Initial quality performance results using a phantom to simulate chest computed radiography

Development and clinical feasibility of a reduced-dose radiograph in children for feeding tube placement

BACKGROUND

Temporary feeding tubes are commonly used but may lead to complications if malpositioned. Radiographs are the gold standard for assessing tube position, but clinician concern over radiation risks may curtail their use.

OBJECTIVE

We describe development and use of a reduced dose feeding tube radiograph (RDFTR) targeted for evaluation of feeding tube position.

MATERIALS AND METHODS

Age-based abdominal radiograph was adapted to use the lowest mAs setting of 0.32 mAs with field of view between carina and iliac crests. The protocol was tested in DIGI-13 line-pair plates and anthropomorphic phantoms. Retrospective review of initial clinical use compared dose area product (DAP) for RDFTR and routine abdomen, chest, or infant chest and abdomen. Review of RDFTR reports assessed tube visibility, malpositioning, and incidental critical findings.

RESULTS

Testing through a line-pair phantom showed loss of spatial resolution from 2.2 line pairs to 0.6 line pairs but preserved visibility of feeding tube tip in RDFTR protocol. DAP comparisons across 23,789 exams showed RDFTR reduced median DAP 72-93% compared to abdomen, 55-78% compared to chest, and 76-79% compared to infant chest and abdomen (p<0.001). Review of 3286 reports showed tube was visible in 3256 (99.1%), malpositioned in airway 8 times (0.2%) and in the esophagus 74 times (2.3%). The tip was not visualized in 30 (0.9%). Pneumothorax or pneumoperitoneum was noted seven times (0.2%) but was expected or spurious in five of these cases.

CONCLUSION

RDFTR significantly reduces radiation dose in children with temporary feeding tubes while maintaining visibility of tube tip.

Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography

Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We collected 3316 images (1016 pneumothorax and 2300 normal images), and all images were set to the standard contrast level (100%) and stored in the Digital Imaging and Communication in Medicine and Joint Photographic Experts Group (JPEG) formats. Data were randomly separated into 80% of training and 20% of test sets, and the contrast of images in the test set was changed to 5 levels (50%, 75%, 100%, 125%, and 150%). We trained the model to detect pneumothorax using ResNet-50 with 100% level images and tested with 5-level images in the two formats. While comparing the overall performance between each contrast level in the two formats, the area under the receiver-operating characteristic curve (AUC) was significantly different (all p < 0.001) except between 125 and 150% in JPEG format (p = 0.382). When comparing the two formats at same contrast levels, AUC was significantly different (all p < 0.001) except 50% and 100% (p = 0.079 and p = 0.082, respectively). The contrast level and format of medical images could influence the performance of the deep learning model. It is required to train with various contrast levels and formats of image, and further image processing for improvement and maintenance of the performance.