Is There a Need for Repeat Radiologic Examination of Children with Esophageal Coin Foreign Body?

Chest X-ray Foreign Objects Detection Using Artificial Intelligence

Diagnostic imaging has become an integral part of the healthcare system. In recent years, scientists around the world have been working on artificial intelligence-based tools that help in achieving better and faster diagnoses. Their accuracy is crucial for successful treatment, especially for imaging diagnostics. This study used a deep convolutional neural network to detect four categories of objects on digital chest X-ray images. The data were obtained from the publicly available National Institutes of Health (NIH) Chest X-ray (CXR) Dataset. In total, 112,120 CXRs from 30,805 patients were manually checked for foreign objects: vascular port, shoulder endoprosthesis, necklace, and implantable cardioverter-defibrillator (ICD). Then, they were annotated with the use of a computer program, and the necessary image preprocessing was performed, such as resizing, normalization, and cropping. The object detection model was trained using the You Only Look Once v8 architecture and the Ultralytics framework. The results showed not only that the obtained average precision of foreign object detection on the CXR was 0.815 but also that the model can be useful in detecting foreign objects on the CXR images. Models of this type may be used as a tool for specialists, in particular, with the growing popularity of radiology comes an increasing workload. We are optimistic that it could accelerate and facilitate the work to provide a faster diagnosis.

Which coin is easier to pass esophagus spontaneously?

OBJECTIVE

To determine the factors associated with the spontaneous passage (SP) of coins lodged in the esophagus in children.

SUBJECTS AND METHODS

A total of 351 pediatric patients with coin ingestion admitted to our hospital from March 2016 to March 2019 were included in the study. The patients underwent a period of overnight watch with a repeated chest x-ray within 24 h after the commencement of hospitalization. The influencing factors (sex, age, types of coin, time in the esophagus, and location) were analyzed.

RESULTS

The repeated chest x-ray showed coins that had passed into the stomach or intestine in 68 patients. Sex, age, time in the esophagus, location in the esophagus or the types of coins were not associated with SP, but the distribution of the esophageal coins varied statistically significantly in the different ages.

CONCLUSION

Coins pass spontaneously through the esophagus (19.4%) within 24 h, unrelated to sex, age, time of esophagus lodging, coin location in the esophagus, or coin types. Children approximately two years old were more likely to ingest small coins (10 or 50 cents), whereas children approximately five years old were more likely to ingest a large coin (1 Yuan).

Accuracy of chest X-Ray measurements of pediatric esophageal coins

OBJECTIVE

To determine the accuracy of chest x-ray measurements in children using ingested radiopaque foreign bodies of known size.

METHODS

A database of foreign body ingestions at a tertiary care children's hospital was queried from 2013 to 2016 for children who had ingested a US coin, had a pre-operative chest x-ray and documentation of coin type at the time of endoscopic removal. Four blinded research subjects measured the coin diameter on chest x-ray using iSite PACS software and based on the measurement, predicted the coin type. Measurements were compared to the known coin diameters published by the US Mint.

RESULTS

A total of 51 patients with sixteen esophageal quarters (diameter 24.26 mm), fourteen nickels (21.21 mm), fourteen pennies (19.05 mm) and seven dimes (17.91 mm) were included in the study. The four subjects had a mean accuracy of 60.3% (range 49.0%-72.5%) in predicting the correct coin type. Across all raters, there was poor agreement for pennies (kappa = 0.161) and dimes (kappa = 0.131), fair agreement for nickels (kappa = 0.259), good agreement for quarters (kappa = 0.687), and fair agreement overall (kappa = 0.371). The study measurements overestimated the coin size in 203 of the 204 measurements by a mean of 1.84 mm (range -0.31-3.85 mm). The mean size discrepancy was larger (2.40 vs. 1.30 mm, p < 0.001) and accuracy of coin type identification was worse (44.6% vs. 74.1%, p = 0.001) in children <4 years old.

CONCLUSIONS

Measurement of esophageal coins on chest x-ray is relatively inaccurate and overestimates the size in the majority of cases. Clinicians should use caution when performing fine measurements on chest x-rays, especially in children younger than 4 years old.

Clinical features and standardized diagnosis and treatment of esophageal foreign bodies

AIM

To summarize the clinical characteristics of esophageal foreign bodies and to explore their standardized diagnosis and treatment.

METHODS

This retrospective study was conducted at our hospital from July 2011 to July 2017, and we reviewed the clinical data for 1190 patients with esophageal foreign bodies with regard to their sex, age, department patients first visited, treatment time, type, incarcerated site, treatment plan, and length of hospital stay.

RESULTS

Of 1190 patients included, 568 were male and 622 were female, with a male-to-female ratio of 1.0:1.1. They aged from 2 mo to 99 years (mean, 45 years ± 28.44 years), with a median age of 54 years; 293 (24.6%) patients were under 15 years, 293 (24.6%) were between 15 and 55 years, and 604 (50.8%) over 55 years. Otolaryngology and head surgery department was the most first-visited department (966, 81.2%), followed by gastroenterology department (138, 11.6%), thoracic surgery department (46, 3.4%), and others (40, 3.4%). There were 716 (60.2%) patients who visited hospital within 24 h, 126 (10.6%) in 24 to 72 h, and 348 (29.2%) over 72 h. The foreign bodies were plant-based in 448 (37.6%) patients, animal-based in 403 (33.9%), metallic in 200 (16.8%), and composite material-based in 139 (11.7%), with jujube pits, chicken bones, and coins accounting for 62.9% (750 patients) of all cases. The foreign bodies were most commonly located in the upper orifice of the esophagus (827, 69.5%), followed by the upper part (245, 20.6%), the middle and lower parts (94, 7.8%), and others (25, 2.1%). We treated 1088 (91.4%) patients by endoscopy and 41 (3.4%) by surgery. The duration of hospitalization ranged from 1 to 71 d (median, 5 d; mean, 5.9 d ± 4.9 d).

CONCLUSION

Esophageal foreign bodies most commonly occur in the upper orifice of the esophagus. Standardized diagnosis and treatment are important. Esophageal foreign bodies should be taken out within 24 h. Timely correction of water and electrolyte disturbance, effective antibiotic therapy, high nutrition support, and temporary esophageal, if necessary, are beneficial to the patient's recovery.