A novel deep learning-based approach for prediction of neonatal respiratory disorders from chest X-ray images

• Autorzy: Erdogan Yildirim Ayse , Canayaz Murat

Identyfikatory

DOI

10.1016/j.bbe.2023.08.004

• Języki publikacji: EN

Abstrakty

EN

In recent years, many diseases can be diagnosed in a short time with the use of deep learning models in the field of medicine. Most of the studies in this area focus on adult or pediatric patients. However, deep learning studies for the diagnosis of diseases in neonatal are not sufficient. Also, since it is known that respiratory disorders such as pneumonia have a large place among the causes of neonatal death, early and accurate diagnosis of respiratory diseases in neonates is crucial. For this reason, our study aims to detect the presence of respiratory disorders through the developed deep-learning approach using chest X-ray images of patients hospitalized in the Neonatal Intensive Care Unit. Accordingly, the enhanced version of C+EffxNet, the new hybrid deep learning model, is designed to predict respiratory disorders in neonates. In this version, the features selected by PCA are combined as 100, 200, and 300, then the binary classification process was carried out. In the study, the accuracy and kappa value were obtained as 0.965, and 0.904, respectively before feature merging, while these values were obtained as 0.977, and 0.935 after feature merging. This method, which was developed for the diagnosis of respiratory disorders in neonates, was also subsequently applied to a chest X-ray dataset that is frequently used in the literature for the diagnosis of pediatric pneumonia. For this data set, while the accuracy was 0.992, the kappa value was 0.982. The results obtained confirm the success of the proposed method for both datasets.

Słowa kluczowe

EN

deep learning; neonatal respiratory; chest X-ray; disease diagnosis; respiratory disorders; pediatric pneumonia

PL

uczenie głębokie; układ oddechowy noworodka; rentgen klatki piersiowej; diagnostyka choroby; zapalenie płuc

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2023
• Tom: Vol. 43, no. 4
• Strony: 635--655
• Opis fizyczny: Bibliogr. 81 poz., rys., tab.

Twórcy

autor

Erdogan Yildirim Ayse

• Department of Computer Engineering, Faculty of Engineering, University of Firat, Elazıg, Turkey

autor

Canayaz Murat

• Department of Computer Engineering, Faculty of Engineering, University of Van Yuzuncu Yıl, Van, Turkey

