nach oben

Erschienen in:

30.06.2023 | Imaging Informatics and Artificial Intelligence

Pneumonia-Plus: a deep learning model for the classification of bacterial, fungal, and viral pneumonia based on CT tomography

verfasst von: Fang Wang, Xiaoming Li, Ru Wen, Hu Luo, Dong Liu, Shuai Qi, Yang Jing, Peng Wang, Gang Deng, Cong Huang, Tingting Du, Limei Wang, Hongqin Liang, Jian Wang, Chen Liu

Erschienen in: European Radiology | Ausgabe 12/2023

Einloggen, um Zugang zu erhalten

Abstract

Objectives

This study aims to develop a deep learning algorithm, Pneumonia-Plus, based on computed tomography (CT) images for accurate classification of bacterial, fungal, and viral pneumonia.

Methods

A total of 2763 participants with chest CT images and definite pathogen diagnosis were included to train and validate an algorithm. Pneumonia-Plus was prospectively tested on a nonoverlapping dataset of 173 patients. The algorithm’s performance in classifying three types of pneumonia was compared to that of three radiologists using the McNemar test to verify its clinical usefulness.

Results

Among the 173 patients, area under the curve (AUC) values for viral, fungal, and bacterial pneumonia were 0.816, 0.715, and 0.934, respectively. Viral pneumonia was accurately classified with sensitivity, specificity, and accuracy of 0.847, 0.919, and 0.873. Three radiologists also showed good consistency with Pneumonia-Plus. The AUC values of bacterial, fungal, and viral pneumonia were 0.480, 0.541, and 0.580 (radiologist 1: 3-year experience); 0.637, 0.693, and 0.730 (radiologist 2: 7-year experience); and 0.734, 0.757, and 0.847 (radiologist 3: 12-year experience), respectively. The McNemar test results for sensitivity showed that the diagnostic performance of the algorithm was significantly better than that of radiologist 1 and radiologist 2 (p < 0.05) in differentiating bacterial and viral pneumonia. Radiologist 3 had a higher diagnostic accuracy than the algorithm.

Conclusions

The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist and reduce the risk of misdiagnosis. The Pneumonia-Plus is important for appropriate treatment and avoiding the use of unnecessary antibiotics, and provide timely information to guide clinical decision-making and improve patient outcomes.

Clinical relevance statement

Pneumonia-Plus algorithm could assist in the accurate classification of pneumonia based on CT images, which has great clinical value in avoiding the use of unnecessary antibiotics, and providing timely information to guide clinical decision-making and improve patient outcomes.

Key Points

• The Pneumonia-Plus algorithm trained from data collected from multiple centers can accurately identify bacterial, fungal, and viral pneumonia.

• The Pneumonia-Plus algorithm was found to have better sensitivity in classifying viral and bacterial pneumonia in comparison to radiologist 1 (5-year experience) and radiologist 2 (7-year experience).

• The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist.

Nur mit Berechtigung zugänglich

Yang W, Ma Y, Wang J, Li Y, Zhang Y, Zhang T (2019) Fungal pneumonia manifesting as cavitary lesions in a critically ill elderly patient. J Infect Dev Ctries 13:1170–1173CrossRefPubMed

Cilloniz C, Martin-Loeches I, Garcia-Vidal C, San Jose A, Torres A (2016) Microbial etiology of pneumonia: epidemiology, diagnosis and resistance patterns. Int J Mol Sci 17(12):2120

Shen L, Wang L, Liu C, Shi S, Takahashi T, Wang T (2021) Community-acquired pneumonia: trends in and research on drug resistance and advances in new antibiotics. Biosci Trends 15:266–275CrossRefPubMed

Li X, Zeng W, Li X et al (2020) CT imaging changes of corona virus disease 2019(COVID-19): a multi-center study in Southwest China. J Transl Med 18:154CrossRefPubMedPubMedCentral

van Vugt SF, Verheij TJ, de Jong PA et al (2013) Diagnosing pneumonia in patients with acute cough: clinical judgment compared to chest radiography. Eur Respir J 42:1076–1082CrossRefPubMed

Albano D, Messina C, Vitale J, Sconfienza LM (2020) Imaging of sarcopenia: old evidence and new insights. Eur Radiol 30:2199–2208CrossRefPubMed

Wang S, Zha Y, Li W et al (2020) A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis. Eur Respir J 56(2):2000775CrossRefPubMedPubMedCentral

Zellweger NM, Huber J, Tsakiris DA, Tzankov A, Gebhard CE, Siegemund M (2021) Haemophagocytic lymphohistiocytosis and liver failure-induced massive hyperferritinaemia in a male COVID-19 patient. Swiss Med Wkly 151:w20420CrossRefPubMed

Kermany DS, Goldbaum M, Cai W et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(1122–1131):e1129

10.

