Determining the View of Chest Radiographs

Automatic identification of frontal (posteroanterior/anteroposterior) vs. lateral chest radiographs is an important preprocessing step in computer-assisted diagnosis, content-based image retrieval, as well as picture archiving and communication systems. Here, a new approach is presented. After the radiographs are reduced substantially in size, several distance measures are applied for nearest-neighbor classification. Leaving-one-out experiments were performed based on 1,867 radiographs from clinical routine. For comparison to existing approaches, subsets of 430 and 5 training images are also considered. The overall best correctness of 99.7% is obtained for feature images of 32 × 32 pixels, the tangent distance, and a 5-nearest-neighbor classification scheme. Applying the normalized cross correlation function, correctness yields still 99.6% and 99.3% for feature images of 32 × 32 and 8 × 8 pixel, respectively. Remaining errors are caused by image altering pathologies, metal artifacts, or other interferences with routine conditions. The proposed algorithm outperforms existing but sophisticated approaches and is easily implemented at the same time.

[1]  Michael G. Evanoff,et al.  Automatically determining the orientation of chest images , 1997, Medical Imaging.

[2]  Yann LeCun,et al.  Efficient Pattern Recognition Using a New Transformation Distance , 1992, NIPS.

[3]  Thomas Martin Deserno,et al.  Content-based image retrieval in medical applications: a novel multistep approach , 1999, Electronic Imaging.

[4]  Thomas M. Lehmanna,et al.  Header for SPIE use Content-Based Image Retrieval in Medical Applications: A Novel Multi-Step Approach , 2022 .

[5]  Max A. Viergever,et al.  Computer-aided diagnosis in chest radiography: a survey , 2001, IEEE Transactions on Medical Imaging.

[6]  T M Lehmann,et al.  Content-based Image Retrieval in Medical Applications , 2004, Methods of Information in Medicine.

[7]  Thomas Martin Deserno,et al.  Automatic detection of the view position of chest radiographs , 2003, SPIE Medical Imaging.

[8]  Thomas Martin Deserno,et al.  A Distributed Architecture for Content-Based Image Retrieval in Medical Applications , 2002, PRIS.

[9]  Richard H. Daffner,et al.  Clinical Radiology: The Essentials , 1992 .

[10]  Kunio Doi,et al.  Performance evaluation of an advanced method for automated identification of view positions of chest radiographs by use of a large database , 2002, SPIE Medical Imaging.

[11]  Hermann Ney,et al.  Statistical framework for model-based image retrieval in medical applications , 2003, J. Electronic Imaging.

[12]  R A Novelline,et al.  Helical CT in emergency radiology. , 1999, Radiology.

[13]  H K Huang,et al.  Image Preprocessing for a Picture Archiving and Communication System , 1992, Investigative radiology.