A novel bone suppression method that improves lung nodule detection

Berg, Jens von; Young, Stewart; Carolus, Heike; Wolz, Robin; Saalbach, Axel; Hidalgo, Alberto; Giménez, A.; Franquet, Tomás

doi:10.1007/s11548-015-1278-y

Cited by 20 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While these results are very promising, we have to consider that within this proof-of-principle (reader) study none of the lately developed ribcage suppression algorithms had been applied 22–25 . Although these are yet not applied in daily clinical routine, they yield the potential to increase the quality of lung nodule visualization in transmission radiography as such 22, 25, 26 .…”

Section: Discussionmentioning

confidence: 99%

“…Although these are yet not applied in daily clinical routine, they yield the potential to increase the quality of lung nodule visualization in transmission radiography as such 22, 25, 26 . In addition, in translating our findings to clinical imaging, it is uncertain to which degree scatter caused by the human ribcage and spine will corrupt the visibility of the human lung.…”

Section: Discussionmentioning

confidence: 99%

“…However, a very initial benchmark (Fig. 5) following the method described by von Berg et al suggests that the inherent micro-structural sensitivity of dark-field imaging strongly outweighs the diagnostic benefits arising from ribcage suppression/correction algorithms only 25 : while one small nodule in the left upper lung (green box) does indeed become detectable in the transmission image after removing the ribcage, another tumor in the upper right lung (blue box) remains hidden in the transmission signal throughout rib-removal, and is reliably detected in the darkfield channel only.

Figure 5Outlook: initial comparison of ribcage-corrected transmission versus dark-field radiography and impact on tumor detection quality. In the left upper lung (green box) a small nodule is superimposed by multiple ribs and is visible only after ribcage removal, as indicated by a white circle in the filtered transmission radiogram.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

X-ray Dark-field Radiography - In-Vivo Diagnosis of Lung Cancer in Mice

Scherer

Yaroshenko

Bölükbas

et al. 2017

Sci Rep

View full text Add to dashboard Cite

Accounting for about 1.5 million deaths annually, lung cancer is the prevailing cause of cancer deaths worldwide, mostly associated with long-term smoking effects. Numerous small-animal studies are performed currently in order to better understand the pathogenesis of the disease and to develop treatment strategies. Within this letter, we propose to exploit X-ray dark-field imaging as a novel diagnostic tool for the detection of lung cancer on projection radiographs. Here, we demonstrate in living mice bearing lung tumors, that X-ray dark-field radiography provides significantly improved lung tumor detection rates without increasing the number of false-positives, especially in the case of small and superimposed nodules, when compared to conventional absorption-based imaging. While this method still needs to be adapted to larger mammals and finally humans, the technique presented here can already serve as a valuable tool in evaluating novel lung cancer therapies, tested in mice and other small animal models.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

X-ray Dark-field Radiography - In-Vivo Diagnosis of Lung Cancer in Mice

Scherer

Yaroshenko

Bölükbas

et al. 2017

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In the original Indiana images we suppress the bones (ribs and clavicles) using a method from [8], [9]. The method preserves the remaining details originally overlaid with the bones (see Fig.…”

Section: Bone Suppressionmentioning

confidence: 99%

When Does Bone Suppression And Lung Field Segmentation Improve Chest X-Ray Disease Classification?

Baltruschat

Steinmeister

Ittrich

et al. 2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

Self Cite

View full text Add to dashboard Cite

Chest radiography is the most common clinical examination type. To improve the quality of patient care and to reduce workload, methods for automatic pathology classification have been developed. In this contribution we investigate the usefulness of two advanced image pre-processing techniques, initially developed for image reading by radiologists, for the performance of Deep Learning methods. First, we use bone suppression, an algorithm to artificially remove the rib cage. Secondly, we employ an automatic lung field detection to crop the image to the lung area. Furthermore, we consider the combination of both in the context of an ensemble approach.In a five-times re-sampling scheme, we use Receiver Operating Characteristic (ROC) statistics to evaluate the effect of the pre-processing approaches. Using a Convolutional Neural Network (CNN), optimized for X-ray analysis, we achieve a good performance with respect to all pathologies on average. Superior results are obtained for selected pathologies when using pre-processing, i.e. for mass the area under the ROC curve increased by 9.95%. The ensemble with pre-processed trained models yields the best overall results.

show abstract

“…The identification of ribs has many applications in chest radiography. Ribs may obscure important findings in the lung parenchyma, why rib shadows can be either excluded from the automatic analysis (Candemir et al, 2016) or suppressed from the image (von Berg et al, 2016) to minimize their impact. In contrast to rib segmentation, rib labeling is required in chest X-ray quality assessment.…”

Section: Introductionmentioning

confidence: 99%

Sequential Rib Labeling and Segmentation in Chest X-Ray using Mask R-CNN

Jöran¹,

Heinrich²,

Berg³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Mask R-CNN is a state-of-the-art network architecture for the detection and segmentation of object instances in the computer vision domain. In this contribution, it is used to localize, label and segment individual ribs in anterior-posterior chest X-ray images.For this purpose, several extensions have been made to the original architecture, in order to address the specific challenges of this application. This includes the use of rib specific networks, facilitating dedicated anchor boxes sampled from a training set, as well as a sequential processing of all ribs. Here, the segmentation result of the upper neighbor rib is used as additional input to the network.This approach is the first addressing both rib segmentation and anatomical labeling in chest radiographs. The results are comparable or even better than existing methods aiming only at segmentation.

show abstract

A novel bone suppression method that improves lung nodule detection

Abstract: Subtracting all reconstructed bone shadows from the original image results in a soft image where lung nodules are no longer obscured by bone shadows. Both the sensitivity and the specificity of experienced radiologists increased.

Cited by 20 publications

References 21 publications

X-ray Dark-field Radiography - In-Vivo Diagnosis of Lung Cancer in Mice

X-ray Dark-field Radiography - In-Vivo Diagnosis of Lung Cancer in Mice

When Does Bone Suppression And Lung Field Segmentation Improve Chest X-Ray Disease Classification?

Sequential Rib Labeling and Segmentation in Chest X-Ray using Mask R-CNN

Contact Info

Product

Resources

About