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

Chen, Sheng; Zhang, Min; Yao, Liping; Xu, Wentao

doi:10.1007/s11548-016-1430-3

Cited by 17 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, two ways of localizing the tip of the catheter are described in the literature. The first is by tracing from an initial seed point, either manually selected or automatically detected, until a criterion is fulfilled (26,27), e.g. a sudden intensity drop in the searching direction.…”

Section: Q2: Where Is the Tip Of The Catheter?mentioning

confidence: 99%

“…The downside of this operation is the computation complexity that could prevent it from being used in a realtime environment. Kao et al and Chen et al used an even simpler method where the next point is determined on a row basis (26,27). The x location of the next point xnext is the one with the highest intensity values among [xcurrent1, xcurrent, xcurrent+1].…”

Section: Q3: What Is the Course Of The Catheter?mentioning

confidence: 99%

See 1 more Smart Citation

Computer-aided Assessment of Catheters and Tubes on Radiographs: How Good Is Artificial Intelligence for Assessment?

Xin

Adams

Henderson

et al. 2020

Radiology: Artificial Intelligence

View full text Add to dashboard Cite

Catheters are the second most common abnormal finding on radiographs. The position of catheters must be assessed on all radiographs, as serious complications can arise if catheters are malpositioned. However, due to the large number of radiographs performed each day, there can be substantial delays between the time a radiograph is performed and when it is interpreted by a radiologist. Computer-aided approaches hold the potential to assist in prioritizing radiographs with potentially malpositioned catheters for interpretation and automatically insert text indicating the placement of catheters in radiology reports, thereby improving radiologists' efficiency. After 50 years of research in computer-aided diagnosis, there is still a paucity of study in this area. With the development of deep learning approaches, the problem of catheter assessment is far more solvable. Therefore, we have performed a review of current algorithms and identified key challenges in building a reliable computer-aided diagnosis system for assessment of catheters on radiographs. This review may serve to further the development of machine learning approaches for this important use case.

show abstract

Section: Q2: Where Is the Tip Of The Catheter?mentioning

confidence: 99%

Section: Q3: What Is the Course Of The Catheter?mentioning

confidence: 99%

Computer-aided Assessment of Catheters and Tubes on Radiographs: How Good Is Artificial Intelligence for Assessment?

Xin

Adams

Henderson

et al. 2020

Radiology: Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Chest X-ray radiographs (CXRs) are a standard imaging modality that accounts for about 40% of the total radiographs in a department of radiology. One-third of these CXRs are acquired by using the portable devices, such as computer radiograph (CR), digital radiograph (DR) in intensive care units (ICUs) [1]. Compared to the standard CXRs, patient respiratory and movement may lead to artifacts in the image because of the longer exposure time [2].…”

Section: Introductionmentioning

confidence: 99%

Enhancement of Chest Radiograph in Emergency Intensive Care Unit by Means of Reverse Anisotropic Diffusion-Based Unsharp Masking Model

Chen

Cai

2019

Diagnostics

Self Cite

View full text Add to dashboard Cite

In intensive care units (ICUs), supporting devices play an important role, and the placement of these devices must be accurate, such as catheters and tubes. Taking portable chest radiograph (CXRs) for patients in ICU is a standard procedure. However, non-optimized exposure settings and misaligned body positions usually mean that portable CXRs are not in acceptable working condition. The purpose of this study was to enhance ICU CXRs to assist radiologists in the positioning of endotracheal, feeding, and nasogastric tubes in ICU patients. The unsharp masking model (USM) was a classical image enhancement technique. Because of the isotropic diffusion filter applied in this model, USM enhanced the edge information and noise simultaneously. In this paper, we proposed a reverse anisotropic diffusion (RAD)-based USM technique for enhancement of line structures in ICU CXRs. First, a RAD algorithm was applied to replace the Gaussian filter in the classical USM. The RAD algorithm only produced a smoothed image, in which edge information was smoothed while the noise was preserved. Then, the smoothed image was subtracted from the original image to produce the unsharp mask whereby only the edges were retained. Consequently, only edge information was enhanced in the final enhanced image by using the RAD-based USM model. The proposed method was tested for 87 ICU CXRs and the findings indicate that this approach can enhance image edges efficiently while suppressing noise.

show abstract

“…Using the acquired radiographs, Computer-Aided Detection (CAD) systems can assist physicians in automatic detection of the ET tubes. Previous studies used classical approaches to determine seed points followed by a line tracking algorithms [3,4]. A more recent study used a convolutional neural network (CNN) classification system for the presence or absence identification of the ET tube, with reported area under curve (AUC) of 0.99; and a second classification network for identification of low vs normal positioning of the ET tube, with AUC of 0.81 [5].…”

Section: Introductionmentioning

confidence: 99%

“…A more recent study used a convolutional neural network (CNN) classification system for the presence or absence identification of the ET tube, with reported area under curve (AUC) of 0.99; and a second classification network for identification of low vs normal positioning of the ET tube, with AUC of 0.81 [5]. The above studies used private datasets of portable chest X-ray images with a relatively small amount of cases: 64 [3] and 87 [4] were used for the classical approaches; 300 cases were used for the CNN based solution [5].…”

Section: Introductionmentioning

confidence: 99%

Endotracheal Tube Detection and Segmentation in Chest Radiographs using Synthetic Data

Frid-Adar¹,

Amer²,

Greenspan³

2019

Preprint

View full text Add to dashboard Cite

Chest radiographs are frequently used to verify the correct intubation of patients in the emergency room. Fast and accurate identification and localization of the endotracheal (ET) tube is critical for the patient. In this study we propose a novel automated deep learning scheme for accurate detection and segmentation of the ET tubes. Development of automatic systems using deep learning networks for classification and segmentation require large annotated data which is not always available.Here we present an approach for synthesizing ET tubes in real X-ray images. We suggest a method for training the network, first with synthetic data and then with real X-ray images in a fine-tuning phase, which allows the network to train on thousands of cases without annotating any data. The proposed method was tested on 477 real chest radiographs from a public dataset and reached AUC of 0.99 in classifying the presence vs. absence of the ET tube, along with outputting high quality ET tube segmentation maps.

show abstract

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

Abstract: The proposed method could be useful for detecting malpositioned ET tubes in ICU CXRs.

Cited by 17 publications

References 20 publications

Computer-aided Assessment of Catheters and Tubes on Radiographs: How Good Is Artificial Intelligence for Assessment?

Computer-aided Assessment of Catheters and Tubes on Radiographs: How Good Is Artificial Intelligence for Assessment?

Enhancement of Chest Radiograph in Emergency Intensive Care Unit by Means of Reverse Anisotropic Diffusion-Based Unsharp Masking Model

Endotracheal Tube Detection and Segmentation in Chest Radiographs using Synthetic Data

Contact Info

Product

Resources

About