Detection of rib shadows in digital chest radiographs

Sarkar, Soumik; Chaudhuri, Siddhartha

doi:10.1007/3-540-63508-4_143

Cited by 8 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3, it is visible how they influence the segmentations. The confusion between ribs and clavicles is also problematic in other methods, e.g., in [7]. Further, as noticed in Section IV, errors occur in a structured way in the segmentation and not, more or less, randomly scattered through the entire image as is the case in the PC results.…”

Section: Discussionmentioning

confidence: 86%

“…Ribs have been modeled as parabolas [6], [7] or ellipses [8], [9] and the ribcage as a sinusoidal pattern [9], [10]. These models have been fitted, usually with a modified Hough transform, to the image data directly, to edges extracted from the lung fields, or to morphologically processed images [7]. To remove false responses, or infer missing borders, rulebased reasoning schemes have been proposed [6], [11].…”

Section: A Relation To Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of the posterior ribs in chest radiographs using iterated contextual pixel classification

Loog

Ginneken

2006

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

The task of segmenting the posterior ribs within the lung fields of standard posteroanterior chest radiographs is considered. To this end, an iterative, pixel-based, supervised, statistical classification method is used, which is called iterated contextual pixel classification (ICPC). Starting from an initial rib segmentation obtained from pixel classification, ICPC updates it by reclassifying every pixel, based on the original features and, additionally, class label information of pixels in the neighborhood of the pixel to be reclassified. The method is evaluated on 30 radiographs taken from the JSRT (Japanese Society of Radiological Technology) database. All posterior ribs within the lung fields in these images have been traced manually by two observers. The first observer's segmentations are set as the gold standard; ICPC is trained using these segmentations. In a sixfold cross-validation experiment, ICPC achieves a classification accuracy of 0.86 +/- 0.06, as compared to 0.94 +/- 0.02 for the second human observer.

show abstract

Section: Discussionmentioning

confidence: 86%

Section: A Relation To Previous Workmentioning

confidence: 99%

Segmentation of the posterior ribs in chest radiographs using iterated contextual pixel classification

Loog

Ginneken

2006

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…The general approach is first extracting the rib pixels using an edge detection algorithm [25]. Then, the candidate rib pixels/lines are grouped into a complete rib boundary by applying a curve fitting technique [26], using a voting approach such as Hough transform [10, 27], or applying a geometric model such as parabolas [28, 29, 30, 7] or ellipses [31]. Although extracting the rib borders with an edge detection algorithm is a well-known approach, these algorithms produce spurious edges at the apex of the lung due to overlapping bone structures.…”

Section: Literature Reviewmentioning

confidence: 99%

Atlas-based rib-bone detection in chest X-rays

Candemir

Jaeger

Bağcı

et al. 2016

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

This paper investigates using rib-bone atlases for automatic detection of rib-bones in chest X-rays (CXRs). We built a system that takes patient X-ray and model atlases as input and automatically computes the posterior rib borders with high accuracy and efficiency. In addition to conventional atlas, we propose two alternative atlases: (i) automatically computed rib bone models using Computed Tomography (CT) scans, and (ii) dual energy CXRs. We test the proposed approach with each model on 25 CXRs from the Japanese Society of Radiological Technology (JSRT) dataset and another 25 CXRs from the National Library of Medicine CXR dataset. We achieve an area under the ROC curve (AUC) of about 95% for Montgomery and 91% for JSRT datasets. Using the optimal operating point of the ROC curve, we achieve a segmentation accuracy of 88.91 ± 1.8 % for Montgomery and 85.48 ± 3.3 % for JSRT datasets. Our method produces comparable results with the state-of-the-art algorithms. The performance of our method is also excellent on challenging X-rays as it successfully addressed the rib-shape variance between patients and number of visible rib-bones due to patient respiration.

show abstract

“…On the other hand, classical shape recognition techniques present serious drawbacks when applied to these images, as structural information such as relationships between objects in the image are not considered. Other systems have been developed that attempt to extract the pulmonary areas either to measure the cardiothoracic ratio (CRT) (4), to use them as masks in digital radiography systems (5), to detect rib shadows (6,7), or to detect abnormal asymmetry (8). Nakamori et al.…”

Section: Introductionmentioning

confidence: 99%