Automated Computer Analysis of Radiographic Images

Meyers, Phillip H.; Nice, Charles M.

doi:10.1080/00039896.1964.10663755

Cited by 28 publications

(25 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computer-aided diagnosis -which may be defined as a diagnosis made by a radiologist who takes into account the result of a computer analysis -is one domain of this huge field of artificial intelligence. The first articles about computer analysis of radiographic images appeared in the 1960s [16,182]. Articles describing techniques specifically designed for computerized detection of abnormalities in chest radiographs began to appear in the 1970s.…”

Section: Chapter 2 Computer Analysis Of Chest Radiographs -A Reviewmentioning

confidence: 99%

“…Segmentation of (parts of) the heart boundary has been studied by several researchers [182,96,143,217,189,188,252], usually with the aim of detecting cardiomegaly (enlarged heart size). Note that a correct segmentation of the lung fields is sufficient to compute the cardiothoracic ratio indicative of cardiomegaly, since parts of the boundaries on the lung fields coincide with the heart contour.…”

Section: Other Structuresmentioning

confidence: 99%

“…An example is the estimation of enlarged heart size (cardiomegaly) usually performed by measuring the cardiothoracic ratio (CTR), the maximal horizontal diameter of the heart divided by the maximal horizontal diameter of the thorax. This is the subject of probably the earliest studies of computer analysis of chest radiographs by Becker, Meyers, and co-workers [16,182]. They detected points on the rib cage boundary and heart boundary using horizontal profiles and estimated the CTR of 37 radiographs.…”

Section: Size Measurementsmentioning

confidence: 99%

See 2 more Smart Citations

Computer aided diagnosis in chest radiography

Mouton¹,

Douglas

2003

Academic Radiology

View full text Add to dashboard Cite

Section: Chapter 2 Computer Analysis Of Chest Radiographs -A Reviewmentioning

confidence: 99%

Section: Other Structuresmentioning

confidence: 99%

Section: Size Measurementsmentioning

confidence: 99%

See 1 more Smart Citation

Computer aided diagnosis in chest radiography

Mouton¹,

Douglas

2003

Academic Radiology

View full text Add to dashboard Cite

“…For determination of cardiac phase, the average pixel value was measured in the region of interest (ROI) located around the left ventricular wall throughout all frames, as shown in Fig. 2a [9,15]. Increases and decreases in pixel values were determined as the diastole phase and the systole phase, respectively (Fig.…”

Section: -3-1 Preprocessingmentioning

confidence: 99%

Development of pulmonary blood flow evaluation method with a dynamic flat-panel detector: quantitative correlation analysis with findings on perfusion scan

Tanaka

Sanada

Fujimura

et al. 2009

Radiol Phys Technol

View full text Add to dashboard Cite

Pulmonary blood flow is reflected in dynamic chest radiographs as changes in X-ray translucency, i.e., pixel values. Thus, decreased blood flow should be observed as a reduction of the variation of X-ray translucency. We performed the present study to investigate the feasibility of pulmonary blood flow evaluation with a dynamic flat-panel detector (FPD). Sequential chest radiographs of 14 subjects were obtained with a dynamic FPD system. The changes in pixel value in each local area were measured and mapped on the original image by use of a gray scale in which small and large changes were shown in white and black, respectively. The resulting images were compared to the findings in perfusion scans. The cross-correlation coefficients of the changes in pixel value and radioactivity counts in each local area were also computed. In all patients, pulmonary blood flow disorder was indicated as a reduction of changes in pixel values on the mapping image, and a correlation was observed between the distribution of changes in pixel value and those in radioactivity counts (0.7 ≤ r, 3 cases; 0.4 ≤ r < 0.7, 7 cases; 0.2 ≤ r < 0.4, 4 cases). The results indicated that the distribution of changes in -1 -pixel value could provide a relative measure related to pulmonary blood flow. The present method is potentially useful for evaluating pulmonary blood flow as an additional examination in conventional chest radiography.

show abstract

“…We used the definition of horizontal and vertical thoracic signature (equations 1 and 2) suggested by Meyers et al [18]:…”

Section: Reference Linesmentioning

confidence: 99%

Lung Segmentation on Postero-anterior Digital Chest Radiographs Using Active Contours

Iglesias

Tahoces

Souto

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.A computerized pulmonary segmentation based on the detection of oriented edges was performed in postero-anterior (PA) digital radiography (DR) images. To further improve detection of lung contours, a method based on the use of active contours models was developed. First, the technique calculates a set of reference lines to determine the relative position of the lungs in the image. Then, vertical and horizontal rectangular regions of interest (ROIs) are studied to identify the preliminary edge. These points are an approximation to the lung edges that are adjusted using the active contours models. We studied the influence of the different parameters of the active contours on the final result over 30 DR images. Results prove that the active contour models, with selected parameters, can be used to improve the results of a given segmentation scheme.

show abstract

Automated Computer Analysis of Radiographic Images

Cited by 28 publications

References 2 publications

Computer aided diagnosis in chest radiography

Computer aided diagnosis in chest radiography

Development of pulmonary blood flow evaluation method with a dynamic flat-panel detector: quantitative correlation analysis with findings on perfusion scan

Lung Segmentation on Postero-anterior Digital Chest Radiographs Using Active Contours

Contact Info

Product

Resources

About