Volumetric Analysis of Liver Metastases in Computed Tomography With the Fuzzy C-Means Algorithm

Abstract: Tumor size is often determined from computed tomography (CT) images to assess disease progression. A study was conducted to demonstrate the advantages of the fuzzy C-means (FCM) algorithm for volumetric analysis of colorectal liver metastases in comparison with manual contouring. Intra-and interobserver variability was assessed for manual contouring and the FCM algorithm in a study involving contrast-enhanced helical CT images of 43 hypoattenuating liver lesions from 15 patients with a history of colorectal cancer. Measurement accuracy and interscan variability of the FCM and manual methods were assessed in a phantom study using paraffin pseudotumors. In the clinical imaging study, intra-and interobserver variability was reduced using the FCM algorithm as compared with manual contouring (P = 0.0070 and P = 0.0019, respectively). Accuracy of the measurement of the pseudotumor volume was improved using the FCM method as compared with the manual method (P = 0.047). Interscan variability of the pseudotumor volumes was measured using the FCM method as compared with the manual method (P = 0.04). The FCM algorithm volume was highly correlated with the manual contouring volume (r = 0.9997). Finally, the shorter time spent in calculating tumor volume using the FCM method versus the manual contouring method was marginally statistically significant (P = 0.080). These results suggest that the FCM algorithm has substantial advantages over manual contouring for volumetric measurement of colorectal liver metastases from CT.

[1]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[2]  E T Bullmore,et al.  A modified fuzzy clustering algorithm for operator independent brain tissue classification of dual echo MR images. , 1999, Magnetic resonance imaging.

[3]  K D Hopper,et al.  The impact of 2D versus 3D quantitation of tumor bulk determination on current methods of assessing response to treatment. , 1996, Journal of computer assisted tomography.

[4]  L O Hall,et al.  Review of MR image segmentation techniques using pattern recognition. , 1993, Medical physics.

[5]  G T Chen,et al.  Computerized tomography in the quantitative assessment of tumour response. , 1980, The British journal of cancer. Supplement.

[6]  Sankar K. Pal,et al.  Fuzzy models for pattern recognition , 1992 .

[7]  M. van Glabbeke,et al.  New guidelines to evaluate the response to treatment in solid tumors , 2000, Journal of the National Cancer Institute.

[8]  Peter J. Yim,et al.  Volumetry of hepatic metastases in computed tomography using the watershed and active contour algorithms , 2003, 16th IEEE Symposium Computer-Based Medical Systems, 2003. Proceedings..

[9]  L. Clarke,et al.  Monitoring brain tumor response to therapy using MRI segmentation. , 1997, Magnetic resonance imaging.

[10]  P. Lavin,et al.  Studies in variation associated with the measurement of solid tumors , 1980, Cancer.

[11]  A. Boudraa,et al.  Automated detection of the left ventricular region in magnetic resonance images by Fuzzy C-Means model , 1997, The International Journal of Cardiac Imaging.

[12]  R P Velthuizen,et al.  MRI segmentation: methods and applications. , 1995, Magnetic resonance imaging.

[13]  E. Fishman,et al.  CT Volumetrics of Primary Liver Cancers , 1986, Journal of computer assisted tomography.

[14]  A. Beckett,et al.  AKUFO AND IBARAPA. , 1965, Lancet.

[15]  A. Miller,et al.  Reporting results of cancer treatment , 1981, Cancer.

[16]  Jong-Min Lee,et al.  Modified Magnetic Resonance Image Based Parcellation Method for Cerebral Cortex using Successive Fuzzy Clustering and Boundary Detection , 2004, Annals of Biomedical Engineering.

[17]  L. Schumm,et al.  Tumor size on computed tomography scans , 2001, Cancer.

[18]  E. Halpern,et al.  CT tumor measurement for therapeutic response assessment: comparison of unidimensional, bidimensional, and volumetric techniques initial observations. , 2002, Radiology.

[19]  M. Chopp,et al.  Multiparametric MRI Tissue Characterization in Clinical Stroke With Correlation to Clinical Outcome: Part 2 , 2001, Stroke.

[20]  James C. Bezdek,et al.  A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain , 1992, IEEE Trans. Neural Networks.

[21]  H Soltanian-Zadeh,et al.  A Model for Multiparametric MRI Tissue Characterization in Experimental Cerebral Ischemia With Histological Validation in Rat: Part 1 , 2001, Stroke.

[22]  J M Bland,et al.  Statistical methods for assessing agreement between two methods of clinical measurement , 1986 .

[23]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[24]  W E Phillips,et al.  Application of fuzzy c-means segmentation technique for tissue differentiation in MR images of a hemorrhagic glioblastoma multiforme. , 1995, Magnetic Resonance Imaging.

[25]  C. Cann,et al.  Volumetric CT Analysis of Hepatic Tumors , 1981, Journal of computer assisted tomography.

[26]  M Van Glabbeke,et al.  New guidelines to evaluate the response to treatment in solid tumors. European Organization for Research and Treatment of Cancer, National Cancer Institute of the United States, National Cancer Institute of Canada. , 2000, Journal of the National Cancer Institute.

[27]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.