Bai HX, Wang R, Xiong Z et al (2021) Artificial intelligence augmentation of radiologist performance in distinguishing COVID-19 from pneumonia of other origin at chest CT. Radiology 299:E225CrossRefPubMed

11.

Harmon SA, Sanford TH, Xu S et al (2020) Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets. Nat Commun 11:4080CrossRefPubMedPubMedCentral

12.

Shen B, Yi X, Sun Y et al (2020) Proteomic and metabolomic characterization of COVID-19 patient sera. Cell 182(59–72):e15

13.

Wiemken TL, Kelley RR, Fernandez-Botran R et al (2017) Using cluster analysis of cytokines to identify patterns of inflammation in hospitalized patients with community-acquired pneumonia: a pilot study. Univ Louisville J Respir Infect 1:3–11PubMedPubMedCentral

14.

Zhu Y, Xu B, Li C et al (2021) A multicenter study of viral aetiology of community-acquired pneumonia in hospitalized children in Chinese Mainland. Virol Sin 36:1543–1553CrossRefPubMedPubMedCentral

15.

Liu AA, Xu N, Nie WZ, Su YT, Zhang YD (2018) Multi-domain & multi-task learning for human action recognition. IEEE Trans Image Process: a publication of the IEEE Signal Processing Society. https://doi.org/10.1109/tip.2018.2872879CrossRef

16.

Wang S, Yang DM, Rong R, Zhan X, Xiao G (2019) Pathology image analysis using segmentation deep learning algorithms. Am J Pathol 189:1686–1698CrossRefPubMedPubMedCentral

17.

Ahn Y, Lee SM, Noh HN et al (2021) Use of a commercially available deep learning algorithm to measure the solid portions of lung cancer manifesting as subsolid lesions at CT: comparisons with radiologists and invasive component size at pathologic examination. Radiology 299:202–210CrossRefPubMed

18.

Bhuiyan MU, Snelling TL, West R et al (2019) The contribution of viruses and bacteria to community-acquired pneumonia in vaccinated children: a case-control study. Thorax 74:261–269CrossRefPubMed

19.

Torres A, Lee N, Cilloniz C, Vila J, Van der Eerden M (2016) Laboratory diagnosis of pneumonia in the molecular age. Eur Respir J 48:1764–1778CrossRefPubMed

20.

Wallihan RG, Suarez NM, Cohen DM et al (2018) Molecular distance to health transcriptional score and disease severity in children hospitalized with community-acquired pneumonia. Front Cell Infect Microbiol 8:382CrossRefPubMedPubMedCentral

21.

Johansson EW, Nsona H, Carvajal-Aguirre L, Amouzou A, Hildenwall H (2017) Determinants of Integrated Management of Childhood Illness (IMCI) non-severe pneumonia classification and care in Malawi health facilities: analysis of a national facility census. J Glob Health 7:020408CrossRefPubMedPubMedCentral

22.

Hwang EJ, Park S, Jin KN et al (2019) Development and validation of a deep learning-based automated detection algorithm for major thoracic diseases on chest radiographs. JAMA Netw Open 2:e191095CrossRefPubMedPubMedCentral

23.

Stephen O, Sain M, Maduh UJ, Jeong DU (2019) An efficient deep learning approach to pneumonia classification in healthcare. J Healthc Eng 2019:4180949CrossRefPubMedPubMedCentral

24.

Amyar A, Modzelewski R, Li H, Ruan S (2020) Multi-task deep learning based CT imaging analysis for COVID-19 pneumonia: classification and segmentation. Comput Biol Med 126:104037CrossRefPubMedPubMedCentral

25.

