Automatic detection of foreign objects in computed radiography

Abstract

This paper presents an effective two-step scheme for automatic object detection in computed radiography (CR) images. First, various structure elements of the morphological filters, designed by incorporating available morphological features of the objects of interest including their sizes and rough shape descriptions, are used to effectively distinguish the foreign object candidates from the complex background structures. Second, since the boundaries of the objects are the key features in reflecting object characteristics, active contour models are employed to accurately outline the morphological shapes of the suspicious foreign objects to further reduce the rate of false alarms. The actual detection scheme is accomplished by jointly using these two steps. The proposed methods are tested with a database of 50 hand-wrist computed radiographic images containing various types of foreign objects. Our experimental results demonstrate that the combined use of morphological filters and active contour models can provide an effective automatic detection of foreign objects in CR images achieving good sensitivity and specificity, and the accurate descriptions of the object morphological characteristics.

Abnormal Presentation of a Plastic Foreign Body in The Retropharyngeal Space.

“…Newer techniques are also emerging which are more accurate in identifying non-metallic foreign bodies. These include computer algorithms for processing of CT and MRI images [15][16]. The use of such algorithms has yet to become standard practice in the trauma setting.…”

PE-CMOS based C-scan ultrasound for foreign object detection in soft tissue

“…The image characteristic of C-scan ultrasound is different from other imaging modalities, e.g. radiography 19.0 2,3 1.8 2.9 14.2 2 14.1 2 12.5 2 3.6 1 From Selfridge (12) and Wegst (13), 2 Experimental data computed by using the C-scan prototype, 3 Approximate value with air contained inside its fibrotic structure In this experiment, a 5MHz transducer was employed to acquire ultrasound images of the porcine tissue sample using the C-scan prototype. Figure 9 shows a series of the C-scan images with each centered at a foreign object.…”

An Ensemble of Deep Learning Object Detection Models for Anatomical and Pathological Regions in Brain MRI

“…Object detection describes the process of accurately representing relevant objects in an image in terms of their position, size, and shape definition. Object detection approaches are generally divided into two categories [ 23 ]: data-centered, such as edge detection and region growth; and goal-directed, such as knowledge-guided boundary detection. In this context, object detection offers great opportunities for disease diagnosis and treatment planning.…”