Bibliografia

• [1] Katz J, Lee AC, Kozuki N, Lawn JE, Cousens S, Blencowe H, et al. Mortality risk in preterm and small-for-gestational-age infants in low-income and middle-income countries: a pooled country analysis. Lancet 2013;382:417-25. https://doi. org/10.1016/S0140-6736(13)60993-9.
• [2] Rajaraman S, Candemir S, Kim I, Thoma G, Antari S. Visualization and interpretation of convolutional neural network predictions in detecting pneumonia in pediatric chest radiographs. Appl Sci 2018;8:1715. https://doi.org/10.3390/app8101715.
• [3] Moreira A, Tovar M, Smith AM, Lee GC, Meunier JA, Cheema Z, et al. Development of a peripheral blood transcriptomic gene signature to predict bronchopulmonary dysplasia. Am J Physiol Lung Cell Mol Physiol 2023;324(1):L76-87. https://doi.org/10.1152/ajplung.00250.2022.
• [4] Hysinger EB, Higano NS, Critser PJ, Woods JC. Imaging in neonatal respiratory disease. Paediatr Respir Rev 2022;43:44-52. https://doi.org/10.1016/j.prrv.2021.12.002.
• [5] Liszewski MC, Stanescu AL, Phillips GS, Lee EY. Respiratory distress in neonates: underlying causes and current imaging assessment. Radiol Clin North Am 2017;55:629-44. https:// doi.org/10.1016/j.rcl.2017.02.006.
• [6] Delacourt C, Bertille N, Salomon LJ, Rahshenas M, Benachi A, Bonnard A, et al. for the MALFPULM study group; members of the MALFPULM study group. Predicting the risk of respiratory distress in newborns with congenital pulmonary malformations. Eur Respir J 2022;59(2):2100949. https://doi. Org/10.1183/13993003.00949-2021.
• [7] Columbo C, Landolfo F, De Rose DU, Massolo AC, Secinaro A, Santangelo TP, et al. The role of lung function testing in newborn infants with congenital thoracic arterial anomalies. Front Pediatr 2021;9:682551. https://doi.org/10.3389/ fped.2021.682551.
• [8] Amatya Y, Russell FM, Rijal S, Adhikari S, Nti B, House DR. Bedside lung ultrasound for the diagnosis of pneumonia in children presenting to an emergency department in a resource-limited setting. Int J Emerg Med 2023;16(1):2. https:// doi.org/10.1186/s12245-022-00474-w.
• [9] Ornek AH, Ceylan M. CodCAM: A new ensemble visual explanation for classification of medical thermal images. Quanti InfraRed Thermog J 2023. https://doi.org/10.1080/ 17686733.2023.2167459 (Online Press).
• [10] Boughdir M, Daib A, Bouthour H, Tlili S, Laribi S, Kchaou R, et al. Esophageal lung associated to isolated dextrocardia in a six-month-old infant. J Pediatr Surg Case Rep 2022;76:102115. https://doi.org/10.1016/j.epsc.2021.102115.
• [11] Meedeniya D, Kumarasinghe H, Kolonne S, Fernando C, Díez IDT, Marques G. Chest X-ray analysis empowered with deep learning: A systematic review. Appl Soft Comput 2022;126:109319. https://doi.org/10.1016/j.asoc.2022.109319.
• [12] Padash S, Mohebbian MR, Adams SJ, Henderson RDE, Babyn P. Pediatric chest radiograph interpretation: how far has artificial intelligence come? A systematic literature review. Pediatr Radiol 2022;52:1568-80. https://doi.org/10.1007/s00247-022-05368-w.
• [13] Wang Z, Liu C, Cheng D, Wang L, Yang X, Cheng K-T. Automated detection of clinically significant prostate cancer in mp-MRI images based on an end-to-end deep neural network. IEEE Trans Med Imag 2018;37:1127-39. https://doi. org/10.1109/TMI.2017.2789181.
• [14] Ait Nasser A, Akhloufi MA. A review of recent advances in deep learning models for chest disease detection using radiography. Diagnostics 2023;13(1):159. https://doi.org/ 10.3390/diagnostics13010159.
• [15] Piparia S, Defante A, Tantisira K, Ryu J. Using machine learning to improve our understanding of COVID-19 infection in children. PLoS One 2023;18(2):e0281666.
