1
|
Kaplan SL, Jalloul M, Akbari E, White AM, Shumyatsky G, Flowers C, Srinivasan V, Zhu X, Irving SY. Development and clinical feasibility of a reduced-dose radiograph in children for feeding tube placement. Pediatr Radiol 2024; 54:218-227. [PMID: 38141080 DOI: 10.1007/s00247-023-05829-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/29/2023] [Revised: 12/04/2023] [Accepted: 12/05/2023] [Indexed: 12/24/2023]
Abstract
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.
Collapse
Affiliation(s)
- Summer L Kaplan
- Department of Radiology, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, 19104, USA.
- Perelman School of Medicine, University of Pennsylvania, 3400 Spruce St, Philadelphia, PA, USA.
| | - Mohammad Jalloul
- Department of Radiology, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, 19104, USA
| | - Erfan Akbari
- Department of Radiology, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, 19104, USA
| | - Ammie M White
- Department of Radiology, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, 19104, USA
- Perelman School of Medicine, University of Pennsylvania, 3400 Spruce St, Philadelphia, PA, USA
| | | | - Colleen Flowers
- Department of Radiology, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, 19104, USA
| | - Vijay Srinivasan
- Perelman School of Medicine, University of Pennsylvania, 3400 Spruce St, Philadelphia, PA, USA
- Division of Critical Care Medicine, Department of Pediatrics, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, USA
| | - Xiaowei Zhu
- Department of Radiology, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, 19104, USA
| | - Sharon Y Irving
- Division of Critical Care Medicine, Department of Pediatrics, Children's Hospital of Philadelphia, 3401 Civic Center Blvd, Philadelphia, PA, USA
- University of Pennsylvania School of Nursing, 418 Curie Blvd, Philadelphia, PA, USA
| |
Collapse
|
2
|
Yoon MS, Kwon G, Oh J, Ryu J, Lim J, Kang BK, Lee J, Han DK. Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography. J Digit Imaging 2023; 36:1237-1247. [PMID: 36698035 PMCID: PMC10287877 DOI: 10.1007/s10278-022-00772-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2022] [Revised: 12/23/2022] [Accepted: 12/29/2022] [Indexed: 01/26/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Myeong Seong Yoon
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
- Machine Learning Research Center for Medical Data, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
- Department of Radiological Science, Eulji University, 553 Sanseong-daero, Seongnam-si, Gyeonggi Do, 13135, Republic of Korea
| | - Gitaek Kwon
- Department of Computer Science, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
- VUNO, Inc, 479 Gangnam-daero, Seocho-gu, Seoul, 06541, Republic of Korea
| | - Jaehoon Oh
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea.
- Machine Learning Research Center for Medical Data, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea.
| | - Jongbin Ryu
- Department of Software and Computer Engineering, Ajou University, 206 World cup-ro, Suwon-si, Gyeonggi Do, 16499, Republic of Korea.
| | - Jongwoo Lim
- Department of Computer Science, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
- Machine Learning Research Center for Medical Data, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
| | - Bo-Kyeong Kang
- Machine Learning Research Center for Medical Data, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
- Department of Radiology, College of Medicine, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
| | - Juncheol Lee
- Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-Ro, Seongdong-Gu, Seoul, 04763, Republic of Korea
| | - Dong-Kyoon Han
- Department of Radiological Science, Eulji University, 553 Sanseong-daero, Seongnam-si, Gyeonggi Do, 13135, Republic of Korea
| |
Collapse
|