{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:22:16Z","timestamp":1760149336553,"version":"build-2065373602"},"reference-count":34,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T00:00:00Z","timestamp":1690761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data"],"abstract":"<jats:p>Although exhaled aerosols and their patterns may seem chaotic in appearance, they inherently contain information related to the underlying respiratory physiology and anatomy. This study presented a multi-level database of simulated exhaled aerosol images from both normal and diseased lungs. An anatomically accurate mouth-lung geometry extending to G9 was modified to model two stages of obstructions in small airways and physiology-based simulations were utilized to capture the fluid-particle dynamics and exhaled aerosol images from varying breath tests. The dataset was designed to test two performance metrics of convolutional neural network (CNN) models when used for transfer learning: interpolation and extrapolation. To this aim, three testing datasets with decreasing image similarities were developed (i.e., level 1, inbox, and outbox). Four network models (AlexNet, ResNet-50, MobileNet, and EfficientNet) were tested and the performances of all models decreased for the outbox test images, which were outside the design space. The effect of continuous learning was also assessed for each model by adding new images into the training dataset and the newly trained network was tested at multiple levels. Among the four network models, ResNet-50 excelled in performance in both multi-level testing and continuous learning, the latter of which enhanced the accuracy of the most challenging classification task (i.e., 3-class with outbox test images) from 60.65% to 98.92%. The datasets can serve as a benchmark training\/testing database for validating existent CNN models or quantifying the performance metrics of new CNN models.<\/jats:p>","DOI":"10.3390\/data8080126","type":"journal-article","created":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T02:13:32Z","timestamp":1690769612000},"page":"126","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Datasets of Simulated Exhaled Aerosol Images from Normal and Diseased Lungs with Multi-Level Similarities for Neural Network Training\/Testing and Continuous Learning"],"prefix":"10.3390","volume":"8","author":[{"given":"Mohamed","family":"Talaat","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, University of Massachusetts, Lowell, MA 01854, USA"}]},{"given":"Xiuhua","family":"Si","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, California Baptist University, Riverside, CA 92504, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2536-2708","authenticated-orcid":false,"given":"Jinxiang","family":"Xi","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Massachusetts, Lowell, MA 01854, USA"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1109\/TMI.2022.3149171","article-title":"Chest X-Ray diagnostic quality assessment: How much Is pixel-wise supervision needed?","volume":"41","author":"Hu","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3015","DOI":"10.1007\/s11606-020-05951-7","article-title":"Lung cancer screening with low-dose CT: A meta-analysis","volume":"35","author":"Hoffman","year":"2020","journal-title":"J. Gen. Intern. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1823","DOI":"10.2147\/COPD.S308922","article-title":"A novel model-based questionnaire based on low-dose CT screening data for chronic obstructive pulmonary disease diagnosis in Shimane, Japan","volume":"16","author":"Tanino","year":"2021","journal-title":"Int. J. Chron. Obstruct. Pulmon. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1056\/NEJMe1916361","article-title":"Mortality reduction with low-dose CT screening for lung cancer","volume":"382","author":"Duffy","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1097\/MCP.0000000000000459","article-title":"Artificial intelligence in diagnosis of obstructive lung disease: Current status and future potential","volume":"24","author":"Das","year":"2018","journal-title":"Curr. Opin. Pulm. Med."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kanjanasurat, I., Tenghongsakul, K., Purahong, B., and Lasakul, A. (2023). CNN-RNN network integration for the diagnosis of COVID-19 using Chest X-ray and CT images. Sensors, 23.","DOI":"10.3390\/s23031356"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.lungcan.2021.01.027","article-title":"Lung cancer prediction by Deep Learning to identify benign lung nodules","volume":"154","author":"Heuvelmans","year":"2021","journal-title":"Lung Cancer"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"100391","DOI":"10.1016\/j.imu.2020.100391","article-title":"Hybrid deep learning for detecting lung diseases from X-ray images","volume":"20","author":"Bharati","year":"2020","journal-title":"Inform. Med. Unlocked"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Xi, J., Si, X.A., Kim, J., Mckee, E., and Lin, E.-B. (2014). Exhaled aerosol pattern discloses lung structural abnormality: A sensitivity study using computational modeling and fractal analysis. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0104682"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1111\/all.13596","article-title":"Exhaled breath condensate volatilome allows sensitive diagnosis of persistent asthma","volume":"74","author":"Mendes","year":"2019","journal-title":"Allergy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"228","DOI":"10.3390\/jnt4030011","article-title":"Convolutional neural network classification of exhaled aerosol images for diagnosis of obstructive respiratory diseases","volume":"4","author":"Talaat","year":"2023","journal-title":"J. Nanotheranostics"},{"key":"ref_12","unstructured":"Talaat, M., Si, X.A., and Xi, J. (2023, July 21). CFD Lung Diagnosis|Kaggle. Available online: https:\/\/www.kaggle.com\/datasets\/mohamedtalaat92\/cfd-lung-diagnosis."