{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:41:58Z","timestamp":1759970518652,"version":"build-2065373602"},"reference-count":51,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T00:00:00Z","timestamp":1737590400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"FCT\u2014Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia, I.P. (Portuguese Foundation for Science and Technology)","award":["2022.03488.PTDC","2023.02607.BD","2024.04595.BD"],"award-info":[{"award-number":["2022.03488.PTDC","2023.02607.BD","2024.04595.BD"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Lung cancer stands as the most prevalent and deadliest type of cancer, with adenocarcinoma being the most common subtype. Computed Tomography (CT) is widely used for detecting tumours and their phenotype characteristics, for an early and accurate diagnosis that impacts patient outcomes. Machine learning algorithms have already shown the potential to recognize patterns in CT scans to classify the cancer subtype. In this work, two distinct pipelines were employed to perform binary classification between adenocarcinoma and non-adenocarcinoma. Firstly, radiomic features were classified by Random Forest and eXtreme Gradient Boosting classifiers. Next, a deep learning approach, based on a Residual Neural Network and a Transformer-based architecture, was utilised. Both 2D and 3D CT data were initially explored, with the Lung-PET-CT-Dx dataset being employed for training and the NSCLC-Radiomics and NSCLC-Radiogenomics datasets used for external evaluation. Overall, the 3D models outperformed the 2D ones, with the best result being achieved by the Hybrid Vision Transformer, with an AUC of 0.869 and a balanced accuracy of 0.816 on the internal test set. However, a lack of generalization capability was observed across all models, with the performances decreasing on the external test sets, a limitation that should be studied and addressed in future work.<\/jats:p>","DOI":"10.3390\/app15031148","type":"journal-article","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T12:24:09Z","timestamp":1737635049000},"page":"1148","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparing 2D and 3D Feature Extraction Methods for Lung Adenocarcinoma Prediction Using CT Scans: A Cross-Cohort Study"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0268-7921","authenticated-orcid":false,"given":"Margarida","family":"Gouveia","sequence":"first","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), 4200-465 Porto, Portugal"},{"name":"Faculty of Engineering, University of Porto (FEUP), 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9638-0973","authenticated-orcid":false,"given":"T\u00e2nia","family":"Mendes","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), 4200-465 Porto, Portugal"},{"name":"Faculty of Engineering, University of Porto (FEUP), 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-1433","authenticated-orcid":false,"given":"Eduardo M.","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), 4200-465 Porto, Portugal"},{"name":"Faculty of Science, University of Porto (FCUP), 4169-007 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6193-8540","authenticated-orcid":false,"given":"H\u00e9lder P.","family":"P. Oliveira","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), 4200-465 Porto, Portugal"},{"name":"Faculty of Science, University of Porto (FCUP), 4169-007 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1681-2436","authenticated-orcid":false,"given":"Tania","family":"Pereira","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), 4200-465 Porto, Portugal"},{"name":"Faculty of Sciences and Technology, University of Coimbra (FCTUC), 3004-516 Coimbra, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2024, November 06). Global Cancer Burden Growing, Amidst Mounting Need for Services. Available online: https:\/\/www.who.int\/news\/item\/01-02-2024-global-cancer-burden-growing--amidst-mounting-need-for-services."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1158\/1055-9965.EPI-19-0221","article-title":"Cancer Progress and Priorities: Lung Cancer","volume":"28","author":"Schabath","year":"2019","journal-title":"Cancer Epidemiol. Biomark. Prev."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Luo, W. (2023). Nasopharyngeal carcinoma ecology theory: Cancer as multidimensional spatiotemporal \u201cunity of ecology and evolution\u201d pathological ecosystem. Theranostics, 1607\u20131631.","DOI":"10.7150\/thno.82690"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Khodabakhshi, Z., Mostafaei, S., Arabi, H., Oveisi, M., Shiri, I., and Zaidi, H. (2021). Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature. Comput. Biol. Med., 136.","DOI":"10.1016\/j.compbiomed.2021.104752"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"374","DOI":"10.18383\/j.tom.2016.00244","article-title":"An Approach Toward Automatic Classification of Tumor Histopathology of Non\u2013Small Cell Lung Cancer Based on Radiomic Features","volume":"2","author":"Patil","year":"2016","journal-title":"Tomography"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"D\u2019Arnese, E., di Donato, G.W., del Sozzo, E., and Santambrogio, M.D. (2019, January 19\u201322). Towards an Automatic Imaging Biopsy of Non-Small Cell Lung Cancer. Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Chicago, IL, USA.","DOI":"10.1109\/BHI.2019.8834485"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s11517-020-02302-w","article-title":"Lung cancer histology classification from CT images based on radiomics and deep learning models","volume":"59","author":"Marentakis","year":"2021","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s40644-020-00320-3","article-title":"A CT-based radiomics nomogram for prediction of lung adenocarcinomas and granulomatous lesions in patient with solitary sub-centimeter solid nodules","volume":"20","author":"Chen","year":"2020","journal-title":"Cancer Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1007\/s00066-020-01625-9","article-title":"Radiomics and deep learning in lung cancer","volume":"196","author":"Avanzo","year":"2020","journal-title":"Strahlenther. Und Onkol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.lungcan.2017.10.015","article-title":"Radiomics and radiogenomics in lung cancer: A review for the clinician","volume":"115","author":"Thawani","year":"2018","journal-title":"Lung Cancer"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Saikia, T., Hansdah, M., Singh, K.K., and Bajpai, M.K. (2022, January 21\u201323). Classification of Lung Nodules based on Transfer Learning with K-Nearest Neighbor (KNN). Proceedings of the 2022 IEEE International Conference on Imaging Systems and Techniques (IST), Virtual Conference.","DOI":"10.1109\/IST55454.2022.9827668"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4799","DOI":"10.1109\/ACCESS.2019.2962862","article-title":"A Deep Model for Lung Cancer Type Identification by Densely Connected Convolutional Networks and Adaptive Boosting","volume":"8","author":"Pang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chaunzwa, T.L., Hosny, A., Xu, Y., Shafer, A., Diao, N., Lanuti, M., Christiani, D.C., Mak, R.H., and Aerts, H.J.W.L. (2021). Deep learning classification of lung cancer histology using CT images. Sci. Rep., 11.","DOI":"10.1038\/s41598-021-84630-x"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2756765","DOI":"10.21037\/qims-20-734","article-title":"Identifying the histologic subtypes of non-small cell lung cancer with computed tomography imaging: A comparative study of capsule net, convolutional neural network, and radiomics","volume":"11","author":"Liu","year":"2021","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e258","DOI":"10.1016\/j.acra.2020.06.010","article-title":"Histological Subtypes Classification of Lung Cancers on CT Images Using 3D Deep Learning and Radiomics","volume":"28","author":"Guo","year":"2021","journal-title":"Acad. Radiol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Malaviya, N., Rahevar, M., Virani, A., Ganatra, A., and Bhuva, K. (2023, January 27\u201329). LViT: Vision Transformer for Lung cancer Detection. Proceedings of the 2023 International Conference on Artificial Intelligence and Smart Communication (AISC), Greater Noida, India.","DOI":"10.1109\/AISC56616.2023.10085230"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Nejad, R.R., and Hooshmand, S. (2023, January 7\u20139). HViT4Lung: Hybrid Vision Transformers Augmented by Transfer Learning to Enhance Lung Cancer Diagnosis. Proceedings of the 2023 5th International Conference on Bio-Engineering for Smart Technologies (BioSMART), Paris, France.","DOI":"10.1109\/BioSMART58455.2023.10162074"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pandey, A., and Kumar, A. (2022, January 11\u201313). Deep Features Based Automated Multimodel System for Classification of Non-Small Cell Lung Cancer. Proceedings of the 2022 IEEE Delhi Section Conference (DELCON), New Delhi, India.","DOI":"10.1109\/DELCON54057.2022.9753643"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1007\/s10278-020-00337-x","article-title":"Prediction of Non-small Cell Lung Cancer Histology by a Deep Ensemble of Convolutional and Bidirectional Recurrent Neural Network","volume":"33","author":"Moitra","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"ref_21","unstructured":"Yu, S., Zhang, Z., Yuen, P.C., Han, J., Tan, T., Guo, Y., Lai, J., and Zhang, J. (2022, January 4\u20137). TransPND: A Transformer Based Pulmonary Nodule Diagnosis Method on CT Image. Proceedings of the Pattern Recognition and Computer Vision, Shenzhen, China."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.ejmp.2021.08.015","article-title":"Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples","volume":"90","author":"Ubaldi","year":"2021","journal-title":"Phys. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2772","DOI":"10.1007\/s00330-017-5221-1","article-title":"Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer","volume":"28","author":"Zhu","year":"2018","journal-title":"Eur. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Bianconi, F., Palumbo, I., Spanu, A., Nuvoli, S., Fravolini, M.L., and Palumbo, B. (2020). PET\/CT Radiomics in Lung Cancer: An Overview. Appl. Sci., 10.","DOI":"10.3390\/app10051718"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Egger, J., Gsaxner, C., Pepe, A., Pomykala, K.L., Jonske, F., Kurz, M., Li, J., and Kleesiek, J. (2022). Medical deep learning\u2014A systematic meta-review. Comput. Methods Programs Biomed., 221.","DOI":"10.1016\/j.cmpb.2022.106874"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Tomassini, S., Falcionelli, N., Sernani, P., Burattini, L., and Dragoni, A.F. (2022). Lung nodule diagnosis and cancer histology classification from computed tomography data by convolutional neural networks: A survey. Comput. Biol. Med., 