Radiomics and machine learning for the diagnosis of pediatric cervical non-tuberculous mycobacterial lymphadenitis.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
22 02 2022
22 02 2022
Historique:
received:
09
12
2021
accepted:
09
02
2022
entrez:
23
2
2022
pubmed:
24
2
2022
medline:
22
3
2022
Statut:
epublish
Résumé
Non-tuberculous mycobacterial (NTM) infection is an emerging infectious entity that often presents as lymphadenitis in the pediatric age group. Current practice involves invasive testing and excisional biopsy to diagnose NTM lymphadenitis. In this study, we performed a retrospective analysis of 249 lymph nodes selected from 143 CT scans of pediatric patients presenting with lymphadenopathy at the Montreal Children's Hospital between 2005 and 2018. A Random Forest classifier was trained on the ten most discriminative features from a set of 1231 radiomic features. The model classifying nodes as pyogenic, NTM, reactive, or proliferative lymphadenopathy achieved an accuracy of 72%, a precision of 68%, and a recall of 70%. Between NTM and all other causes of lymphadenopathy, the model achieved an area under the curve (AUC) of 89%. Between NTM and pyogenic lymphadenitis, the model achieved an AUC of 90%. Between NTM and the reactive and proliferative lymphadenopathy groups, the model achieved an AUC of 93%. These results indicate that radiomics can achieve a high accuracy for classification of NTM lymphadenitis. Such a non-invasive highly accurate diagnostic approach has the potential to reduce the need for invasive procedures in the pediatric population.
Identifiants
pubmed: 35194075
doi: 10.1038/s41598-022-06884-3
pii: 10.1038/s41598-022-06884-3
pmc: PMC8863781
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
2962Informations de copyright
© 2022. The Author(s).
Références
Lacroix, A. et al. Emergence of nontuberculous mycobacterial lymphadenitis in children after the discontinuation of mandatory Bacillus Calmette and GuÉrin immunization in France. Pediatr. Infect. Dis. J. 37(10), e257–e260 (2018).
pubmed: 29570591
doi: 10.1097/INF.0000000000001977
Lyly, A. et al. Childhood nontuberculous mycobacterial lymphadenitis-observation alone is a good alternative to surgery. Int. J. Pediatr. Otorhinolaryngol. 129, 109778 (2020).
pubmed: 31756659
doi: 10.1016/j.ijporl.2019.109778
Gallois, Y. et al. Nontuberculous lymphadenitis in children: What management strategy?. Int. J. Pediatr. Otorhinolaryngol. 122, 196–202 (2019).
pubmed: 31039497
doi: 10.1016/j.ijporl.2019.04.012
Naselli, A. et al. Management of nontuberculous mycobacterial lymphadenitis in a tertiary care children’s hospital: A 20year experience. J. Pediatr. Surg. 52(4), 593–597 (2017).
pubmed: 27614809
doi: 10.1016/j.jpedsurg.2016.08.005
Panesar, J. et al. Nontuberculous mycobacterial cervical adenitis: A ten-year retrospective review. Laryngoscope 113(1), 149–154 (2003).
pubmed: 12514400
doi: 10.1097/00005537-200301000-00028
Pumberger, W. et al. Cervicofacial lymphadenitis due to atypical mycobacteria: A surgical disease. Pediatr. Dermatol. 21(1), 24–29 (2004).
pubmed: 14871321
doi: 10.1111/j.0736-8046.2004.21111.x
Aliano, D. & Thomson, R. The epidemiology of extrapulmonary non-tuberculous mycobacterial infection in a pediatric population. Pediatr. Infect. Dis. J. 39(8), 671–677 (2020).
pubmed: 32235244
doi: 10.1097/INF.0000000000002658
Blanc, P. et al. Nontuberculous mycobacterial infections in a French hospital: A 12-year retrospective study. PLoS ONE 11(12), e0168290 (2016).
pubmed: 27959960
pmcid: 5154556
doi: 10.1371/journal.pone.0168290
Kontturi, A. et al. Increase in childhood nontuberculous mycobacterial infections after Bacille Calmette-Guérin coverage drop: A nationwide, population-based retrospective study, Finland, 1995–2016. Clin. Infect. Dis. 67(8), 1256–1261 (2018).
pubmed: 29584893
doi: 10.1093/cid/ciy241
Loizos, A. et al. Lymphadenitis by non-tuberculous mycobacteria in children. Pediatr. Int. 60(12), 1062–1067 (2018).
pubmed: 30290041
Park, S. G. et al. Cluster of lymphadenitis due to nontuberculous mycobacterium in children and adolescents 8–15 years of age. J. Korean Med. Sci. 34(46), e302 (2019).
