Making Artificial Intelligence Lemonade Out of Data Lemons: Adaptation of a Public Apical Echo Database for Creation of a Subxiphoid Visual Estimation Automatic Ejection Fraction Machine Learning Algorithm.
artificial intelligence
deep learning
echocardiography
ejection fraction
image manipulationimage manipulation
point-of-care ultrasound
Journal
Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine
ISSN: 1550-9613
Titre abrégé: J Ultrasound Med
Pays: England
ID NLM: 8211547
Informations de publication
Date de publication:
Aug 2022
Aug 2022
Historique:
revised:
02
11
2021
received:
15
10
2021
accepted:
09
11
2021
pubmed:
26
11
2021
medline:
19
7
2022
entrez:
25
11
2021
Statut:
ppublish
Résumé
A paucity of point-of-care ultrasound (POCUS) databases limits machine learning (ML). Assess feasibility of training ML algorithms to visually estimate left ventricular ejection fraction (EF) from a subxiphoid (SX) window using only apical 4-chamber (A4C) images. Researchers used a long-short-term-memory algorithm for image analysis. Using the Stanford EchoNet-Dynamic database of 10,036 A4C videos with calculated exact EF, researchers tested 3 ML training permeations. First, training on unaltered Stanford A4C videos, then unaltered and 90° clockwise (CW) rotated videos and finally unaltered, 90° rotated and horizontally flipped videos. As a real-world test, we obtained 615 SX videos from Harbor-UCLA (HUCLA) with EF calculations in 5% ranges. Researchers performed 1000 randomizations of EF point estimation within HUCLA EF ranges to compensate for ML and HUCLA EF mismatch, obtaining a mean value for absolute error (MAE) comparison and performed Bland-Altman analyses. The ML algorithm EF mean MAE was estimated at 23.0, with a range of 22.8-23.3 using unaltered A4C video, mean MAE was 16.7, with a range of 16.5-16.9 using unaltered and 90° CW rotated video, mean MAE was 16.6, with a range of 16.3-16.8 using unaltered, 90° CW rotated and horizontally flipped video training. Bland-Altman showed weakest agreement at 40-45% EF. Researchers successfully adapted unrelated ultrasound window data to train a POCUS ML algorithm with fair MAE using data manipulation to simulate a different ultrasound examination. This may be important for future POCUS algorithm design to help overcome a paucity of POCUS databases.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2059-2069Informations de copyright
© 2021 American Institute of Ultrasound in Medicine.
Références
Karp J, Burke K, Daubaras SM, McDermott C. The role of PoCUS in the assessment of COVID-19 patients. J Ultrasound 2021; 19:1-9.
Khanji MY, Ricci F, Patel RS, et al. Special article - the role of hand-held ultrasound for cardiopulmonary assessment during a pandemic. Prog Cardiovasc Dis 2020; 63:690-695.
Bashir K, Azad AM, Hereiz A, Bashir MT, Masood M, Elmoheen A. Current use, perceived barriers, and learning preference of point of care ultrasound (POCUS) in the emergency medicine in Qatar - a mixed design. Open Access Emerg Med 2021; 18:177-182.
Filipiak-Strzecka D, Kasprzak JD, Wejner-Mik P, Szymczyk E, Wdowiak-Okrojek K, Lipiec P. Artificial intelligence-powered measurement of left ventricular ejection fraction using a handheld ultrasound device. Ultrasound Med Biol 2021; 47:1120-1125.
Narang A, Bae R, Hong H, et al. Utility of a deep-learning algorithm to guide novices to acquire echocardiograms for limited diagnostic use. JAMA Cardiol 2021; 6:624-632.
Aldaas OM, Igata S, Raisinghani A, Kraushaar M, DeMaria AN. Accuracy of left ventricular ejection fraction determined by automated analysis of handheld echocardiograms: a comparison of experienced and novice examiners. Echocardiography 2019; 36:2145-2151.
Sanna GD, Canonico ME, Santoro C, et al. Echocardiographic longitudinal strain analysis in heart failure: real usefulness for clinical management beyond diagnostic value and prognostic correlations? A comprehensive review. Curr Heart Fail Rep 2021; 18:290-303.
Spencer KT, Bednarz J, Mor-Avi V, et al. The role of echocardiographic harmonic imaging and contrast enhancement for improvement of endocardial border delineation. J Am Soc Echocardiogr 2000; 13:131-138.
Soni NJ, Schnobrich D, Mathews BK, et al. Point-of-care ultrasound for hospitalists: a position statement of the Society of Hospital Medicine. J Hosp Med 2019; 14:E1-E6.
Nosir YF, Fioretti PM, Vletter WB, et al. Accurate measurement of left ventricular ejection fraction by three-dimensional echocardiography. A comparison with radionuclide angiography. Circulation 1996; 94:460-466.
Pardamean B, Cenggoro T, Rahutomo R, Budiarto A, Karappiah E. Transfer learning from chest X-ray pre-trained convolutional neural network for learning mammogram data. Procedia Comput Sci 2018; 135:400-407.
Bien N, Rajpurkar P, Ball RL, et al. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet. PLoS Med 2018; 15:1-19.
Abiyev RH, Ma'aitah MKS. Deep convolutional neural networks for chest diseases detection. J Healthc Eng 2018; 2018:4168538.
Kim TK, Yi PH, Wei J, et al. Deep learning method for automated classification of anteroposterior and posteroanterior chest radiographs. J Digit Imaging 2019; 32:925-930.
