Ashok Suragala
Gurugubelli Sai Dilip Kumar
Sri Karthik Avala
- Assistant Professor, Department of Computer Science and Engineering, Jawaharlal Nehru Technological University, Gurajada, Vizianagaram, Andhra Pradesh, India
- Student, Department of Mechanical Engineering, Andhra University College of Engineering, Visakhapatnam, Andhra Pradesh, India
- Student, Department of Computer Science & Engineering, VIT Chennai University, Chennai, Tamil Nadu, India
Abstract
Tube misplacement can lead to complications in patients together with serious medical malpractice cases. Intubation and the insertion of various medical tubes are employed to safeguard the airways of critically ill patients. Critically unwell patients undergo intubation, with the insertion of various medical tubes to safeguard their airways. The nasogastric tube serves the purpose of providing nutrition, while the central venous catheter finds application in a range of medical procedures. The significant challenge lies in doctors adhering to medical protocols to ensure the correct installation of these tubes. The implementation of medical protocols by physicians to guarantee the correct placement of tubes presents a significant challenge. Misplaced tubes increase the probability of complications in patients and, in the worst of cases, even lead to mortality. So, identifying the proper positioning of tubes before starting the procedure is crucial. In this paper, we propose identifying the misplaced tube and catheters detection using deep learning approach with accurate outcome.
Keywords: Tube misalignment, EfficientNet B7, central venous catheter, deep learning, nasogastric tube, EfficientNet model
[This article belongs to International Journal of Computer Science Languages(ijcsl)]
Browse Figures
References
Mallon DH, McNamara CD, Rahmani GS, O’Regan DP, Amiras DG. Automated detection of enteric tubes misplaced in the respiratory tract on chest radiographs using deep learning with two centre validation. Clin Radiol. 2022; 77 (10): e758–e764.
Jung HC, Kim C, Oh J, Kim TH, Kim B, Lee J, Chung JH, Byun H, Yoon MS, Lee DK. Position classification of the endotracheal tube with automatic segmentation of the trachea and the tube on plain chest radiography using deep convolutional neural network. J Person Med. 2022; 12 (9): 1363.
Elaanba A, Ridouani M, Hassouni L. Automatic detection using deep convolutional neural networks for 11 abnormal positioning of tubes and catheters in chest X-ray images. In: 2021 IEEE World AI IoT Congress (AIIoT), Seattle, WA, USA, May 10–13, 2021. pp. 0007–0012.
Yang C, Qiao S, Yu Q, Yuan X, Zhu Y, Yuille A, Adam H, Chen LC. Moat: alternating mobile convolution and attention brings strong vision models. arXiv preprint arXiv:2210.01820. October 2022. doi: 10.48550/arXiv.2210.01820.
Rapeti D, Reddy VD. A multi range morphological model on dermoscopy images with edge based segmentation for image quality enhancement for skin lesion classification. Rev d’Intell Artif. 2023; 37 (2): 331–339.
Mirza MW, Siddiq A, Khan IR. A comparative study of medical image enhancement algorithms and quality assessment metrics on COVID-19 CT images. Signal Image Video Process. 2023; 17 (4): 915–924.
Pham TX. Image Segmentation Through Metaheuristics Optimization: Application to Brain Magnetic Resonance Images. Doctoral Dissertation. Paris, France: Université Paris-Est; 2019.
Yu TT, Wnorowski AM, Lane BF, Wong-You-Cheong JJ. Performing a basic US examination: road map for radiology residents. RadioGraphics. 2019; 39 (4): 1075–1076.
Suh RD, Genshaft SJ, Kirsch J, Kanne JP, Chung JH, Donnelly EF, Ginsburg ME, Heitkamp DE, Henry TS, Kazerooni EA, Ketai LH. ACR Appropriateness Criteria® intensive care unit patients. J Thoracic Imaging. 2015; 30 (6): W63–W65.
Hansen L, Sieren M, Hobe M, Saalbach A, Schulz H, Barkhausen J, Heinrich MP. Radiographic assessment of CVC malpositioning: how can AI best support clinicians? In: Medical Imaging with Deep Learning, Lübeck, Germany, July 7–9, 2021. pp. 1–3.
| Volume | 01 |
| Issue | 02 |
| Received | August 28, 2023 |
| Accepted | October 9, 2023 |
| Published | November 16, 2023 |