• [16] Arya V, Kumar T. Enhancing image for CNN-based diagnostic of pediatric pneumonia through chest radiographs. Int J Adv Comput Sci Appl 2023;14(2):374-80.
• [17] McAdams RM, Kaur R, Sun Y, Bindra H, Cho SJ, Singh H. Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review. J Perinatol 2022;42:1561-75. https://doi. org/10.1038/s41372-022-01392-8.
• [18] Kaur K, Singh C, Kumar Y. Diagnosis and detection of congenital diseases in new-borns or fetuses using artificial intelligence techniques: A systematic review. Arch Computat Methods Eng 2023. https://doi.org/10.1007/s11831-023-09892-2 (Online Press).
• [19] Chioma R, Sbordone A, Patti ML, Perri A, Vento G, Nobile S. Applications of artificial intelligence in neonatology. Appl Sci 2023;13(5):3211. https://doi.org/10.3390/app13053211.
• [20] Shaw P, Pachpor K, Sankaranarayanan S. Explainable AI enabled infant mortality prediction based on neonatal sepsis. Comput Syst Sci Eng 2023;44(1):311-25. https://doi.org/ 10.32604/csse.2023.025281.
• [21] Honoré A, Forsberg D, Adolphson K, Chatterjee S, Jost K, Herlenius E. Vital sign-based detection of sepsis in neonates using machine learning. Acta Paediatr 2023;112(4):686-96. https://doi.org/10.1111/apa.16660.
• [22] Fraiwan L, Alkhodari M. Neonatal sleep stage identification using long short-term memory learning system. Med Biol Eng Compu 2020;58:1383-91. https://doi.org/10.1007/s11517-020- 02169-x.
• [23] Salekina MS, Zamzmia G, Goldgofa D, Kasturia R, Hob T, Sun Y. (2021) Multimodal spatio-temporal deep learning approach for neonatal postoperative pain assessment. Comput Biol Med 2021;129:104150. https://doi.org/10.1016/ j.compbiomed.2020.104150.
• [24] Ashwini K, Raj VPMD, Kathiravan S, Chuan-Yu C. Deep learning assisted neonatal cry classification via support vector machine models. Front Public Health 2021;9:670352. https://doi.org/10.3389/fpubh.2021.670352.
• [25] Chen JV, Chaudhari G, Hess CP, Glenn OA, Sugrue LP, Rauschecker AM, et al. Deep learning to predict neonatal and infant brain age from myelination on brain MRI scans. Radiology 2022. https://doi.org/10.1148/radiol.211860 (Online Press).
• [26] Leigh RM, Pham A, Rao SS, Vora FM, Hou G, Kent C, et al. Machine learning for prediction of bronchopulmonary dysplasia-free survival among very preterm infants. BMC Pediatr 2022;22(1):542. https://doi.org/10.1186/s12887-022-03602-w.
• [27] Ervural S, Ceylan M. Convolutional neural networks-based approach to detect neonatal respiratory system anomalies with limited thermal image. Traitement du Signal 2021;38 (2):437-42. https://doi.org/10.18280/ts.380222.
• [28] Liang G, Zheng L. A transfer learning method with deep residual network for pediatric pneumonia diagnosis. Comput Methods Prog Biomed 2020;187:104964. https://doi.org/ 10.1016/j.cmpb.2019.06.023.
• [29] Yee SLK, Raymond WJK. Pneumonia diagnosis using chest Xray images and machine learning. In: Proceedings of the 2020 10th International Conference on Biomedical Engineering and Technology (ICBET 2020); Sep 15-18; Tokyo, Japan; 2020; p. 101-105. https://doi.org/10.1145/3397391.3397412.
• [30] Dey N, Zhang Y, Rajinikanth V, Pugalenthi R, Raja NSM. Customized VGG19 architecture for pneumonia detection in chest X-rays. Pattern Recogn Lett 2021;143:67-74. https://doi. org/10.1016/j.patrec.2020.12.010.
• [31] Mahomed N, van Ginneken B, Philipsen RHHM, Melendez J, Moore DP, Moodley H, et al. Computer-aided diagnosis for World Health Organization-defined chest radiograph primary-endpoint pneumonia in children. Pediatr Radiol 2020;50(4):482-91. https://doi.org/10.1007/s00247-019-04593-0.
• [32] Menashe SJ, Iyer RS, Parisi MT, Otto RK, Stanescu AL. Pediatric chest radiographs: common and less common errors. AJR Am J Roentgenol 2016;207:1-9. https://doi.org/ 10.2214/AJR.16.16449?mobileUi=0.
