Image-based deep learning in diagnosing the etiology of pneumonia on pediatric chest X-rays.
deep-learning
image classification
pediatric chest X-rays
pneumonia etiology diagnosis
Journal
Pediatric pulmonology
ISSN: 1099-0496
Titre abrégé: Pediatr Pulmonol
Pays: United States
ID NLM: 8510590
Informations de publication
Date de publication:
05 2021
05 2021
Historique:
revised:
07
12
2020
received:
05
05
2020
accepted:
13
12
2020
pubmed:
18
12
2020
medline:
21
10
2021
entrez:
17
12
2020
Statut:
ppublish
Résumé
Comparing the efficacy of a deep-learning model in classifying the etiology of pneumonia on pediatric chest X-rays (CXRs) with that of human readers. We built a clinical-pediatric CXR set containing 4035 patients to exploit a deep-learning model called Resnet-50 for differentiating viral from bacterial pneumonia. The dataset was split into training (80%) and validation (20%). Model performance was assessed by receiver operating characteristic curve and area under the curve (AUC) on the first test set of 400 CXRs collected from different studies. For the second test set composed of 100 independent examinations obtained from the daily clinical practice at our institution, the kappa coefficient was selected to measure the interrater agreement in a pairwise fashion for the reference standard, all reviewers, and the model. Gradient-weighted class activation mapping was used to visualize the significant areas contributing to the model prediction. On the first test set, the best-performing classifier achieved an AUC of 0.919 (p < .001), with a sensitivity of 79.0% and specificity of 88.9%. On the second test set, the classifier achieved performance similar to that of human experts, which resulted in a sensitivity of 74.3% and specificity of 90.8%, positive and negative likelihood ratios of 8.1 and 0.3, respectively. Contingence tables and kappa values further revealed that expert reviewers and model reached substantial agreements on differentiating the etiology of pediatric pneumonia. This study demonstrated that the model performed similarly as human reviewers and recognized the regions of pathology on CXRs.
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1036-1044Informations de copyright
© 2020 Wiley Periodicals LLC.
Références
Wardlaw T, Johansson EW, Hodge M. Pneumonia: the forgotten killer of children. New York New York Unicef. 2006;368(9541):1048-1050.
Rudan I, Boschi-Pinto C, Biloglav Z, Mulholland K, Campbell H. Epidemiology and etiology of childhood pneumonia. Bull World Health Organ. 2008;86(5):408-416.
Mcluckie A. Respiratory Disease and Its Management. Vol 57. Springer; 2009.
Elena C, Elisabetta V, Luisa G, Vas N, Maurizio DM. Diagnostic features of community-acquired pneumonia in children: what's new? Acta Paediatr Suppl. 2014;102(s465):17-24.
Douglas IS. New diagnostic methods for pneumonia in the ICU. Curr Opin Infect Dis. 2016;29(2):1-204.
Vincent JL, Brealey D, Libert N, et al. Rapid diagnosis of infection in the critically Ill, a multicenter study of molecular detection in bloodstream infections, pneumonia, and sterile site infections. Crit Care Med. 2015;43(11):2283-2291.
Kunin CM. Report of a symposium on use and abuse of antibiotics worldwide. Rev Infect Dis. 1990;12(1):12-19.
Chang Y, Chusri S, Sangthong R, et al. Clinical pattern of antibiotic overuse and misuse in primary healthcare hospitals in the southwest of China. PLoS One. 2019;14(6):e0214779.
Griffin AT, Peyrani P, Wiemken TL, Ramirez JA, Arnold FW. Empiric therapy directed against MRSA in patients admitted to the intensive care unit does not improve outcomes in community-acquired pneumonia. Infection. 2013;41(2):517-523.
Charles PGP. Early diagnosis of lower respiratory tract infections (point-of-care tests). Curr Opin Pulm Med. 2008;14(3):176-182.