pubmed: 31779059
pmcid: 6882942
doi: 10.3346/jkms.2019.34.e302
Varghese, B. et al. Burden of non-tuberculous mycobacterial diseases in Saudi Arabian children: The first nationwide experience. J. Infect. Public Health 12(6), 803–808 (2019).
pubmed: 31078494
doi: 10.1016/j.jiph.2019.04.004
Olivas-Mazón, R. et al. Diagnosis of nontuberculous mycobacterial lymphadenitis: The role of fine-needle aspiration. Eur. J. Pediatr. 180(4), 1279–1286 (2021).
pubmed: 33205252
doi: 10.1007/s00431-020-03875-2
Spinelli, G. et al. Surgical treatment for chronic cervical lymphadenitis in children. Experience from a tertiary care paediatric centre on non-tuberculous mycobacterial infections. Int. J. Pediatr. Otorhinolaryngol. 108, 137–142 (2018).
pubmed: 29605343
doi: 10.1016/j.ijporl.2018.02.042
Piersimoni, C. & Scarparo, C. Extrapulmonary infections associated with nontuberculous mycobacteria in immunocompetent persons. Emerg. Infect. Dis. 15(9), 1351–1358 (2009) (quiz 1544).
pubmed: 19788801
pmcid: 2819852
doi: 10.3201/eid1509.081259
Bagla, S., Tunkel, D. & Kraut, M. A. Nontuberculous mycobacterial lymphadenitis of the head and neck: Radiologic observations and clinical context. Pediatr. Radiol. 33(6), 402–406 (2003).
pubmed: 12692697
doi: 10.1007/s00247-003-0884-y
Hanck, C., Fleisch, F. & Katz, G. Imaging appearance of nontuberculous mycobacterial infection of the neck. Am. J. Neuroradiol. 25(2), 349–350 (2004).
pubmed: 14970045
pmcid: 7974600
Hazra, R. et al. Lymphadenitis due to nontuberculous mycobacteria in children: Presentation and response to therapy. Clin. Infect. Dis. 28(1), 123–129 (1999).
pubmed: 10028082
doi: 10.1086/515091
Lindeboom, J. A. et al. The sonographic characteristics of nontuberculous mycobacterial cervicofacial lymphadenitis in children. Pediatr. Radiol. 36(10), 1063–1067 (2006).
pubmed: 16906393
doi: 10.1007/s00247-006-0271-6
Martínez-Planas, A. et al. Interferon-gamma release assays differentiate between mycobacterium avium complex and tuberculous lymphadenitis in children. J. Pediatr. 236, 211.e2-218.e2 (2021).
doi: 10.1016/j.jpeds.2021.05.008
Moe, J. et al. Diagnosis and management of children with mycobacterium abscessus infections in the head and neck. J. Oral Maxillofac. Surg. 76(9), 1902–1911 (2018).
pubmed: 29649431
doi: 10.1016/j.joms.2018.03.016
Nadel, D. M. Imaging of granulomatous neck masses in children. Int. J. Pediatr. Otorhinolaryngol. 37(2), 151 (1996).
pubmed: 8894813
doi: 10.1016/0165-5876(96)01400-0
Robson, C. D. Imaging of granulomatous lesions of the neck in children. Radiol. Clin. N. Am. 38(5), 969–977 (2000).
pubmed: 11054963
doi: 10.1016/S0033-8389(05)70215-3
Robson, C. D. et al. Nontuberculous mycobacterial infection of the head and neck in immunocompetent children: CT and MR findings. AJNR Am. J. Neuroradiol. 20(10), 1829–1835 (1999).
pubmed: 10588104
pmcid: 7657772
Willemse, S. H. et al. Diagnosing nontuberculous mycobacterial cervicofacial lymphadenitis in children: A systematic review. Int. J. Pediatr. Otorhinolaryngol. 112, 48–54 (2018).
pubmed: 30055739
doi: 10.1016/j.ijporl.2018.06.034
Hill, A. R. The tuberculin skin test: A useful screen for nontuberculous mycobacterial lymphadenitis in regions with a low prevalence of tuberculosis?. Clin. Infect. Dis. 43(12), 1552–1554 (2006).
pubmed: 17109287
doi: 10.1086/509334
Lindeboom, J. A. et al. Tuberculin skin testing is useful in the screening for nontuberculous mycobacterial cervicofacial lymphadenitis in children. Clin. Infect. Dis. 43(12), 1547–1551 (2006).
