Computer-Aided Diagnostic (CAD) Scheme by Use of Contralateral Subtraction Technique

We developed a computer-aided diagnostic (CAD) scheme for detection of subtle image findings of acute cerebral infarction in brain computed tomography (CT) by using a contralateral subtraction technique. In our computerized scheme, the lateral inclination of image was first corrected automatically by rotating and shifting. The contralateral subtraction image was then derived by subtraction of reversed image from original image. Initial candidates for acute cerebral infarctions were identified using the multiple-thresholding and image filtering techniques. As the 1st step for removing false positive candidates, fourteen image features were extracted in each of the initial candidates. Halfway candidates were detected by applying the rule-based test with these image features. At the 2nd step, five image features were extracted using the overlapping scale with halfway candidates in interest slice and upper/lower slice image. Finally, acute cerebral infarction candidates were detected by applying the rule-based test with five image features. The sensitivity in the detection for 74 training cases was 97.4% with 3.7 false positives per image. The performance of CAD scheme for 44 testing cases had an approximate result to training cases. Our CAD scheme using the contralateral subtraction technique can reveal suspected image findings of acute cerebral infarctions in CT images.

[1]  Atsushi Takemura.  Automatic generating algorithm of locally adaptive smoothing filter-An application to speckle suppression of ultrasonic images- , 2005 .

[2]  K. Doi,et al.  Computer-aided diagnosis in chest radiography: results of large-scale observer tests at the 1996-2001 RSNA scientific assemblies. , 2003, Radiographics : a review publication of the Radiological Society of North America, Inc.

[3]  Qiang Li,et al.  Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. , 2003, Medical physics.

[4]  Kunio Doi,et al.  Elimination of False Positives Based on Shape Analysis of Nodule Candidates on Chest Radiographs , 2001 .

[5]  Du-Yih Tsai,et al.  [Improvement in visibility and detectability of early sign of acute stroke in nonenhanced CT images by using an adaptive partial smoothing filter]. , 2005, Nihon Hoshasen Gijutsu Gakkai zasshi.

[6]  K. Doi,et al.  Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification. , 2006, Medical physics.

[7]  S Katsuragawa,et al.  Improved contralateral subtraction images by use of elastic matching technique. , 2000, Medical physics.

[8]  Kunio Doi,et al.  Computer-aided diagnosis to distinguish benign from malignant solitary pulmonary nodules on radiographs: ROC analysis of radiologists' performance--initial experience. , 2003, Radiology.

[9]  K. Doi.  Overview on research and development of computer-aided diagnostic schemes. , 2004, Seminars in ultrasound, CT, and MR.

[10]  K. Doi,et al.  Current status and future potential of computer-aided diagnosis in medical imaging. , 2005, The British journal of radiology.

[11]  H Yoshida,et al.  Contralateral subtraction: a novel technique for detection of asymmetric abnormalities on digital chest radiographs. , 2000, Medical physics.