• [33] Greenough A, Greenough A, Milner AD, editors. Transient tachypnea of the newborn. Neonatal Respiratory Disorder. London: CRC Press; 2003.
• [34] Oliveira LLG, E Silva SA, Ribeiro LHV, de Oliveira RM, Coelho CJ, Andrade ALSS. Computer aided diagnosis in chest radiography for detection of childhood pneumonia. Int J Med Inform 2008;77:555-64. https://doi.org/10.1016/j. Ijmedinf.2007.10.010.
• [35] Sousa RT, Marques O, Soares FAAMN, Sene IIG, de Oliveira LLG, Spoto ES. Comparative performance analysis of machine learning classifers in detection of childhood pneumonia using chest radiographs. Procedia Comput Sci 2013;18:2579-82. https://doi.org/10.1016/j.procs.2013.05.444.
• [36] Akgundogdu A. Detection of pneumonia in chest X-ray images by using 2D discrete wavelet feature extraction with random forest. Int J Imaging Syst Technol 2020;31:82-93. https://doi.org/10.1002/ima.22501.
• [37] Barakat N, Awad M, Abu-Nabah BA. A machine learning approach on chest X-rays for pediatric pneumonia detection. Digital. Health 2023:9. https://doi.org/10.1177/ 20552076231180008.
• [38] Kermany DS, Goldbaum M, Cai W, Valentim CCS, Liang H, Baxter SL, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 2018;172:1122-31. https://doi.org/10.1016/j.cell.2018.02.010.
• [39] Jain R, Nagrath P, Kataria G, Kaushik VS, Hemanth DJ. Pneumonia detection in chest X-ray images using convolutional neural networks and transfer learning. Measurement 2020;165:108046. https://doi.org/10.1016/j. Measurement.2020.108046.
• [40] Chouhan V, Singh SK, Khamparia A, Gupta D, Tiwari P, Moreira C, et al. A novel transfer learning based approach for pneumonia detection in chest X-ray images. Appl Sci 2020;10 (2):559. https://doi.org/10.3390/app10020559.
• [41] Yue Z, Ma L, Zhang R. Comparison and validation of deep learning models for the diagnosis of pneumonia. Comput Intell Neurosci 2020;2020:1-8. https://doi.org/10.1155/2020/8876798.
• [42] Chen KC, Yu HR, Chen WS, Lin WC, Lee YC, Chen HH, et al. Diagnosis of common pulmonary diseases in children by Xray images and deep learning. Sci Rep 2020;10:17374. https:// doi.org/10.1038/s41598-020-73831-5.
• [43] Salehi M, Mohammadi R, Ghaffari H, Sadighi N, Reiazi R. Automated detection of pneumonia cases using deep transfer learning with pediatric chest X-ray images. Br J Radiol 2021;94(1121):20201263. https://doi.org/10.1259/bjr.20201263.
• [44] Chen Y, Roberts CS, Ou W, Petigara T, Goldmacher GV, Fancourt N, et al. Deep learning for classification of pediatric chest radiographs by WHO’s standardized methodology. PLoS One 2021;16(6):e0253239.
• [45] Costa NJ, Sousa JVM, Domingos, Santos BS, Junior FM, Melo R. Classification of X-ray images for detection of childhood pneumonia using pre-trained neural networks. Brazilian J Appl Comput 2020;12:132-41. https://doi.org/10.5335/rbca. V12i3.10343.
• [46] Masud M, Bairagi AK, Nahid AA, Sikder N, Rubaiee S, Ahmed A, et al. A pneumonia diagnosis scheme based on hybrid features extracted from chest radiographs using an ensemble learning algorithm. J Healthc Eng 2021;2021:8862089. https:// doi.org/10.1155/2021/8862089.
• [47] Chagas JVS, Rodrigues DA, Ivo RF, Hassan MM, Albuquerque VHC, Filho PPR. A new approach for the detection of pneumonia in children using CXR images based on an realtime IoT system. J Real Time Image Process 2021;18 (14):1099-114. https://doi.org/10.1007/s11554-021-01086-y.
• [48] Gupta A, Sheth P, Xie P. Neural architecture search for pneumonia diagnosis from chest X-rays. Sci Rep 2022;12:11309. https://doi.org/10.1038/s41598-022-15341-0.
• [49] Guail AAA, Jinsong G, Oloulade BM, Al-Sabri R. A principal neighborhood aggregation-based graph convolutional network for pneumonia detection. Sensors 2022;22(8):3049. https://doi.org/10.3390/s22083049.