pubmed: 17109286
doi: 10.1086/509326
Van Coppenraet, B. E. S. et al. Real-time PCR assay using fine-needle aspirates and tissue biopsy specimens for rapid diagnosis of mycobacterial lymphadenitis in children. J. Clin. Microbiol. 42(6), 2644–2650 (2004).
pmcid: 427856
doi: 10.1128/JCM.42.6.2644-2650.2004
Kommareddi, S. et al. Nontuberculous mycobacterial infections: Comparison of the fluorescent auramine-O and Ziehl–Neelsen techniques in tissue diagnosis. Hum. Pathol. 15(11), 1085–1089 (1984).
pubmed: 6208117
doi: 10.1016/S0046-8177(84)80253-1
Gillies, R. J., Kinahan, P. E. & Hricak, H. Radiomics: Images are more than pictures, they are data. Radiology 278(2), 563–577 (2016).
pubmed: 26579733
doi: 10.1148/radiol.2015151169
Kumar, V. et al. Radiomics: The process and the challenges. Magn. Reson. Imaging 30(9), 1234–1248 (2012).
pubmed: 22898692
pmcid: 3563280
doi: 10.1016/j.mri.2012.06.010
Lambin, P. et al. Radiomics: Extracting more information from medical images using advanced feature analysis. Eur. J. Cancer 48(4), 441–446 (2012).
pubmed: 22257792
pmcid: 4533986
doi: 10.1016/j.ejca.2011.11.036
Seidler, M. et al. Dual-energy CT texture analysis with machine learning for the evaluation and characterization of cervical lymphadenopathy. Comput. Struct. Biotechnol. J. 17, 1009–1015 (2019).
pubmed: 31406557
pmcid: 6682309
doi: 10.1016/j.csbj.2019.07.004
Maleki, F. et al. Machine learning algorithm validation: From essentials to advanced applications and implications for regulatory certification and deployment. Neuroimaging Clin. 30(4), 433–445 (2020).
doi: 10.1016/j.nic.2020.08.004
Maleki, F. et al. Overview of machine learning part 1: Fundamentals and classic approaches. Neuroimaging Clin. N. Am. 30(4), e17–e32 (2020).
pubmed: 33039003
doi: 10.1016/j.nic.2020.08.007
Forghani, R. Precision digital oncology: Emerging role of radiomics-based biomarkers and artificial intelligence for advanced imaging and characterization of brain tumors. Radiol. Imaging Cancer 2(4), e190047 (2020).
pubmed: 33778721
pmcid: 7983689
doi: 10.1148/rycan.2020190047
Castellano, G. et al. Texture analysis of medical images. Clin. Radiol. 59(12), 1061–1069 (2004).
pubmed: 15556588
doi: 10.1016/j.crad.2004.07.008
Chen, D.-R., Chang, R.-F. & Huang, Y.-L. Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. Radiology 213(2), 407–412 (1999).
pubmed: 10551220
doi: 10.1148/radiology.213.2.r99nv13407
Davnall, F. et al. Assessment of tumor heterogeneity: An emerging imaging tool for clinical practice?. Insights Imaging 3(6), 573–589 (2012).
pubmed: 23093486
pmcid: 3505569
doi: 10.1007/s13244-012-0196-6
Ganeshan, B. & Miles, K. A. Quantifying tumour heterogeneity with CT. Cancer Imaging 13(1), 140–149 (2013).
pubmed: 23545171
pmcid: 3613789
doi: 10.1102/1470-7330.2013.0015
Karu, K., Jain, A. K. & Bolle, R. M. Is there any texture in the image?. Pattern Recogn. 29(9), 1437–1446 (1996).
doi: 10.1016/0031-3203(96)00004-0
Lubner, M. G. et al. CT texture analysis: Definitions, applications, biologic correlates, and challenges. Radiographics 37(5), 1483–1503 (2017).
pubmed: 28898189
doi: 10.1148/rg.2017170056
Tourassi, G. D. Journey toward computer-aided diagnosis: Role of image texture analysis. Radiology 213(2), 317–320 (1999).
pubmed: 10551208
doi: 10.1148/radiology.213.2.r99nv49317
Zwanenburg, A. et al. The image biomarker standardization initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295(2), 328–338 (2020).
pubmed: 32154773
doi: 10.1148/radiol.2020191145
Andersen, M. B. et al. CT texture analysis can help differentiate between malignant and benign lymph nodes in the mediastinum in patients suspected for lung cancer. Acta Radiol. 57(6), 669–676 (2015).
pubmed: 26271125
doi: 10.1177/0284185115598808
Bayanati, H. et al. Quantitative CT texture and shape analysis: Can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer?. Eur. Radiol. 25(2), 480–487 (2015).
pubmed: 25216770
doi: 10.1007/s00330-014-3420-6
Bogowicz, M., et al. Combined CT radiomics of primary tumor and metastatic lymph nodes improves prediction of loco-regional control in head and neck cancer. Sci. Rep. 9(1) (2019).
