Postprocedural chest radiograph: Impact on the management in critical care unit

Gupta, Prashant; Gupta, Kumkum; Jain, Manish; Garg, Tanuj

doi:10.4103/0259-1162.134481

Cited by 19 publications

(22 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Optimal positioning of an ETT is essential for therapeutic effect and is commonly cited to be approximately 5 ± 2 cm above the carina [2]. By contrast, a misplaced ETT may often result in serious complications including the collapse or hyperinflation of a lung [3], the overall risk of which may be as high as 40% in the ICU setting [4]. ETT position is typically assessed using a frontal chest radiograph.…”

Section: Introductionmentioning

confidence: 99%

Identification and Localization of Endotracheal Tube on Chest Radiographs Using a Cascaded Convolutional Neural Network Approach

Kara¹,

Akers

Chang

2021

J Digit Imaging

View full text Add to dashboard Cite

Rapid and accurate assessment of endotracheal tube (ETT) location is essential in the intensive care unit (ICU) setting, where timely identification of a mispositioned support device may prevent significant patient morbidity and mortality. This study proposes a series of deep learning-based algorithms which together iteratively identify and localize the position of an ETT relative to the carina on chest radiographs. Using the open-source MIMIC Chest X-Ray (MIMIC-CXR) dataset, a total of 16,000 patients were identified (8000 patients with an ETT and 8000 patients without an ETT). Three different convolutional neural network (CNN) algorithms were created. First, a regression loss function CNN was trained to estimate the coordinate location of the carina, which was then used to crop the original radiograph to the distal trachea and proximal bronchi. Second, a classifier CNN was trained using the cropped inputs to determine the presence or absence of an ETT. Finally, for radiographs containing an ETT, a third regression CNN was trained to both refine the coordinate location of the carina and identify the location of the distal ETT tip. Model accuracy was assessed by comparing the absolute distance of prediction and ground-truth coordinates as well as CNN predictions relative to measurements documented in original radiologic reports. Upon five-fold cross validation, binary classification for the presence or absence of ETT demonstrated an accuracy, sensitivity, specificity, PPV, NPV, and AUC of 97.14%, 97.37%, 96.89%, 97.12%, 97.15%, and 99.58% respectively. CNN predicted coordinate location of the carina, and distal ETT tip was estimated within a median error of 0.46 cm and 0.60 cm from ground-truth annotations respectively. Overall final CNN assessment of distance between the carina and distal ETT tip was predicted within a median error of 0.60 cm from manual ground-truth annotations, and a median error of 0.66 cm from measurements documented in the original radiology reports. A serial cascaded CNN approach demonstrates high accuracy for both identification and localization of ETT tip and carina on chest radiographs. High performance of the proposed multi-step strategy is in part related to iterative refinement of coordinate localization as well as explicit image cropping which focuses algorithm attention to key anatomic regions of interest.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification and Localization of Endotracheal Tube on Chest Radiographs Using a Cascaded Convolutional Neural Network Approach

Kara¹,

Akers

Chang

2021

J Digit Imaging

View full text Add to dashboard Cite

show abstract

“…В целом анализ литературных источников зарубежных авторов показал, что мобильная цифровая рентгенография на основе портативного оборудования -полезный инструмент для обследования пациентов в отделениях интенсивной терапии [6], в домах престарелых [4,5], в местах лишения свободы или в приютах для бездомных [7], там, где транспортировка пациента в отдел лучевой диагностики больницы может быть затруднена. В нашей стране анализ данных, посвященных съемке в Рис.…”

Section: Discussionunclassified

Analysis of X-Ray Research in Wards

Алексеева

2017

Medicinskaâ vizualizaciâ

View full text Add to dashboard Cite

Introduction.X-ray is a common diagnostic procedure in a multi-disciplinary hospitals. In the available scientific litera ture, there are some studies of the radiography in nonspecialized conditions. However, there are few aggregate data of these studies to date.Objectives.Analysis of the results of radiography in wards and resuscitation rooms, performed in multi-purpose hospitals, with the aim of forming requirements to the class of equipment for radiography in the conditions of the ward.Materials and methods.4081 X-ray studies were studied from 2015 to 2016.Results.During the analysis it was determined that in unspecialized conditions 75.0% of the shots fell to chest organs, studies of the musculoskeletal system were revealed in 22.0% of cases and abdominal organs were observed in 3%. Pathological changes were not detected for 2221 patients, which amounted to 54.4%. It was found that the most frequent disease of the chest were pneumonia of various genesis, complicated by the presence of hydro thorax.Conclusions.Based on the analysis of X-ray researches, the indications for the studies were refined and supplemented, medical requirements for X-ray machines for shooting under these conditions were formulated.

show abstract

“…Patients admitted to COVID-units are often intubated for mechanical ventilation and require nutrition via an enteral feeding tube. Gastric tube placement is generally a safe procedure, but in rare instances, complications such as bronchial placement, pneumothorax, pneumonia, tracheal or esophageal injury can occur[ 30 ]. Typically, a CXR is required for confirmation of the tube placement in the stomach.…”

Section: Introductionmentioning

confidence: 99%

Point-of-care ultrasound in a pandemic: Practical guidance in COVID-19 units

Deshwal

Pradhan

Mukherjee

2021

wjccm

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) pandemic has stretched our healthcare system to the brink, highlighting the importance of efficient resource utilization without compromising healthcare provider safety. While advanced imaging is a great resource for diagnostic purposes, the risk of contamination and infection transmission is high and requires extensive logistical planning for intrahospital patient transport, healthcare provider safety, and post-imaging decontamination. This dilemma has necessitated the transition to more bedside imaging. More so than ever, during the current pandemic, the clinical utility and importance of point-of-care ultrasound (POCUS) cannot be overstressed. It allows for safe and efficient beside procedural guidance and provides front line providers with valuable diagnostic information that can be acted upon in real-time for immediate clinical decision-making. The authors have been routinely using POCUS for the management of COVID-19 patients both in the emergency department and in intensive care units turned into “COVID-units.” In this article, we review the nuances of using POCUS in a pandemic situation and maximizing diagnostic output from this bedside technology. Additionally, we review various methods and diagnostic uses of POCUS which can replace conventional imaging and bridge current literature and common clinical practices in critically ill patients. We discuss practical guidance and pertinent review of the literature for the most relevant procedural and diagnostic guidance of respiratory illness, hemodynamic decompensation, renal failure, and gastrointestinal disorders experienced by many patients admitted to COVID-units.

show abstract

Postprocedural chest radiograph: Impact on the management in critical care unit

Cited by 19 publications

References 12 publications

Identification and Localization of Endotracheal Tube on Chest Radiographs Using a Cascaded Convolutional Neural Network Approach

Identification and Localization of Endotracheal Tube on Chest Radiographs Using a Cascaded Convolutional Neural Network Approach

Analysis of X-Ray Research in Wards

Point-of-care ultrasound in a pandemic: Practical guidance in COVID-19 units

Contact Info

Product

Resources

About