Bag-of-frequencies: a descriptor of pulmonary nodules in computed tomography images
- PMID: 25420257
- DOI: 10.1109/TMI.2014.2371821
Bag-of-frequencies: a descriptor of pulmonary nodules in computed tomography images
Abstract
We present a novel descriptor for the characterization of pulmonary nodules in computed tomography (CT) images. The descriptor encodes information on nodule morphology and has scale-invariant and rotation-invariant properties. Information on nodule 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 and labeled via unsupervised clustering, obtaining a Bag-of-Frequencies, which is used to assign each spectra a label. The descriptor is obtained as the histogram of labels along all the spheres. Additional contributions are a technique to estimate the nodule size, based on the sampling strategy, as well as a technique to choose the most informative plane to cut a 2-D view of the nodule in the 3-D image. We evaluate the descriptor on several nodule morphology classification problems, namely discrimination of nodules versus vascular structures and characterization of spiculation. We validate the descriptor on data from European screening trials NELSON and DLCST and we compare it with state-of-the-art approaches for 3-D shape description in medical imaging and computer vision, namely SPHARM and 3-D SIFT, outperforming them in all the considered experiments.
Similar articles
-
Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box.Med Image Anal. 2015 Dec;26(1):195-202. doi: 10.1016/j.media.2015.08.001. Epub 2015 Sep 8. Med Image Anal. 2015. PMID: 26458112
-
Solid, part-solid, or non-solid?: classification of pulmonary nodules in low-dose chest computed tomography by a computer-aided diagnosis system.Invest Radiol. 2015 Mar;50(3):168-73. doi: 10.1097/RLI.0000000000000121. Invest Radiol. 2015. PMID: 25478740 Clinical Trial.
-
Pulmonary nodule detection, characterization, and management with multidetector computed tomography.J Thorac Imaging. 2011 May;26(2):90-105. doi: 10.1097/RTI.0b013e31821639a9. J Thorac Imaging. 2011. PMID: 21508732 Review.
-
Toward precise pulmonary nodule descriptors for nodule type classification.Med Image Comput Comput Assist Interv. 2010;13(Pt 3):626-33. doi: 10.1007/978-3-642-15711-0_78. Med Image Comput Comput Assist Interv. 2010. PMID: 20879453
-
[CAD for identifying malignant lung nodules in early diagnosis: a survey].Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2009 Oct;26(5):1141-5, 1157. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2009. PMID: 19947507 Review. Chinese.
Cited by
-
A proposed methodology for detecting the malignant potential of pulmonary nodules in sarcoma using computed tomographic imaging and artificial intelligence-based models.Front Oncol. 2023 Aug 21;13:1212526. doi: 10.3389/fonc.2023.1212526. eCollection 2023. Front Oncol. 2023. PMID: 37671060 Free PMC article.
-
A Novel Deep Learning Model Based on Multi-Scale and Multi-View for Detection of Pulmonary Nodules.J Digit Imaging. 2023 Apr;36(2):688-699. doi: 10.1007/s10278-022-00749-x. Epub 2022 Dec 21. J Digit Imaging. 2023. PMID: 36544067 Free PMC article.
-
A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images.Front Oncol. 2021 Dec 17;11:737368. doi: 10.3389/fonc.2021.737368. eCollection 2021. Front Oncol. 2021. PMID: 34976794 Free PMC article.
-
A CNN-LSTM network with multi-level feature extraction-based approach for automated detection of coronavirus from CT scan and X-ray images.Appl Soft Comput. 2021 Dec;113:107918. doi: 10.1016/j.asoc.2021.107918. Epub 2021 Sep 27. Appl Soft Comput. 2021. PMID: 34608379 Free PMC article.
-
Lung Nodule Detection from Feature Engineering to Deep Learning in Thoracic CT Images: a Comprehensive Review.J Digit Imaging. 2020 Jun;33(3):655-677. doi: 10.1007/s10278-020-00320-6. J Digit Imaging. 2020. PMID: 31997045 Free PMC article. Review.
