Deep learning enabled brain shunt valve identification using mobile phones. (October 2021)

• Record Type: Journal Article
• Authors: Sujit, Sheeba J.; Bonfante, Eliana; Aein, Azin; Coronado, Ivan; Riascos-Castaneda, Roy; Giancardo, Luca
• Is Part Of: Computer methods and programs in biomedicine. Volume 210(2021)
• Publication Date: 2021-10
• Subjects: Programmable cerebrospinal fluid shunt valve -- Magnetic resonance imaging -- Deep learning -- Mobile phone camera; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106356
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We propose a new pipeline to identify implantable device MRI compatibility using mobile phone-quality images. We estimate the domain-shift-induced generalization error of two deep learning approaches with medical X-rays captured from PACS and with mobile phone images. We evaluate the performance of the models with and without images of X-rays containing valves, thereby simulating operator errors. Abstract: Background and Objective: Accurate information concerning implanted medical devices prior to a Magnetic resonance imaging (MRI) examination is crucial to assure safety of the patient and to address MRI induced unintended changes in device settings. The identification of these devices still remains a very challenging task. In this paper, with the aim of providing a faster device detection, we propose the adoption of deep learning for medical device detection from X-rays. Method: In particular, we propose a pipeline for the identification of implanted programmable cerebrospinal fluid shunt valves using X-ray images of the radiologist workstation screens captured with mobile phone integrated cameras at different angles and illuminations. We compare the proposed convolutional neural network with published methods. Results: Experimental results show that this approach outperforms methods trained on images digitally transferred directly from the scanners and then applied on mobile phones images (mean accuracy 95% vs 77%, Avg. Precision 0.96 vs 0.77, Avg. Recall 0.95 vs 0.77, Avg. F1-score 0.95 vs 0.77) and existing published methods based on transfer learning fine-tuned directly on the mobile phone images (mean accuracy 94% vs 75%, Avg. Precision 0.94 vs 0.75, Avg. Recall 0.94 vs 0.75, Avg. F1-score 0.94 vs 0.75). Conclusion: An automated shunt valve identification system is a promising safety tool for radiologists to efficiently coordinate the care of patients with implanted devices . An image-based safety system able to be deployed on a mobile phone would have significant advantages over methods requiring direct input from X-ray scanners or clinical picture archiving and communication system (PACS) in terms of ease of integration in the hospital or clinical ecosystems.