Skip to main content
Top
Published in:

01-12-2022 | Pleural Effusion | Research

Deep transfer learning to quantify pleural effusion severity in chest X-rays

Authors: Tao Huang, Rui Yang, Longbin Shen, Aozi Feng, Li Li, Ningxia He, Shuna Li, Liying Huang, Jun Lyu

Published in: BMC Medical Imaging | Issue 1/2022

Login to get access

Abstract

Purpose

The detection of pleural effusion in chest radiography is crucial for doctors to make timely treatment decisions for patients with chronic obstructive pulmonary disease. We used the MIMIC-CXR database to develop a deep learning model to quantify pleural effusion severity in chest radiographs.

Methods

The Medical Information Mart for Intensive Care Chest X-ray (MIMIC-CXR) dataset was divided into patients ‘with’ or ‘without’ chronic obstructive pulmonary disease (COPD). The label of pleural effusion severity was obtained from the extracted COPD radiology reports and classified into four categories: no effusion, small effusion, moderate effusion, and large effusion. A total of 200 datasets were randomly sampled to manually check each item and determine whether the tags are correct. A professional doctor re-tagged these items as a verification cohort without knowing their previous tags. The learning models include eight common network structures including Resnet, DenseNet, and GoogleNET. Three data processing methods (no sampling, downsampling, and upsampling) and two loss algorithms (focal loss and cross-entropy loss) were used for unbalanced data. The Neural Network Intelligence tool was applied to train the model. Receiver operating characteristic curves, Area under the curve, and confusion matrix were employed to evaluate the model results. Grad-CAM was used for model interpretation.

Results

Among the 8533 patients, 15,620 chest X-rays with clearly marked pleural effusion severity were obtained (no effusion, 5685; small effusion, 4877; moderate effusion, 3657; and large effusion, 1401). The error rate of the manual check label was 6.5%, and the error rate of the doctor’s relabeling was 11.0%. The highest accuracy rate of the optimized model was 73.07. The micro-average AUCs of the testing and validation cohorts was 0.89 and 0.90, respectively, and their macro-average AUCs were 0.86 and 0.89, respectively. The AUC of the distinguishing results of each class and the other three classes were 0.95 and 0.94, 0.76 and 0.83, 0.85 and 0.83, and 0.87 and 0.93.