• [50] Ayan E, Karabulut B, Ünver HM. Diagnosis of pediatric pneumonia with ensemble of deep convolutional neural networks in chest X-ray images. Arab J Sci Eng 2022;47 (2):2123-39. https://doi.org/10.1007/s13369-021-06127-z.
• [51] Alshamrani K, Alshamrani HA, Asiri AA, Alqahtani FF, Mohammad WT, Alshehri AH. The use of chest radiographs and machine learning model for the rapid detection of pneumonitis in pediatric. Biomed Res Int 2022;2022:5260231. https://doi.org/10.1155/2022/5260231.
• [52] Wang HN, Zheng LX, Pan SW, Yan T, Su QL. Image recognition of pediatric pneumonia based on fusion of texture features and depth features. Comput Math Methods Med 2022;2022:1973508. https://doi.org/10.1155/2022/1973508.
• [53] Khalilzad Z, Hasasneh A, Tadj C. Newborn cry-based diagnostic system to distinguish between sepsis and respiratory distress syndrome using combined acoustic features. Diagnostics 2022;12(11):2802. https://doi.org/10.3390/diagnostics12112802.
• [54] Sasikaladevi N, Revathi A. Intelligent prognostic system for pediatric pneumonia based on sustainable IoHT. Multimed Tools Appl 2023;82:26901-17. https://doi.org/10.1007/s11042-023-14930-z.
• [55] Jayakanthan AP, Rupan SS, Sowmya V, Krichen M, Ravi V. Transfer learning based pediatric pneumonia diagnosis using residual attention learning. In: Abraham A, Bajaj A, Gandhi N, Madureira AM, Kahraman C, editors. Innovations in BioInspired Computing and Applications. Lecture Notes in Networks and Systems, vol. 649. Cham: Springer; 2023. https://doi.org/10.1007/978-3-031-27499-2_5.
• [56] Yuan D, Liu Y, Xu Z, Zhan Y, Chen J, Lukasiewicz T. Painless and accurate medical image analysis using deep reinforcement learning with task-oriented homogenized automatic pre-processing. Comput Biol Med 2023;153:106487. https://doi.org/10.1016/j.compbiomed.2022.106487.
• [57] Wen R, Xu P, Cai Y, Wang F, Li M, Zeng X, et al. A deep learning model for the diagnosis and discrimination of gram-positive and gram-negative bacterial pneumonia for children using chest radiography images and clinical information. Infect Drug Resist 2023;6:4083-92. https://doi.org/10.2147/IDR.S404786.
• [58] Yao D, Xu Z, Lin Y, Zhan Y. Accurate and intelligent diagnosis of pediatric pneumonia using X-ray images and blood testing data. Front Bioeng Biotechnol 2023;11:1058888. https://doi.org/10.3389/fbioe.2023.1058888.
• [59] Arya V, Kumar T. Boosting X-ray scans feature for enriched diagnosis of pediatric pneumonia using deep learning models. Int J Performab Eng 2023;19(3):175-83. https://doi.org/ 10.23940/ijpe.23.03.p3.175183.
• [60] Sharma S, Guleria K. A deep learning based model for the detection of pneumonia from chest X-ray images using VGG16 and neural networks. Proc Comput Sci 2023;218:357-66. https://doi.org/10.1016/j.procs.2023.01.018.
• [61] Prodhan MMA, Yousuf MA. Combination of the features of pre-trained Xception and VGG16 models to identify childhood pneumonia from chest X-ray images. In: Proceedings of the 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE); Chittagong, Bangladesh; 2023; p. 1-6. https://doi.org/ 10.1109/ECCE57851.2023.10101489.
• [62] Prakash JA, Asswin CR, Kumar KSD, Avinash D, Vinayakumar R, Sowmya V, et al. Transfer learning approach for pediatric pneumonia diagnosis using channel attention deep CNN architectures. Eng Appl Artif Intel 2023;123(Part B):106416. https://doi.org/10.1016/j.engappai.2023.106416.
• [63] Ravi V, Acharya V, Alazab M. A multichannel EfficientNet deep learning-based stacking ensemble approach for lung disease detection using chest X-ray images. Cluster Comput 2023;26:1181-203. https://doi.org/10.1007/s10586-022-03664-6.