World Health Organization. Borrás CB. IAEA/WHO Expert Committee on Medical Radiation Physics, WHO. Standardization of interpretation of chest radiographs for the diagnosis of pneumonia in children. Organization, development, quality assurance and radiation protection in radiology services: imaging and radiation therapy; 2001; Organización, Desarrollo.
Upchurch CP, Grijalva CG, Wunderink RG, et al. Community-acquired pneumonia visualized on computed tomography but not chest X-ray: pathogens, severity, and clinical outcomes. Chest. 2017;153(3):601-610.
Koo HJ, Lim S, Choe J, Choi SH, Sung H, Do KH. Radiographic and CT features of viral pneumonia. Radiographics. 2018;38(3):719-739.
Neuman MI, Lee EY, Bixby S, et al. Variability in the interpretation of chest radiographs for the diagnosis of pneumonia in children. J Hospital Med. 2012;7(4):294-298.
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.
Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115-118.
Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP. Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology. 2018;287(1):313-322.
E L, Zhao, Guo Y, et al. Using deep-learning techniques for pulmonary-thoracic segmentations and improvement of pneumonia diagnosis in pediatric chest radiographs. Pediatr Pulmonol. 2019;54(10):1617-1626.
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436-444.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Paper presented at: International Conference on Neural Information Processing Systems; 2012.
Kohli M, Prevedello LM, Filice RW, Geis JR. Implementing machine learning in radiology practice and research. AJR Am J Roentgenol. 2017;208(4):754-760.
Simonyan K, Vedaldi A, Zisserman A. Deep inside convolutional networks: visualising image classification models and saliency maps. Proceedings of the Second International Conference on Learning Representations; 2014; Banff, Alberta, Canada.
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. Paper presented at: IEEE International Conference on Computer Vision; 2017.
Chattopadhyay A, Sarkar A, Howlader P, Balasubramanian VN. Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks. Proceedings of the IEEE Winter Conference on Applications of Computer Vision; 2018; Lake Tahoe, NV.
Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. Radiographics. 2017;37(2):505-515.
Oliveira LL, Silva SA, Ribeiro LH, de Oliveira RM, Coelho CJ, Andrade ALSA. Computer-aided diagnosis in chest radiography for detection of childhood pneumonia. Int J Med Inform. 2008;77(8):555-564.
Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284(2):574-582.
Kermany DS, Goldbaum M, Cai W, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. 2018;172(5):1122-1131.
Khobragade S, Tiwari A, Patil CY, Narke V. Automatic detection of major lung diseases using Chest Radiographs and classification by feed-forward artificial neural network. Paper presented at: IEEE International Conference on Power Electronics; 2017.
He K, Zhang X, Ren S, Jian S. Deep residual learning for image recognition. Paper presented at: IEEE Conference on Computer Vision and Pattern Recognition; 2016.
Kingma D, Ba J. Adam: a method for stochastic optimization. Proceedings of the International Conference on Learning Representations; 2014.
Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115(3):211-252.
Obuchowski NA. Receiver operating characteristic curves and their use in radiology. Radiology. 2003;229(1):3-8.
Steyerberg EW, Vickers AJ, Cook NR, et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2010;21(1):128-138.
Agresti A, Coull BA. Approximate is better than “exact” for interval estimation of binomial proportions. Am Stat. 1998;54:119-126.
Cohen J. Weighted kappa: nominal scale agreement with provision for scaled disagreement or partial credit. Psychol Bull. 1968;70(4):213-220.
Levinsky Y, Mimouni FB, Fisher D, Ehrlichman M. Chest radiography of acute paediatric lower respiratory infections: experience versus interobserver variation. Acta Paediatr. 2013;102(7):e310-e314.
Liu CY, Wang JD, Yu JT, et al. Influenza B virus-associated pneumonia in pediatric patients: clinical features, laboratory data, and chest X-ray findings. Pediatrics and neonatology. 2014;55(1):58-64.
Franquet T. Imaging of pulmonary viral pneumonia. Radiology. 2011;260(1):18-39.