Conclusion

The deep transfer learning model can grade the severity of pleural effusion.
Literature
1.
go back to reference Liu K, Jin S, Song Z, Jiang L. High accuracy detection of malignant pleural effusion based on label-free surface-enhanced Raman spectroscopy and multivariate statistical analysis. Spectrochim Acta Part A Mol Biomol Spectrosc. 2020;226:117632.CrossRef Liu K, Jin S, Song Z, Jiang L. High accuracy detection of malignant pleural effusion based on label-free surface-enhanced Raman spectroscopy and multivariate statistical analysis. Spectrochim Acta Part A Mol Biomol Spectrosc. 2020;226:117632.CrossRef
2.
go back to reference Zhan N, Guo Y, Tian S, Huang B, Tian X, Zou J, Xiong Q, Tang D, Zhang L, Dong W. Clinical characteristics of COVID-19 complicated with pleural effusion. BMC Infect Dis. 2021;21(1):1–10.CrossRef Zhan N, Guo Y, Tian S, Huang B, Tian X, Zou J, Xiong Q, Tang D, Zhang L, Dong W. Clinical characteristics of COVID-19 complicated with pleural effusion. BMC Infect Dis. 2021;21(1):1–10.CrossRef
3.
go back to reference Sahn SA, Heffner JE. Pleural fluid analysis. Textb Pleur Dis. 2008;2:209–26. Sahn SA, Heffner JE. Pleural fluid analysis. Textb Pleur Dis. 2008;2:209–26.
4.
go back to reference Heller SJ, Noordhoek E, Tenner SM, Ramagopal V, Abramowitz M, Hughes M, Banks PA. Pleural effusion as a predictor of severity in acute pancreatitis. Pancreas. 1997;15(3):222–5.CrossRef Heller SJ, Noordhoek E, Tenner SM, Ramagopal V, Abramowitz M, Hughes M, Banks PA. Pleural effusion as a predictor of severity in acute pancreatitis. Pancreas. 1997;15(3):222–5.CrossRef
5.
go back to reference Ferreiro L, Toubes ME, San José ME, Suárez-Antelo J, Golpe A, Valdés L. Advances in pleural effusion diagnostics. Expert Rev Respir Med. 2020;14(1):51–66.CrossRef Ferreiro L, Toubes ME, San José ME, Suárez-Antelo J, Golpe A, Valdés L. Advances in pleural effusion diagnostics. Expert Rev Respir Med. 2020;14(1):51–66.CrossRef
6.
go back to reference Vignon P, Chastagner C, Berkane V, Chardac E, François B, Normand S, Bonnivard M, Clavel M, Pichon N, Preux P-M, et al. Quantitative assessment of pleural effusion in critically ill patients by means of ultrasonography. Crit Care Med. 2005;33(8):1757–63.CrossRef Vignon P, Chastagner C, Berkane V, Chardac E, François B, Normand S, Bonnivard M, Clavel M, Pichon N, Preux P-M, et al. Quantitative assessment of pleural effusion in critically ill patients by means of ultrasonography. Crit Care Med. 2005;33(8):1757–63.CrossRef
7.
go back to reference Nishida O, Arellano R, Cheng DCH, DeMajo W, Kavanagh BP. Gas exchange and hemodynamics in experimental pleural effusion. Crit Care Med. 1999;27(3):583–7.CrossRef Nishida O, Arellano R, Cheng DCH, DeMajo W, Kavanagh BP. Gas exchange and hemodynamics in experimental pleural effusion. Crit Care Med. 1999;27(3):583–7.CrossRef
8.
go back to reference Traylor JJ, Chan K, Wong I, Roxas JN, Chandraratna PAN. Large pleural effusions producing signs of cardiac tamponade resolved by thoracentesis. Am J Cardiol. 2002;89(1):106–8.CrossRef Traylor JJ, Chan K, Wong I, Roxas JN, Chandraratna PAN. Large pleural effusions producing signs of cardiac tamponade resolved by thoracentesis. Am J Cardiol. 2002;89(1):106–8.CrossRef
9.
go back to reference Vetrugno L, Bignami E, Orso D, Vargas M, Guadagnin GM, Saglietti F, Servillo G, Volpicelli G, Navalesi P, Bove T. Utility of pleural effusion drainage in the ICU: an updated systematic review and META-analysis. J Crit Care. 2019;52:22–32.CrossRef Vetrugno L, Bignami E, Orso D, Vargas M, Guadagnin GM, Saglietti F, Servillo G, Volpicelli G, Navalesi P, Bove T. Utility of pleural effusion drainage in the ICU: an updated systematic review and META-analysis. J Crit Care. 2019;52:22–32.CrossRef
10.
go back to reference Rezaeijo SM, Ghorvei M, Abedi-Firouzjah R, Mojtahedi H, Entezari Zarch H. Detecting COVID-19 in chest images based on deep transfer learning and machine learning algorithms. Egypt J Radiol Nucl Med. 2021;52(1):145.CrossRef Rezaeijo SM, Ghorvei M, Abedi-Firouzjah R, Mojtahedi H, Entezari Zarch H. Detecting COVID-19 in chest images based on deep transfer learning and machine learning algorithms. Egypt J Radiol Nucl Med. 2021;52(1):145.CrossRef
11.
go back to reference Stubblefield J, Hervert M, Causey JL, Qualls JA, Dong W, Cai L, Fowler J, Bellis E, Walker K, Moore JH, et al. Transfer learning with chest X-rays for ER patient classification. Sci Rep. 2020;10(1):20900.CrossRef Stubblefield J, Hervert M, Causey JL, Qualls JA, Dong W, Cai L, Fowler J, Bellis E, Walker K, Moore JH, et al. Transfer learning with chest X-rays for ER patient classification. Sci Rep. 2020;10(1):20900.CrossRef