Moore CL, Rose GA, Tayal VS, Sullivan DM, Arrowood JA, Kline JA. Determination of left ventricular function by emergency physician echocardiography of hypotensive patients. Acad Emerg Med 2002; 9:186-193.
Blaivas M, Adhikari S, Savitsky EA, Blaivas LN, Liu YT. Artificial intelligence versus expert: a comparison of rapid visual inferior vena cava collapsibility assessment between POCUS experts and a deep learning algorithm. J Am Coll Emerg Physicians Open 2020; 1:857-864.
Ouyang D, He B, Ghorbani A, et al. EchoNet-dynamic: a large new cardiac motion video data resource for medical machine learning. Paper presented at: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019); 2019:1-11.
Blaivas L, Blaivas M. Are convolutional neural networks trained on ImageNet images wearing Rose-colored glasses?: a quantitative comparison of ImageNet, computed tomographic, magnetic resonance, chest X-ray, and point-of-care ultrasound images for quality. J Ultrasound Med 2021; 40:377-383.
Komura D, Ishikawa S. Machine learning approaches for pathologic diagnosis. Virchows Arch 2019; 475:131-138.
Blaivas M, Blaivas L. Are all deep learning architectures alike for point-of-care ultrasound?: evidence from a cardiac image classification model suggests otherwise. J Ultrasound Med 2020; 39:1187-1194.
Blaivas M, Blaivas L, Philips G, et al. Development of a deep learning network to classify inferior vena cava collapse to predict fluid responsiveness. J Ultrasound Med 2021; 40:1495-1504.
American College of Emergency Physicians. ACEP emergency ultrasound guidelines-2001. Ann Emerg Med 2001; 38:470-481.
Jones AE, Craddock PA, Tayal VS, Kline JA. Diagnostic accuracy of left ventricular function for identifying sepsis among emergency department patients with nontraumatic symptomatic undifferentiated hypotension. Shock 2005; 24:513-517.
Jones AE, Tayal VS, Sullivan DM, Kline JA. Randomized, controlled trial of immediate versus delayed goal-directed ultrasound to identify the cause of nontraumatic hypotension in emergency department patients. Crit Care Med 2004; 32:1703-1708.
Kaddoura R, Elmoheen A, Badawy E, et al. Vasoactive pharmacologic therapy in cardiogenic shock: a critical review. J Drug Assess 2021; 10:68-85.
Blaivas M, Fox JC. Outcome in cardiac arrest patients found to have cardiac standstill on the bedside emergency department echocardiogram. Acad Emerg Med 2001; 8:616-621.
Plummer D, Brunette D, Asinger R, Ruiz E. Emergency department echocardiography improves outcome in penetrating cardiac injury. Ann Emerg Med 1992; 21:709-712.
Salen P, Melniker L, Chooljian C, et al. Does the presence or absence of sonographically identified cardiac activity predict resuscitation outcomes of cardiac arrest patients? Am J Emerg Med 2005; 23:459-462.
Weiss J, Taron J, Jin Z, et al. Radiologists can visually predict mortality risk based on the gestalt of chest radiographs comparable to a deep learning network. Sci Rep 2021; 11:19586.
Hering A, Häger S, Moltz J, Lessmann N, Heldmann S, van Ginneken B. CNN-based lung CT registration with multiple anatomical constraints. Med Image Anal 2021; 72:102139.
Nastase SA, Liu YF, Hillman H, et al. The “narratives” fMRI dataset for evaluating models of naturalistic language comprehension. Sci Data 2021; 8:250.
Blaivas M, Arntfield R, White M. Creation and testing of a deep learning algorithm to automatically identify and label vessels, nerves, tendons, and bones on cross-sectional point-of-care ultrasound scans for peripheral intravenous catheter placement by novices. J Ultrasound Med 2020; 39:1721-1727.
Liang Y, Cui Q, Luo X, Xie Z. Research on classification of fine-grained rock images based on deep learning. Comput Intell Neurosci 2021; 20:5779740.
Chlap P, Min H, Vandenberg N, Dowling J, Holloway L, Haworth A. A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol 2021; 65:545-563.
Sorin V, Barash Y, Konen E, Klang E. Creating artificial images for radiology applications using generative adversarial networks (GANs) - a systematic review. Acad Radiol 2020; 27:1175-1185.
Vitale S, Orlando JI, Iarussi E, et al. Improving realism in patient-specificabdominal ultrasound simulation using CycleGANs. Int J Comput Assist Radiol Surg 2019; 15:183-192. https://doi.org/10.1007/s11548-019-02046-5.
Blaivas M, Arntfield R, White M. DIY AI, deep learning network development for automated image classification in a point-of-care ultrasound quality assurance program. J Am Coll Emerg Physicians Open 2020; 1:124-131.
Nazir T, Nawaz M, Rashid J, et al. Detection of diabetic eye disease from retinal images using a deep learning based CenterNet model. Sensors (Basel) 2021; 21:5283.
Blaivas M, Blaivas LN, Tsung JW. Deep learning pitfall: impact of novel ultrasound equipment introduction on algorithm performance and the realities of domain adaptation. J Ultrasound Med 2021; 41:855-863.
Farsalinos KE, Daraban AM, Ünlü S, Thomas JD, Badano LP, Voigt JU. Head-to-head comparison of global longitudinal strain measurements among nine different vendors. J Am Soc Echocardiogr 2015; 28:1171-1182.