146.","DOI":"10.1016\/j.compbiomed.2022.105691"},{"key":"ref_27","first-page":"1024","article-title":"Enhanced convolutional neural network for non-small cell lung cancer classification","volume":"13","author":"Tashtoush","year":"2023","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ma, C., and Yue, S. (2022). Minimum Sample Size Estimate for Classifying Invasive Lung Adenocarcinoma. Appl. Sci., 12.","DOI":"10.3390\/app12178469"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"101141","DOI":"10.1016\/j.tranon.2021.101141","article-title":"Deep learning for predicting subtype classification and survival of lung adenocarcinoma on computed tomography","volume":"14","author":"Wang","year":"2021","journal-title":"Transl. Oncol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"106126","DOI":"10.1016\/j.engappai.2023.106126","article-title":"Vision Transformers in medical computer vision\u2014A contemplative retrospection","volume":"122","author":"Parvaiz","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_31","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Guo, J., Han, K., Wu, H., Tang, Y., Chen, X., Wang, Y., and Xu, C. (2022, January 18\u201324). CMT: Convolutional Neural Networks Meet Vision Transformers. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41746-022-00592-y","article-title":"Machine learning for medical imaging: Methodological failures and recommendations for the future","volume":"5","author":"Varoquaux","year":"2022","journal-title":"npj Digit. Med."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1001\/archinte.1997.00440290031002","article-title":"The probability of malignancy in solitary pulmonary nodules. Application to small radiologically indeterminate nodules","volume":"157","author":"Swensen","year":"1997","journal-title":"Arch. Intern. Med."},{"key":"ref_35","unstructured":"Li, P., Wang, S., Li, T., Lu, J., HuangFu, Y., and Wang, D. (2020). A Large-Scale CT and PET\/CT Dataset for Lung Cancer Diagnosis, The Cancer Imaging Archive."},{"key":"ref_36","unstructured":"Aerts, H.J.W.L., Wee, L., Rios Velazquez, E., Leijenaar, R.T.H., Parmar, C., Grossmann, P., Carvalho, S., Bussink, J., Monshouwer, R., and Haibe-Kains, B. (2019). Data from NSCLC-Radiomics, The Cancer Imaging Archive."},{"key":"ref_37","unstructured":"Bakr, S., Gevaert, O., Echegaray, S., Ayers, K., Zhou, M., Shafiq, M., Zheng, H., Zhang, W., Leung, A., and Kadoch, M. (2017). Data for NSCLC Radiogenomics Collection, The Cancer Imaging Archive."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","article-title":"The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository","volume":"26","author":"Clark","year":"2013","journal-title":"J. Digit. Imaging"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"100464","DOI":"10.1016\/j.patter.2022.100464","article-title":"Machine vision-assisted identification of the lung adenocarcinoma category and high-risk tumor area based on CT images","volume":"3","author":"Chen","year":"2022","journal-title":"Patterns"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational Radiomics System to Decode the Radiographic Phenotype","volume":"77","author":"Fedorov","year":"2017","journal-title":"Cancer Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"Image biomarker standardisation initiative","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_43","first-page":"559","article-title":"Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"Nogueira","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref_44","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_45","unstructured":"Cardoso, M.J., Li, W., Brown, R., Ma, N., Kerfoot, E., Wang, Y., Murrey, B., Myronenko, A., Zhao, C., and Yang, D. (2022). MONAI: An open-source framework for deep learning in healthcare. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_47","unstructured":"Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9 Buc, F., Fox, E., and Garnett, R. (2019, January 8\u201314). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Proceedings of the Advances in Neural Information Processing Systems 32, Vancouver, BC, Canada."},{"key":"ref_48","unstructured":"Chen, S., Ma, K., and Zheng, Y. (2019). Med3D: Transfer Learning for 3D Medical Image Analysis. arXiv."},{"key":"ref_49","unstructured":"Lucidrains GitHub (2024, September 06). Lucidrains\/Vit-Pytorch: Implementation of Vision Transformer, a Simple Way to Achieve SOTA in Vision Classification With Only a Single Transformer Encoder, in Pytorch. Available online: https:\/\/github.com\/lucidrains\/vit-pytorch\/."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Rami-Porta, R. (2021). Future Perspectives on the TNM Staging for Lung Cancer. Cancers, 13.","DOI":"10.3390\/cancers13081940"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Dunn, B., Pierobon, M., and Wei, Q. (2023). Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis. Bioengineering, 10.","DOI":"10.3390\/bioengineering10060690"}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/3\/1148\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:34:54Z","timestamp":1759919694000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/15\/3\/1148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":51,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["app15031148"],"URL":"https:\/\/doi.org\/10.3390\/app15031148","relation":{},"ISSN":["2076-3417"],"issn-type":[{"type":"electronic","value":"2076-3417"}],"subject":[],"published":{"date-parts":[[2025,1,23]]}}}