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3303","DOI":"10.1016\/j.xphs.2017.06.011","article-title":"Sensitivity analysis and uncertainty quantification in pulmonary drug delivery of orally inhaled pharmaceuticals","volume":"106","author":"Lu","year":"2017","journal-title":"J. Pharm. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1001\/jama.2021.1117","article-title":"Screening for lung cancer: US preventive services task force recommendation statement","volume":"325","author":"Force","year":"2021","journal-title":"JAMA"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/S0140-6736(99)06093-6","article-title":"Early lung cancer action project: Overall design and findings from baseline screening","volume":"354","author":"Henschke","year":"1999","journal-title":"Lancet"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1054\/bjoc.2000.1531","article-title":"Results of three-year mass screening programme for lung cancer using low-dose spiral computed tomography scanner","volume":"84","author":"Sone","year":"2001","journal-title":"Br. J. Cancer"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1136\/bmj.326.7395.894","article-title":"Screening for cancer with computed tomography","volume":"326","author":"Swensen","year":"2003","journal-title":"BMJ"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5131","DOI":"10.1038\/s41467-020-18918-3","article-title":"Deep transfer learning for reducing health care disparities arising from biomedical data inequality","volume":"11","author":"Gao","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ayana, G., Dese, K., and Choe, S.W. (2021). Transfer learning in breast cancer diagnoses via ultrasound imaging. Cancers, 13.","DOI":"10.3390\/cancers13040738"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Valverde, J.M., Imani, V., Abdollahzadeh, A., De Feo, R., Prakash, M., Ciszek, R., and Tohka, J. (2021). Transfer learning in magnetic resonance brain imaging: A systematic review. J. Imaging, 7.","DOI":"10.3390\/jimaging7040066"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102600","DOI":"10.1016\/j.scs.2020.102600","article-title":"Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection","volume":"65","author":"Loey","year":"2021","journal-title":"Sustain. Cities Soc."},{"key":"ref_22","unstructured":"Benali Amjoud, A., and Amrouch, M. (2020). Image and Signal Processing, Springer."},{"key":"ref_23","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th ICML, Long Beach, CA, USA."},{"key":"ref_24","unstructured":"Tan, M., and Le, Q. (2021, January 18\u201324). Efficientnetv2: Smaller models and faster training. Proceedings of the 38th ICML, Online."},{"key":"ref_25","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18\u201323). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE CVPR, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"94","DOI":"10.3390\/jnt2030007","article-title":"Deciphering exhaled aerosol fingerprints for early diagnosis and personalized therapeutics of obstructive respiratory diseases in small airways","volume":"2","author":"Si","year":"2021","journal-title":"J. Nanotheranostics"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Xi, J., and Zhao, W. (2019). Correlating exhaled aerosol images to small airway obstructive diseases: A study with dynamic mode decomposition and machine learning. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0211413"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.compbiomed.2017.05.019","article-title":"Multi-resolution classification of exhaled aerosol images to detect obstructive lung diseases in small airways","volume":"87","author":"Xi","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1007\/s11325-017-1588-0","article-title":"Numerical study of dynamic glottis and tidal breathing on respiratory sounds in a human upper airway model","volume":"22","author":"Xi","year":"2018","journal-title":"Sleep Breath."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"106079","DOI":"10.1016\/j.cmpb.2021.106079","article-title":"Leveraging statistical shape modeling in computational respiratory dynamics: Nanomedicine delivery in remodeled airways","volume":"204","author":"Talaat","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"105623","DOI":"10.1016\/j.jaerosci.2020.105623","article-title":"The application of statistical shape modeling for lung morphology in aerosol inhalation dosimetry","volume":"151","author":"Xi","year":"2021","journal-title":"J. Aerosol Sci."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Xiao, Q., Stewart, N.J., Willmering, M.M., Gunatilaka, C.C., Thomen, R.P., Schuh, A., Krishnamoorthy, G., Wang, H., Amin, R.S., and Dumoulin, C.L. (2021). Human upper-airway respiratory airflow: In vivo comparison of computational fluid dynamics simulations and hyperpolarized 129Xe phase contrast MRI velocimetry. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0256460"}],"container-title":["Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5729\/8\/8\/126\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:22:53Z","timestamp":1760127773000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5729\/8\/8\/126"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,31]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["data8080126"],"URL":"https:\/\/doi.org\/10.3390\/data8080126","relation":{},"ISSN":["2306-5729"],"issn-type":[{"type":"electronic","value":"2306-5729"}],"subject":[],"published":{"date-parts":[[2023,7,31]]}}}