeer review

  2. New Developments in Vector Velocity Imaging using the Transverse Oscillation Approach

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Preliminary study of synthetic aperture tissue harmonic imaging on in-vivo data

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Age and gender related differences in aortic blood flow

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. Chest x-ray findings in tuberculosis patients identified by passive and active case finding: A retrospective study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Observer variability for Lung-RADS categorisation of lung cancer screening CTs: impact on patient management

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Interstitial lung abnormalities are associated with increased mortality in smokers

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Malignancy risk estimation of pulmonary nodules in screening CTs: Comparison between a computer model and human observers

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  5. Ground-Glass Opacity Lung Nodules in the Era of Lung Cancer CT Screening: Radiology, Pathology, and Clinical Management

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Vis graf over relationer
We present a fully automatic method for the assessment of spiculation of pulmonary nodules in low-dose Computed Tomography (CT) images. Spiculation is considered as one of the indicators of nodule malignancy and an important feature to assess in order to decide on a patient-tailored follow-up procedure. For this reason, lung cancer screening scenario would benefit from the presence of a fully automatic system for the assessment of spiculation. The presented framework relies on the fact that spiculated nodules mainly differ from non-spiculated ones in their morphology. In order to discriminate the two categories, information on morphology is captured by sampling intensity profiles along circular patterns on spherical surfaces centered on the nodule, in a multi-scale fashion. Each intensity profile is interpreted as a periodic signal, where the Fourier transform is applied, obtaining a spectrum. A library of spectra is created by clustering data via unsupervised learning. The centroids of the clusters are used to label back each spectrum in the sampling pattern. A compact descriptor encoding the nodule morphology is obtained as the histogram of labels along all the spherical surfaces and used to classify spiculated nodules via supervised learning. We tested our approach on a set of nodules from the Danish Lung Cancer Screening Trial (DLCST) dataset. Our results show that the proposed method outperforms other 3-D descriptors of morphology in the automatic assessment of spiculation. © 2015 SPIE.
OriginalsprogEngelsk
Artikelnummer941409
TidsskriftProceedings of SPIE, the International Society for Optical Engineering
Vol/bind9414
ISSN1605-7422
DOI
StatusUdgivet - 20 mar. 2015

ID: 46260162