Automatic Annotation of Radiological Observations in Liver CT Images

We aim to predict radiological observations using computationally-derived imaging features extracted from computed tomography (CT) images. We created a dataset of 79 CT images containing liver lesions identified and annotated by a radiologist using a controlled vocabulary of 76 semantic terms. Computationally-derived features were extracted describing intensity, texture, shape, and edge sharpness. Traditional logistic regression was compared to L(1)-regularized logistic regression (LASSO) in order to predict the radiological observations using computational features. The approach was evaluated by leave one out cross-validation. Informative radiological observations such as lesion enhancement, hypervascular attenuation, and homogeneous retention were predicted well by computational features. By exploiting relationships between computational and semantic features, this approach could lead to more accurate and efficient radiology reporting.

[1]  Stefano Soatto,et al.  Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[2]  Martin D. Fox,et al.  Classifying mammographic lesions using computerized image analysis , 1993, IEEE Trans. Medical Imaging.

[3]  Peter N. Heller,et al.  The application of multiwavelet filterbanks to image processing , 1999, IEEE Trans. Image Process..

[4]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[5]  Geoffrey McLennan,et al.  The Lung Image Database Consortium (LIDC): an evaluation of radiologist variability in the identification of lung nodules on CT scans. , 2007, Academic radiology.

[6]  W W Lautt,et al.  Conceptual review of the hepatic vascular bed , 1987, Hepatology.

[7]  H. Greenspan,et al.  Automated retrieval of CT images of liver lesions on the basis of image similarity: method and preliminary results. , 2010, Radiology.

[8]  Daniel L. Rubin,et al.  Managing Biomedical Image Metadata for Search and Retrieval of Similar Images , 2011, Journal of Digital Imaging.

[9]  Osman Ratib,et al.  OsiriX: An Open-Source Software for Navigating in Multidimensional DICOM Images , 2004, Journal of Digital Imaging.

[10]  R. Baron,et al.  Understanding and optimizing use of contrast material for CT of the liver. , 1994, AJR. American journal of roentgenology.

[11]  T.G. Zhuang,et al.  Liver CT-image retrieval based on Gabor texture , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[12]  R. Rangayyan.  Biomedical Image Analysis , 2004 .

[13]  Daniel L. Rubin,et al.  iPad: Semantic Annotation and Markup of Radiological Images , 2008, AMIA.

[14]  James Ze Wang,et al.  Content-based image indexing and searching using Daubechies' wavelets , 1998, International Journal on Digital Libraries.

[15]  Daniel Cremers,et al.  Integral Invariants for Shape Matching , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[17]  O. Matsui,et al.  Benign and malignant nodules in cirrhotic livers: distinction based on blood supply. , 1991, Radiology.

[18]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[19]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[20]  C. Langlotz.  RadLex: a new method for indexing online educational materials. , 2006, Radiographics : a review publication of the Radiological Society of North America, Inc.

[21]  Daniel L. Rubin,et al.  A Comprehensive Descriptor of Shape: Method and Application to Content-Based Retrieval of Similar Appearing Lesions in Medical Images , 2012, Journal of Digital Imaging.