Wu J, Wu X, Zeng W et al (2020) Chest CT findings in patients with coronavirus disease 2019 and its relationship with clinical features. Invest Radiol 55:257–261CrossRefPubMedPubMedCentral

26.

Nishio M, Noguchi S, Matsuo H, Murakami T (2020) Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methods. Sci Rep 10:17532CrossRefPubMedPubMedCentral

27.

Wang J, Sun K, Cheng T et al (2021) Deep high-resolution representation learning for visual recognition. IEEE Trans Pattern Anal Mach Intell 43:3349–3364CrossRefPubMed

28.

Chao P, Kao C-Y, Ruan Y-S et al (2019) Hardnet: a low memory traffic network. Proceedings of the IEEE/CVF international conference on computer vision. arXiv preprint arXiv:3552.3561

29.

Pham TD (2020) A comprehensive study on classification of COVID-19 on computed tomography with pretrained convolutional neural networks. Sci Rep 10:16942CrossRefPubMedPubMedCentral

30.

Polsinelli M, Cinque L, Placidi G (2020) A light CNN for detecting COVID-19 from CT scans of the chest. Pattern Recognit Lett 140:95–100CrossRefPubMedPubMedCentral

31.

Wang J, Bao Y, Wen Y et al (2020) Prior-attention residual learning for more discriminative COVID-19 screening in CT images. IEEE Trans Med Imaging 39:2572–2583CrossRefPubMed

32.

Zhang YH, Hu XF, Ma JC et al (2021) Clinical applicable AI system based on deep learning algorithm for differentiation of pulmonary infectious disease. Front Med (Lausanne) 8:753055CrossRefPubMed

33.

De Pauw B, Walsh TJ, Donnelly JP et al (2008) Revised definitions of invasive fungal disease from the European Organization for Research and Treatment of Cancer/Invasive Fungal Infections Cooperative Group and the National Institute of Allergy and Infectious Diseases Mycoses Study Group (EORTC/MSG) Consensus Group. Clin Infect Dis 46:1813–1821CrossRefPubMed

34.

Kunihiro Y, Tanaka N, Kawano R et al (2019) Differential diagnosis of pulmonary infections in immunocompromised patients using high-resolution computed tomography. Eur Radiol 29:6089–6099CrossRefPubMed

35.

Walsh SLF, Calandriello L, Silva M, Sverzellati N (2018) Deep learning for classifying fibrotic lung disease on high-resolution computed tomography: a case-cohort study. Lancet Respir Med 6:837–845CrossRefPubMed

36.

Chen W, Han X, Wang J et al (2022) Deep diagnostic agent forest (DDAF): a deep learning pathogen recognition system for pneumonia based on CT. Comput Biol Med 141:105143CrossRefPubMed

37.

Ni Q, Sun ZY, Qi L et al (2020) A deep learning approach to characterize 2019 coronavirus disease (COVID-19) pneumonia in chest CT images. Eur Radiol 30:6517–6527CrossRefPubMedPubMedCentral

38.

Choe J, Hwang HJ, Seo JB et al (2022) Content-based image retrieval by using deep learning for interstitial lung disease diagnosis with chest CT. Radiology 302:187–197CrossRefPubMed

Titel: Pneumonia-Plus: a deep learning model for the classification of bacterial, fungal, and viral pneumonia based on CT tomography
verfasst von: Fang Wang
Xiaoming Li
Ru Wen
Hu Luo
Dong Liu
Shuai Qi
Yang Jing
Peng Wang
Gang Deng
Cong Huang
Tingting Du
Limei Wang
Hongqin Liang
Jian Wang
Chen Liu
Publikationsdatum: 30.06.2023
Verlag: Springer Berlin Heidelberg
Erschienen in: European Radiology / Ausgabe 12/2023
Print ISSN: 0938-7994
Elektronische ISSN: 1432-1084
DOI: https://doi.org/10.1007/s00330-023-09833-4

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Klimawandel und Gesundheit: Was Sie in der Hausarztpraxis wissen müssen und tun können

Springer Medizin

Pneumonia-Plus: a deep learning model for the classification of bacterial, fungal, and viral pneumonia based on CT tomography