An improved automatic computer aided tube detection and labeling system on chest radiographs

Ramakrishna, Bharath; Brown, Matthew S.; Goldin, Jonathan G.; Enzmann, Dieter R.

doi:10.1117/12.911839

Cited by 17 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past, conventional computer-aided detection (CAD) solutions often required hand-engineered rules, significant image-preprocessing and feature extraction [4]. For example, one CAD study achieved approximately 84% sensitivity for feeding tube position on radiography, but with lower specificity with up to 0.02 false positives per image, limiting its suitability for clinical use [5]. Recent significant advances in artificial intelligence using deep learning to classify images using multi-layered neural networks make an automated solution for nasoenteric feeding tube placement detection possible [6–8].…”

Section: Purposementioning

confidence: 99%

Assessment of Critical Feeding Tube Malpositions on Radiographs Using Deep Learning

et al. 2019

View full text Add to dashboard Cite

Assess the efficacy of deep convolutional neural networks (DCNNs) in detection of critical enteric feeding tube malpositions on radiographs. 5475 de-identified HIPAA compliant frontal view chest and abdominal radiographs were obtained, consisting of 174 x-rays of bronchial insertions and 5301 non-critical radiographs, including normal course, normal chest, and normal abdominal x-rays. The ground-truth classification for enteric feeding tube placement was performed by two board-certified radiologists. Untrained and pretrained deep convolutional neural network models for Inception V3, ResNet50, and DenseNet 121 were each employed. The radiographs were fed into each deep convolutional neural network, which included untrained and pretrained models. The Tensorflow framework was used for Inception V3, ResNet50, and DenseNet. Images were split into training (4745), validation (630), and test (100). Both real-time and preprocessing image augmentation strategies were performed. Receiver operating characteristic (ROC) and area under the curve (AUC) on the test data were used to assess the models. Statistical differences among the AUCs were obtained. p < 0.05 was considered statistically significant. The pretrained Inception V3, which had an AUC of 0.87 (95 CI; 0.80–0.94), performed statistically significantly better ( p < .001) than the untrained Inception V3, with an AUC of 0.60 (95 CI; 0.52–0.68). The pretrained Inception V3 also had the highest AUC overall, as compared with ResNet50 and DenseNet121, with AUC values ranging from 0.82 to 0.85. Each pretrained network outperformed its untrained counterpart. ( p < 0.05). Deep learning demonstrates promise in differentiating critical vs. non-critical placement with an AUC of 0.87. Pretrained networks outperformed untrained ones in all cases. DCNNs may allow for more rapid identification and communication of critical feeding tube malpositions.

show abstract

Section: Purposementioning

confidence: 99%

Assessment of Critical Feeding Tube Malpositions on Radiographs Using Deep Learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Ramakrishna et al [10] proposed a method combing template matching, morphological processing, and region growing to detect and classify catheters on chest radiographs. They did some further work regarding a tube detection and labeling system [11]. The proposed computer-aided detection (CAD) system is based on generating tube candidates from multiple seed points using a voting scheme to identify the tubes.…”

Section: Introductionmentioning

confidence: 99%

Endotracheal tubes positioning detection in adult portable chest radiography for intensive care unit

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Suppression of catheters is a new research area; we are not aware of any previously published method that addresses this topic. In this experiment we used manual segmentations of the catheters, but automatic catheter (tip) detection methods in chest radiographs have been developed [49], [50] and could be combined with the presented algorithm to achieve fully automatic catheter removal in chest radiographs. The removal of foreign objects, such as catheters, is also important for automatic processing by computer aided detection algorithms to prevent false positives [51].…”

Section: Discussionmentioning

confidence: 99%

Suppression of Translucent Elongated Structures: Applications in Chest Radiography

Hogeweg

Sánchez

Ginneken

2013

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Projection images, such as those routinely acquired in radiological practice, are difficult to analyze because multiple 3-D structures superimpose at a single point in the 2-D image. Removal of particular superimposed structures may improve interpretation of these images, both by humans and by computers. This work therefore presents a general method to isolate and suppress structures in 2-D projection images. The focus is on elongated structures, which allows an intensity model of a structure of interest to be extracted using local information only. The model is created from profiles sampled perpendicular to the structure. Profiles containing other structures are detected and removed to reduce the influence on the model. Subspace filtering, using blind source separation techniques, is applied to separate the structure to be suppressed from other structures. By subtracting the modeled structure from the original image a structure suppressed image is created. The method is evaluated in four experiments. In the first experiment ribs are suppressed in 20 artificial radiographs simulated from 3-D lung computed tomography (CT) images. The proposed method with blind source separation and outlier detection shows superior suppression of ribs in simulated radiographs, compared to a simplified approach without these techniques. Additionally, the ability of three observers to discriminate between patches containing ribs and containing no ribs, as measured by the area under the receiver operating characteristic curve (AUC), reduced from 0.99-1.00 on original images to 0.75-0.84 on suppressed images. In the second experiment clavicles are suppressed in 253 chest radiographs. The effect of suppression on clavicle visibility is evaluated using the clavicle contrast and border response, showing a reduction of 78% and 34%, respectively. In the third experiment nodules extracted from CT were simulated close to the clavicles in 100 chest radiographs. It was found that after suppression contrast of the nodules was higher than of the clavicles (1.35 and 0.55, respectively) than on original images (1.83 and 2.46, respectively). In the fourth experiment catheters were suppressed in chest radiographs. The ability of three observers to discriminate between patches originating from 36 images with and 21 images without catheters, as measured by the AUC, reduced from 0.98-0.99 on original images to 0.64-0.74 on suppressed images. We conclude that the presented method can markedly reduce the visibility of elongated structures in chest radiographs and shows potential to enhance diagnosis.

show abstract

An improved automatic computer aided tube detection and labeling system on chest radiographs

Cited by 17 publications

References 0 publications

Assessment of Critical Feeding Tube Malpositions on Radiographs Using Deep Learning

Assessment of Critical Feeding Tube Malpositions on Radiographs Using Deep Learning

Endotracheal tubes positioning detection in adult portable chest radiography for intensive care unit

Suppression of Translucent Elongated Structures: Applications in Chest Radiography

Contact Info

Product

Resources

About