The LoG Characteristic Scale: A Consistent Measurement of Lung Nodule Size in CT Imaging

被引:21
作者
Diciotti, Stefano [1 ]
Lombardo, Simone [1 ]
Coppini, Giuseppe [2 ]
Grassi, Luca [3 ]
Falchini, Massimo [3 ]
Mascalchi, Mario [3 ]
机构
[1] Univ Florence, Dept Elect & Telecommun, I-50134 Florence, Italy
[2] CNR, Inst Clin Physiol, I-56124 Pisa, Italy
[3] Univ Florence, Dept Clin Physiopathol, I-50139 Florence, Italy
关键词
Computer aided diagnosis; Laplacian of Gaussian; lung cancer; lung nodules; lung nodules characterization; lung nodules segmentation; multiscale processing; scale-space; DATABASE CONSORTIUM LIDC; SMALL PULMONARY NODULES; SPIRAL COMPUTED-TOMOGRAPHY; THORACIC CT; VOLUMETRIC MEASUREMENTS; SEGMENTATION; CANCER; IMAGES; VARIABILITY; SCANS;
D O I
10.1109/TMI.2009.2032542
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Nodule growth as observed in computed tomography (CT) scans acquired at different times is the primary feature to malignancy of indeterminate small lung nodules. In this paper, we propose the estimation of nodule size through a scale-space representation which needs no segmentation and has high intra -and inter-operator reproducibility. Lung nodules usually appear in CT images as blob-like patterns and can be analyzed in the scale-space by Laplacian of Gaussian (LoG) kernels. For each nodular pattern the LoG scale-space signature was computed and the related characteristic scale adopted as measurement of nodule size. Both in vitro and in vivo validation of LoG characteristic scale were carried out. In vitro validation was done by 40 nondeformable phantoms and 10 deformable phantoms. A close relationship between the characteristic scale and the equivalent diameter, i.e., the diameter of the sphere having the same volume of nodules, (Pearson correlation coefficient was 0.99) and, for nodules undergoing little deformations (obtained at constant volume), small variability of the characteristic scale was observed. The in vivo validation was performed on low and standard-dose CT scans collected from the ITALUNG screening trial (86 nodules) and from the LIDC public data set (89 solid nodules and 40 part-solid nodules or ground-glass opacities). The Pearson correlation coefficient between characteristic scale and equivalent diameter was 0.83-0.93 for ITALUNG and 0.68-0.83 for LIDC data set. Intra-and inter-operator reproducibility of characteristic scale was excellent: on a set of 40 lung nodules of ITALUNG data, two radiologists produced identical results in repeated measurements. The scan-rescan variability of the characteristic scale was also investigated on 86 two-year-stable solid lung nodules (each one observed, on average, in four CT scans) identified in the ITALUNG screening trial: a coefficient of repeatability of about 0.9 mm was observed. Experimental evidence supports the clinical use of the LoG characteristic scale to measure nodule size in CT imaging.
引用
收藏
页码:397 / 409
页数:13
相关论文
共 45 条
  • [21] Screening for lung cancer: the early lung cancer action approach
    Henschke, CI
    Yankelevitz, DF
    Smith, JP
    Miettinen, OS
    [J]. LUNG CANCER, 2002, 35 (02) : 143 - 148
  • [22] Small pulmonary nodules: Volume measurement at chest CT - Phantom study
    Ko, JP
    Rusinek, H
    Jacobs, EL
    Babb, JS
    Betke, M
    McGuinness, G
    Naidich, DP
    [J]. RADIOLOGY, 2003, 228 (03) : 864 - 870
  • [23] Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images
    Kostis, WJ
    Reeves, AP
    Yankelevitz, DF
    Henschke, CI
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2003, 22 (10) : 1259 - 1274
  • [24] Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans
    Kuhnigk, JM
    Dicken, V
    Bornemann, L
    Bakai, A
    Wormanns, D
    Krass, S
    Peitgen, HO
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2006, 25 (04) : 417 - 434
  • [25] Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique
    Lee, Y
    Hara, T
    Fujita, H
    Itoh, S
    Ishigaki, T
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (07) : 595 - 604
  • [26] Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans
    Li, Q
    Sone, S
    Doi, K
    [J]. MEDICAL PHYSICS, 2003, 30 (08) : 2040 - 2051
  • [27] DETECTING SALIENT BLOB-LIKE IMAGE STRUCTURES AND THEIR SCALES WITH A SCALE-SPACE PRIMAL SKETCH - A METHOD FOR FOCUS-OF-ATTENTION
    LINDEBERG, T
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1993, 11 (03) : 283 - 318
  • [28] The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation
    McNitt-Gray, Michael F.
    Armato, Samuel G., III
    Meyer, Charles R.
    Reeves, Anthony P.
    McLennan, Geoffrey
    Pais, Richie C.
    Freymann, John
    Brown, Matthew S.
    Engelmann, Roger M.
    Bland, Peyton H.
    Laderach, Gary E.
    Piker, Chris
    Guo, Junfeng
    Towfic, Zaid
    Qing, David P. -Y.
    Yankelevitz, David F.
    Aberle, Denise R.
    van Beek, Edwin J. R.
    MacMahon, Heber
    Kazerooni, Ella A.
    Croft, Barbara Y.
    Clarke, Laurence P.
    [J]. ACADEMIC RADIOLOGY, 2007, 14 (12) : 1464 - 1474
  • [29] Scale-space signatures for the detection of clustered microcalcifications in digital mammograms
    Netsch, T
    Peitgen, HO
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 1999, 18 (09) : 774 - 786
  • [30] Robust anisotropic Gaussian fitting for volumetric characterization of pulmonary nodules in multislice CT
    Okada, K
    Comaniciu, D
    Krishnan, A
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2005, 24 (03) : 409 - 423