• [64] Prakash JA, Ravi V, Sowmya V, et al. Stacked ensemble learning based on deep convolutional neural networks for pediatric pneumonia diagnosis using chest X-ray images. Neural Comput Appl 2023;35:8259-79. https://doi.org/10.1007/s00521-022-08099-z.
• [65] Prakash JA, Asswin C, Ravi V, et al. Pediatric pneumonia diagnosis using stacked ensemble learning on multi-model deep CNN architectures. Multimed Tools Appl 2023;82:21311-51. https://doi.org/10.1007/s11042-022-13844-6.
• [66] Kermany D, Zhang K, Goldbaum M. Labeled optical coherence tomography (OCT) and chest X-ray images for classification. Mendeley Data 2018;v2. https://doi.org/ 10.17632/rscbjbr9sj.2.
• [67] Chowdhury NK, Kabir MA, Rahman MM, Rezoana N. ECOVNet: an ensemble of deep convolutional neural networks based on EfficientNet to detect COVID-19 from chest X-rays. PeerJ Comput Sci 2021;7:e551.
• [68] Tan M, Le Q V. EfficientNet: Rethinking model scaling for convolutional neural networks 2019; arXiv:1905.11946v5.
• [69] Canayaz M. C+EffxNet: A novel hybrid approach for COVID-19 diagnosis on CT images based on CBAM and EfficientNet. Chaos Solitons Fractals 2021;151:111310. https://doi.org/10.1016/j.chaos.2021.111310.
• [70] Sinha A, Dolz J. Multi-scale self-guided attention for medical image segmentation. IEEE J Biomed Heal Informatics 2021;25:121-30. https://doi.org/10.1109/JBHI.2020.2986926.
• [71] Woo S, Park J, Lee J-Y, Kweon IS. CBAM: Convolutional block attention module. ECCV 2018;2018:1-17. https://doi.org/ 10.48550/arXiv.1807.06521.
• [72] Gul MSK, Mukati U, Bätz M, Forchhammer S, Keinert J. Light-field view synthesis using convolutional block attention module. In: Proceedings of 2021 IEEE International Conference on Image Processing (ICIP); Anchorage, AK, USA; 2021; p. 3398-402. https://doi.org/10.1109/ICIP42928.2021.9506586.
• [73] Oktay O, Schlemper J, Le Folgoc L, Lee M, Heinrich M, Misawa K, et al. Attention U-Net: learning where to look for the Pancreas. 2018:1-10. arXiv:1804.03999v3.
• [74] Dhiman G, Juneja S, Viriyasitavat W, Mohafez H, Hadizadeh M, Islam MA, et al. A novel machine-learning-based hybrid CNN model for tumor identification in medical image processing. Sustainability 2022;14(3):1-13. https://doi.org/ 10.3390/su14031447.
• [75] Trivedi M, Gupta A. A lightweight deep learning architecture for the automatic detection of pneumonia using chest X-ray images. Multimed Tools Appl 2022;81:5515-36. https://doi. org/10.1007/s11042-021-11807-x.
• [76] Fayemiwo MA, Olowookere TA, Arekete SA, Ogunde AO, Odim MO, Oguntunde BO, et al. Modeling a deep transfer learning framework for the classification of COVID-19 radiology dataset. PeerJ Comput Sci 2021;7:e614.
• [77] Haq EU, Jianjun H, Huarong X, Li K, Weng L. A hybrid approach based on deep CNN and machine learning classifiers for the tumor segmentation and classification in brain MRI. Comput Math Methods Med 2022;2022:6446680. https://doi.org/10.1155/2022/6446680.
• [78] Alluhaidan AS. DNA sequence analysis for brain disorder using deep learning and secure storage. Comput Mater Continua 2022;71(3):5949-62.
• [79] Selvaraj S, Gangadharan SS. Privacy preserving hybrid recommender system based on deep learning. Turk J Electr Eng Comput Sci 2021;29(5):9. https://doi.org/10.3906/elk-2010-40.
• [80] Cheng H, Garrick D, Fernando R. Efficient strategies for leaveone-out cross validation for genomic best linear unbiased prediction. J Animal Sci Biotechnol 2017;8:38. https://doi.org/ 10.1186/s40104-017-0164-6.
• [81] Rafało M. Cross validation methods: Analysis based on diagnostics of thyroid cancer metastasis. ICT Express 2022;8 (2):183-8. https://doi.org/10.1016/j.icte.2021.05.001.