Cahalane, A. M. et al. Computed tomography texture features can discriminate benign from malignant lymphadenopathy in pediatric patients: A preliminary study. Pediatr. Radiol. 49(6), 737–745 (2019).
pubmed: 30741316
doi: 10.1007/s00247-019-04350-3
Carvalho, S. et al. 18F-fluorodeoxyglucose positron-emission tomography (FDG-PET)—Radiomics of metastatic lymph nodes and primary tumor in non-small cell lung cancer (NSCLC)—A prospective externally validated study. PLoS ONE 13(3), e0192859 (2018).
pubmed: 29494598
pmcid: 5832210
doi: 10.1371/journal.pone.0192859
Gao, X. et al. The method and efficacy of support vector machine classifiers based on texture features and multi-resolution histogram from 18F-FDG PET-CT images for the evaluation of mediastinal lymph nodes in patients with lung cancer. Eur. J. Radiol. 84(2), 312–317 (2015).
pubmed: 25487819
doi: 10.1016/j.ejrad.2014.11.006
Tsung-Ying, H. T. Y. Classifying neck lymph nodes of head and neck squamous cell carcinoma in MRI images with radiomic features. J. Digit. Imaging (2020).
Zhang, M., et al. A generalized approach to determine confident samples for deep neural networks on unseen data. In Uncertainty for Safe Utilization of Machine Learning in Medical Imaging and Clinical Image-Based Procedures 65–74 (Springer, 2019)
Park, S.-H., et al. Magnetic resonance imaging features of tumor and lymph node to predict clinical outcome in node-positive cervical cancer: A retrospective analysis. Radiat. Oncol. 15(1) (2020).
Pham, T. D. et al. Texture analysis and synthesis of malignant and benign mediastinal lymph nodes in patients with lung cancer on computed tomography. Sci. Rep. 7(1), 43209 (2017).
pubmed: 28233795
pmcid: 5324097
doi: 10.1038/srep43209
Qiu, X., et al. Could ultrasound‐based radiomics noninvasively predict axillary lymph node metastasis in breast cancer? J. Ultrasound Med. (2020).
Trebeschi, S. et al. Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers. Ann. Oncol. 30(6), 998–1004 (2019).
pubmed: 30895304
pmcid: 6594459
doi: 10.1093/annonc/mdz108
Zhiguo, Z. Z. Multifaceted radiomics for distant metastasis prediction in headneck cancer. Phys. Med. Biol. (2020).
Santiago, R. et al. CT-based radiomics model with machine learning for predicting primary treatment failure in diffuse large B-cell lymphoma. Transl. Oncol. 14(10), 101188 (2021).
pubmed: 34343854
pmcid: 8348197
doi: 10.1016/j.tranon.2021.101188
Forghani, R. et al. Head and neck squamous cell carcinoma: Prediction of cervical lymph node metastasis by dual-energy CT texture analysis with machine learning. Eur. Radiol. 29(11), 6172–6181 (2019).
pubmed: 30980127
doi: 10.1007/s00330-019-06159-y
Amir, J. Non-tuberculous mycobacterial lymphadenitis in children: Diagnosis and management. ISR Med. Assoc. J. 12(1), 49–52 (2010).
pubmed: 20450132
Penn, R. et al. Nontuberculous mycobacterial cervicofacial lymphadenitis—A review and proposed classification system. Int. J. Pediatr. Otorhinolaryngol. 75(12), 1599–1603 (2011).
pubmed: 22014500
doi: 10.1016/j.ijporl.2011.09.018
Fedorov, A. et al. 3D slicer as an image computing platform for the quantitative imaging network. Magn. Reson. Imaging 30(9), 1323–1341 (2012).
pubmed: 22770690
pmcid: 3466397
doi: 10.1016/j.mri.2012.05.001
Van Griethuysen, J. J. et al. Computational radiomics system to decode the radiographic phenotype. Can. Res. 77(21), e104–e107 (2017).
doi: 10.1158/0008-5472.CAN-17-0339
DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics 44, 837–845 (1988).
pubmed: 3203132
doi: 10.2307/2531595
Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Van Rossum, G. & Drake, F. L. Jr. Python Reference Manual (Centrum voor Wiskunde en Informatica, 1995).