12.
go back to reference Rezaeijo SM, Ghorvei M, Mofid B. Predicting breast cancer response to neoadjuvant chemotherapy using ensemble deep transfer learning based on CT images. J Xray Sci Technol. 2021;29:835–50.PubMed Rezaeijo SM, Ghorvei M, Mofid B. Predicting breast cancer response to neoadjuvant chemotherapy using ensemble deep transfer learning based on CT images. J Xray Sci Technol. 2021;29:835–50.PubMed
13.
go back to reference Diamant I, Bar Y, Geva O, Wolf L, Zimmerman G, Lieberman S, Konen E, Greenspan H: Chapter 13: chest radiograph pathology categorization via transfer learning. In: deep learning for medical image analysis. Zhou SK, Greenspan H, Shen D, editors Academic Press; 2017: pp. 299–320. Diamant I, Bar Y, Geva O, Wolf L, Zimmerman G, Lieberman S, Konen E, Greenspan H: Chapter 13: chest radiograph pathology categorization via transfer learning. In: deep learning for medical image analysis. Zhou SK, Greenspan H, Shen D, editors Academic Press; 2017: pp. 299–320.
14.
go back to reference Niehues SM, Adams LC, Gaudin RA, Erxleben C, Keller S, Makowski MR, Vahldiek JL, Bressem KK. Deep-learning-based diagnosis of bedside chest X-ray in intensive care and emergency medicine. Invest Radiol. 2021;56(8):525–34.CrossRef Niehues SM, Adams LC, Gaudin RA, Erxleben C, Keller S, Makowski MR, Vahldiek JL, Bressem KK. Deep-learning-based diagnosis of bedside chest X-ray in intensive care and emergency medicine. Invest Radiol. 2021;56(8):525–34.CrossRef
15.
go back to reference Nakata N. Recent technical development of artificial intelligence for diagnostic medical imaging. Jpn J Radiol. 2019;37(2):103–8.CrossRef Nakata N. Recent technical development of artificial intelligence for diagnostic medical imaging. Jpn J Radiol. 2019;37(2):103–8.CrossRef
16.
go back to reference Yang J, Li Y, Liu Q, Li L, Feng A, Wang T, Zheng S, Xu A, Lyu J. Brief introduction of medical database and data mining technology in big data era. J Evid Based Med. 2020;13(1):57–69.CrossRef Yang J, Li Y, Liu Q, Li L, Feng A, Wang T, Zheng S, Xu A, Lyu J. Brief introduction of medical database and data mining technology in big data era. J Evid Based Med. 2020;13(1):57–69.CrossRef
17.
go back to reference Johnson AEW, Pollard TJ, Berkowitz SJ, Greenbaum NR, Lungren MP, Deng C-Y, Mark RG, Horng S. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data. 2019;6(1):1–8.CrossRef Johnson AEW, Pollard TJ, Berkowitz SJ, Greenbaum NR, Lungren MP, Deng C-Y, Mark RG, Horng S. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data. 2019;6(1):1–8.CrossRef
18.
go back to reference Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, Marklund H, Haghgoo B, Ball R, Shpanskaya K, et al. Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Proc AAAI Conf Artif Intell. 2019;33(01):590–7. Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, Marklund H, Haghgoo B, Ball R, Shpanskaya K, et al. Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Proc AAAI Conf Artif Intell. 2019;33(01):590–7.
19.
go back to reference Phillips NA, Rajpurkar P, Sabini M, Krishnan R, Zhou S, Pareek A, Phu NM, Wang C, Jain M, Du ND et al. CheXphoto: 10,000+ Photos and transformations of chest X-rays for benchmarking deep learning robustness. In: 2020: PMLR; 2020, pp. 318–327. Phillips NA, Rajpurkar P, Sabini M, Krishnan R, Zhou S, Pareek A, Phu NM, Wang C, Jain M, Du ND et al. CheXphoto: 10,000+ Photos and transformations of chest X-rays for benchmarking deep learning robustness. In: 2020: PMLR; 2020, pp. 318–327.
20.
go back to reference Chen H, Miao S, Xu D, Hager GD, Harrison AP. Deep hiearchical multi-label classification applied to chest X-ray abnormality taxonomies. Med Image Anal. 2020;66:101811.CrossRef Chen H, Miao S, Xu D, Hager GD, Harrison AP. Deep hiearchical multi-label classification applied to chest X-ray abnormality taxonomies. Med Image Anal. 2020;66:101811.CrossRef
21.
go back to reference Wang G, Liu X, Shen J, Wang C, Li Z, Ye L, Wu X, Chen T, Wang K, Zhang X, et al. A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images. Nat Biomed Eng. 2021;5(6):509–21.CrossRef Wang G, Liu X, Shen J, Wang C, Li Z, Ye L, Wu X, Chen T, Wang K, Zhang X, et al. A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images. Nat Biomed Eng. 2021;5(6):509–21.CrossRef
