Enter Your Email Address to Receive a
Copy of MedicExhange Member Demograhpics

‘Journal of Digital Imaging’ reports of a new system for accurate identification and labelling of ribs and vertebrae automatically. The computer-aided system was developed by radiologists of Nihon University School of Medicine and Iwate Prefectural Central Hospital, Japan.  

The development of such a system is crucial because exact knowledge of the thoraco-lumbar skeleton is required to diagnose the various bony abnormalities from Computed Tomography (CT) films and there is no automated method to identify the various bones. Ascertaining unquestionably the anatomical numbers of the ribs and the thoracic and lumbar vertebrae from axial images alone is complicated. If bone lesions in these bones are detected, radiologists are required to refer to a CT localizer which is tedious and time consuming. Also several methods have been described to count ribs which are time-consuming and imprecise.

A candidate bone was extracted from the CT image volume data by pixel thresholding and connectivity analysis. All non-bony anatomical structures were removed using a linear discriminate of distribution of CT values and anatomical characteristics. The vertebrae were separated from the ribs on the basis of their distances from the centers of the vertebral bodies. Finally, the thoracic cage and lumbar vertebrae were extracted, and each vertebra was labelled with its own anatomical number by histogram analysis along the craniocaudal midline. The ribs were labelled in a similar manner, based on location data.
Twenty-three cases were used for accuracy comparison between our method and the radiologist’s. The new system was found to be accurate except for the identification of the first two ribs which were frequently misidentified, presumably because of pericostal anatomical clutter or high densities of contrast material in the injected veins.

The authors are confident that this system can contribute usefully as part of a picture archiving and communication system workstation, though further technical improvement is required for identification of the upper ribs.