22.
go back to reference Baltruschat I-M. Deep learning for automatic lung disease analysis in chest x-rays. PhD Thesis. Technische Universität Hamburg; 2021. Baltruschat I-M. Deep learning for automatic lung disease analysis in chest x-rays. PhD Thesis. Technische Universität Hamburg; 2021.
23.
go back to reference Johnson A, Lungren M, Peng Y, Lu Z, Mark R, Berkowitz S, Horng S. MIMIC-CXR-JPG: chest radiographs with structured labels (version 2.0.0). PhysioNet 2019. Johnson A, Lungren M, Peng Y, Lu Z, Mark R, Berkowitz S, Horng S. MIMIC-CXR-JPG: chest radiographs with structured labels (version 2.0.0). PhysioNet 2019.
24.
go back to reference Fuchs BC, Lyke B, Price R, Smith M. The Health Insurance Portability and Accountability Act (HIPAA) of 1996: Guidance on Frequently Asked Questions. In: 1998; 1998. Fuchs BC, Lyke B, Price R, Smith M. The Health Insurance Portability and Accountability Act (HIPAA) of 1996: Guidance on Frequently Asked Questions. In: 1998; 1998.
25.
go back to reference Wu WT, Li YJ, Feng AZ, Li L, Huang T, Xu AD, Lyu J. Data mining in clinical big data: the frequently used databases, steps, and methodological models. Mil Med Res. 2021;8(1):44.PubMedPubMedCentral Wu WT, Li YJ, Feng AZ, Li L, Huang T, Xu AD, Lyu J. Data mining in clinical big data: the frequently used databases, steps, and methodological models. Mil Med Res. 2021;8(1):44.PubMedPubMedCentral
26.
go back to reference Goodyear, MD, Krleza-Jeric K, Lemmens T. The declaration of Helsinki. BMJ: British Medical Journal (International Edition) 2007. Goodyear, MD, Krleza-Jeric K, Lemmens T. The declaration of Helsinki. BMJ: British Medical Journal (International Edition) 2007.
27.
go back to reference Peng Y, Wang X, Lu L, Bagheri M, Summers R, Lu Z. NegBio: a high-performance tool for negation and uncertainty detection in radiology reports. AMIA Summits Transl Sci Proc. 2018;2018:188.PubMedCentral Peng Y, Wang X, Lu L, Bagheri M, Summers R, Lu Z. NegBio: a high-performance tool for negation and uncertainty detection in radiology reports. AMIA Summits Transl Sci Proc. 2018;2018:188.PubMedCentral
28.
go back to reference Microsoft: Neural Network Intelligence (NNI). In: 2021; 2021. Microsoft: Neural Network Intelligence (NNI). In: 2021; 2021.
29.
go back to reference Wang X, Schwab E, Rubin J, Klassen P, Liao R, Berkowitz S, Golland P, Horng S, Dalal S. Pulmonary edema severity estimation in chest radiographs using deep learning. In: 2019; 2019. Wang X, Schwab E, Rubin J, Klassen P, Liao R, Berkowitz S, Golland P, Horng S, Dalal S. Pulmonary edema severity estimation in chest radiographs using deep learning. In: 2019; 2019.
30.
go back to reference Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K. Densenet. Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:14041869 2014. Iandola F, Moskewicz M, Karayev S, Girshick R, Darrell T, Keutzer K. Densenet. Implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:14041869 2014.
31.
go back to reference Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: 2015; 2015, pp. 1–9 Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: 2015; 2015, pp. 1–9
32.
go back to reference Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: 2016; 2016. pp. 2818–2826. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: 2016; 2016. pp. 2818–2826.
33.
go back to reference Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. Mobilenetv2: inverted residuals and linear bottlenecks. In: 2018; 2018. pp. 4510–4520. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C. Mobilenetv2: inverted residuals and linear bottlenecks. In: 2018; 2018. pp. 4510–4520.
34.
go back to reference He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016; 2016. pp. 770–778. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016; 2016. pp. 770–778.
35.
go back to reference Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017;60(6):84–90.CrossRef Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017;60(6):84–90.CrossRef
36.
go back to reference Lin T-Y, Goyal P, Girshick R, He K, Dollár P: Focal loss for dense object detection. In: 2017; 2017. pp. 2980–2988. Lin T-Y, Goyal P, Girshick R, He K, Dollár P: Focal loss for dense object detection. In: 2017; 2017. pp. 2980–2988.
37.
go back to reference Sutskever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning. In: 2013: PMLR; 2013. pp. 1139–1147. Sutskever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning. In: 2013: PMLR; 2013. pp. 1139–1147.
38.
go back to reference Zeiler MD. Adadelta: an adaptive learning rate method. arXiv preprint arXiv:12125701 2012. Zeiler MD. Adadelta: an adaptive learning rate method. arXiv preprint arXiv:12125701 2012.
39.
go back to reference Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980 2014. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980 2014.
40.
go back to reference Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: 2017; 2017. pp. 618–626. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: 2017; 2017. pp. 618–626.
41.
go back to reference Meveychuck A, Osadchy A, Chen B, Shitrit D. Pleural effusion in chronic obstructive pulmonary medicine (COPD) patients in a medical intensive care unit: characteristics and clinical implications. Harefuah. 2012;151(4):198–201.PubMed Meveychuck A, Osadchy A, Chen B, Shitrit D. Pleural effusion in chronic obstructive pulmonary medicine (COPD) patients in a medical intensive care unit: characteristics and clinical implications. Harefuah. 2012;151(4):198–201.PubMed
42.
go back to reference Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz CP, et al. Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 2018;15(11):e1002686.CrossRef Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz CP, et al. Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 2018;15(11):e1002686.CrossRef
43.
go back to reference Bressem KK, Adams LC, Erxleben C, Hamm B, Niehues SM, Vahldiek JL. Comparing different deep learning architectures for classification of chest radiographs. Sci Rep. 2020;10(1):1–16.CrossRef Bressem KK, Adams LC, Erxleben C, Hamm B, Niehues SM, Vahldiek JL. Comparing different deep learning architectures for classification of chest radiographs. Sci Rep. 2020;10(1):1–16.CrossRef
44.
go back to reference Tran GS, Nghiem TP, Nguyen VT, Luong CM, Burie J-C. Improving accuracy of lung nodule classification using deep learning with focal loss. J Healthc Eng. 2019;2019:5156416.CrossRef Tran GS, Nghiem TP, Nguyen VT, Luong CM, Burie J-C. Improving accuracy of lung nodule classification using deep learning with focal loss. J Healthc Eng. 2019;2019:5156416.CrossRef
45.
go back to reference Pasupa K, Vatathanavaro S, Tungjitnob S. Convolutional neural networks based focal loss for class imbalance problem: a case study of canine red blood cells morphology classification. J Ambient Intell Humaniz Comput 2020. Pasupa K, Vatathanavaro S, Tungjitnob S. Convolutional neural networks based focal loss for class imbalance problem: a case study of canine red blood cells morphology classification. J Ambient Intell Humaniz Comput 2020.
46.
go back to reference Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: 2017; 2017. pp. 2097–2106. Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. Chestx-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: 2017; 2017. pp. 2097–2106.
47.
go back to reference Ferri C, Hernández-Orallo J, Salido MA: Volume under the ROC surface for multi-class problems. In: 2003: Springer; 2003. pp. 108–120. Ferri C, Hernández-Orallo J, Salido MA: Volume under the ROC surface for multi-class problems. In: 2003: Springer; 2003. pp. 108–120.
48.
go back to reference Zhang M-L, Li Y-K, Yang H, Liu X-Y. Towards class-imbalance aware multi-label learning. IEEE Transactions on Cybernetics 2020. Zhang M-L, Li Y-K, Yang H, Liu X-Y. Towards class-imbalance aware multi-label learning. IEEE Transactions on Cybernetics 2020.
49.
go back to reference Susmaga R. Confusion matrix visualization. In: Intelligent information processing and web mining. Springer; 2004. pp. 107–116. Susmaga R. Confusion matrix visualization. In: Intelligent information processing and web mining. Springer; 2004. pp. 107–116.
50.
go back to reference Blackmore CC, Black WC, Dallas RV, Crow HC. Pleural fluid volume estimation: a chest radiograph prediction rule. Acad Radiol. 1996;3(2):103–9.CrossRef Blackmore CC, Black WC, Dallas RV, Crow HC. Pleural fluid volume estimation: a chest radiograph prediction rule. Acad Radiol. 1996;3(2):103–9.CrossRef
Metadata
Title
Deep transfer learning to quantify pleural effusion severity in chest X-rays
Authors
Tao Huang
Rui Yang
Longbin Shen
Aozi Feng
Li Li
Ningxia He
Shuna Li
Liying Huang
Jun Lyu
Publication date
01-12-2022
Publisher
BioMed Central
Published in
BMC Medical Imaging / Issue 1/2022
Electronic ISSN: 1471-2342
DOI
https://doi.org/10.1186/s12880-022-00827-0

Other articles of this Issue 1/2022

BMC Medical Imaging 1/2022 Go to the issue